From 6387b30d107184e5178ee0335e694416eee4d6a0 Mon Sep 17 00:00:00 2001 From: liaozhaorun Date: Wed, 7 May 2025 16:45:47 +0800 Subject: [PATCH] Classify2 --- main/train/Classify2.ipynb | 246 ++-- .../catboost_info/catboost_training.json | 686 +++++++--- .../catboost_info/learn/events.out.tfevents | Bin 22556 -> 56740 bytes main/train/catboost_info/learn_error.tsv | 686 +++++++--- .../catboost_info/test/events.out.tfevents | Bin 22556 -> 56740 bytes main/train/catboost_info/test_error.tsv | 686 +++++++--- main/train/catboost_info/time_left.tsv | 684 +++++++--- main/train/predictions_test.tsv | 1126 ++++++++--------- 8 files changed, 2702 insertions(+), 1412 deletions(-) diff --git a/main/train/Classify2.ipynb b/main/train/Classify2.ipynb index b7e8b93..ebde1f1 100644 --- a/main/train/Classify2.ipynb +++ b/main/train/Classify2.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 53, + "execution_count": 1, "id": "79a7758178bafdd3", "metadata": { "ExecuteTime": { @@ -18,8 +18,6 @@ "name": "stdout", "output_type": "stream", "text": [ - "The autoreload extension is already loaded. To reload it, use:\n", - " %reload_ext autoreload\n", "e:\\PyProject\\NewStock\\main\\train\n" ] } @@ -46,7 +44,7 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 2, "id": "a79cafb06a7e0e43", "metadata": { "ExecuteTime": { @@ -60,7 +58,13 @@ "name": "stdout", "output_type": "stream", "text": [ - "daily data\n", + "daily data\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ "daily basic\n", "inner merge on ['ts_code', 'trade_date']\n", "stk limit\n", @@ -145,7 +149,7 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": 3, "id": "cac01788dac10678", "metadata": { "ExecuteTime": { @@ -160,30 +164,6 @@ "text": [ "industry\n" ] - }, - { - "ename": "KeyboardInterrupt", - "evalue": "", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", - "Cell \u001b[1;32mIn[55], line 45\u001b[0m\n\u001b[0;32m 41\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n\u001b[0;32m 44\u001b[0m \u001b[38;5;66;03m# 使用示例\u001b[39;00m\n\u001b[1;32m---> 45\u001b[0m df \u001b[38;5;241m=\u001b[39m merge_with_industry_data(df, industry_df)\n", - "Cell \u001b[1;32mIn[55], line 19\u001b[0m, in \u001b[0;36mmerge_with_industry_data\u001b[1;34m(df, industry_df)\u001b[0m\n\u001b[0;32m 16\u001b[0m df_sorted \u001b[38;5;241m=\u001b[39m df\u001b[38;5;241m.\u001b[39msort_values([\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtrade_date\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mts_code\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m 18\u001b[0m \u001b[38;5;66;03m# 使用 merge_asof 进行向后合并\u001b[39;00m\n\u001b[1;32m---> 19\u001b[0m merged \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mmerge_asof(\n\u001b[0;32m 20\u001b[0m df_sorted,\n\u001b[0;32m 21\u001b[0m industry_df_sorted,\n\u001b[0;32m 22\u001b[0m by\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mts_code\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;66;03m# 按 ts_code 分组\u001b[39;00m\n\u001b[0;32m 23\u001b[0m left_on\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtrade_date\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m 24\u001b[0m right_on\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124min_date\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m 25\u001b[0m direction\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbackward\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m 26\u001b[0m )\n\u001b[0;32m 28\u001b[0m \u001b[38;5;66;03m# 获取每个 ts_code 的最早 in_date 记录\u001b[39;00m\n\u001b[0;32m 29\u001b[0m min_in_date_per_ts \u001b[38;5;241m=\u001b[39m (industry_df_sorted\n\u001b[0;32m 30\u001b[0m \u001b[38;5;241m.\u001b[39mgroupby(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mts_code\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 31\u001b[0m \u001b[38;5;241m.\u001b[39mfirst()\n\u001b[0;32m 32\u001b[0m \u001b[38;5;241m.\u001b[39mreset_index()[[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mts_code\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124ml2_code\u001b[39m\u001b[38;5;124m'\u001b[39m]])\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\reshape\\merge.py:708\u001b[0m, in \u001b[0;36mmerge_asof\u001b[1;34m(left, right, on, left_on, right_on, left_index, right_index, by, left_by, right_by, suffixes, tolerance, allow_exact_matches, direction)\u001b[0m\n\u001b[0;32m 456\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 457\u001b[0m \u001b[38;5;124;03mPerform a merge by key distance.\u001b[39;00m\n\u001b[0;32m 458\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 689\u001b[0m \u001b[38;5;124;03m4 2016-05-25 13:30:00.048 AAPL 98.00 100 NaN NaN\u001b[39;00m\n\u001b[0;32m 690\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 691\u001b[0m op \u001b[38;5;241m=\u001b[39m _AsOfMerge(\n\u001b[0;32m 692\u001b[0m left,\n\u001b[0;32m 693\u001b[0m right,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 706\u001b[0m direction\u001b[38;5;241m=\u001b[39mdirection,\n\u001b[0;32m 707\u001b[0m )\n\u001b[1;32m--> 708\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m op\u001b[38;5;241m.\u001b[39mget_result()\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\reshape\\merge.py:1946\u001b[0m, in \u001b[0;36m_OrderedMerge.get_result\u001b[1;34m(self, copy)\u001b[0m\n\u001b[0;32m 1943\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 1944\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfill_method must be \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mffill\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m or None\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m-> 1946\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reindex_and_concat(\n\u001b[0;32m 1947\u001b[0m join_index, left_join_indexer, right_join_indexer, copy\u001b[38;5;241m=\u001b[39mcopy\n\u001b[0;32m 1948\u001b[0m )\n\u001b[0;32m 1949\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_maybe_add_join_keys(result, left_indexer, right_indexer)\n\u001b[0;32m 1951\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\reshape\\merge.py:879\u001b[0m, in \u001b[0;36m_MergeOperation._reindex_and_concat\u001b[1;34m(self, join_index, left_indexer, right_indexer, copy)\u001b[0m\n\u001b[0;32m 877\u001b[0m left\u001b[38;5;241m.\u001b[39mcolumns \u001b[38;5;241m=\u001b[39m llabels\n\u001b[0;32m 878\u001b[0m right\u001b[38;5;241m.\u001b[39mcolumns \u001b[38;5;241m=\u001b[39m rlabels\n\u001b[1;32m--> 879\u001b[0m result \u001b[38;5;241m=\u001b[39m concat([left, right], axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m, copy\u001b[38;5;241m=\u001b[39mcopy)\n\u001b[0;32m 880\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\reshape\\concat.py:395\u001b[0m, in \u001b[0;36mconcat\u001b[1;34m(objs, axis, join, ignore_index, keys, levels, names, verify_integrity, sort, copy)\u001b[0m\n\u001b[0;32m 380\u001b[0m copy \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m 382\u001b[0m op \u001b[38;5;241m=\u001b[39m _Concatenator(\n\u001b[0;32m 383\u001b[0m objs,\n\u001b[0;32m 384\u001b[0m axis\u001b[38;5;241m=\u001b[39maxis,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 392\u001b[0m sort\u001b[38;5;241m=\u001b[39msort,\n\u001b[0;32m 393\u001b[0m )\n\u001b[1;32m--> 395\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m op\u001b[38;5;241m.\u001b[39mget_result()\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\reshape\\concat.py:684\u001b[0m, in \u001b[0;36m_Concatenator.get_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 680\u001b[0m indexers[ax] \u001b[38;5;241m=\u001b[39m obj_labels\u001b[38;5;241m.\u001b[39mget_indexer(new_labels)\n\u001b[0;32m 682\u001b[0m mgrs_indexers\u001b[38;5;241m.\u001b[39mappend((obj\u001b[38;5;241m.\u001b[39m_mgr, indexers))\n\u001b[1;32m--> 684\u001b[0m new_data \u001b[38;5;241m=\u001b[39m concatenate_managers(\n\u001b[0;32m 685\u001b[0m mgrs_indexers, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnew_axes, concat_axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbm_axis, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcopy\n\u001b[0;32m 686\u001b[0m )\n\u001b[0;32m 687\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcopy \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m using_copy_on_write():\n\u001b[0;32m 688\u001b[0m new_data\u001b[38;5;241m.\u001b[39m_consolidate_inplace()\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\concat.py:131\u001b[0m, in \u001b[0;36mconcatenate_managers\u001b[1;34m(mgrs_indexers, axes, concat_axis, copy)\u001b[0m\n\u001b[0;32m 124\u001b[0m \u001b[38;5;66;03m# Assertions disabled for performance\u001b[39;00m\n\u001b[0;32m 125\u001b[0m \u001b[38;5;66;03m# for tup in mgrs_indexers:\u001b[39;00m\n\u001b[0;32m 126\u001b[0m \u001b[38;5;66;03m# # caller is responsible for ensuring this\u001b[39;00m\n\u001b[0;32m 127\u001b[0m \u001b[38;5;66;03m# indexers = tup[1]\u001b[39;00m\n\u001b[0;32m 128\u001b[0m \u001b[38;5;66;03m# assert concat_axis not in indexers\u001b[39;00m\n\u001b[0;32m 130\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m concat_axis \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m--> 131\u001b[0m mgrs \u001b[38;5;241m=\u001b[39m _maybe_reindex_columns_na_proxy(axes, mgrs_indexers, needs_copy)\n\u001b[0;32m 132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m mgrs[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mconcat_horizontal(mgrs, axes)\n\u001b[0;32m 134\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mgrs_indexers) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m mgrs_indexers[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mnblocks \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\concat.py:230\u001b[0m, in \u001b[0;36m_maybe_reindex_columns_na_proxy\u001b[1;34m(axes, mgrs_indexers, needs_copy)\u001b[0m\n\u001b[0;32m 220\u001b[0m mgr \u001b[38;5;241m=\u001b[39m mgr\u001b[38;5;241m.\u001b[39mreindex_indexer(\n\u001b[0;32m 221\u001b[0m axes[i],\n\u001b[0;32m 222\u001b[0m indexers[i],\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 227\u001b[0m use_na_proxy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, \u001b[38;5;66;03m# only relevant for i==0\u001b[39;00m\n\u001b[0;32m 228\u001b[0m )\n\u001b[0;32m 229\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m needs_copy \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m indexers:\n\u001b[1;32m--> 230\u001b[0m mgr \u001b[38;5;241m=\u001b[39m mgr\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[0;32m 232\u001b[0m new_mgrs\u001b[38;5;241m.\u001b[39mappend(mgr)\n\u001b[0;32m 233\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m new_mgrs\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:604\u001b[0m, in \u001b[0;36mBaseBlockManager.copy\u001b[1;34m(self, deep)\u001b[0m\n\u001b[0;32m 601\u001b[0m res\u001b[38;5;241m.\u001b[39m_blklocs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_blklocs\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[0;32m 603\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m deep:\n\u001b[1;32m--> 604\u001b[0m res\u001b[38;5;241m.\u001b[39m_consolidate_inplace()\n\u001b[0;32m 605\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m res\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:1791\u001b[0m, in \u001b[0;36mBlockManager._consolidate_inplace\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1789\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_is_consolidated \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m 1790\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_known_consolidated \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m-> 1791\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_rebuild_blknos_and_blklocs()\n", - "File \u001b[1;32minternals.pyx:755\u001b[0m, in \u001b[0;36mpandas._libs.internals.BlockManager._rebuild_blknos_and_blklocs\u001b[1;34m()\u001b[0m\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\base.py:84\u001b[0m, in \u001b[0;36mDataManager.shape\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 82\u001b[0m \u001b[38;5;129m@property\u001b[39m\n\u001b[0;32m 83\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mshape\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Shape:\n\u001b[1;32m---> 84\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mlen\u001b[39m(ax) \u001b[38;5;28;01mfor\u001b[39;00m ax \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes)\n", - "File \u001b[1;32me:\\Python\\anaconda\\envs\\new_trader\\Lib\\site-packages\\pandas\\core\\internals\\base.py:84\u001b[0m, in \u001b[0;36m\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 82\u001b[0m \u001b[38;5;129m@property\u001b[39m\n\u001b[0;32m 83\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mshape\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Shape:\n\u001b[1;32m---> 84\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mlen\u001b[39m(ax) \u001b[38;5;28;01mfor\u001b[39;00m ax \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes)\n", - "\u001b[1;31mKeyboardInterrupt\u001b[0m: " - ] } ], "source": [ @@ -237,7 +217,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "c4e9e1d31da6dba6", "metadata": { "ExecuteTime": { @@ -329,7 +309,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "a735bc02ceb4d872", "metadata": { "ExecuteTime": { @@ -345,7 +325,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "53f86ddc0677a6d7", "metadata": { "ExecuteTime": { @@ -408,7 +388,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "dbe2fd8021b9417f", "metadata": { "ExecuteTime": { @@ -436,7 +416,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "85c3e3d0235ffffa", "metadata": { "ExecuteTime": { @@ -459,7 +439,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "id": "92d84ce15a562ec6", "metadata": { "ExecuteTime": { @@ -540,13 +520,53 @@ "Finished vol_wgt_hist_pos_20.\n", "Calculating vol_adj_roc_20...\n", "Finished vol_adj_roc_20.\n", + "Calculating cs_rank_net_lg_flow_val...\n", + "Finished cs_rank_net_lg_flow_val.\n", + "Calculating cs_rank_flow_divergence...\n", + "Finished cs_rank_flow_divergence.\n", + "Calculating cs_rank_ind_adj_lg_flow...\n", + "Error calculating cs_rank_ind_adj_lg_flow: Missing 'cat_l2_code' column. Assigning NaN.\n", + "Calculating cs_rank_elg_buy_ratio...\n", + "Finished cs_rank_elg_buy_ratio.\n", + "Calculating cs_rank_rel_profit_margin...\n", + "Finished cs_rank_rel_profit_margin.\n", + "Calculating cs_rank_cost_breadth...\n", + "Finished cs_rank_cost_breadth.\n", + "Calculating cs_rank_dist_to_upper_cost...\n", + "Finished cs_rank_dist_to_upper_cost.\n", + "Calculating cs_rank_winner_rate...\n", + "Finished cs_rank_winner_rate.\n", + "Calculating cs_rank_intraday_range...\n", + "Finished cs_rank_intraday_range.\n", + "Calculating cs_rank_close_pos_in_range...\n", + "Finished cs_rank_close_pos_in_range.\n", + "Calculating cs_rank_opening_gap...\n", + "Error calculating cs_rank_opening_gap: Missing 'pre_close' column. Assigning NaN.\n", + "Calculating cs_rank_pos_in_hist_range...\n", + "Finished cs_rank_pos_in_hist_range.\n", + "Calculating cs_rank_vol_x_profit_margin...\n", + "Finished cs_rank_vol_x_profit_margin.\n", + "Calculating cs_rank_lg_flow_price_concordance...\n", + "Finished cs_rank_lg_flow_price_concordance.\n", + "Calculating cs_rank_turnover_per_winner...\n", + "Finished cs_rank_turnover_per_winner.\n", + "Calculating cs_rank_ind_cap_neutral_pe (Placeholder - requires statsmodels)...\n", + "Finished cs_rank_ind_cap_neutral_pe (Placeholder).\n", + "Calculating cs_rank_volume_ratio...\n", + "Finished cs_rank_volume_ratio.\n", + "Calculating cs_rank_elg_buy_sell_sm_ratio...\n", + "Finished cs_rank_elg_buy_sell_sm_ratio.\n", + "Calculating cs_rank_cost_dist_vol_ratio...\n", + "Finished cs_rank_cost_dist_vol_ratio.\n", + "Calculating cs_rank_size...\n", + "Finished cs_rank_size.\n", "\n", "Index: 4502216 entries, 0 to 4502215\n", - "Columns: 157 entries, ts_code to vol_adj_roc_20\n", - "dtypes: bool(10), datetime64[ns](1), float64(141), int32(3), object(2)\n", - "memory usage: 5.0+ GB\n", + "Columns: 177 entries, ts_code to cs_rank_size\n", + "dtypes: bool(10), datetime64[ns](1), float64(161), int32(3), object(2)\n", + "memory usage: 5.6+ GB\n", "None\n", - "['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'pct_chg', 'turnover_rate', 'pe_ttm', 'circ_mv', 'total_mv', 'volume_ratio', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate', 'cat_l2_code', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'log_circ_mv', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'flow_divergence_diff', 'flow_divergence_ratio', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'price_cost_divergence', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20']\n" + "['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'pct_chg', 'turnover_rate', 'pe_ttm', 'circ_mv', 'total_mv', 'volume_ratio', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate', 'cat_l2_code', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'log_circ_mv', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'flow_divergence_diff', 'flow_divergence_ratio', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'price_cost_divergence', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_flow_divergence', 'cs_rank_ind_adj_lg_flow', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_opening_gap', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_ind_cap_neutral_pe', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size']\n" ] } ], @@ -601,7 +621,6 @@ "vol_wgt_hist_pos(df, N=20)\n", "vol_adj_roc(df, N=20)\n", "\n", - "calculate_complex_factor(df)\n", "cs_rank_net_lg_flow_val(df)\n", "cs_rank_flow_divergence(df)\n", "cs_rank_industry_adj_lg_flow(df) # Needs cat_l2_code\n", @@ -634,7 +653,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "id": "b87b938028afa206", "metadata": { "ExecuteTime": { @@ -672,7 +691,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "id": "f4f16d63ad18d1bc", "metadata": { "ExecuteTime": { @@ -918,7 +937,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "id": "40e6b68a91b30c79", "metadata": { "ExecuteTime": { @@ -1209,7 +1228,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "id": "47c12bb34062ae7a", "metadata": { "ExecuteTime": { @@ -1243,7 +1262,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "id": "b76ea08a", "metadata": {}, "outputs": [ @@ -1255,7 +1274,7 @@ "0 000001.SZ 2019-01-02 16.574219\n", "2738 000001.SZ 2019-01-03 16.583965\n", "5477 000001.SZ 2019-01-04 16.633371\n", - "['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n", + "['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n", "去除极值\n", "开始截面 MAD 去极值处理 (k=3.0)...\n" ] @@ -1264,7 +1283,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "MAD Filtering: 100%|██████████| 114/114 [00:22<00:00, 5.04it/s]\n" + "MAD Filtering: 100%|██████████| 130/130 [00:30<00:00, 4.28it/s]\n" ] }, { @@ -1279,7 +1298,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "MAD Filtering: 100%|██████████| 114/114 [00:18<00:00, 6.16it/s]\n" + "MAD Filtering: 100%|██████████| 130/130 [00:23<00:00, 5.44it/s]\n" ] }, { @@ -1317,7 +1336,7 @@ "output_type": "stream", "text": [ "截面 MAD 去极值处理完成。\n", - "feature_columns: ['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n", + "feature_columns: ['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n", "df最小日期: 2019-01-02\n", "df最大日期: 2025-05-06\n", "2058185\n", @@ -1485,7 +1504,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "id": "e23d1759", "metadata": {}, "outputs": [], @@ -1493,43 +1512,43 @@ "# feature_columns = [\n", "# 'undist_profit_ps', \n", "# 'AR_BR', \n", - "# 'pe_ttm',\n", - "# 'alpha_22_improved', \n", - "# 'alpha_003', \n", - "# 'alpha_007', \n", - "# 'alpha_013', \n", - "# 'cat_up_limit', \n", - "# 'cat_down_limit', \n", - "# 'up_limit_count_10d', \n", - "# 'down_limit_count_10d', \n", - "# 'consecutive_up_limit', \n", - "# 'vol_break', \n", - "# 'weight_roc5', \n", - "# 'price_cost_divergence', \n", - "# 'smallcap_concentration', \n", - "# 'cost_stability', \n", - "# 'high_cost_break_days', \n", - "# 'liquidity_risk', \n", - "# 'turnover_std', \n", - "# 'mv_volatility', \n", - "# 'volume_growth', \n", - "# 'mv_growth', \n", - "# 'lg_flow_mom_corr_20_60', \n", - "# 'lg_flow_accel', \n", - "# 'profit_pressure', \n", - "# 'underwater_resistance', \n", - "# 'cost_conc_std_20', \n", - "# 'profit_decay_20', \n", - "# 'vol_amp_loss_20', \n", - "# 'vol_drop_profit_cnt_5', \n", - "# 'lg_flow_vol_interact_20', \n", - "# 'cost_break_confirm_cnt_5', \n", - "# 'atr_norm_channel_pos_14', \n", - "# 'turnover_diff_skew_20', \n", - "# 'lg_sm_flow_diverge_20', \n", - "# 'pullback_strong_20_20', \n", - "# 'vol_wgt_hist_pos_20', \n", - "# 'vol_adj_roc_20',\n", + "# # 'pe_ttm',\n", + "# # 'alpha_22_improved', \n", + "# # 'alpha_003', \n", + "# # 'alpha_007', \n", + "# # 'alpha_013', \n", + "# # 'cat_up_limit', \n", + "# # 'cat_down_limit', \n", + "# # 'up_limit_count_10d', \n", + "# # 'down_limit_count_10d', \n", + "# # 'consecutive_up_limit', \n", + "# # 'vol_break', \n", + "# # 'weight_roc5', \n", + "# # 'price_cost_divergence', \n", + "# # 'smallcap_concentration', \n", + "# # 'cost_stability', \n", + "# # 'high_cost_break_days', \n", + "# # 'liquidity_risk', \n", + "# # 'turnover_std', \n", + "# # 'mv_volatility', \n", + "# # 'volume_growth', \n", + "# # 'mv_growth', \n", + "# # 'lg_flow_mom_corr_20_60', \n", + "# # 'lg_flow_accel', \n", + "# # 'profit_pressure', \n", + "# # 'underwater_resistance', \n", + "# # 'cost_conc_std_20', \n", + "# # 'profit_decay_20', \n", + "# # 'vol_amp_loss_20', \n", + "# # 'vol_drop_profit_cnt_5', \n", + "# # 'lg_flow_vol_interact_20', \n", + "# # 'cost_break_confirm_cnt_5', \n", + "# # 'atr_norm_channel_pos_14', \n", + "# # 'turnover_diff_skew_20', \n", + "# # 'lg_sm_flow_diverge_20', \n", + "# # 'pullback_strong_20_20', \n", + "# # 'vol_wgt_hist_pos_20', \n", + "# # 'vol_adj_roc_20',\n", "# 'cashflow_to_ev_factor',\n", "# 'ocfps',\n", "# 'book_to_price_ratio',\n", @@ -1542,7 +1561,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "id": "8f134d435f71e9e2", "metadata": { "ExecuteTime": { @@ -1618,17 +1637,19 @@ " # cat_features = []\n", "\n", " params = {\n", - " 'loss_function': 'CrossEntropy', # 适用于二分类\n", + " 'loss_function': 'Logloss', # 适用于二分类\n", " 'eval_metric': 'Precision', # 评估指标\n", " 'iterations': 500,\n", - " 'learning_rate': 0.05,\n", + " 'learning_rate': 0.01,\n", " 'depth': 8, # 控制模型复杂度\n", - " 'l2_leaf_reg': 3, # L2 正则化\n", + " 'l2_leaf_reg': 1, # L2 正则化\n", " 'verbose': 500,\n", - " 'early_stopping_rounds': 100,\n", + " 'early_stopping_rounds': 300,\n", " # 'one_hot_max_size': 50,\n", " # 'class_weights': [0.6, 1.2]\n", - " 'task_type': 'GPU'\n", + " 'task_type': 'GPU',\n", + " 'has_time': True,\n", + " 'random_seed': 7\n", " }\n", "\n", " train_pool = Pool(data=X_train, label=y_train, cat_features=cat_features)\n", @@ -1645,7 +1666,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "id": "c6eb5cd4-e714-420a-ac48-39af3e11ee81", "metadata": { "ExecuteTime": { @@ -1660,13 +1681,13 @@ "text": [ "train data size: 36400\n", "原始样本数: 36400, 去除标签为空后样本数: 36400\n", - "cat_features: [27, 30, 37, 39, 41, 80, 86, 87, 88, 100, 102, 125]\n" + "cat_features: [27, 30, 37, 39, 41, 80, 86, 87, 88, 100, 102, 141]\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "a830a64e308a436b919bfc0dc59eb9a7", + "model_id": "66258c1f2f874fd0bfd05d169b09cc51", "version_major": 2, "version_minor": 0 }, @@ -1681,10 +1702,11 @@ "name": "stdout", "output_type": "stream", "text": [ - "0:\tlearn: 0.6527197\ttest: 0.3052632\tbest: 0.3052632 (0)\ttotal: 170ms\tremaining: 1m 25s\n", - "bestTest = 0.4869565217\n", - "bestIteration = 83\n", - "Shrink model to first 84 iterations.\n" + "0:\tlearn: 0.6593407\ttest: 0.2558140\tbest: 0.2558140 (0)\ttotal: 118ms\tremaining: 58.9s\n", + "499:\tlearn: 0.9223881\ttest: 0.3881579\tbest: 0.4090909 (449)\ttotal: 43.8s\tremaining: 0us\n", + "bestTest = 0.4090909091\n", + "bestIteration = 449\n", + "Shrink model to first 450 iterations.\n" ] } ], @@ -1696,12 +1718,16 @@ "# feature_contri = [2 if feat.startswith('act_factor') or 'buy' in feat or 'sell' in feat else 1 for feat in feature_columns]\n", "# light_params['feature_contri'] = feature_contri\n", "# print(f'feature_contri: {feature_contri}')\n", - "model, scaler, pca = train_model(train_data.dropna(subset=['label']).groupby('trade_date', group_keys=False).apply(lambda x: x.nsmallest(50, 'total_mv')).merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left').merge(index_data, on='trade_date', how='left'), feature_columns)\n" + "model, scaler, pca = train_model(train_data\n", + " .dropna(subset=['label']).groupby('trade_date', group_keys=False)\n", + " .apply(lambda x: x.nsmallest(50, 'total_mv'))\n", + " .merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n", + " .merge(index_data, on='trade_date', how='left'), feature_columns)\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "id": "5d1522a7538db91b", "metadata": { "ExecuteTime": { @@ -1742,7 +1768,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "id": "09b1799e", "metadata": {}, "outputs": [ @@ -1750,8 +1776,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "174\n", - "['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n" + "190\n", + "['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'undist_profit_ps', 'ocfps', 'AR', 'BR', 'AR_BR', 'cashflow_to_ev_factor', 'book_to_price_ratio', 'turnover_rate_mean_5', 'variance_20', 'bbi_ratio_factor', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'alpha_007', 'alpha_013', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'lg_flow_mom_corr_20_60', 'lg_flow_accel', 'profit_pressure', 'underwater_resistance', 'cost_conc_std_20', 'profit_decay_20', 'vol_amp_loss_20', 'vol_drop_profit_cnt_5', 'lg_flow_vol_interact_20', 'cost_break_confirm_cnt_5', 'atr_norm_channel_pos_14', 'turnover_diff_skew_20', 'lg_sm_flow_diverge_20', 'pullback_strong_20_20', 'vol_wgt_hist_pos_20', 'vol_adj_roc_20', 'cs_rank_net_lg_flow_val', 'cs_rank_elg_buy_ratio', 'cs_rank_rel_profit_margin', 'cs_rank_cost_breadth', 'cs_rank_dist_to_upper_cost', 'cs_rank_winner_rate', 'cs_rank_intraday_range', 'cs_rank_close_pos_in_range', 'cs_rank_pos_in_hist_range', 'cs_rank_vol_x_profit_margin', 'cs_rank_lg_flow_price_concordance', 'cs_rank_turnover_per_winner', 'cs_rank_volume_ratio', 'cs_rank_elg_buy_sell_sm_ratio', 'cs_rank_cost_dist_vol_ratio', 'cs_rank_size', 'cat_up_limit', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile', '000852.SH_MACD', '000905.SH_MACD', '399006.SZ_MACD', '000852.SH_MACD_hist', '000905.SH_MACD_hist', '399006.SZ_MACD_hist', '000852.SH_RSI', '000905.SH_RSI', '399006.SZ_RSI', '000852.SH_Signal_line', '000905.SH_Signal_line', '399006.SZ_Signal_line', '000852.SH_amount_change_rate', '000905.SH_amount_change_rate', '399006.SZ_amount_change_rate', '000852.SH_amount_mean', '000905.SH_amount_mean', '399006.SZ_amount_mean', '000852.SH_daily_return', '000905.SH_daily_return', '399006.SZ_daily_return', '000852.SH_up_ratio_20d', '000905.SH_up_ratio_20d', '399006.SZ_up_ratio_20d', '000852.SH_volatility', '000905.SH_volatility', '399006.SZ_volatility', '000852.SH_volume_change_rate', '000905.SH_volume_change_rate', '399006.SZ_volume_change_rate']\n" ] } ], @@ -1762,7 +1788,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "id": "7e9023cc", "metadata": {}, "outputs": [], @@ -1962,7 +1988,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "id": "a0000d75", "metadata": {}, "outputs": [ @@ -1972,7 +1998,7 @@ "text": [ "开始分析 'score' 在 'circ_mv' 和 'future_return' 下的表现...\n", "准备数据，处理 NaN 值...\n", - "原始数据 173284 行，移除 NaN 后剩余 172470 行用于分析。\n", + "原始数据 173284 行，移除 NaN 后剩余 172527 行用于分析。\n", "对 'circ_mv' 和 'future_return' 进行 100 分位数分箱...\n", "按二维分箱分组计算 Spearman Rank IC...\n", "整理结果用于绘图...\n", @@ -2011,7 +2037,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] diff --git a/main/train/catboost_info/catboost_training.json b/main/train/catboost_info/catboost_training.json index b72fdf8..00e6e1b 100644 --- a/main/train/catboost_info/catboost_training.json +++ b/main/train/catboost_info/catboost_training.json @@ -1,188 +1,504 @@ { -"meta":{"test_sets":["test"],"test_metrics":[{"best_value":"Max","name":"Precision"},{"best_value":"Min","name":"CrossEntropy"}],"learn_metrics":[{"best_value":"Max","name":"Precision"},{"best_value":"Min","name":"CrossEntropy"}],"launch_mode":"Train","parameters":"","iteration_count":500,"learn_sets":["learn"],"name":"experiment"}, +"meta":{"test_sets":["test"],"test_metrics":[{"best_value":"Max","name":"Precision"},{"best_value":"Min","name":"Logloss"}],"learn_metrics":[{"best_value":"Max","name":"Precision"},{"best_value":"Min","name":"Logloss"}],"launch_mode":"Train","parameters":"","iteration_count":500,"learn_sets":["learn"],"name":"experiment"}, "iterations":[ -{"learn":[0.6527196653,0.6539506586],"iteration":0,"passed_time":0.1704216301,"remaining_time":85.04039341,"test":[0.3052631579,0.6606884766]}, -{"learn":[0.7857142857,0.62],"iteration":1,"passed_time":0.2950779788,"remaining_time":73.47441672,"test":[0.3103448276,0.6303273112]}, -{"learn":[0.7876106195,0.5895233377],"iteration":2,"passed_time":0.4276100571,"remaining_time":70.84073279,"test":[0.3035714286,0.6038824327]}, -{"learn":[0.8407079646,0.5620427264],"iteration":3,"passed_time":0.5542017602,"remaining_time":68.72101827,"test":[0.3333333333,0.5790144314]}, -{"learn":[0.8421052632,0.5384506159],"iteration":4,"passed_time":0.6721673662,"remaining_time":66.54456925,"test":[0.3333333333,0.5570897895]}, -{"learn":[0.8854166667,0.5166076215],"iteration":5,"passed_time":0.7938193308,"remaining_time":65.35779157,"test":[0.275862069,0.5386381836]}, -{"learn":[0.9069767442,0.4981064667],"iteration":6,"passed_time":0.9169473001,"remaining_time":64.57928842,"test":[0.2666666667,0.5219863824]}, -{"learn":[0.8910891089,0.4814881886],"iteration":7,"passed_time":1.038504212,"remaining_time":63.86800903,"test":[0.2972972973,0.5076717122]}, -{"learn":[0.8727272727,0.466400298],"iteration":8,"passed_time":1.158593073,"remaining_time":63.20768878,"test":[0.325,0.4940914171]}, -{"learn":[0.8679245283,0.4533062343],"iteration":9,"passed_time":1.278586087,"remaining_time":62.65071826,"test":[0.3333333333,0.4827998589]}, -{"learn":[0.8782608696,0.4415312072],"iteration":10,"passed_time":1.399151768,"remaining_time":62.19865587,"test":[0.3181818182,0.4726039497]}, -{"learn":[0.8740740741,0.4312919494],"iteration":11,"passed_time":1.520614059,"remaining_time":61.83830506,"test":[0.2950819672,0.4643194444]}, -{"learn":[0.8689655172,0.4220624715],"iteration":12,"passed_time":1.65168178,"remaining_time":61.87454051,"test":[0.328358209,0.4554793837]}, -{"learn":[0.8721804511,0.413855426],"iteration":13,"passed_time":1.776064504,"remaining_time":61.65481063,"test":[0.3333333333,0.4476724718]}, -{"learn":[0.8741258741,0.406276303],"iteration":14,"passed_time":1.897701386,"remaining_time":61.35901148,"test":[0.3243243243,0.4417778863]}, -{"learn":[0.8857142857,0.3991897383],"iteration":15,"passed_time":2.022444838,"remaining_time":61.17895635,"test":[0.2898550725,0.4361890734]}, -{"learn":[0.9084507042,0.3933755916],"iteration":16,"passed_time":2.145029892,"remaining_time":60.94408458,"test":[0.3529411765,0.4313453776]}, -{"learn":[0.904,0.3882018776],"iteration":17,"passed_time":2.268690386,"remaining_time":60.75048701,"test":[0.3636363636,0.4262438965]}, -{"learn":[0.9078014184,0.3829967282],"iteration":18,"passed_time":2.391550211,"remaining_time":60.54398166,"test":[0.3333333333,0.4224629449]}, -{"learn":[0.9275362319,0.3780131586],"iteration":19,"passed_time":2.516720082,"remaining_time":60.40128196,"test":[0.3580246914,0.4182514106]}, -{"learn":[0.9310344828,0.3741117915],"iteration":20,"passed_time":2.637116202,"remaining_time":60.1513648,"test":[0.325,0.4148546821]}, -{"learn":[0.9361702128,0.3698772169],"iteration":21,"passed_time":2.7655478,"remaining_time":60.08781129,"test":[0.3582089552,0.4119712728]}, -{"learn":[0.9361702128,0.3662776217],"iteration":22,"passed_time":2.893542191,"remaining_time":60.00954893,"test":[0.350877193,0.4090849338]}, -{"learn":[0.9481481481,0.3634891081],"iteration":23,"passed_time":3.022570118,"remaining_time":59.94764067,"test":[0.3620689655,0.4063893229]}, -{"learn":[0.9618320611,0.3606119554],"iteration":24,"passed_time":3.143817095,"remaining_time":59.73252481,"test":[0.3269230769,0.4043189833]}, -{"learn":[0.9562043796,0.3583850365],"iteration":25,"passed_time":3.264164702,"remaining_time":59.50823341,"test":[0.3043478261,0.4021975098]}, -{"learn":[0.958041958,0.3559227803],"iteration":26,"passed_time":3.386818987,"remaining_time":59.33205114,"test":[0.3191489362,0.4007753364]}, -{"learn":[0.9507042254,0.3537762674],"iteration":27,"passed_time":3.50884831,"remaining_time":59.14915723,"test":[0.2941176471,0.3991743435]}, -{"learn":[0.9503546099,0.3512843579],"iteration":28,"passed_time":3.636351478,"remaining_time":59.05936367,"test":[0.3529411765,0.3976788194]}, -{"learn":[0.9473684211,0.3493274549],"iteration":29,"passed_time":3.758162672,"remaining_time":58.87788186,"test":[0.34375,0.3960837131]}, -{"learn":[0.9480519481,0.3476888615],"iteration":30,"passed_time":3.878833699,"remaining_time":58.68300015,"test":[0.3442622951,0.3951454536]}, -{"learn":[0.9407894737,0.3458803675],"iteration":31,"passed_time":3.99919837,"remaining_time":58.48827616,"test":[0.3928571429,0.3936280653]}, -{"learn":[0.9426751592,0.3436222628],"iteration":32,"passed_time":4.12195062,"remaining_time":58.33184665,"test":[0.3859649123,0.3925985514]}, -{"learn":[0.9622641509,0.3419754362],"iteration":33,"passed_time":4.241224935,"remaining_time":58.12972999,"test":[0.3888888889,0.3917349718]}, -{"learn":[0.9518072289,0.3403367002],"iteration":34,"passed_time":4.361181747,"remaining_time":57.94141464,"test":[0.387755102,0.3910504015]}, -{"learn":[0.9520958084,0.3387332487],"iteration":35,"passed_time":4.483649917,"remaining_time":57.78926559,"test":[0.46,0.3901231011]}, -{"learn":[0.95,0.3373228288],"iteration":36,"passed_time":4.603690386,"remaining_time":57.60834186,"test":[0.4666666667,0.3894119737]}, -{"learn":[0.9451219512,0.3361083272],"iteration":37,"passed_time":4.722536707,"remaining_time":57.41610417,"test":[0.4285714286,0.3887729763]}, -{"learn":[0.9515151515,0.3348690907],"iteration":38,"passed_time":4.842935168,"remaining_time":57.24597724,"test":[0.4,0.388536594]}, -{"learn":[0.9553072626,0.33377502],"iteration":39,"passed_time":4.977564421,"remaining_time":57.24199084,"test":[0.4821428571,0.3876555447]}, -{"learn":[0.9516129032,0.3329283688],"iteration":40,"passed_time":5.095291287,"remaining_time":57.04240733,"test":[0.4259259259,0.3868581814]}, -{"learn":[0.9441624365,0.3318725764],"iteration":41,"passed_time":5.214816884,"remaining_time":56.8663365,"test":[0.4210526316,0.3866296929]}, -{"learn":[0.945,0.3308382043],"iteration":42,"passed_time":5.338435483,"remaining_time":56.73639572,"test":[0.4482758621,0.3860138346]}, -{"learn":[0.95,0.3292620538],"iteration":43,"passed_time":5.465617855,"remaining_time":56.64367596,"test":[0.3818181818,0.3857928331]}, -{"learn":[0.9466019417,0.3283621194],"iteration":44,"passed_time":5.58926307,"remaining_time":56.51365993,"test":[0.4,0.3855309787]}, -{"learn":[0.9468599034,0.3272893262],"iteration":45,"passed_time":5.712551007,"remaining_time":56.38039472,"test":[0.3962264151,0.3852399902]}, -{"learn":[0.9488372093,0.3261484589],"iteration":46,"passed_time":5.840725769,"remaining_time":56.29465476,"test":[0.4333333333,0.3847372504]}, -{"learn":[0.9497716895,0.3251783474],"iteration":47,"passed_time":5.966260754,"remaining_time":56.18228877,"test":[0.3846153846,0.384755995]}, -{"learn":[0.9475982533,0.3244344848],"iteration":48,"passed_time":6.087916427,"remaining_time":56.03367977,"test":[0.358490566,0.3844680718]}, -{"learn":[0.9475982533,0.323543425],"iteration":49,"passed_time":6.209089608,"remaining_time":55.88180647,"test":[0.358490566,0.3843583713]}, -{"learn":[0.9605263158,0.3229784443],"iteration":50,"passed_time":6.331174542,"remaining_time":55.73916411,"test":[0.3653846154,0.3842032064]}, -{"learn":[0.9570815451,0.3219528399],"iteration":51,"passed_time":6.457371993,"remaining_time":55.63274333,"test":[0.3653846154,0.3838373752]}, -{"learn":[0.9565217391,0.3212596231],"iteration":52,"passed_time":6.584279947,"remaining_time":55.53156861,"test":[0.3191489362,0.383723036]}, -{"learn":[0.9567099567,0.3205928875],"iteration":53,"passed_time":6.705895701,"remaining_time":55.38573116,"test":[0.3265306122,0.3835469564]}, -{"learn":[0.9608695652,0.3193251383],"iteration":54,"passed_time":6.838459636,"remaining_time":55.32935523,"test":[0.3333333333,0.3837113173]}, -{"learn":[0.9663865546,0.3186993185],"iteration":55,"passed_time":6.965939149,"remaining_time":55.22994611,"test":[0.3492063492,0.3836729058]}, -{"learn":[0.9628099174,0.3180124458],"iteration":56,"passed_time":7.087588682,"remaining_time":55.08424186,"test":[0.3442622951,0.3837430556]}, -{"learn":[0.9674796748,0.3170894161],"iteration":57,"passed_time":7.210565306,"remaining_time":54.94948043,"test":[0.380952381,0.3837650011]}, -{"learn":[0.9603174603,0.3165342011],"iteration":58,"passed_time":7.335569909,"remaining_time":54.83027678,"test":[0.4179104478,0.3837915853]}, -{"learn":[0.9619771863,0.3155287337],"iteration":59,"passed_time":7.463969063,"remaining_time":54.73577313,"test":[0.4090909091,0.383500217]}, -{"learn":[0.962962963,0.3146865733],"iteration":60,"passed_time":7.587886848,"remaining_time":54.60790699,"test":[0.4153846154,0.38315389]}, -{"learn":[0.9635036496,0.3140015896],"iteration":61,"passed_time":7.708142525,"remaining_time":54.4542972,"test":[0.4029850746,0.383358724]}, -{"learn":[0.9642857143,0.313511063],"iteration":62,"passed_time":7.824912191,"remaining_time":54.27756552,"test":[0.3943661972,0.3832910699]}, -{"learn":[0.9615384615,0.3127688398],"iteration":63,"passed_time":7.945784422,"remaining_time":54.13065638,"test":[0.4027777778,0.3833045247]}, -{"learn":[0.9612676056,0.312167149],"iteration":64,"passed_time":8.066603549,"remaining_time":53.98419298,"test":[0.4303797468,0.3834173448]}, -{"learn":[0.9620689655,0.3110078553],"iteration":65,"passed_time":8.191536296,"remaining_time":53.86555686,"test":[0.4285714286,0.3834139811]}, -{"learn":[0.9632107023,0.3105276289],"iteration":66,"passed_time":8.312480346,"remaining_time":53.72095507,"test":[0.4285714286,0.3833682997]}, -{"learn":[0.9636963696,0.3099715585],"iteration":67,"passed_time":8.432648044,"remaining_time":53.57211698,"test":[0.4186046512,0.3834855143]}, -{"learn":[0.9617834395,0.3091966882],"iteration":68,"passed_time":8.554677971,"remaining_time":53.43574211,"test":[0.4137931034,0.3837184516]}, -{"learn":[0.9692307692,0.3085731852],"iteration":69,"passed_time":8.672996662,"remaining_time":53.27697949,"test":[0.404494382,0.3835157335]}, -{"learn":[0.9607250755,0.3076873289],"iteration":70,"passed_time":8.798956841,"remaining_time":53.16552796,"test":[0.4090909091,0.3835523275]}, -{"learn":[0.9643916914,0.3061730868],"iteration":71,"passed_time":8.924453169,"remaining_time":53.05091606,"test":[0.4137931034,0.3835948351]}, -{"learn":[0.9591836735,0.3057069029],"iteration":72,"passed_time":9.041490202,"remaining_time":52.88652488,"test":[0.4090909091,0.3834436578]}, -{"learn":[0.9548022599,0.3049678518],"iteration":73,"passed_time":9.165797079,"remaining_time":52.76526427,"test":[0.4137931034,0.383366428]}, -{"learn":[0.9582172702,0.3040258967],"iteration":74,"passed_time":9.291281678,"remaining_time":52.65059617,"test":[0.4,0.3833662109]}, -{"learn":[0.958677686,0.3035014399],"iteration":75,"passed_time":9.408687289,"remaining_time":52.49057119,"test":[0.4210526316,0.3832851291]}, -{"learn":[0.9568733154,0.3029796561],"iteration":76,"passed_time":9.528549381,"remaining_time":52.3451479,"test":[0.4141414141,0.3835284288]}, -{"learn":[0.9572192513,0.3022192917],"iteration":77,"passed_time":9.661554109,"remaining_time":52.27148505,"test":[0.4537037037,0.3835838759]}, -{"learn":[0.9603174603,0.3015648167],"iteration":78,"passed_time":9.78353326,"remaining_time":52.13756332,"test":[0.4545454545,0.3836141493]}, -{"learn":[0.9557291667,0.3011355925],"iteration":79,"passed_time":9.907809037,"remaining_time":52.01599745,"test":[0.4587155963,0.3835327148]}, -{"learn":[0.9567430025,0.300810333],"iteration":80,"passed_time":10.03221249,"remaining_time":51.89502513,"test":[0.4818181818,0.3835458442]}, -{"learn":[0.9573934837,0.3003533089],"iteration":81,"passed_time":10.15267684,"remaining_time":51.75388927,"test":[0.4821428571,0.3835291612]}, -{"learn":[0.9580246914,0.3000302235],"iteration":82,"passed_time":10.27560952,"remaining_time":51.62565263,"test":[0.4774774775,0.3835062391]}, -{"learn":[0.9581280788,0.2995648951],"iteration":83,"passed_time":10.40172755,"remaining_time":51.51331738,"test":[0.4869565217,0.3834068197]}, -{"learn":[0.9608801956,0.2991294337],"iteration":84,"passed_time":10.52954193,"remaining_time":51.40894001,"test":[0.4833333333,0.3833978136]}, -{"learn":[0.9591346154,0.2989826642],"iteration":85,"passed_time":10.64606112,"remaining_time":51.24964308,"test":[0.4836065574,0.3834318576]}, -{"learn":[0.9578454333,0.2979737041],"iteration":86,"passed_time":10.77236674,"remaining_time":51.13778696,"test":[0.4833333333,0.3833043077]}, -{"learn":[0.9627039627,0.2973494526],"iteration":87,"passed_time":10.90129542,"remaining_time":51.03788312,"test":[0.4833333333,0.3831566026]}, -{"learn":[0.9608294931,0.2969713019],"iteration":88,"passed_time":11.02439735,"remaining_time":50.91041923,"test":[0.475,0.3831979167]}, -{"learn":[0.9567198178,0.2965064011],"iteration":89,"passed_time":11.14676163,"remaining_time":50.77969188,"test":[0.4615384615,0.3832379286]}, -{"learn":[0.9573033708,0.2960730782],"iteration":90,"passed_time":11.26428745,"remaining_time":50.62740185,"test":[0.4705882353,0.3833047689]}, -{"learn":[0.9577777778,0.2954965678],"iteration":91,"passed_time":11.38460454,"remaining_time":50.48824622,"test":[0.4615384615,0.3834944661]}, -{"learn":[0.9558498896,0.2948055607],"iteration":92,"passed_time":11.50721485,"remaining_time":50.35953167,"test":[0.4628099174,0.3836822645]}, -{"learn":[0.9564270153,0.2939628122],"iteration":93,"passed_time":11.62947966,"remaining_time":50.22945471,"test":[0.4634146341,0.3837473145]}, -{"learn":[0.9569892473,0.293530612],"iteration":94,"passed_time":11.74780507,"remaining_time":50.08274795,"test":[0.4634146341,0.383617079]}, -{"learn":[0.9574468085,0.2922860473],"iteration":95,"passed_time":11.87327676,"remaining_time":49.96670637,"test":[0.4596774194,0.3836049805]}, -{"learn":[0.9576271186,0.2914134138],"iteration":96,"passed_time":11.99836233,"remaining_time":49.84886616,"test":[0.4621848739,0.3837751194]}, -{"learn":[0.9604166667,0.2907755653],"iteration":97,"passed_time":12.1164863,"remaining_time":49.70232136,"test":[0.4758064516,0.3837325846]}, -{"learn":[0.9608247423,0.2901806284],"iteration":98,"passed_time":12.23866496,"remaining_time":49.57277425,"test":[0.4758064516,0.3837513021]}, -{"learn":[0.9633401222,0.2895748745],"iteration":99,"passed_time":12.35783213,"remaining_time":49.4313285,"test":[0.472,0.3836912435]}, -{"learn":[0.9618473896,0.288912309],"iteration":100,"passed_time":12.48495607,"remaining_time":49.32175714,"test":[0.4761904762,0.3834313151]}, -{"learn":[0.9620758483,0.2882808223],"iteration":101,"passed_time":12.60736898,"remaining_time":49.19345936,"test":[0.4596774194,0.3834144423]}, -{"learn":[0.9608610568,0.2876833728],"iteration":102,"passed_time":12.72942753,"remaining_time":49.06390999,"test":[0.4462809917,0.3839306912]}, -{"learn":[0.9610136452,0.286969306],"iteration":103,"passed_time":12.85518263,"remaining_time":48.94858,"test":[0.44,0.3839262967]}, -{"learn":[0.9619771863,0.286024464],"iteration":104,"passed_time":12.978483,"remaining_time":48.823817,"test":[0.44,0.3838380534]}, -{"learn":[0.961038961,0.2852715307],"iteration":105,"passed_time":13.10284896,"remaining_time":48.70304238,"test":[0.4186046512,0.3838293186]}, -{"learn":[0.9616087751,0.284758176],"iteration":106,"passed_time":13.22961176,"remaining_time":48.59100394,"test":[0.4108527132,0.384031901]}, -{"learn":[0.9616087751,0.2843796868],"iteration":107,"passed_time":13.35321679,"remaining_time":48.4672313,"test":[0.421875,0.3838463542]}, -{"learn":[0.9583333333,0.2836953446],"iteration":108,"passed_time":13.47640899,"remaining_time":48.34198088,"test":[0.4351145038,0.3837952474]}, -{"learn":[0.9584837545,0.2826532918],"iteration":109,"passed_time":13.60248921,"remaining_time":48.22700722,"test":[0.4263565891,0.3839005263]}, -{"learn":[0.9625,0.2820946196],"iteration":110,"passed_time":13.72331078,"remaining_time":48.09340446,"test":[0.4453125,0.3837520616]}, -{"learn":[0.9625668449,0.2815772197],"iteration":111,"passed_time":13.84336606,"remaining_time":47.95737529,"test":[0.44,0.3839232585]}, -{"learn":[0.963028169,0.2812213803],"iteration":112,"passed_time":13.96402904,"remaining_time":47.82371009,"test":[0.4444444444,0.3838974609]}, -{"learn":[0.9602763385,0.280713746],"iteration":113,"passed_time":14.0873207,"remaining_time":47.6991736,"test":[0.4461538462,0.3840630968]}, -{"learn":[0.9605488851,0.280147518],"iteration":114,"passed_time":14.20686771,"remaining_time":47.56212232,"test":[0.4552238806,0.3841141493]}, -{"learn":[0.9641638225,0.2793720062],"iteration":115,"passed_time":14.33028732,"remaining_time":47.43819251,"test":[0.4552238806,0.3842514648]}, -{"learn":[0.9642248722,0.2788365363],"iteration":116,"passed_time":14.45207665,"remaining_time":47.30893466,"test":[0.4718309859,0.3843915473]}, -{"learn":[0.9644067797,0.278158057],"iteration":117,"passed_time":14.57452588,"remaining_time":47.1819397,"test":[0.4620689655,0.3844533963]}, -{"learn":[0.9646464646,0.2771244333],"iteration":118,"passed_time":14.70143969,"remaining_time":47.06931532,"test":[0.4557823129,0.3845418023]}, -{"learn":[0.9647058824,0.2767586322],"iteration":119,"passed_time":14.82560353,"remaining_time":46.94774451,"test":[0.4657534247,0.3844443359]}, -{"learn":[0.9648241206,0.2761904796],"iteration":120,"passed_time":14.9468225,"remaining_time":46.81690683,"test":[0.46,0.3846325955]}, -{"learn":[0.9633943428,0.2758859632],"iteration":121,"passed_time":15.07671395,"remaining_time":46.71309732,"test":[0.4630872483,0.3846319987]}, -{"learn":[0.9636963696,0.2752923094],"iteration":122,"passed_time":15.19680306,"remaining_time":46.57881913,"test":[0.4630872483,0.3846895616]}, -{"learn":[0.9623567921,0.2747471808],"iteration":123,"passed_time":15.31794667,"remaining_time":46.44796732,"test":[0.4557823129,0.3846195747]}, -{"learn":[0.9627831715,0.2743734318],"iteration":124,"passed_time":15.43890562,"remaining_time":46.31671687,"test":[0.4765100671,0.3847169596]}, -{"learn":[0.9632,0.2735782462],"iteration":125,"passed_time":15.56165715,"remaining_time":46.19095058,"test":[0.4709677419,0.3849635688]}, -{"learn":[0.9634920635,0.273085884],"iteration":126,"passed_time":15.68618915,"remaining_time":46.07046106,"test":[0.4585987261,0.3850583767]}, -{"learn":[0.9636650869,0.2727205285],"iteration":127,"passed_time":15.80627133,"remaining_time":45.93697606,"test":[0.4545454545,0.3852940538]}, -{"learn":[0.963836478,0.2722575701],"iteration":128,"passed_time":15.92681884,"remaining_time":45.80503713,"test":[0.4575163399,0.3853448079]}, -{"learn":[0.9609375,0.2718730397],"iteration":129,"passed_time":16.05113122,"remaining_time":45.68398886,"test":[0.474025974,0.3852395562]}, -{"learn":[0.9625585023,0.2715995844],"iteration":130,"passed_time":16.16967387,"remaining_time":45.5466386,"test":[0.464516129,0.3851817763]}, -{"learn":[0.9628482972,0.2709222457],"iteration":131,"passed_time":16.29191733,"remaining_time":45.41989075,"test":[0.461038961,0.385196913]}, -{"learn":[0.9615975422,0.2703818039],"iteration":132,"passed_time":16.41715677,"remaining_time":45.30147769,"test":[0.4545454545,0.3849804145]}, -{"learn":[0.9630200308,0.2697465393],"iteration":133,"passed_time":16.54478982,"remaining_time":45.18950054,"test":[0.4551282051,0.3849924859]}, -{"learn":[0.9618902439,0.2693822351],"iteration":134,"passed_time":16.66373437,"remaining_time":45.05380033,"test":[0.4575163399,0.3848855252]}, -{"learn":[0.9653614458,0.269036197],"iteration":135,"passed_time":16.78448197,"remaining_time":44.92317233,"test":[0.4539473684,0.3850203451]}, -{"learn":[0.9654654655,0.2682332416],"iteration":136,"passed_time":16.91057141,"remaining_time":44.80684248,"test":[0.4539473684,0.3852070584]}, -{"learn":[0.9689349112,0.2676281471],"iteration":137,"passed_time":17.03539256,"remaining_time":44.68704425,"test":[0.4503311258,0.385253852]}, -{"learn":[0.9693877551,0.2671804609],"iteration":138,"passed_time":17.15566682,"remaining_time":44.55536491,"test":[0.4520547945,0.3853320041]}, -{"learn":[0.969740634,0.2666987376],"iteration":139,"passed_time":17.27763805,"remaining_time":44.42821212,"test":[0.4585987261,0.3856692166]}, -{"learn":[0.9713467049,0.2663339523],"iteration":140,"passed_time":17.39819883,"remaining_time":44.2975417,"test":[0.4615384615,0.3857099067]}, -{"learn":[0.9715099715,0.2655467324],"iteration":141,"passed_time":17.52105746,"remaining_time":44.17280683,"test":[0.464516129,0.3856298286]}, -{"learn":[0.9702549575,0.2647545941],"iteration":142,"passed_time":17.64559282,"remaining_time":44.05228416,"test":[0.4591194969,0.3853765734]}, -{"learn":[0.9664335664,0.264308494],"iteration":143,"passed_time":17.76426858,"remaining_time":43.91721955,"test":[0.4782608696,0.3855229221]}, -{"learn":[0.9705469846,0.2636648359],"iteration":144,"passed_time":17.88727948,"remaining_time":43.79299458,"test":[0.4691358025,0.3854374729]}, -{"learn":[0.9694019471,0.2633127388],"iteration":145,"passed_time":18.00748594,"remaining_time":43.66198645,"test":[0.472392638,0.3854031033]}, -{"learn":[0.9708737864,0.2630347036],"iteration":146,"passed_time":18.13334175,"remaining_time":43.54469142,"test":[0.4785276074,0.3854896105]}, -{"learn":[0.9710743802,0.2628232814],"iteration":147,"passed_time":18.2567341,"remaining_time":43.42142164,"test":[0.4720496894,0.385499566]}, -{"learn":[0.9725274725,0.2625271762],"iteration":148,"passed_time":18.37609875,"remaining_time":43.28866216,"test":[0.472392638,0.3856041667]}, -{"learn":[0.9702300406,0.2618719883],"iteration":149,"passed_time":18.50105793,"remaining_time":43.16913516,"test":[0.472392638,0.3857845323]}, -{"learn":[0.9689608637,0.261406945],"iteration":150,"passed_time":18.62245265,"remaining_time":43.04129784,"test":[0.472392638,0.385792589]}, -{"learn":[0.9666221629,0.2607731595],"iteration":151,"passed_time":18.75292121,"remaining_time":42.93431961,"test":[0.4764705882,0.3857090115]}, -{"learn":[0.9667994688,0.2604694628],"iteration":152,"passed_time":18.87279837,"remaining_time":42.8030133,"test":[0.4698795181,0.3857729221]}, -{"learn":[0.9670184697,0.2600434285],"iteration":153,"passed_time":19.01008333,"remaining_time":42.71096645,"test":[0.4610778443,0.3858970812]}, -{"learn":[0.9659685864,0.259592499],"iteration":154,"passed_time":19.14002223,"remaining_time":42.60198496,"test":[0.4545454545,0.3860140516]}, -{"learn":[0.9676165803,0.25914132],"iteration":155,"passed_time":19.26319087,"remaining_time":42.47780552,"test":[0.4375,0.3861292318]}, -{"learn":[0.9664516129,0.2588320099],"iteration":156,"passed_time":19.38714896,"remaining_time":42.35536365,"test":[0.4472049689,0.386065918]}, -{"learn":[0.9715394567,0.2581554017],"iteration":157,"passed_time":19.51471911,"remaining_time":42.24072111,"test":[0.4625,0.386123291]}, -{"learn":[0.9716494845,0.2574764235],"iteration":158,"passed_time":19.63969699,"remaining_time":42.12035643,"test":[0.4556962025,0.3860105252]}, -{"learn":[0.9704749679,0.2567622854],"iteration":159,"passed_time":19.76338724,"remaining_time":41.99719788,"test":[0.4625,0.3859614258]}, -{"learn":[0.9694267516,0.2560285805],"iteration":160,"passed_time":19.88981703,"remaining_time":41.87980108,"test":[0.4528301887,0.3859398058]}, -{"learn":[0.9707750953,0.2553710938],"iteration":161,"passed_time":20.01206766,"remaining_time":41.75357327,"test":[0.4534161491,0.3861076118]}, -{"learn":[0.9721518987,0.2546564924],"iteration":162,"passed_time":20.138895,"remaining_time":41.63685654,"test":[0.4567901235,0.3861334093]}, -{"learn":[0.9738480697,0.2542799634],"iteration":163,"passed_time":20.26082495,"remaining_time":41.50998282,"test":[0.4634146341,0.3860480957]}, -{"learn":[0.973880597,0.2539259773],"iteration":164,"passed_time":20.38106181,"remaining_time":41.37973155,"test":[0.4666666667,0.3861162109]}, -{"learn":[0.975308642,0.2536220667],"iteration":165,"passed_time":20.50097195,"remaining_time":41.24894356,"test":[0.4666666667,0.3862133789]}, -{"learn":[0.9754901961,0.2529050061],"iteration":166,"passed_time":20.62402327,"remaining_time":41.12454939,"test":[0.4596273292,0.3863245985]}, -{"learn":[0.9755501222,0.2525285841],"iteration":167,"passed_time":20.75490886,"remaining_time":41.01565321,"test":[0.450617284,0.3864905328]}, -{"learn":[0.9722222222,0.2520549512],"iteration":168,"passed_time":20.87656001,"remaining_time":40.88841043,"test":[0.4573170732,0.3863822971]}, -{"learn":[0.9723557692,0.2518949055],"iteration":169,"passed_time":20.99534728,"remaining_time":40.75567413,"test":[0.4545454545,0.3864398872]}, -{"learn":[0.972322503,0.2511279119],"iteration":170,"passed_time":21.12215327,"remaining_time":40.63852881,"test":[0.4578313253,0.3864295519]}, -{"learn":[0.9736211031,0.2506003543],"iteration":171,"passed_time":21.24658113,"remaining_time":40.5167361,"test":[0.4561403509,0.3866640354]}, -{"learn":[0.9702026222,0.2503210538],"iteration":172,"passed_time":21.37206483,"remaining_time":40.39690867,"test":[0.4534883721,0.3867054579]}, -{"learn":[0.9714285714,0.2500940743],"iteration":173,"passed_time":21.4941889,"remaining_time":40.27072174,"test":[0.4444444444,0.3866737196]}, -{"learn":[0.9695193435,0.2495754626],"iteration":174,"passed_time":21.61924276,"remaining_time":40.15002227,"test":[0.4425287356,0.3867723253]}, -{"learn":[0.972027972,0.2491294872],"iteration":175,"passed_time":21.74764265,"remaining_time":40.03543307,"test":[0.4540229885,0.3868446181]}, -{"learn":[0.9699769053,0.2486089152],"iteration":176,"passed_time":21.8725331,"remaining_time":39.91428357,"test":[0.4488636364,0.3868221571]}, -{"learn":[0.9711316397,0.2481818652],"iteration":177,"passed_time":21.99563282,"remaining_time":39.78985264,"test":[0.450867052,0.3870137804]}, -{"learn":[0.9711981567,0.247761373],"iteration":178,"passed_time":22.11940045,"remaining_time":39.66663433,"test":[0.450867052,0.3871307237]}, -{"learn":[0.9726339795,0.2473678789],"iteration":179,"passed_time":22.24268922,"remaining_time":39.54255861,"test":[0.4593023256,0.3872641602]}, -{"learn":[0.9727272727,0.2472103459],"iteration":180,"passed_time":22.36284925,"remaining_time":39.4129774,"test":[0.4488636364,0.3872341309]}, -{"learn":[0.9751972943,0.2463777729],"iteration":181,"passed_time":22.49028226,"remaining_time":39.29620747,"test":[0.4425287356,0.3873837619]}, -{"learn":[0.9741863075,0.2460682311],"iteration":182,"passed_time":22.61111091,"remaining_time":39.16788065,"test":[0.4431818182,0.3874805773]}, -{"learn":[0.9765100671,0.2458297217],"iteration":183,"passed_time":22.73156903,"remaining_time":39.03899898,"test":[0.4413407821,0.3874806315]} +{"learn":[0.6593406593,0.68530972],"iteration":0,"passed_time":0.1180197195,"remaining_time":58.89184005,"test":[0.2558139535,0.6860087891]}, +{"learn":[0.722972973,0.6775917398],"iteration":1,"passed_time":0.2132850159,"remaining_time":53.10796895,"test":[0.2533333333,0.6800897895]}, +{"learn":[0.8018018018,0.6700164661],"iteration":2,"passed_time":0.3076668622,"remaining_time":50.9701435,"test":[0.2564102564,0.6740666233]}, +{"learn":[0.8288288288,0.6627022981],"iteration":3,"passed_time":0.396012656,"remaining_time":49.10556934,"test":[0.2878787879,0.6674326714]}, +{"learn":[0.828125,0.6555495837],"iteration":4,"passed_time":0.4895227564,"remaining_time":48.46275289,"test":[0.2876712329,0.6612948134]}, +{"learn":[0.8529411765,0.6486192689],"iteration":5,"passed_time":0.5783312764,"remaining_time":47.61594176,"test":[0.2881355932,0.6558291016]}, +{"learn":[0.8526315789,0.6416034871],"iteration":6,"passed_time":0.6650988341,"remaining_time":46.84196074,"test":[0.3064516129,0.6503930122]}, +{"learn":[0.8571428571,0.6349575872],"iteration":7,"passed_time":0.7358145387,"remaining_time":45.25259413,"test":[0.3064516129,0.6443145074]}, +{"learn":[0.8928571429,0.62841526],"iteration":8,"passed_time":0.8211591903,"remaining_time":44.79879582,"test":[0.2881355932,0.6391426324]}, +{"learn":[0.925,0.6219793568],"iteration":9,"passed_time":0.9101159911,"remaining_time":44.59568356,"test":[0.2619047619,0.633491428]}, +{"learn":[0.9012345679,0.6156481666],"iteration":10,"passed_time":1.000327094,"remaining_time":44.46908625,"test":[0.2857142857,0.6278338759]}, +{"learn":[0.8974358974,0.6094561188],"iteration":11,"passed_time":1.084060358,"remaining_time":44.08512121,"test":[0.2777777778,0.623121582]}, +{"learn":[0.8915662651,0.6034505446],"iteration":12,"passed_time":1.172384707,"remaining_time":43.9193348,"test":[0.2894736842,0.6177204861]}, +{"learn":[0.8717948718,0.5977210809],"iteration":13,"passed_time":1.25881362,"remaining_time":43.69881567,"test":[0.2682926829,0.612516059]}, +{"learn":[0.8888888889,0.5921640839],"iteration":14,"passed_time":1.344031775,"remaining_time":43.45702739,"test":[0.2558139535,0.6081722005]}, +{"learn":[0.8815789474,0.5866051979],"iteration":15,"passed_time":1.429580418,"remaining_time":43.24480765,"test":[0.25,0.603886122]}, +{"learn":[0.8783783784,0.5813390311],"iteration":16,"passed_time":1.515724421,"remaining_time":43.06440561,"test":[0.234375,0.5989835069]}, +{"learn":[0.8658536585,0.5761386576],"iteration":17,"passed_time":1.601031065,"remaining_time":42.87205408,"test":[0.2222222222,0.5947909071]}, +{"learn":[0.875,0.5708657191],"iteration":18,"passed_time":1.694479211,"remaining_time":42.89707898,"test":[0.2461538462,0.5907475586]}, +{"learn":[0.8717948718,0.5658757342],"iteration":19,"passed_time":1.787276272,"remaining_time":42.89463053,"test":[0.2686567164,0.5870367839]}, +{"learn":[0.8734177215,0.5609954166],"iteration":20,"passed_time":1.926566853,"remaining_time":43.94407251,"test":[0.3055555556,0.5832600369]}, +{"learn":[0.8780487805,0.5562411254],"iteration":21,"passed_time":2.090959391,"remaining_time":45.43084495,"test":[0.2923076923,0.5788447808]}, +{"learn":[0.9054054054,0.5516046276],"iteration":22,"passed_time":2.179079003,"remaining_time":45.19220368,"test":[0.2923076923,0.5752951931]}, +{"learn":[0.904109589,0.5470313569],"iteration":23,"passed_time":2.272870833,"remaining_time":45.07860485,"test":[0.2835820896,0.5718381619]}, +{"learn":[0.904109589,0.5426306241],"iteration":24,"passed_time":2.342988907,"remaining_time":44.51678922,"test":[0.28125,0.567686849]}, +{"learn":[0.9066666667,0.5382543054],"iteration":25,"passed_time":2.424572992,"remaining_time":44.20183071,"test":[0.3125,0.5637638889]}, +{"learn":[0.9066666667,0.5339250684],"iteration":26,"passed_time":2.509839235,"remaining_time":43.96866511,"test":[0.2985074627,0.5603147786]}, +{"learn":[0.9090909091,0.5298334854],"iteration":27,"passed_time":2.587084829,"remaining_time":43.61085855,"test":[0.2727272727,0.5568883464]}, +{"learn":[0.9090909091,0.5258193858],"iteration":28,"passed_time":2.683374348,"remaining_time":43.58170061,"test":[0.2957746479,0.5530471463]}, +{"learn":[0.9230769231,0.521902693],"iteration":29,"passed_time":2.765402094,"remaining_time":43.32463281,"test":[0.2857142857,0.5499983181]}, +{"learn":[0.9358974359,0.5180032861],"iteration":30,"passed_time":2.853083735,"remaining_time":43.16439587,"test":[0.2638888889,0.5463741319]}, +{"learn":[0.9259259259,0.5142040303],"iteration":31,"passed_time":2.933209166,"remaining_time":42.89818405,"test":[0.2535211268,0.5435324978]}, +{"learn":[0.9277108434,0.5104505018],"iteration":32,"passed_time":3.009037854,"remaining_time":42.58244479,"test":[0.2702702703,0.5401762695]}, +{"learn":[0.9285714286,0.5068626326],"iteration":33,"passed_time":3.094212938,"remaining_time":42.4089185,"test":[0.2702702703,0.5369085286]}, +{"learn":[0.9318181818,0.50327708],"iteration":34,"passed_time":3.180827358,"remaining_time":42.25956347,"test":[0.2777777778,0.534016276]}, +{"learn":[0.9342105263,0.4999440793],"iteration":35,"passed_time":3.26561702,"remaining_time":42.09017493,"test":[0.2898550725,0.5308427192]}, +{"learn":[0.9342105263,0.4965771484],"iteration":36,"passed_time":3.351992618,"remaining_time":41.94520493,"test":[0.2857142857,0.5285250651]}, +{"learn":[0.9444444444,0.4933516766],"iteration":37,"passed_time":3.4294536,"remaining_time":41.69493587,"test":[0.2923076923,0.5255940213]}, +{"learn":[0.9452054795,0.4901509395],"iteration":38,"passed_time":3.504704767,"remaining_time":41.42740763,"test":[0.2941176471,0.5230288628]}, +{"learn":[0.9459459459,0.4870445797],"iteration":39,"passed_time":3.58457061,"remaining_time":41.22256201,"test":[0.2816901408,0.5206044922]}, +{"learn":[0.9452054795,0.4840240078],"iteration":40,"passed_time":3.670372788,"remaining_time":41.09027096,"test":[0.2739726027,0.5177706163]}, +{"learn":[0.9444444444,0.4811060105],"iteration":41,"passed_time":3.754792982,"remaining_time":40.94512347,"test":[0.2608695652,0.5149946289]}, +{"learn":[0.9333333333,0.478205406],"iteration":42,"passed_time":3.84292368,"remaining_time":40.84223539,"test":[0.2647058824,0.5125646701]}, +{"learn":[0.9358974359,0.4753474281],"iteration":43,"passed_time":3.933099019,"remaining_time":40.76120802,"test":[0.2835820896,0.5104003906]}, +{"learn":[0.9358974359,0.472622997],"iteration":44,"passed_time":4.0164182,"remaining_time":40.61045069,"test":[0.2794117647,0.5082639974]}, +{"learn":[0.9605263158,0.4699823577],"iteration":45,"passed_time":4.088635381,"remaining_time":40.35305354,"test":[0.2898550725,0.5061141493]}, +{"learn":[0.9459459459,0.467461187],"iteration":46,"passed_time":4.174281469,"remaining_time":40.2329682,"test":[0.3,0.5033800456]}, +{"learn":[0.92,0.4648738666],"iteration":47,"passed_time":4.261116371,"remaining_time":40.12551249,"test":[0.2972972973,0.5013963759]}, +{"learn":[0.9230769231,0.4623380831],"iteration":48,"passed_time":4.34657231,"remaining_time":40.00620636,"test":[0.3026315789,0.4989671766]}, +{"learn":[0.9444444444,0.4599138914],"iteration":49,"passed_time":4.396765385,"remaining_time":39.57088847,"test":[0.2835820896,0.4965728082]}, +{"learn":[0.9452054795,0.4574885236],"iteration":50,"passed_time":4.465140883,"remaining_time":39.31075013,"test":[0.2698412698,0.4943103299]}, +{"learn":[0.9459459459,0.4551268818],"iteration":51,"passed_time":4.548380365,"remaining_time":39.18604622,"test":[0.265625,0.4923652886]}, +{"learn":[0.9459459459,0.4528412266],"iteration":52,"passed_time":4.630943827,"remaining_time":39.05720548,"test":[0.2647058824,0.4899832899]}, +{"learn":[0.9444444444,0.4505661211],"iteration":53,"passed_time":4.701529466,"remaining_time":38.83115077,"test":[0.2608695652,0.4883125]}, +{"learn":[0.9342105263,0.448414868],"iteration":54,"passed_time":4.785150821,"remaining_time":38.71622028,"test":[0.2571428571,0.4860696072]}, +{"learn":[0.9452054795,0.4462228059],"iteration":55,"passed_time":4.869391115,"remaining_time":38.60731527,"test":[0.2753623188,0.484335178]}, +{"learn":[0.9189189189,0.4441773352],"iteration":56,"passed_time":4.952339405,"remaining_time":38.48923433,"test":[0.2786885246,0.4827406141]}, +{"learn":[0.92,0.4420920535],"iteration":57,"passed_time":5.033112598,"remaining_time":38.35578911,"test":[0.2835820896,0.481109592]}, +{"learn":[0.925,0.440192283],"iteration":58,"passed_time":5.107178298,"remaining_time":38.17399372,"test":[0.2567567568,0.4791935764]}, +{"learn":[0.9024390244,0.4382421875],"iteration":59,"passed_time":5.190890824,"remaining_time":38.06653271,"test":[0.2666666667,0.4771906467]}, +{"learn":[0.9024390244,0.4363475493],"iteration":60,"passed_time":5.276589156,"remaining_time":37.97414163,"test":[0.2597402597,0.4752754449]}, +{"learn":[0.9024390244,0.4345450787],"iteration":61,"passed_time":5.359365701,"remaining_time":37.86132543,"test":[0.2467532468,0.4733751628]}, +{"learn":[0.9036144578,0.4326472685],"iteration":62,"passed_time":5.442692164,"remaining_time":37.75327739,"test":[0.2658227848,0.4716966146]}, +{"learn":[0.8977272727,0.4308568801],"iteration":63,"passed_time":5.522406531,"remaining_time":37.62139449,"test":[0.2727272727,0.470465115]}, +{"learn":[0.9,0.4291056256],"iteration":64,"passed_time":5.60578845,"remaining_time":37.51566116,"test":[0.2763157895,0.4687495117]}, +{"learn":[0.902173913,0.4273129562],"iteration":65,"passed_time":5.683152312,"remaining_time":37.37103187,"test":[0.2658227848,0.4677815213]}, +{"learn":[0.9090909091,0.4256047559],"iteration":66,"passed_time":5.769686056,"remaining_time":37.28767257,"test":[0.2658227848,0.4665981445]}, +{"learn":[0.8988764045,0.4240742972],"iteration":67,"passed_time":5.853039531,"remaining_time":37.18401584,"test":[0.2658227848,0.4650780165]}, +{"learn":[0.8941176471,0.4224448991],"iteration":68,"passed_time":5.936225134,"remaining_time":37.07989902,"test":[0.2763157895,0.4639363607]}, +{"learn":[0.8953488372,0.4209080249],"iteration":69,"passed_time":6.020384125,"remaining_time":36.98235962,"test":[0.2592592593,0.4623651259]}, +{"learn":[0.8988764045,0.4193174398],"iteration":70,"passed_time":6.109963124,"remaining_time":36.9179462,"test":[0.2658227848,0.4612811415]}, +{"learn":[0.9,0.4177749344],"iteration":71,"passed_time":6.286077567,"remaining_time":37.36723887,"test":[0.2658227848,0.4600519206]}, +{"learn":[0.8988764045,0.4162908445],"iteration":72,"passed_time":6.396948879,"remaining_time":37.41776947,"test":[0.2631578947,0.4586888563]}, +{"learn":[0.9,0.4148385464],"iteration":73,"passed_time":6.481246756,"remaining_time":37.31096105,"test":[0.2666666667,0.4571987305]}, +{"learn":[0.9032258065,0.4133756629],"iteration":74,"passed_time":6.567378911,"remaining_time":37.21514716,"test":[0.2763157895,0.4557921007]}, +{"learn":[0.9052631579,0.4120514941],"iteration":75,"passed_time":6.647588834,"remaining_time":37.08654823,"test":[0.2692307692,0.4544327528]}, +{"learn":[0.8958333333,0.4107138529],"iteration":76,"passed_time":6.716560244,"remaining_time":36.89746731,"test":[0.2763157895,0.4530524902]}, +{"learn":[0.89,0.409451735],"iteration":77,"passed_time":6.797764214,"remaining_time":36.77764742,"test":[0.2763157895,0.4517415365]}, +{"learn":[0.8932038835,0.4082081147],"iteration":78,"passed_time":6.88316382,"remaining_time":36.68116415,"test":[0.2763157895,0.4503851997]}, +{"learn":[0.8921568627,0.4069098212],"iteration":79,"passed_time":6.968326889,"remaining_time":36.58371617,"test":[0.2763157895,0.4495440809]}, +{"learn":[0.8952380952,0.4056634566],"iteration":80,"passed_time":7.051894693,"remaining_time":36.47831946,"test":[0.2820512821,0.4485981717]}, +{"learn":[0.9134615385,0.4043676936],"iteration":81,"passed_time":7.135907983,"remaining_time":36.37572606,"test":[0.2674418605,0.4474966363]}, +{"learn":[0.9038461538,0.4031632071],"iteration":82,"passed_time":7.220888259,"remaining_time":36.2784386,"test":[0.2613636364,0.4467199164]}, +{"learn":[0.9065420561,0.4020146057],"iteration":83,"passed_time":7.306636485,"remaining_time":36.18524736,"test":[0.2674418605,0.4459931098]}, +{"learn":[0.9065420561,0.4008684991],"iteration":84,"passed_time":7.392598197,"remaining_time":36.09327355,"test":[0.2738095238,0.4448997125]}, +{"learn":[0.9082568807,0.3996890682],"iteration":85,"passed_time":7.477298425,"remaining_time":35.99536684,"test":[0.2738095238,0.4441131727]}, +{"learn":[0.9174311927,0.3986428633],"iteration":86,"passed_time":7.562183889,"remaining_time":35.89864306,"test":[0.2674418605,0.4434606391]}, +{"learn":[0.9181818182,0.3975681455],"iteration":87,"passed_time":7.646474719,"remaining_time":35.79940437,"test":[0.2727272727,0.4426331923]}, +{"learn":[0.9026548673,0.3964486984],"iteration":88,"passed_time":7.730912398,"remaining_time":35.70117972,"test":[0.2727272727,0.4419074164]}, +{"learn":[0.9099099099,0.3954416272],"iteration":89,"passed_time":7.815474154,"remaining_time":35.6038267,"test":[0.2727272727,0.4411972114]}, +{"learn":[0.9115044248,0.3943964915],"iteration":90,"passed_time":7.903632971,"remaining_time":35.52292181,"test":[0.2643678161,0.4401203071]}, +{"learn":[0.9107142857,0.3933641152],"iteration":91,"passed_time":7.9890384,"remaining_time":35.42964855,"test":[0.2643678161,0.4394165039]}, +{"learn":[0.9026548673,0.3924092937],"iteration":92,"passed_time":8.072586589,"remaining_time":35.32841658,"test":[0.2588235294,0.4385617676]}, +{"learn":[0.8947368421,0.3914568602],"iteration":93,"passed_time":8.156461224,"remaining_time":35.22897082,"test":[0.2558139535,0.4376505805]}, +{"learn":[0.8965517241,0.390547374],"iteration":94,"passed_time":8.242271262,"remaining_time":35.1381038,"test":[0.2558139535,0.4368015679]}, +{"learn":[0.8965517241,0.3896693944],"iteration":95,"passed_time":8.326359039,"remaining_time":35.04009429,"test":[0.2619047619,0.4361459418]}, +{"learn":[0.8728813559,0.3887562728],"iteration":96,"passed_time":8.41250347,"remaining_time":34.95091648,"test":[0.2588235294,0.4352419705]}, +{"learn":[0.8760330579,0.3878669594],"iteration":97,"passed_time":8.497793498,"remaining_time":34.85829578,"test":[0.2588235294,0.4345669759]}, +{"learn":[0.8813559322,0.3870453995],"iteration":98,"passed_time":8.582997732,"remaining_time":34.76547566,"test":[0.2894736842,0.4337903375]}, +{"learn":[0.868852459,0.386205128],"iteration":99,"passed_time":8.675004036,"remaining_time":34.70001615,"test":[0.2820512821,0.433221951]}, +{"learn":[0.8833333333,0.385424377],"iteration":100,"passed_time":8.752795262,"remaining_time":34.57787435,"test":[0.28,0.432351237]}, +{"learn":[0.8833333333,0.3846496137],"iteration":101,"passed_time":8.836811446,"remaining_time":34.48089172,"test":[0.2837837838,0.431708252]}, +{"learn":[0.9043478261,0.3838790559],"iteration":102,"passed_time":8.890875077,"remaining_time":34.26871268,"test":[0.2957746479,0.4309409451]}, +{"learn":[0.906779661,0.3831366546],"iteration":103,"passed_time":8.97555761,"remaining_time":34.17616167,"test":[0.2727272727,0.4302190484]}, +{"learn":[0.8974358974,0.3823459597],"iteration":104,"passed_time":9.058036794,"remaining_time":34.07547175,"test":[0.2972972973,0.4295053711]}, +{"learn":[0.905982906,0.3816439396],"iteration":105,"passed_time":9.143446538,"remaining_time":33.98601826,"test":[0.2916666667,0.4286525065]}, +{"learn":[0.8925619835,0.3809453054],"iteration":106,"passed_time":9.237197594,"remaining_time":33.92727714,"test":[0.2916666667,0.4278721788]}, +{"learn":[0.9043478261,0.380220974],"iteration":107,"passed_time":9.318178707,"remaining_time":33.82153753,"test":[0.3043478261,0.4273490397]}, +{"learn":[0.9130434783,0.3795425482],"iteration":108,"passed_time":9.402406501,"remaining_time":33.72789855,"test":[0.2763157895,0.4270652941]}, +{"learn":[0.9130434783,0.3788851149],"iteration":109,"passed_time":9.484597275,"remaining_time":33.62720852,"test":[0.2763157895,0.4266154514]}, +{"learn":[0.8947368421,0.3782476049],"iteration":110,"passed_time":9.569309375,"remaining_time":33.53568781,"test":[0.28,0.4261146105]}, +{"learn":[0.9026548673,0.377613659],"iteration":111,"passed_time":9.655144117,"remaining_time":33.44817783,"test":[0.2816901408,0.4254941949]}, +{"learn":[0.9008264463,0.3769072551],"iteration":112,"passed_time":9.738993226,"remaining_time":33.35389715,"test":[0.2777777778,0.4248485786]}, +{"learn":[0.8991596639,0.3762798315],"iteration":113,"passed_time":9.825498539,"remaining_time":33.2687933,"test":[0.2702702703,0.4241246202]}, +{"learn":[0.8991596639,0.3756611399],"iteration":114,"passed_time":9.909808012,"remaining_time":33.17631378,"test":[0.2739726027,0.4233796115]}, +{"learn":[0.8976377953,0.3750953752],"iteration":115,"passed_time":9.991838772,"remaining_time":33.0764318,"test":[0.2702702703,0.4228316515]}, +{"learn":[0.9032258065,0.374501169],"iteration":116,"passed_time":10.07527816,"remaining_time":32.98146613,"test":[0.2702702703,0.4221863607]}, +{"learn":[0.905511811,0.3739479856],"iteration":117,"passed_time":10.15895946,"remaining_time":32.88747893,"test":[0.2702702703,0.4217787815]}, +{"learn":[0.8947368421,0.3733265497],"iteration":118,"passed_time":10.23998547,"remaining_time":32.78516357,"test":[0.2666666667,0.4214532335]}, +{"learn":[0.890625,0.3727895116],"iteration":119,"passed_time":10.32347404,"remaining_time":32.69100114,"test":[0.2631578947,0.4208398166]}, +{"learn":[0.9,0.3722381815],"iteration":120,"passed_time":10.50604595,"remaining_time":32.90736706,"test":[0.2631578947,0.4204434408]}, +{"learn":[0.9076923077,0.371693837],"iteration":121,"passed_time":10.61746535,"remaining_time":32.8967369,"test":[0.25,0.420049018]}, +{"learn":[0.9076923077,0.3711173443],"iteration":122,"passed_time":10.70118302,"remaining_time":32.79956097,"test":[0.2592592593,0.4197871636]}, +{"learn":[0.9090909091,0.3705372163],"iteration":123,"passed_time":10.78984542,"remaining_time":32.71759578,"test":[0.2738095238,0.4194444987]}, +{"learn":[0.9083969466,0.3700201728],"iteration":124,"passed_time":10.87565229,"remaining_time":32.62695688,"test":[0.2771084337,0.4189313694]}, +{"learn":[0.9090909091,0.3695156393],"iteration":125,"passed_time":10.95420223,"remaining_time":32.51485423,"test":[0.2705882353,0.4191120334]}, +{"learn":[0.9104477612,0.3690077198],"iteration":126,"passed_time":11.03866254,"remaining_time":32.4206388,"test":[0.2674418605,0.4187457411]}, +{"learn":[0.9124087591,0.3685299883],"iteration":127,"passed_time":11.12519882,"remaining_time":32.33260908,"test":[0.2727272727,0.4181769206]}, +{"learn":[0.9117647059,0.3680443801],"iteration":128,"passed_time":11.21124736,"remaining_time":32.24319977,"test":[0.2666666667,0.417857449]}, +{"learn":[0.9124087591,0.3676033944],"iteration":129,"passed_time":11.29630688,"remaining_time":32.15102728,"test":[0.2666666667,0.4174021267]}, +{"learn":[0.9117647059,0.367166757],"iteration":130,"passed_time":11.37907344,"remaining_time":32.05250458,"test":[0.2637362637,0.4170373806]}, +{"learn":[0.897810219,0.3667144374],"iteration":131,"passed_time":11.46370997,"remaining_time":31.95943386,"test":[0.2717391304,0.4165036621]}, +{"learn":[0.9,0.3662658959],"iteration":132,"passed_time":11.5478091,"remaining_time":31.86500707,"test":[0.2747252747,0.4159618327]}, +{"learn":[0.9057971014,0.3658401645],"iteration":133,"passed_time":11.63995344,"remaining_time":31.79270865,"test":[0.2747252747,0.4157437609]}, +{"learn":[0.9084507042,0.3653852076],"iteration":134,"passed_time":11.70957904,"remaining_time":31.65923223,"test":[0.2747252747,0.4153919271]}, +{"learn":[0.9078014184,0.3649000627],"iteration":135,"passed_time":11.79743205,"remaining_time":31.5754799,"test":[0.2747252747,0.4150895454]}, +{"learn":[0.9014084507,0.364462855],"iteration":136,"passed_time":11.88585096,"remaining_time":31.49316715,"test":[0.2659574468,0.4147197537]}, +{"learn":[0.8958333333,0.3640970005],"iteration":137,"passed_time":11.96654594,"remaining_time":31.39050457,"test":[0.2608695652,0.4142384711]}, +{"learn":[0.8958333333,0.3636442533],"iteration":138,"passed_time":12.05289583,"remaining_time":31.30284457,"test":[0.2659574468,0.41371148]}, +{"learn":[0.88,0.363245217],"iteration":139,"passed_time":12.13862088,"remaining_time":31.21359655,"test":[0.2736842105,0.4133129069]}, +{"learn":[0.8823529412,0.3628620409],"iteration":140,"passed_time":12.22364732,"remaining_time":31.12261977,"test":[0.2708333333,0.4130907932]}, +{"learn":[0.8881578947,0.3624502809],"iteration":141,"passed_time":12.31142276,"remaining_time":31.03865739,"test":[0.2783505155,0.4126178385]}, +{"learn":[0.8896103896,0.3620806127],"iteration":142,"passed_time":12.39697739,"remaining_time":30.94909741,"test":[0.2631578947,0.4122840983]}, +{"learn":[0.891025641,0.3617276959],"iteration":143,"passed_time":12.4814261,"remaining_time":30.85685897,"test":[0.2783505155,0.4120744629]}, +{"learn":[0.8917197452,0.3613753136],"iteration":144,"passed_time":12.56453115,"remaining_time":30.76143834,"test":[0.2828282828,0.4116843533]}, +{"learn":[0.8853503185,0.3610250342],"iteration":145,"passed_time":12.65164908,"remaining_time":30.67591625,"test":[0.2828282828,0.411454617]}, +{"learn":[0.8917197452,0.3606988481],"iteration":146,"passed_time":12.74071425,"remaining_time":30.59504851,"test":[0.2828282828,0.4110407172]}, +{"learn":[0.8860759494,0.3602493442],"iteration":147,"passed_time":12.82797967,"remaining_time":30.50978949,"test":[0.2828282828,0.4106690809]}, +{"learn":[0.88125,0.3599184891],"iteration":148,"passed_time":12.91527852,"remaining_time":30.42458229,"test":[0.28,0.4106021864]}, +{"learn":[0.8765432099,0.3596188911],"iteration":149,"passed_time":13.01984798,"remaining_time":30.3796453,"test":[0.28,0.4104062229]}, +{"learn":[0.8773006135,0.3592183936],"iteration":150,"passed_time":13.12597869,"remaining_time":30.3375269,"test":[0.28,0.4100428331]}, +{"learn":[0.8780487805,0.3588919223],"iteration":151,"passed_time":13.21023634,"remaining_time":30.24448847,"test":[0.28,0.4099163411]}, +{"learn":[0.8711656442,0.3585073563],"iteration":152,"passed_time":13.29365745,"remaining_time":30.14966755,"test":[0.2828282828,0.4097328016]}, +{"learn":[0.8711656442,0.3581781763],"iteration":153,"passed_time":13.39616821,"remaining_time":30.09788441,"test":[0.28,0.409455485]}, +{"learn":[0.8773006135,0.3578482479],"iteration":154,"passed_time":13.49009313,"remaining_time":30.02633632,"test":[0.28,0.4093768175]}, +{"learn":[0.8734939759,0.3575392763],"iteration":155,"passed_time":13.58464875,"remaining_time":29.95589211,"test":[0.2772277228,0.4091545681]}, +{"learn":[0.875,0.3572412466],"iteration":156,"passed_time":13.67848486,"remaining_time":29.88356883,"test":[0.2745098039,0.4087884386]}, +{"learn":[0.8787878788,0.3568917156],"iteration":157,"passed_time":13.76336279,"remaining_time":29.79158275,"test":[0.2815533981,0.4084727105]}, +{"learn":[0.8773006135,0.3565857023],"iteration":158,"passed_time":13.83941724,"remaining_time":29.68076277,"test":[0.2815533981,0.4082925347]}, +{"learn":[0.8848484848,0.3563088076],"iteration":159,"passed_time":13.93121092,"remaining_time":29.60382321,"test":[0.2788461538,0.4078967828]}, +{"learn":[0.8855421687,0.3559962007],"iteration":160,"passed_time":14.02631099,"remaining_time":29.53366103,"test":[0.2788461538,0.4075260959]}, +{"learn":[0.8902439024,0.3556571125],"iteration":161,"passed_time":14.11654308,"remaining_time":29.45303434,"test":[0.2815533981,0.4072051324]}, +{"learn":[0.8855421687,0.35543956],"iteration":162,"passed_time":14.20074664,"remaining_time":29.35982587,"test":[0.2788461538,0.4069268934]}, +{"learn":[0.8848484848,0.3551621664],"iteration":163,"passed_time":14.28811784,"remaining_time":29.27321705,"test":[0.2788461538,0.4067253689]}, +{"learn":[0.8902439024,0.354874722],"iteration":164,"passed_time":14.37340628,"remaining_time":29.18237032,"test":[0.2735849057,0.4064859755]}, +{"learn":[0.896969697,0.3545863509],"iteration":165,"passed_time":14.46708995,"remaining_time":29.10848218,"test":[0.2735849057,0.4063747287]}, +{"learn":[0.8963414634,0.3542585253],"iteration":166,"passed_time":14.59872472,"remaining_time":29.11003193,"test":[0.2735849057,0.4062399902]}, +{"learn":[0.8963414634,0.3539345489],"iteration":167,"passed_time":14.76935546,"remaining_time":29.18705959,"test":[0.2761904762,0.4061812609]}, +{"learn":[0.8909090909,0.3536960039],"iteration":168,"passed_time":14.85546684,"remaining_time":29.09561848,"test":[0.2761904762,0.4059018826]}, +{"learn":[0.8963414634,0.3534498674],"iteration":169,"passed_time":14.94000312,"remaining_time":29.00118253,"test":[0.2735849057,0.4057597928]}, +{"learn":[0.875739645,0.353215635],"iteration":170,"passed_time":15.02772854,"remaining_time":28.91299819,"test":[0.2788461538,0.4056279568]}, +{"learn":[0.8848484848,0.3529295806],"iteration":171,"passed_time":15.11615009,"remaining_time":28.82614669,"test":[0.2788461538,0.4054673394]}, +{"learn":[0.8915662651,0.352638679],"iteration":172,"passed_time":15.20251972,"remaining_time":28.73539855,"test":[0.2788461538,0.4051953125]}, +{"learn":[0.8902439024,0.3523191934],"iteration":173,"passed_time":15.28648601,"remaining_time":28.64019792,"test":[0.2788461538,0.4052173394]}, +{"learn":[0.8963414634,0.3520754448],"iteration":174,"passed_time":15.3703647,"remaining_time":28.54496302,"test":[0.2857142857,0.4052035862]}, +{"learn":[0.8982035928,0.3518537936],"iteration":175,"passed_time":15.45627806,"remaining_time":28.4536028,"test":[0.2857142857,0.4049254015]}, +{"learn":[0.8941176471,0.3516214145],"iteration":176,"passed_time":15.54225601,"remaining_time":28.36242199,"test":[0.2857142857,0.4048539225]}, +{"learn":[0.8888888889,0.3513249886],"iteration":177,"passed_time":15.63026577,"remaining_time":28.27497516,"test":[0.2924528302,0.4046717665]}, +{"learn":[0.8982035928,0.3511203738],"iteration":178,"passed_time":15.71254564,"remaining_time":28.17724665,"test":[0.2897196262,0.4047108019]}, +{"learn":[0.9,0.3509067775],"iteration":179,"passed_time":15.79876558,"remaining_time":28.08669436,"test":[0.2830188679,0.4044972059]}, +{"learn":[0.9053254438,0.3507023765],"iteration":180,"passed_time":15.87988585,"remaining_time":27.98720213,"test":[0.2830188679,0.4044252658]}, +{"learn":[0.9053254438,0.350465578],"iteration":181,"passed_time":15.96604914,"remaining_time":27.89672323,"test":[0.2857142857,0.4040943739]}, +{"learn":[0.9101796407,0.3502760749],"iteration":182,"passed_time":16.05573204,"remaining_time":27.81238828,"test":[0.2924528302,0.4038273112]}, +{"learn":[0.9058823529,0.3500263743],"iteration":183,"passed_time":16.14284456,"remaining_time":27.72358087,"test":[0.2815533981,0.4037972005]}, +{"learn":[0.9058823529,0.3498100693],"iteration":184,"passed_time":16.23263432,"remaining_time":27.63935033,"test":[0.2815533981,0.4035525445]}, +{"learn":[0.9117647059,0.3496086978],"iteration":185,"passed_time":16.31726814,"remaining_time":27.54635589,"test":[0.2788461538,0.4035713433]}, +{"learn":[0.9117647059,0.3494197651],"iteration":186,"passed_time":16.40091655,"remaining_time":27.45180149,"test":[0.2745098039,0.4033901367]}, +{"learn":[0.9122807018,0.349233042],"iteration":187,"passed_time":16.48958846,"remaining_time":27.3657,"test":[0.2745098039,0.4031182454]}, +{"learn":[0.9075144509,0.3489871194],"iteration":188,"passed_time":16.59129503,"remaining_time":27.30101986,"test":[0.2718446602,0.4028556858]}, +{"learn":[0.9132947977,0.3487706361],"iteration":189,"passed_time":16.67744418,"remaining_time":27.21056682,"test":[0.28,0.4027982856]}, +{"learn":[0.9142857143,0.3485947836],"iteration":190,"passed_time":16.7622203,"remaining_time":27.11793756,"test":[0.28,0.402790446]}, +{"learn":[0.9248554913,0.3483899193],"iteration":191,"passed_time":16.84885642,"remaining_time":27.02837385,"test":[0.2772277228,0.4029530165]}, +{"learn":[0.9248554913,0.3482065109],"iteration":192,"passed_time":16.93512237,"remaining_time":26.93825165,"test":[0.2772277228,0.4028009983]}, +{"learn":[0.9142857143,0.3479946966],"iteration":193,"passed_time":17.03191455,"remaining_time":26.86477244,"test":[0.2828282828,0.4026370985]}, +{"learn":[0.9147727273,0.3477309535],"iteration":194,"passed_time":17.11523988,"remaining_time":26.76999058,"test":[0.2828282828,0.4026086426]}, +{"learn":[0.9147727273,0.3474873475],"iteration":195,"passed_time":17.20898619,"remaining_time":26.69148878,"test":[0.28,0.4025202637]}, +{"learn":[0.9147727273,0.3472967396],"iteration":196,"passed_time":17.30043016,"remaining_time":26.60929105,"test":[0.2772277228,0.4022954644]}, +{"learn":[0.9157303371,0.347078902],"iteration":197,"passed_time":17.38887038,"remaining_time":26.52241847,"test":[0.2772277228,0.4022045085]}, +{"learn":[0.9157303371,0.34688056],"iteration":198,"passed_time":17.47760429,"remaining_time":26.43597433,"test":[0.2815533981,0.4020537923]}, +{"learn":[0.9162011173,0.3466977575],"iteration":199,"passed_time":17.56481979,"remaining_time":26.34722969,"test":[0.2815533981,0.4019348687]}, +{"learn":[0.9116022099,0.3465445013],"iteration":200,"passed_time":17.65671884,"remaining_time":26.26546732,"test":[0.2884615385,0.4017687717]}, +{"learn":[0.912568306,0.3462837876],"iteration":201,"passed_time":17.74228214,"remaining_time":26.17425782,"test":[0.2815533981,0.4015941026]}, +{"learn":[0.912568306,0.346108149],"iteration":202,"passed_time":17.83030821,"remaining_time":26.08670708,"test":[0.2884615385,0.4014142524]}, +{"learn":[0.9086021505,0.3459622348],"iteration":203,"passed_time":17.9082637,"remaining_time":25.98453949,"test":[0.2924528302,0.4013045247]}, +{"learn":[0.9081081081,0.3457472129],"iteration":204,"passed_time":17.99378794,"remaining_time":25.89349971,"test":[0.2897196262,0.4012243924]}, +{"learn":[0.9086021505,0.3455854742],"iteration":205,"passed_time":18.08153043,"remaining_time":25.80567935,"test":[0.2897196262,0.4010365397]}, +{"learn":[0.9095744681,0.345429937],"iteration":206,"passed_time":18.16650382,"remaining_time":25.71394019,"test":[0.2980769231,0.4008413086]}, +{"learn":[0.9100529101,0.3452428932],"iteration":207,"passed_time":18.25403074,"remaining_time":25.62585085,"test":[0.2962962963,0.4006917589]}, +{"learn":[0.9114583333,0.3450315423],"iteration":208,"passed_time":18.33960654,"remaining_time":25.53505025,"test":[0.3047619048,0.4003455404]}, +{"learn":[0.9109947644,0.3448759694],"iteration":209,"passed_time":18.41668992,"remaining_time":25.43257179,"test":[0.3009708738,0.4003435872]}, +{"learn":[0.90625,0.3446913136],"iteration":210,"passed_time":18.49472119,"remaining_time":25.33163234,"test":[0.2941176471,0.4002464735]}, +{"learn":[0.90625,0.3444859503],"iteration":211,"passed_time":18.58055808,"remaining_time":25.24151287,"test":[0.2980769231,0.4000997721]}, +{"learn":[0.90625,0.3442730668],"iteration":212,"passed_time":18.66636298,"remaining_time":25.15139049,"test":[0.3047619048,0.4001095649]}, +{"learn":[0.9057591623,0.3440894089],"iteration":213,"passed_time":18.76614745,"remaining_time":25.07999145,"test":[0.3047619048,0.3999580621]}, +{"learn":[0.9067357513,0.3439525833],"iteration":214,"passed_time":18.92735253,"remaining_time":25.08974638,"test":[0.3039215686,0.3999697266]}, +{"learn":[0.9114583333,0.3438305486],"iteration":215,"passed_time":19.03597572,"remaining_time":25.0287829,"test":[0.2980769231,0.3999312337]}, +{"learn":[0.9114583333,0.3436801437],"iteration":216,"passed_time":19.1161907,"remaining_time":24.93033165,"test":[0.2980769231,0.3998933377]}, +{"learn":[0.9119170984,0.3435236442],"iteration":217,"passed_time":19.18543092,"remaining_time":24.81785101,"test":[0.3106796117,0.3998292914]}, +{"learn":[0.9114583333,0.3433478273],"iteration":218,"passed_time":19.26134459,"remaining_time":24.71432798,"test":[0.3106796117,0.3997649468]}, +{"learn":[0.9119170984,0.3432052991],"iteration":219,"passed_time":19.34310299,"remaining_time":24.61849471,"test":[0.3238095238,0.3997563477]}, +{"learn":[0.9072164948,0.3430779183],"iteration":220,"passed_time":19.42462207,"remaining_time":24.52248668,"test":[0.3173076923,0.3998943956]}, +{"learn":[0.9081632653,0.342938277],"iteration":221,"passed_time":19.50466691,"remaining_time":24.42476307,"test":[0.3173076923,0.3997731662]}, +{"learn":[0.9086294416,0.3427751126],"iteration":222,"passed_time":19.59064066,"remaining_time":24.33456262,"test":[0.3142857143,0.3997895779]}, +{"learn":[0.9086294416,0.3426143719],"iteration":223,"passed_time":19.67711258,"remaining_time":24.24501371,"test":[0.3142857143,0.3997546658]}, +{"learn":[0.9086294416,0.3423794266],"iteration":224,"passed_time":19.76737075,"remaining_time":24.16011981,"test":[0.3076923077,0.3996602919]}, +{"learn":[0.9095477387,0.3422408902],"iteration":225,"passed_time":19.83605043,"remaining_time":24.0490169,"test":[0.3142857143,0.3995736491]}, +{"learn":[0.9090909091,0.3420682453],"iteration":226,"passed_time":19.90743236,"remaining_time":23.9415376,"test":[0.3113207547,0.3995743001]}, +{"learn":[0.9145728643,0.3419356966],"iteration":227,"passed_time":19.99098239,"remaining_time":23.84889127,"test":[0.3047619048,0.3995620388]}, +{"learn":[0.9191919192,0.3417886419],"iteration":228,"passed_time":20.07767823,"remaining_time":23.76004716,"test":[0.3047619048,0.3994820421]}, +{"learn":[0.9191919192,0.3416593721],"iteration":229,"passed_time":20.1627888,"remaining_time":23.66936076,"test":[0.3027522936,0.3994935981]}, +{"learn":[0.923857868,0.3415157034],"iteration":230,"passed_time":20.25874282,"remaining_time":23.59134986,"test":[0.3076923077,0.3994675564]}, +{"learn":[0.923857868,0.3413484047],"iteration":231,"passed_time":20.3425071,"remaining_time":23.49910303,"test":[0.3106796117,0.3995485569]}, +{"learn":[0.9246231156,0.3412097613],"iteration":232,"passed_time":20.4444625,"remaining_time":23.42777463,"test":[0.3106796117,0.3993754883]}, +{"learn":[0.9303482587,0.3410308437],"iteration":233,"passed_time":20.52879222,"remaining_time":23.33614842,"test":[0.320754717,0.3992836914]}, +{"learn":[0.9306930693,0.3408708514],"iteration":234,"passed_time":20.61961925,"remaining_time":23.25191107,"test":[0.320754717,0.3991391059]}, +{"learn":[0.935,0.3407408688],"iteration":235,"passed_time":20.70025336,"remaining_time":23.15621562,"test":[0.320754717,0.3990222711]}, +{"learn":[0.9310344828,0.3405847613],"iteration":236,"passed_time":20.78831696,"remaining_time":23.06889181,"test":[0.320754717,0.3988642578]}, +{"learn":[0.9359605911,0.3404300083],"iteration":237,"passed_time":20.88085071,"remaining_time":22.98648272,"test":[0.320754717,0.3987768012]}, +{"learn":[0.9362745098,0.3402643134],"iteration":238,"passed_time":20.95694544,"remaining_time":22.88603665,"test":[0.3238095238,0.3987998047]}, +{"learn":[0.9317073171,0.3401302321],"iteration":239,"passed_time":21.04336866,"remaining_time":22.79698271,"test":[0.320754717,0.3987548014]}, +{"learn":[0.9323671498,0.3399919451],"iteration":240,"passed_time":21.12140978,"remaining_time":22.69894246,"test":[0.3113207547,0.3986414388]}, +{"learn":[0.9414634146,0.3398047588],"iteration":241,"passed_time":21.20604501,"remaining_time":22.60809757,"test":[0.308411215,0.3986066081]}, +{"learn":[0.9371980676,0.3396306883],"iteration":242,"passed_time":21.28521188,"remaining_time":22.51152039,"test":[0.308411215,0.3984570312]}, +{"learn":[0.9375,0.339554773],"iteration":243,"passed_time":21.37668739,"remaining_time":22.42799988,"test":[0.3148148148,0.3984090441]}, +{"learn":[0.9375,0.3394041187],"iteration":244,"passed_time":21.46241466,"remaining_time":22.33843158,"test":[0.3211009174,0.3983217502]}, +{"learn":[0.9380952381,0.3392554246],"iteration":245,"passed_time":21.54815199,"remaining_time":22.2489049,"test":[0.3181818182,0.3982025282]}, +{"learn":[0.9339622642,0.3388922787],"iteration":246,"passed_time":21.64086728,"remaining_time":22.16655636,"test":[0.3119266055,0.3980964898]}, +{"learn":[0.9342723005,0.3387117216],"iteration":247,"passed_time":21.73453563,"remaining_time":22.08509265,"test":[0.3211009174,0.3979176432]}, +{"learn":[0.9339622642,0.3385895087],"iteration":248,"passed_time":21.81657625,"remaining_time":21.9918098,"test":[0.3240740741,0.3979497342]}, +{"learn":[0.9386792453,0.3385190465],"iteration":249,"passed_time":21.90011477,"remaining_time":21.90011477,"test":[0.3211009174,0.3979514431]}, +{"learn":[0.9348837209,0.3382733377],"iteration":250,"passed_time":21.98875443,"remaining_time":21.81354523,"test":[0.3240740741,0.3977641602]}, +{"learn":[0.9345794393,0.3381529425],"iteration":251,"passed_time":22.07250152,"remaining_time":21.72214435,"test":[0.3240740741,0.3976897515]}, +{"learn":[0.9348837209,0.3380619155],"iteration":252,"passed_time":22.15783447,"remaining_time":21.63235223,"test":[0.3177570093,0.3975579427]}, +{"learn":[0.9348837209,0.3378854927],"iteration":253,"passed_time":22.24284451,"remaining_time":21.54228248,"test":[0.3211009174,0.3977282444]}, +{"learn":[0.9348837209,0.3377540132],"iteration":254,"passed_time":22.32620852,"remaining_time":21.45067093,"test":[0.3211009174,0.3978637695]}, +{"learn":[0.9302325581,0.3375425197],"iteration":255,"passed_time":22.41325369,"remaining_time":21.36263242,"test":[0.3272727273,0.3977652724]}, +{"learn":[0.9302325581,0.3374556983],"iteration":256,"passed_time":22.49297462,"remaining_time":21.26767639,"test":[0.3272727273,0.3977806532]}, +{"learn":[0.9299065421,0.3373343408],"iteration":257,"passed_time":22.58533044,"remaining_time":21.1846898,"test":[0.3272727273,0.3976958008]}, +{"learn":[0.9389671362,0.3372118071],"iteration":258,"passed_time":22.67197435,"remaining_time":21.0963159,"test":[0.3243243243,0.3977214355]}, +{"learn":[0.930875576,0.3370945484],"iteration":259,"passed_time":22.77352428,"remaining_time":21.02171472,"test":[0.3303571429,0.3976886393]}, +{"learn":[0.935483871,0.3369541942],"iteration":260,"passed_time":22.86454055,"remaining_time":20.93726127,"test":[0.3274336283,0.3975975749]}, +{"learn":[0.9400921659,0.3368692618],"iteration":261,"passed_time":22.94836268,"remaining_time":20.84622258,"test":[0.3363636364,0.3975189887]}, +{"learn":[0.9400921659,0.3367536425],"iteration":262,"passed_time":23.1106591,"remaining_time":20.82595516,"test":[0.3394495413,0.3974306641]}, +{"learn":[0.9403669725,0.3366149279],"iteration":263,"passed_time":23.24262988,"remaining_time":20.77750247,"test":[0.3457943925,0.3973971354]}, +{"learn":[0.9406392694,0.3365411511],"iteration":264,"passed_time":23.31824797,"remaining_time":20.67844632,"test":[0.3457943925,0.397331543]}, +{"learn":[0.9406392694,0.3363912095],"iteration":265,"passed_time":23.40794718,"remaining_time":20.59195354,"test":[0.3457943925,0.3972553168]}, +{"learn":[0.9403669725,0.3363007527],"iteration":266,"passed_time":23.49067586,"remaining_time":20.49935384,"test":[0.3457943925,0.3972249891]}, +{"learn":[0.9411764706,0.3361698078],"iteration":267,"passed_time":23.57770761,"remaining_time":20.41055286,"test":[0.3457943925,0.3971032444]}, +{"learn":[0.9447004608,0.3360679103],"iteration":268,"passed_time":23.6597604,"remaining_time":20.31748941,"test":[0.3457943925,0.3970613336]}, +{"learn":[0.9417040359,0.3358984375],"iteration":269,"passed_time":23.74729114,"remaining_time":20.22917393,"test":[0.3457943925,0.3969401584]}, +{"learn":[0.9459459459,0.3357251155],"iteration":270,"passed_time":23.83691417,"remaining_time":20.14263227,"test":[0.3490566038,0.3970305718]}, +{"learn":[0.9414414414,0.3356337677],"iteration":271,"passed_time":23.92222219,"remaining_time":20.05245095,"test":[0.3425925926,0.3970181207]}, +{"learn":[0.9424778761,0.335546376],"iteration":272,"passed_time":24.01352681,"remaining_time":19.96729153,"test":[0.3457943925,0.3969299588]}, +{"learn":[0.9424778761,0.3353878094],"iteration":273,"passed_time":24.10112584,"remaining_time":19.8790308,"test":[0.3457943925,0.3969176432]}, +{"learn":[0.9424778761,0.3352970318],"iteration":274,"passed_time":24.19428793,"remaining_time":19.79532649,"test":[0.3425925926,0.3968911947]}, +{"learn":[0.9424778761,0.3351617031],"iteration":275,"passed_time":24.27310368,"remaining_time":19.69991023,"test":[0.3394495413,0.3968352051]}, +{"learn":[0.9424778761,0.3350522497],"iteration":276,"passed_time":24.35506828,"remaining_time":19.60714883,"test":[0.3394495413,0.396862576]}, +{"learn":[0.9429824561,0.3349684934],"iteration":277,"passed_time":24.44127356,"remaining_time":19.51785155,"test":[0.3394495413,0.3967687174]}, +{"learn":[0.9429824561,0.3347801309],"iteration":278,"passed_time":24.52933498,"remaining_time":19.43004671,"test":[0.3394495413,0.396628852]}, +{"learn":[0.943231441,0.3346032448],"iteration":279,"passed_time":24.61264176,"remaining_time":19.33850424,"test":[0.3486238532,0.3965630154]}, +{"learn":[0.9429824561,0.334415203],"iteration":280,"passed_time":24.69966528,"remaining_time":19.24991707,"test":[0.3486238532,0.3965377333]}, +{"learn":[0.9427312775,0.334342638],"iteration":281,"passed_time":24.78072514,"remaining_time":19.15673078,"test":[0.3486238532,0.3965830621]}, +{"learn":[0.9429824561,0.3341694229],"iteration":282,"passed_time":24.86836848,"remaining_time":19.06867831,"test":[0.3486238532,0.3965849881]}, +{"learn":[0.9388646288,0.3340826015],"iteration":283,"passed_time":24.95016344,"remaining_time":18.97618065,"test":[0.3513513514,0.3966135796]}, +{"learn":[0.9391304348,0.3339726491],"iteration":284,"passed_time":25.0300152,"remaining_time":18.88229217,"test":[0.3454545455,0.3966727159]}, +{"learn":[0.9396551724,0.333826343],"iteration":285,"passed_time":25.11599098,"remaining_time":18.79308416,"test":[0.3394495413,0.3965866428]}, +{"learn":[0.9393939394,0.3336900875],"iteration":286,"passed_time":25.20229437,"remaining_time":18.70414181,"test":[0.3394495413,0.3964724392]}, +{"learn":[0.9396551724,0.3335809549],"iteration":287,"passed_time":25.28592235,"remaining_time":18.6132484,"test":[0.3461538462,0.3964127062]}, +{"learn":[0.9393939394,0.333442062],"iteration":288,"passed_time":25.37410148,"remaining_time":18.52572807,"test":[0.3461538462,0.3963361545]}, +{"learn":[0.9396551724,0.3333525676],"iteration":289,"passed_time":25.46533851,"remaining_time":18.44041754,"test":[0.3461538462,0.3963429091]}, +{"learn":[0.9396551724,0.3332697023],"iteration":290,"passed_time":25.54826696,"remaining_time":18.34909895,"test":[0.3523809524,0.3964152561]}, +{"learn":[0.9401709402,0.3331760379],"iteration":291,"passed_time":25.63453612,"remaining_time":18.26021751,"test":[0.358490566,0.3963829753]}, +{"learn":[0.9399141631,0.3330947765],"iteration":292,"passed_time":25.7174481,"remaining_time":18.1689821,"test":[0.358490566,0.3962185059]}, +{"learn":[0.9358974359,0.3329954451],"iteration":293,"passed_time":25.80328332,"remaining_time":18.07985158,"test":[0.3490566038,0.396163954]}, +{"learn":[0.9358974359,0.3329106552],"iteration":294,"passed_time":25.88687786,"remaining_time":17.98918631,"test":[0.3523809524,0.3961566298]}, +{"learn":[0.936440678,0.3327866603],"iteration":295,"passed_time":25.97218943,"remaining_time":17.89975218,"test":[0.3523809524,0.3961437988]}, +{"learn":[0.9361702128,0.3327275319],"iteration":296,"passed_time":26.05394949,"remaining_time":17.80791834,"test":[0.3523809524,0.3961406793]}, +{"learn":[0.9404255319,0.3326225336],"iteration":297,"passed_time":26.13704192,"remaining_time":17.71705526,"test":[0.3431372549,0.3961118707]}, +{"learn":[0.9411764706,0.3324805757],"iteration":298,"passed_time":26.2188269,"remaining_time":17.62536524,"test":[0.3431372549,0.3961145833]}, +{"learn":[0.9377593361,0.3323966768],"iteration":299,"passed_time":26.30088506,"remaining_time":17.53392337,"test":[0.3366336634,0.3960976562]}, +{"learn":[0.9341563786,0.3322237825],"iteration":300,"passed_time":26.38735182,"remaining_time":17.44545851,"test":[0.3269230769,0.3960027669]}, +{"learn":[0.9377593361,0.3321659016],"iteration":301,"passed_time":26.48038584,"remaining_time":17.36131257,"test":[0.3269230769,0.395966824]}, +{"learn":[0.9380165289,0.3320394474],"iteration":302,"passed_time":26.57257589,"remaining_time":17.27655924,"test":[0.3300970874,0.3959388021]}, +{"learn":[0.9380165289,0.3319693773],"iteration":303,"passed_time":26.65808286,"remaining_time":17.18744816,"test":[0.3238095238,0.3958975966]}, +{"learn":[0.9377593361,0.3318825202],"iteration":304,"passed_time":26.74157625,"remaining_time":17.09707334,"test":[0.3333333333,0.3959249946]}, +{"learn":[0.9382716049,0.3317774863],"iteration":305,"passed_time":26.82903094,"remaining_time":17.00925491,"test":[0.3333333333,0.3958734809]}, +{"learn":[0.9382716049,0.3316979713],"iteration":306,"passed_time":26.91411142,"remaining_time":16.91994627,"test":[0.3333333333,0.3958619249]}, +{"learn":[0.9346938776,0.3315895515],"iteration":307,"passed_time":26.99739535,"remaining_time":16.82954515,"test":[0.3333333333,0.395796875]}, +{"learn":[0.9346938776,0.3315500257],"iteration":308,"passed_time":27.07915579,"remaining_time":16.7382484,"test":[0.3394495413,0.3957655165]}, +{"learn":[0.9390243902,0.3314697978],"iteration":309,"passed_time":27.16020958,"remaining_time":16.64658007,"test":[0.3333333333,0.3957682292]}, +{"learn":[0.939516129,0.3314249615],"iteration":310,"passed_time":27.29737224,"remaining_time":16.58907831,"test":[0.320754717,0.3957937826]}, +{"learn":[0.939516129,0.3312820769],"iteration":311,"passed_time":27.48853832,"remaining_time":16.56360642,"test":[0.320754717,0.3957345378]}, +{"learn":[0.9357429719,0.3311679901],"iteration":312,"passed_time":27.57314048,"remaining_time":16.47340981,"test":[0.3271028037,0.3955753852]}, +{"learn":[0.939516129,0.3311195184],"iteration":313,"passed_time":27.65530136,"remaining_time":16.38180272,"test":[0.3271028037,0.3955834961]}, +{"learn":[0.939516129,0.3310690152],"iteration":314,"passed_time":27.73786295,"remaining_time":16.29049094,"test":[0.3301886792,0.3956049262]}, +{"learn":[0.939516129,0.3309855084],"iteration":315,"passed_time":27.8244982,"remaining_time":16.20160655,"test":[0.3396226415,0.395566786]}, +{"learn":[0.939516129,0.3309401731],"iteration":316,"passed_time":27.90723874,"remaining_time":16.11048798,"test":[0.3396226415,0.3955201823]}, +{"learn":[0.9357429719,0.330802492],"iteration":317,"passed_time":27.99192191,"remaining_time":16.02053392,"test":[0.3396226415,0.3954931369]}, +{"learn":[0.9357429719,0.3307062614],"iteration":318,"passed_time":28.07472743,"remaining_time":15.92954754,"test":[0.3364485981,0.3955254991]}, +{"learn":[0.9357429719,0.330692005],"iteration":319,"passed_time":28.11275266,"remaining_time":15.81342337,"test":[0.3364485981,0.3955166558]}, +{"learn":[0.9357429719,0.3306368684],"iteration":320,"passed_time":28.19625145,"remaining_time":15.72314333,"test":[0.3333333333,0.3955898166]}, +{"learn":[0.9282868526,0.3305426337],"iteration":321,"passed_time":28.28182587,"remaining_time":15.63405281,"test":[0.3363636364,0.3955433485]}, +{"learn":[0.9282868526,0.3305008269],"iteration":322,"passed_time":28.36452869,"remaining_time":15.54341046,"test":[0.3363636364,0.3955307346]}, +{"learn":[0.9282868526,0.3303075459],"iteration":323,"passed_time":28.46528905,"remaining_time":15.46262615,"test":[0.3363636364,0.395464681]}, +{"learn":[0.932,0.3302724396],"iteration":324,"passed_time":28.5461113,"remaining_time":15.37098301,"test":[0.3363636364,0.3954533149]}, +{"learn":[0.932,0.3301259552],"iteration":325,"passed_time":28.63491071,"remaining_time":15.283664,"test":[0.3451327434,0.3954586046]}, +{"learn":[0.9288537549,0.3300699989],"iteration":326,"passed_time":28.72012689,"remaining_time":15.19444022,"test":[0.3451327434,0.3954269477]}, +{"learn":[0.9288537549,0.3299974339],"iteration":327,"passed_time":28.80558888,"remaining_time":15.10536978,"test":[0.3363636364,0.3954387478]}, +{"learn":[0.9288537549,0.3298813512],"iteration":328,"passed_time":28.88937836,"remaining_time":15.01545197,"test":[0.3302752294,0.3953312446]}, +{"learn":[0.9288537549,0.3298155936],"iteration":329,"passed_time":28.97041562,"remaining_time":14.9241535,"test":[0.3272727273,0.3954164225]}, +{"learn":[0.9288537549,0.3297789191],"iteration":330,"passed_time":29.05449698,"remaining_time":14.83447127,"test":[0.3333333333,0.3953617893]}, +{"learn":[0.9288537549,0.3297477332],"iteration":331,"passed_time":29.14016874,"remaining_time":14.74562756,"test":[0.3333333333,0.3953370226]}, +{"learn":[0.9291338583,0.3296651888],"iteration":332,"passed_time":29.22393803,"remaining_time":14.6558488,"test":[0.3392857143,0.3956211209]}, +{"learn":[0.93359375,0.3295453638],"iteration":333,"passed_time":29.30799857,"remaining_time":14.56625078,"test":[0.3392857143,0.3955862901]}, +{"learn":[0.93359375,0.3294967495],"iteration":334,"passed_time":29.38998283,"remaining_time":14.47566319,"test":[0.3392857143,0.3956160753]}, +{"learn":[0.9375,0.3294302079],"iteration":335,"passed_time":29.47248305,"remaining_time":14.38537863,"test":[0.3423423423,0.3956462674]}, +{"learn":[0.9375,0.3294071838],"iteration":336,"passed_time":29.55778933,"remaining_time":14.29649751,"test":[0.3423423423,0.3956146105]}, +{"learn":[0.9375,0.3293788136],"iteration":337,"passed_time":29.6352708,"remaining_time":14.20388719,"test":[0.3423423423,0.3955611165]}, +{"learn":[0.9338521401,0.3292367487],"iteration":338,"passed_time":29.72127773,"remaining_time":14.11541509,"test":[0.3423423423,0.3955461968]}, +{"learn":[0.9338521401,0.3291954408],"iteration":339,"passed_time":29.80385042,"remaining_time":14.02534137,"test":[0.3423423423,0.3955703939]}, +{"learn":[0.9338521401,0.3290744754],"iteration":340,"passed_time":29.89068463,"remaining_time":13.9372987,"test":[0.3392857143,0.3955322266]}, +{"learn":[0.9338521401,0.3290348426],"iteration":341,"passed_time":29.97110284,"remaining_time":13.84629897,"test":[0.3392857143,0.3955233019]}, +{"learn":[0.9338521401,0.329009288],"iteration":342,"passed_time":30.05304958,"remaining_time":13.75606059,"test":[0.3392857143,0.3955158691]}, +{"learn":[0.9338521401,0.3289871906],"iteration":343,"passed_time":30.12350035,"remaining_time":13.66065713,"test":[0.3392857143,0.3955268555]}, +{"learn":[0.9302325581,0.3289021869],"iteration":344,"passed_time":30.20867938,"remaining_time":13.57201537,"test":[0.3392857143,0.3955516493]}, +{"learn":[0.9299610895,0.3288670806],"iteration":345,"passed_time":30.29141568,"remaining_time":13.4823064,"test":[0.3451327434,0.395638482]}, +{"learn":[0.9302325581,0.3287844648],"iteration":346,"passed_time":30.37495698,"remaining_time":13.39299256,"test":[0.3421052632,0.3956229655]}, +{"learn":[0.9305019305,0.3286397625],"iteration":347,"passed_time":30.4672946,"remaining_time":13.30755396,"test":[0.3451327434,0.3955362684]}, +{"learn":[0.9307692308,0.3286172018],"iteration":348,"passed_time":30.55018361,"remaining_time":13.21798775,"test":[0.350877193,0.3955777724]}, +{"learn":[0.9307692308,0.3285155894],"iteration":349,"passed_time":30.63660612,"remaining_time":13.12997405,"test":[0.3448275862,0.3955560438]}, +{"learn":[0.9305019305,0.328492102],"iteration":350,"passed_time":30.71888481,"remaining_time":13.04021036,"test":[0.3448275862,0.3956329753]}, +{"learn":[0.9302325581,0.3284671889],"iteration":351,"passed_time":30.80174179,"remaining_time":12.95073234,"test":[0.3448275862,0.3956309408]}, +{"learn":[0.9307692308,0.3284392108],"iteration":352,"passed_time":30.84683407,"remaining_time":12.84556546,"test":[0.3448275862,0.3956252713]}, +{"learn":[0.9307692308,0.3283767678],"iteration":353,"passed_time":30.93101062,"remaining_time":12.75685749,"test":[0.3448275862,0.3956111925]}, +{"learn":[0.9307692308,0.3283334284],"iteration":354,"passed_time":31.01346103,"remaining_time":12.66747,"test":[0.3529411765,0.3956711155]}, +{"learn":[0.9310344828,0.3283064482],"iteration":355,"passed_time":31.09447775,"remaining_time":12.57754156,"test":[0.3529411765,0.3956999512]}, +{"learn":[0.9310344828,0.3282412252],"iteration":356,"passed_time":31.17834808,"remaining_time":12.48880609,"test":[0.3559322034,0.3956701931]}, +{"learn":[0.9310344828,0.328229535],"iteration":357,"passed_time":31.24775345,"remaining_time":12.39436031,"test":[0.3559322034,0.3957055393]}, +{"learn":[0.9310344828,0.3281949276],"iteration":358,"passed_time":31.32933408,"remaining_time":12.30483595,"test":[0.3559322034,0.3956976454]}, +{"learn":[0.9312977099,0.3280923885],"iteration":359,"passed_time":31.42527601,"remaining_time":12.22094067,"test":[0.3559322034,0.3956993815]}, +{"learn":[0.9310344828,0.3279984389],"iteration":360,"passed_time":31.62056317,"remaining_time":12.17523069,"test":[0.3565217391,0.3957347819]}, +{"learn":[0.9315589354,0.3279718151],"iteration":361,"passed_time":31.72592066,"remaining_time":12.09441174,"test":[0.3565217391,0.3957117242]}, +{"learn":[0.928030303,0.3279480782],"iteration":362,"passed_time":31.80770256,"remaining_time":12.00455992,"test":[0.3565217391,0.3957737088]}, +{"learn":[0.9353612167,0.3278811445],"iteration":363,"passed_time":31.8907592,"remaining_time":11.91522871,"test":[0.3565217391,0.3958093533]}, +{"learn":[0.9353612167,0.3277992059],"iteration":364,"passed_time":31.97337751,"remaining_time":11.82576976,"test":[0.3559322034,0.395843967]}, +{"learn":[0.9318181818,0.3277876226],"iteration":365,"passed_time":32.01734514,"remaining_time":11.7221974,"test":[0.358974359,0.3958595378]}, +{"learn":[0.9318181818,0.3276685105],"iteration":366,"passed_time":32.10489984,"remaining_time":11.63474572,"test":[0.3644067797,0.3958884549]}, +{"learn":[0.9318181818,0.3275194956],"iteration":367,"passed_time":32.19236609,"remaining_time":11.54726175,"test":[0.3697478992,0.3958266873]}, +{"learn":[0.9318181818,0.3275007485],"iteration":368,"passed_time":32.25872825,"remaining_time":11.45228564,"test":[0.3697478992,0.3958477376]}, +{"learn":[0.9318181818,0.3274810034],"iteration":369,"passed_time":32.34138888,"remaining_time":11.36319069,"test":[0.3697478992,0.3958608127]}, +{"learn":[0.9318181818,0.3274523124],"iteration":370,"passed_time":32.42542415,"remaining_time":11.2746084,"test":[0.3781512605,0.3959072808]}, +{"learn":[0.9318181818,0.3273819928],"iteration":371,"passed_time":32.50127658,"remaining_time":11.18323495,"test":[0.3719008264,0.3959447971]}, +{"learn":[0.9318181818,0.3273513415],"iteration":372,"passed_time":32.58363401,"remaining_time":11.09415957,"test":[0.375,0.3959988878]}, +{"learn":[0.9320754717,0.3272574276],"iteration":373,"passed_time":32.66838509,"remaining_time":11.00592653,"test":[0.375,0.3960046929]}, +{"learn":[0.9320754717,0.3272349025],"iteration":374,"passed_time":32.76019626,"remaining_time":10.92006542,"test":[0.3719008264,0.3960830078]}, +{"learn":[0.9320754717,0.3272111656],"iteration":375,"passed_time":32.84434197,"remaining_time":10.83164469,"test":[0.368852459,0.396072781]}, +{"learn":[0.9318181818,0.3271826172],"iteration":376,"passed_time":32.93034678,"remaining_time":10.74385319,"test":[0.368852459,0.3961763238]}, +{"learn":[0.9318181818,0.3271223483],"iteration":377,"passed_time":33.03226033,"remaining_time":10.66120572,"test":[0.3719008264,0.3962508952]}, +{"learn":[0.9318181818,0.3270916971],"iteration":378,"passed_time":33.11642369,"remaining_time":10.57278962,"test":[0.3719008264,0.3962410211]}, +{"learn":[0.9318181818,0.3270695284],"iteration":379,"passed_time":33.19619847,"remaining_time":10.48301004,"test":[0.368852459,0.3962506239]}, +{"learn":[0.9320754717,0.3269869839],"iteration":380,"passed_time":33.28201997,"remaining_time":10.39517159,"test":[0.368852459,0.3962119141]}, +{"learn":[0.9318181818,0.3269538022],"iteration":381,"passed_time":33.36486552,"remaining_time":10.30642443,"test":[0.3658536585,0.396279758]}, +{"learn":[0.9320754717,0.3268146242],"iteration":382,"passed_time":33.45158697,"remaining_time":10.2188921,"test":[0.3709677419,0.396169732]}, +{"learn":[0.9323308271,0.3266813626],"iteration":383,"passed_time":33.52688041,"remaining_time":10.12791179,"test":[0.376,0.3962806261]}, +{"learn":[0.9323308271,0.3266648609],"iteration":384,"passed_time":33.60379653,"remaining_time":10.03749767,"test":[0.376,0.3963204481]}, +{"learn":[0.9323308271,0.3266294694],"iteration":385,"passed_time":33.68692631,"remaining_time":9.948988598,"test":[0.376,0.3963378364]}, +{"learn":[0.9323308271,0.3265899079],"iteration":386,"passed_time":33.80437669,"remaining_time":9.870528594,"test":[0.3790322581,0.3962904188]}, +{"learn":[0.9325842697,0.3264602461],"iteration":387,"passed_time":33.90397047,"remaining_time":9.786713125,"test":[0.373015873,0.3962261556]}, +{"learn":[0.9328358209,0.3264275989],"iteration":388,"passed_time":33.98020363,"remaining_time":9.696150649,"test":[0.373015873,0.3962870551]}, +{"learn":[0.9328358209,0.3261832801],"iteration":389,"passed_time":34.07069224,"remaining_time":9.609682428,"test":[0.376,0.3962442491]}, +{"learn":[0.9293680297,0.3261257912],"iteration":390,"passed_time":34.15477033,"remaining_time":9.521406563,"test":[0.376,0.3962138943]}, +{"learn":[0.9328358209,0.3261000585],"iteration":391,"passed_time":34.24146487,"remaining_time":9.433872974,"test":[0.3790322581,0.3962638346]}, +{"learn":[0.9296296296,0.3260115263],"iteration":392,"passed_time":34.32569979,"remaining_time":9.345673988,"test":[0.380952381,0.3961959093]}, +{"learn":[0.9296296296,0.3260047901],"iteration":393,"passed_time":34.40685672,"remaining_time":9.256667036,"test":[0.380952381,0.3962014703]}, +{"learn":[0.9296296296,0.3259721074],"iteration":394,"passed_time":34.49472834,"remaining_time":9.169484748,"test":[0.380952381,0.3962109646]}, +{"learn":[0.9304029304,0.3258751639],"iteration":395,"passed_time":34.5951066,"remaining_time":9.085583552,"test":[0.376,0.3961991645]}, +{"learn":[0.9306569343,0.3258094064],"iteration":396,"passed_time":34.67394654,"remaining_time":8.996011318,"test":[0.373015873,0.3962114258]}, +{"learn":[0.9306569343,0.3257776859],"iteration":397,"passed_time":34.75584044,"remaining_time":8.907275691,"test":[0.3779527559,0.3962099609]}, +{"learn":[0.9306569343,0.3256861599],"iteration":398,"passed_time":34.84176408,"remaining_time":8.819594415,"test":[0.380952381,0.3961769477]}, +{"learn":[0.9306569343,0.3256791386],"iteration":399,"passed_time":34.92599445,"remaining_time":8.731498613,"test":[0.380952381,0.3961794162]}, +{"learn":[0.9306569343,0.3255725365],"iteration":400,"passed_time":35.01651275,"remaining_time":8.644974468,"test":[0.380952381,0.3962463921]}, +{"learn":[0.9306569343,0.3254692133],"iteration":401,"passed_time":35.10140469,"remaining_time":8.557058856,"test":[0.3858267717,0.3963177897]}, +{"learn":[0.9306569343,0.325401745],"iteration":402,"passed_time":35.18285677,"remaining_time":8.468330289,"test":[0.3828125,0.3963453234]}, +{"learn":[0.9309090909,0.3253311759],"iteration":403,"passed_time":35.26862491,"remaining_time":8.380663346,"test":[0.3858267717,0.3962815755]}, +{"learn":[0.9275362319,0.3253155295],"iteration":404,"passed_time":35.34326554,"remaining_time":8.29039562,"test":[0.3858267717,0.3963497179]}, +{"learn":[0.9275362319,0.3252776788],"iteration":405,"passed_time":35.41913638,"remaining_time":8.200489703,"test":[0.3888888889,0.3964297146]}, +{"learn":[0.9277978339,0.3252604998],"iteration":406,"passed_time":35.50216316,"remaining_time":8.112287897,"test":[0.3888888889,0.3965119358]}, +{"learn":[0.9285714286,0.3251181854],"iteration":407,"passed_time":35.59047205,"remaining_time":8.025302522,"test":[0.3888888889,0.3965547689]}, +{"learn":[0.9283154122,0.3250225607],"iteration":408,"passed_time":35.72463278,"remaining_time":7.948512428,"test":[0.380952381,0.3965233832]}, +{"learn":[0.9290780142,0.3249287893],"iteration":409,"passed_time":35.86590439,"remaining_time":7.873003402,"test":[0.380952381,0.3964287923]}, +{"learn":[0.9288256228,0.3247705078],"iteration":410,"passed_time":35.95009748,"remaining_time":7.784814296,"test":[0.380952381,0.3963786892]}, +{"learn":[0.9293286219,0.3247093123],"iteration":411,"passed_time":36.0342634,"remaining_time":7.696638784,"test":[0.3858267717,0.3964873861]}, +{"learn":[0.9293286219,0.3246648323],"iteration":412,"passed_time":36.11567633,"remaining_time":7.607902762,"test":[0.380952381,0.396547526]}, +{"learn":[0.9295774648,0.3246344662],"iteration":413,"passed_time":36.19840628,"remaining_time":7.5194757,"test":[0.3779527559,0.3965904948]}, +{"learn":[0.9293286219,0.3246129747],"iteration":414,"passed_time":36.28581066,"remaining_time":7.432033509,"test":[0.3828125,0.3966258681]}, +{"learn":[0.9295774648,0.3245792584],"iteration":415,"passed_time":36.37135986,"remaining_time":7.344216895,"test":[0.3828125,0.3966491157]}, +{"learn":[0.9295774648,0.3245577312],"iteration":416,"passed_time":36.45174732,"remaining_time":7.25538376,"test":[0.3828125,0.3966849501]}, +{"learn":[0.9298245614,0.3244512717],"iteration":417,"passed_time":36.54117794,"remaining_time":7.16836505,"test":[0.3828125,0.3966029731]}, +{"learn":[0.9300699301,0.3243873674],"iteration":418,"passed_time":36.62014365,"remaining_time":7.07931178,"test":[0.3875968992,0.3965578885]}, +{"learn":[0.9300699301,0.3243661967],"iteration":419,"passed_time":36.69321703,"remaining_time":6.989184196,"test":[0.3828125,0.3966225857]}, +{"learn":[0.9300699301,0.3242703581],"iteration":420,"passed_time":36.78010457,"remaining_time":6.901729835,"test":[0.3798449612,0.3966976997]}, +{"learn":[0.9305555556,0.3242519674],"iteration":421,"passed_time":36.86265422,"remaining_time":6.813476372,"test":[0.3846153846,0.3967369249]}, +{"learn":[0.9303135889,0.3241523865],"iteration":422,"passed_time":36.94839582,"remaining_time":6.725830917,"test":[0.3846153846,0.3967805447]}, +{"learn":[0.9270833333,0.3241283289],"iteration":423,"passed_time":37.01682497,"remaining_time":6.635091268,"test":[0.3893129771,0.3968391385]}, +{"learn":[0.9270833333,0.3240927592],"iteration":424,"passed_time":37.09795012,"remaining_time":6.54669708,"test":[0.3923076923,0.3968234049]}, +{"learn":[0.9278350515,0.3240085039],"iteration":425,"passed_time":37.1860705,"remaining_time":6.459552152,"test":[0.3863636364,0.3967906087]}, +{"learn":[0.9280821918,0.3239215043],"iteration":426,"passed_time":37.26956916,"remaining_time":6.371612527,"test":[0.3875968992,0.3968460558]}, +{"learn":[0.9249146758,0.3238194642],"iteration":427,"passed_time":37.35567279,"remaining_time":6.284131871,"test":[0.390625,0.3968588053]}, +{"learn":[0.9217687075,0.3237158203],"iteration":428,"passed_time":37.44306508,"remaining_time":6.19687091,"test":[0.390625,0.3968582086]}, +{"learn":[0.9217687075,0.3237044865],"iteration":429,"passed_time":37.51398357,"remaining_time":6.106927557,"test":[0.390625,0.3968792318]}, +{"learn":[0.9225589226,0.3236037651],"iteration":430,"passed_time":37.59647593,"remaining_time":6.018925381,"test":[0.390625,0.3968790148]}, +{"learn":[0.9225589226,0.3235472385],"iteration":431,"passed_time":37.67884864,"remaining_time":5.930929878,"test":[0.390625,0.3968627658]}, +{"learn":[0.9222972973,0.323520294],"iteration":432,"passed_time":37.76185434,"remaining_time":5.843058293,"test":[0.390625,0.3969321832]}, +{"learn":[0.9261744966,0.3234630902],"iteration":433,"passed_time":37.84424666,"remaining_time":5.755115851,"test":[0.3969465649,0.3970285645]}, +{"learn":[0.9264214047,0.3232854913],"iteration":434,"passed_time":37.93112239,"remaining_time":5.667868862,"test":[0.3953488372,0.3970230035]}, +{"learn":[0.9266666667,0.3231383654],"iteration":435,"passed_time":38.01926992,"remaining_time":5.580810264,"test":[0.3969465649,0.3969626194]}, +{"learn":[0.9266666667,0.3230566763],"iteration":436,"passed_time":38.10205005,"remaining_time":5.492972891,"test":[0.4015151515,0.396976454]}, +{"learn":[0.9266666667,0.3230444871],"iteration":437,"passed_time":38.18211191,"remaining_time":5.404773832,"test":[0.4015151515,0.3970442708]}, +{"learn":[0.9238410596,0.3230088461],"iteration":438,"passed_time":38.26463892,"remaining_time":5.316954384,"test":[0.3939393939,0.3970479058]}, +{"learn":[0.9238410596,0.3229739536],"iteration":439,"passed_time":38.34672361,"remaining_time":5.229098674,"test":[0.4,0.397092475]}, +{"learn":[0.9238410596,0.3229666472],"iteration":440,"passed_time":38.42725699,"remaining_time":5.141061592,"test":[0.4,0.3970939128]}, +{"learn":[0.9240924092,0.3228943673],"iteration":441,"passed_time":38.50867142,"remaining_time":5.053174078,"test":[0.4,0.3971435276]}, +{"learn":[0.9240924092,0.3228382328],"iteration":442,"passed_time":38.59478868,"remaining_time":4.965920891,"test":[0.3984962406,0.3972034505]}, +{"learn":[0.9243421053,0.3227665232],"iteration":443,"passed_time":38.67677876,"remaining_time":4.878152276,"test":[0.3955223881,0.397237576]}, +{"learn":[0.9245901639,0.3227103173],"iteration":444,"passed_time":38.76027878,"remaining_time":4.790596254,"test":[0.3984962406,0.3972613118]}, +{"learn":[0.9245901639,0.3226070655],"iteration":445,"passed_time":38.85582887,"remaining_time":4.704517397,"test":[0.3984962406,0.3972632378]}, +{"learn":[0.9273927393,0.3225281207],"iteration":446,"passed_time":38.9417956,"remaining_time":4.617259882,"test":[0.3984962406,0.397224745]}, +{"learn":[0.9273927393,0.3225112982],"iteration":447,"passed_time":39.02104276,"remaining_time":4.529228177,"test":[0.3969465649,0.3972553982]}, +{"learn":[0.9245901639,0.322388123],"iteration":448,"passed_time":39.11221534,"remaining_time":4.442590161,"test":[0.4060150376,0.3972791341]}, +{"learn":[0.9245901639,0.3222409615],"iteration":449,"passed_time":39.19942068,"remaining_time":4.355491187,"test":[0.4090909091,0.397282742]}, +{"learn":[0.9248366013,0.3220693858],"iteration":450,"passed_time":39.31363151,"remaining_time":4.271325819,"test":[0.3939393939,0.3972912869]}, +{"learn":[0.9248366013,0.3219415773],"iteration":451,"passed_time":39.48588117,"remaining_time":4.193190921,"test":[0.3863636364,0.3972827691]}, +{"learn":[0.9248366013,0.3219059364],"iteration":452,"passed_time":39.59508957,"remaining_time":4.108099801,"test":[0.3955223881,0.3973428819]}, +{"learn":[0.9248366013,0.3217937742],"iteration":453,"passed_time":39.68335763,"remaining_time":4.020780729,"test":[0.3955223881,0.3973573134]}, +{"learn":[0.9250814332,0.3216357065],"iteration":454,"passed_time":39.77006634,"remaining_time":3.933303264,"test":[0.401459854,0.3973281521]}, +{"learn":[0.9225806452,0.3216104371],"iteration":455,"passed_time":39.84885684,"remaining_time":3.845065133,"test":[0.401459854,0.397368571]}, +{"learn":[0.9223300971,0.3215952184],"iteration":456,"passed_time":40.02634023,"remaining_time":3.766154551,"test":[0.3985507246,0.3973785265]}, +{"learn":[0.9258064516,0.3214618855],"iteration":457,"passed_time":40.15368124,"remaining_time":3.68221531,"test":[0.3941605839,0.3973622504]}, +{"learn":[0.9258064516,0.3213783788],"iteration":458,"passed_time":40.24008719,"remaining_time":3.594430446,"test":[0.3857142857,0.3973475206]}, +{"learn":[0.9260450161,0.3212732736],"iteration":459,"passed_time":40.32521363,"remaining_time":3.506540316,"test":[0.384057971,0.3972845595]}, +{"learn":[0.9260450161,0.3211840286],"iteration":460,"passed_time":40.40998406,"remaining_time":3.418632057,"test":[0.384057971,0.3972377658]}, +{"learn":[0.9260450161,0.3211772211],"iteration":461,"passed_time":40.48603116,"remaining_time":3.330019879,"test":[0.384057971,0.3972808431]}, +{"learn":[0.9260450161,0.3210794936],"iteration":462,"passed_time":40.57693984,"remaining_time":3.24264962,"test":[0.3884892086,0.3972427572]}, +{"learn":[0.9260450161,0.3209590271],"iteration":463,"passed_time":40.68244289,"remaining_time":3.156396431,"test":[0.3884892086,0.3971559245]}, +{"learn":[0.9260450161,0.3208823991],"iteration":464,"passed_time":40.76808342,"remaining_time":3.068565419,"test":[0.3971631206,0.397151964]}, +{"learn":[0.9262820513,0.3208157861],"iteration":465,"passed_time":40.84770204,"remaining_time":2.98030444,"test":[0.3916083916,0.3971584201]}, +{"learn":[0.9262820513,0.3206734717],"iteration":466,"passed_time":40.9372468,"remaining_time":2.892781894,"test":[0.3888888889,0.3971774631]}, +{"learn":[0.923566879,0.32060415],"iteration":467,"passed_time":41.02433071,"remaining_time":2.805082442,"test":[0.3846153846,0.3971876628]}, +{"learn":[0.9265175719,0.3205238509],"iteration":468,"passed_time":41.1090174,"remaining_time":2.717227163,"test":[0.3888888889,0.3971479492]}, +{"learn":[0.9267515924,0.3204176765],"iteration":469,"passed_time":41.19604965,"remaining_time":2.629535084,"test":[0.3862068966,0.3971354438]}, +{"learn":[0.9238095238,0.3203140682],"iteration":470,"passed_time":41.28181967,"remaining_time":2.54176809,"test":[0.3862068966,0.397108941]}, +{"learn":[0.9242902208,0.3202052207],"iteration":471,"passed_time":41.37048,"remaining_time":2.454181017,"test":[0.3931034483,0.3970946994]}, +{"learn":[0.9247648903,0.3201198606],"iteration":472,"passed_time":41.45672854,"remaining_time":2.366451735,"test":[0.3904109589,0.3971469727]}, +{"learn":[0.9247648903,0.3199963646],"iteration":473,"passed_time":41.54438609,"remaining_time":2.278805988,"test":[0.3904109589,0.3971363932]}, +{"learn":[0.9247648903,0.319894075],"iteration":474,"passed_time":41.63214596,"remaining_time":2.191165577,"test":[0.3931034483,0.3971264377]}, +{"learn":[0.9247648903,0.319887232],"iteration":475,"passed_time":41.66554301,"remaining_time":2.100783681,"test":[0.3931034483,0.3971650662]}, +{"learn":[0.9252336449,0.3197591383],"iteration":476,"passed_time":41.75358923,"remaining_time":2.013275791,"test":[0.3888888889,0.3972105035]}, +{"learn":[0.9226006192,0.3196688598],"iteration":477,"passed_time":41.83661336,"remaining_time":1.925534506,"test":[0.3931034483,0.3972187771]}, +{"learn":[0.9223602484,0.3196189624],"iteration":478,"passed_time":41.91791635,"remaining_time":1.83773746,"test":[0.3931034483,0.3971917318]}, +{"learn":[0.9221183801,0.3195125741],"iteration":479,"passed_time":42.02490305,"remaining_time":1.751037627,"test":[0.3986486486,0.3971666667]}, +{"learn":[0.9221183801,0.3194593622],"iteration":480,"passed_time":42.11026567,"remaining_time":1.663399268,"test":[0.3931034483,0.3971700575]}, +{"learn":[0.9228395062,0.3193807738],"iteration":481,"passed_time":42.19727267,"remaining_time":1.57583176,"test":[0.3945578231,0.3971706814]}, +{"learn":[0.9230769231,0.3193528313],"iteration":482,"passed_time":42.28298138,"remaining_time":1.488220877,"test":[0.3918918919,0.3971987033]}, +{"learn":[0.9259259259,0.3192504705],"iteration":483,"passed_time":42.37129658,"remaining_time":1.400704019,"test":[0.3888888889,0.3971587457]}, +{"learn":[0.9287925697,0.3191515668],"iteration":484,"passed_time":42.46659172,"remaining_time":1.313399744,"test":[0.3835616438,0.3971279839]}, +{"learn":[0.9290123457,0.3189851947],"iteration":485,"passed_time":42.56829159,"remaining_time":1.226247083,"test":[0.387755102,0.3971040853]}, +{"learn":[0.9294478528,0.3189042541],"iteration":486,"passed_time":42.66760257,"remaining_time":1.138970911,"test":[0.3904109589,0.3970484755]}, +{"learn":[0.9292307692,0.3188111599],"iteration":487,"passed_time":42.78510024,"remaining_time":1.052092629,"test":[0.3945578231,0.3970767415]}, +{"learn":[0.9263803681,0.3187479685],"iteration":488,"passed_time":42.86975964,"remaining_time":0.9643504214,"test":[0.3851351351,0.3971384549]}, +{"learn":[0.9296636086,0.3186910142],"iteration":489,"passed_time":42.95280064,"remaining_time":0.8765877683,"test":[0.3851351351,0.397127143]}, +{"learn":[0.9296636086,0.318641402],"iteration":490,"passed_time":43.03969064,"remaining_time":0.7889148997,"test":[0.3851351351,0.3971732313]}, +{"learn":[0.9296636086,0.3185637403],"iteration":491,"passed_time":43.123877,"remaining_time":0.7012012521,"test":[0.3825503356,0.3972007378]}, +{"learn":[0.9268292683,0.3184447351],"iteration":492,"passed_time":43.20794805,"remaining_time":0.6135002766,"test":[0.389261745,0.3971315647]}, +{"learn":[0.9270516717,0.3183507142],"iteration":493,"passed_time":43.29854056,"remaining_time":0.5258932052,"test":[0.389261745,0.3970801324]}, +{"learn":[0.9272727273,0.3182590457],"iteration":494,"passed_time":43.38515711,"remaining_time":0.4382339102,"test":[0.389261745,0.3970249023]}, +{"learn":[0.9242424242,0.3181805286],"iteration":495,"passed_time":43.47303744,"remaining_time":0.3505890116,"test":[0.3841059603,0.3969894748]}, +{"learn":[0.9246987952,0.3181252851],"iteration":496,"passed_time":43.55787959,"remaining_time":0.2629248265,"test":[0.3841059603,0.397053304]}, +{"learn":[0.9244712991,0.318031585],"iteration":497,"passed_time":43.64420264,"remaining_time":0.1752779223,"test":[0.3841059603,0.3970036621]}, +{"learn":[0.9251497006,0.3178987511],"iteration":498,"passed_time":43.73634849,"remaining_time":0.08764799297,"test":[0.3841059603,0.397030599]}, +{"learn":[0.9223880597,0.3177505916],"iteration":499,"passed_time":43.82385584,"remaining_time":0,"test":[0.3881578947,0.3969193793]} ]} \ No newline at end of file diff --git a/main/train/catboost_info/learn/events.out.tfevents b/main/train/catboost_info/learn/events.out.tfevents index 8a7e3cb6af66242a4cf6d2ec57f59fb971df9232..12009c12c4a1c043b1d58704eecfc3357209c4bb 100644 GIT binary patch literal 56740 zcmajocU({J`v>qSqi9$e*&<|*kWfk#p-8q;A(WAkojpP_3YAS6B_kuDkR&sdqL5^i zl*q2{{rkMn&$+MbzC4cq{PB7`&voDTxz9QGx!v^{E`W@R|R`xuekGGiKq2W+N%OR`wI1C z?`U1`5ZbGXy{KNG|5m?T+K=|CLN9hvJ=yzH$?`VsX=AUr?F7EQuQ~I3(4IE*%r)xD z-n}~g=hB`I_Ihk~<-M1$qe^K{2YS_Z)|S11JpZG#r;ELoCtY}N-ByFjw5JQbYsUJr zr#oYYJMHOVZ%U>!@AZq%45vLk=p9I@DSNFZ?e9)|)vy;BK92X2k}BV(y=u^Vw4{dY zjj@RhrM>FdQ&R)=bqPp}qrK|TvoNeKd-121k3(LZYCfxhJv2UT4plBh-rppc&w6I+ z$zHh&K|g7)CiVvJ1n0x_Mde!3UQJk^d#JAL-PvWSMtilecP|mN=h2<+>u9eQ^ite) zWX~ts_ABk_WADhV$^3Y!b>quK+S7+#Nmp&zEB7hKoc3yCFUA{qMm_vBX|Fc)`e;>^ zy&E0BRHD5)3f|}UeOA+69q6UK*OEQoh{pJOD~+TPZx%4xTRbba*{JU^G#yJ@c;^oE|SEPGlrN2k)B0ruL*fcj<)U3iZ644`Lxu#)U)I_cy2 zT58Yw3Z8voU|rg)552k}6=m;W9Rqy-qE_Soo>lZ3U@u`XxPN)`VAM6_{Y`@TWomE* z*-O~}5!WZB8e;E9;0%7e)Lf@MoAw&Q`Z9wxWG}+F{4UgglGg}(i!?oXubca>{%_f#(uybd&ZPLofS8dD-jjJiIyWHNoDqbHH0`wbhySnm{iu zzMSmECh0Gsy{6bZ=;y_^XXT`8KD5^qdN)$lWbeT4cT;Jv8TO{P1mk60v&9*-*9>|m zzL)j>`#fz>zsCjIGgRzh7y2EHHs zn*{UAyKz5cFTGpZLApI#Vh`2#XTR+`y1tgMzOskkWN-BMM;^#CSIwWTu!s83JFNz; z?{5;+w{}>G?5$q4RCu0Nd9AVcsQ{dRZM;nI^-uCz!}^@kzR2FCR?qNwky6IkL-V!! zbu~PH{!N1VE;|>?USfb7e*TkEZ4|tI2b;K}{`;E*-l1PbvRBZh)*`z9+G0=p&0Kzb zPF>Z{gZA3O_FTKaQ1)zsObckQ9rn=qu<}i8H`;3ly&6uRWbgW}z=gEe9(#>ePvh%* zyK7q{?X`zqv3h~*{aNHbp7uIm58Y2}O}H?Y_Buds`}us?i*oVB*CVOdJ7N!=e{+2+ zdC^`+=sj7GCwsQbCvT(c>x4Ztzc^{kzC?SSpjX)QgY2DHsbfKVow0|;OQf26Biic> zJ-3SQWzS=O@hRHtqTuN`uZp3)F3`J|@mBVJ#BPqJy{_0p{kPK989(1jJ>M02yQ6Yt zFSECyE%JO-^QQ^+(EY^y4v#HReSec+emM~MM)ua0g!H1lZrDTP#qjC2BHHT)>$9Jq zBYVrjt47jZckK1+4bJzLqaCl(UU%r3OnWVRL56{iXs-wM(EQTTV@G$|>jAx-QQ5M0 zy>|Xe+B3x-T5q*qZ}|_;6nfdtuVgRa{hD~%>xsSI6~XiSn3d)2>H2y?Z-C27*~|G} zvoh_ODR@0!H}a%CGw6Mu@FXd;N!j z_S}*-;TG-nhF;OiOxgRCJ9ZZB^}*hphhY7BO$*mV+Uo;7>s`-f@0Q)tVYFwCy-Ab6 z`uxU2FZR)%IrL)BJd?d?6<2PdJ>hNRi!Z=S4~P`rKd5Fx3+Uarl_7hYZT{fvQJgB( z7uSc@L(FY9k3#kRO@jF|>s`9+ox2~KiRzP5me{*dAJnH~^e&$EEMa|CjXCdanYIn> zSz+%@4tW3YHts%t|0f-(74**7K9%dU_YP90y?)r+(G`r(ixs!3)AjX(Uf<Qa0E_^|>~vT8*yH26`9VAItS=Mz38? z*Jq2pdp*GXIkV%FG}^O;-p|92WY5lOL@4bI#NP0$z+1GeVlM3sgx=KeDYDo8YxHy4 z8-zVaM{qtIR=330BdI3_K~LX?^FrUp>eq1YSN4)ou*5A%ifT~$vEgpLc z>Ul@#RXub^uJ8AXb9%Hl0(%M1r}E<^R@1BoUEc`k<<;Xnw=@0hY0n9J-?YK=*g3oQ zk7&;cdfJEf6IzrN6__+h2D$zx8(Z#+>-G7Tj?mrVQ+yp zn6ICPr{>Y#IOu75a^9vMx>e}<#$#{lD&V~u7=MWN#zXJX*F?F#q}~mDX>WppSHFU> zHSJA+-qjVHSKpxHNZND8p3z*ef1>k6b9_H2^@KC@^r~=PqYD1Q`vBGX=YqYnmSF!x zaL2N{bbT(+^9{Tyx98?RiFo}*I?9RI^Vt7b)eg;B{<2>ILn&!}^j7Z^-pkO4yC(7s;E1J*So6`d~V7$Q9a~1id?coVTj7 zb}?PwWbB=53a$?)Ztbl?dy}EJq&4R~Tv2T;?M=ZR+OOC+>)spMn*zOzYuDxW92His z5AAtiZ&?9o&%pgZvuV!*da08*Z%|>e2JKD7UeQu;KcBiddIs%Hg`Q;<&P(aqW-IMY z!yXzhs|+43qrGX+8+PKF+@5Z4>vyBQ>DcRj8C-9>q?OI3z3I@KJdE?^`>eZ5d!7p3 z`{kZ^K9kNQPw4gh6ED}7G1oDP_Pnr%uD8=R&-p;t=LNkJM>(&c?$6$|Hv@ayBnKWAcZO9)u6``oO~MO5G4B$z+{{D_m=^I~Z00jNGH zH4A&g+XFAG-fBEw|4jlfE{yZ8?)8hHz1a$0(Z-%l>H22F_6#4vd9!|`pP@Z(>;)x* z`z5c+m+|wTRG&BWe5-O^_Mp8zXm1Yo(E8G=+vTn3`sP4y&y}lk|4lKT@R9cBVsGz# zFn@mf65o>c=0dOjJkFaQlGT#-=3x(=f30(Ue$(DO=!F|{p8d<2`1wfch56W1Qv>sL zlB0SP+M5qOtE?+>ds?PHFQx1A!5&(VG|~(Dhvx&ma)F$ulRpISFOce6fW0;2!S(&J zX(-+g{Wl5Dzwp7FSKd)Ck*;r{f>$M?*Q59Scq)Pp#H}>w}B1hu(Lz zn9{u-^8O}4eLCka%l#L=(Qh>EEymv2ji5bWZTyY*3rpT&Sf7nI=iT!8;zWB(u!riq zWN#_#KU1~L66hIqx5nW5K=!LTsXkxf2YDVI0DL%nVz7}Ez4Ypo zHHd-{Gjt{=zAdUyK#R)-5tV59>&Y!zWKkflG~vXJcirmK;tD}THGa*@DWOFc1>%4| zm*ifYJuvGnEv^*AoK$cb469;lOp7cE#Ikr!ykRzS3N5Y@L^P4MSz+cti!2JnE^9e) zbi|V5w76Oj9kRit@M`dRZ(3wgAWj~_i5=swq|o9TK{VY0CY!qIyI&pEwU&O`~SKq_u~eqomXgaqabF#0%B_U!Eb4iMS-Z3#EC~WW`3u| zO@e4Y9=saNzN^-i7FiUCwYG6$9hXP#X>qe4uDA@u7LhB8X^};NxPKxi7Oa0Uju!m| zv2Q(adm37Fb0#gaC=e%f;Y6z~i6*qTMG&v{2jcO3j{&sEqCjk4krTfU>G+5i0|e3G z2w2kdi{8GU7FiUC)=w|UV>LMKXaywts%E*Zf{1GD)W4uH66GimS4VJS%&H3&X>pq% zzI*~|wD!IiM~f^9#ND$w@x#~RU9`Ae5O?na=i`Hum7HjiMS*D6pA+|)CwHU89fH`* z9V~Sp{aXGxEwU&Ozc=Elv=}IeHv@s#aPqt%w8)}BT#$EO9yzs^dUdA7AVEYw zhqP_Jup%w8C=gG^apLW>eJ;}CPC-1U0bW=nrhJ}Gi!2Jn{+l_mTYz&vTHK{1&h34+ zH!ZR#5SzGi;;Yy(r)hDwAfkR8^e3wZEwU&OUw7lg;&C7FwL?0Mg9Xtp6twDS_KtQtD{aHHHWx`eAZE^=~e8jVubpVeih#V>Q2XK^r8-sb;xQLG1kpeiC90lUa7*6a{CI2NY?h!=PkN0j>9YKpM3dG4r$rV8V%y)*@>n&x;AcI&B#5Y0HMR%f=MJfPSQLncr#bOhr*lTMcvukc?FG-sb?jaC(KWIt z5Jzt0#2u}AcA>>1f_Pva5QDo7Izfvp3PfiYPK=Ap#P>OB`v0xQg(-lJC){p{YLsH(g1DzTxL>WdQ{y8ovM3M_*XG2JOTv%R;!#0Ft(sfhsT?h`C=e%p zJ1d_ZqXuR?p~Yi@xS#`=$(^tM?nsL)3dG2#oOmrDqY^D17esVE7Q}7%N2{_Z5IdaV zL^b_$Rb?ArV`z~@fvA0x6RVmp9*;zG)x3H}5YcL<{^JENktj!jsB?@L_gP<{#j}Fw zaUHC7_RL&mON%TDL`#28tZlio4lPD2iSIjP(Mo`C=dtN<3!_1H>cC$ML|Sw9~%7DxI&983dHwir{(jp#UJY`v>2l#9>0*Yk``GM zh%Mf7;*4*@l4$XgAe#Dtk>lW28$Yp1{m7y~JaLZ`dw##snigXPG0Oq0%-3%8Vhvp* zivn?0Bq!#-%JQPc%Yqnn7u4AHQ&KD~vM3O%ZRNxV7yM(9=&PFLt_b3O9kBWPg63=+ zB+5}BYAoVJ(+9u9Xz{8b4!;gQuQTaeEwU&O6Dx3H{@6lmy2iVLh-!R#e>J|( zkq(wcfw;XeN}h8Dq~1P4i}wWaMLMX_RLeM=u8~E7*zq|hj?K}2NQ?Ic(ewupZ)a)> zt7NK?!=gZpxXy{yH*Xw6iw^|R(Gi>-8k0YT&^59s5PyVmVq*W;JGA&v5WkoJaX@M~ ze&Z?iBZ~rY$2Lw}^=5YnEv5*fni^=;67!O6bd4+uM3+UJsN1O(es3im=p!Z3>TVRi zvy!7goafAmJqmu|`&B9SSV_EoKh2M>kwt;%Z^enl1}`q7R#mJ0-`e97L45K8JX?Kf zyLK%S~ep4nLXqF%r1_SX?FN-`{WKke?_vOR~nYghb@so}m z1!8AYPF!&3>SVgcY(Yeup8Lc#YBaw%Z5I;dC=eUFaAMKwg0{5yQ4kvhgBp!{UKZ9mR0qqVKzurg z6E7Yw?@EgWf*5rYh)))G%cN^$Q6M(%#)&C!CgC+?scAk5;)GS8RTp(mtxbz83dBv# zIk9@H!;|P53k5OsBoOu2xV5B376qbb4NhFvb_L#pB-L0Xh*#CYC!3vS)m=f0EDFS& zpAqs*J|$u~zF(EZ&w^-@5Bjl1fk%H@WKkg2$l*kn_4;_0lf+^{R8yPD|Lk7N{Uv^@ zD@TFYID-?TZuQ5%(~)9dl*CPw!_?>+SrmxQH#spZr=2rBa=r>;c_UEcn(l>`w8)}B ze0`b|k1qCIL5n4VXjBLEV`@`3e0`Lfhed&CyOI+(o~-r}iE*llYtiHQf(c*VOL^W>H?Q@A1SrmxDV>t0iPlHfe{2_<~>_9(mY4UI>EwU&O z$2)N1l%EYY(Be-)+%O!p>X9*Jcz=%6sw@h`)}1)<=QrEBwD?O9cbNn6cdxTU=^9xS zh!dM~;<$?e_ziiP7FFbvl(6EA0@Gg%Q{zDWKkdvFFPU6 ztCu^Z*wJFCl6ZcHM;0xzC=lxuaN>mhrZ%)#CWsfCfveS$p3$>tkwt;%oWhBL^GDvG zMPK0$1R~MQD$S4zUSYK65kSq$sN@1K>_5Lzpb*0XKYmX}hG1Csz_;yB)uuAqf3dHarPW-B0 zgzx3lRIycp_+k;50X{oUN=B_JM}cU$niIE2ezirdD#ca{;;W;eRm(M5j$2iZ0(|pOjGsH?C=eSB;lwEo{e|76s*$r^NzCh4hVOGEkwt;%(~}b? zzRnQV$yMS8K}4-O(0dwQL6Srk1!8D>PP~6`vnD-O{RFY75VY#OW_KpgX9tS{(Yqlh zUMS4QPjk|NZWP3vH1HIl=Uj;Q%*#U$OT6L2kuBrh<>yb-^9eRJG zKz#M{xO{!o8B=tQ7B>qb`eO&1*H4c?ttuTXivqEA4kzjc1ZvSD`>GoHW4(jRgBnMA zCrzbA76oF5r<}OZWDedlFCFL>LF{P_M7R69JZO1av5Wo9z;>w$C@bBiNk+VY(2TcYeN6U2;e&Z=efmrIxiNDY8 z&8BM%R1z2ayPujaPK#C=g#(bwx1M5Uu+$)Hv#y>f&578ov0H4bS9q6o`2jIPucgm-y~citQIfRHIApfxdK&EDFR95u7-CUrqd_ z7fC#zBz{{EnM8{$3dG?DIB{g{CxLW79u&kXC&9=WGVNVeT4YfmY6o)SScjbpkr<~M z;)evW+a4hL+)n<9L^%q?Nq(HTTk{Q`$)(s~K}3J5uKup8!hSi`!Lle2U6yiUz4~SN z{i7rvQ4)`hn~0yv!MS*5^tw8)}BG^@*r9n$CF-y%s(6CsGG#@SX&@fBH)0`W*SPTZ4Whu5s6 zSfn6kGy$#JF)$1N+Cq*3u|_#gT-3bkX}VQUDv9b^>+n5*B(f+FbG{vw?>g!{_CAJ0 zwYvYU1V#xWYSoBk_wlc00#r zAKv!g{81>(9WPTXaiQ$UO7l|;2`zxUE2ivsapC?^(9vhtzD3xb%j5saL`f`kgR z$f7{Z*vyGXkA_vF#fyT7S~WGc0AG=%6N^QGxNIFK>PF4MJD<%}b54ws_(=$<|h@6VCMSS2xcyDNT=EJuM@I+GJ0 z+AI+ES*cp}vLK?7)53M&Zn{Pm1>)!NocOkAU{ktPuPBL8{*n0C`cjQ73PeW-PRtLP zFrOB$Dv2w8efvY#$f7`;HG-O|n}Rqt35*=~z4gu`QH}!fQ)#$-_c*p}7~Y>F#S)dow7h|DXpu#M zIQ=Up8eK7+jrvg%Zz+kLLn~LNMHU5O*IZ7#^(gc`EhZ_6<%-6o(jtojF({K0b;}%t z-D|3Tysab#C0v?Di!2JnTTeN$>6?tcbdAYM;^9&6EohNNfq42cCx)31zDSFA1o8Yc zFjm_dKki72EDFSzNu1aHGz<2@y@ zVYS2fYj4spXHg*DIm3x&XFTv;GAVYS5WyYtoc-~_y8u=5uqY5~9_Pf4RlZ-PYkZ(2 zE_GO3jc!#I1)^>^CngQ~gn!2>)%Z|JJaMJcVjiN+Ik@%^fFuq+Bhi}{@B80IOgcB=X@RY?pD{EY8cC6Pse z_|BUXM_CAWR#GfYN%Yq`i|<$EC=kof;>43{8we|bsv4gPBHAzaeYt-a-H$8^#4LAC z96w+H{!N*5py`5GPz~H!MQVM(yPo7I5UpG|(fC}GVtV9c2qLO6fs@1aSd8k$8C=eTV z;KX4Lck9vO3qeF9=ZO7v{EHGvWKkeywBbZI&&0vB_)-v2KNiFcGo@=}Q6RQ&#fg5A zo43>AD<#ovNHsTFWKkfhHQ~hK$_4oPC^b#Cl6d=I;XhiHMS5R2F;{vd@YFR z*H7U~KjX0~9W09i@m6h4{PnhdDlO(HiS2!N;rmrdWKkfR>2ji4#&BC&e4`}(sgk^i z?nf2{;#qA@JeE0jIW6WYiGJ_e-K0ep1!8MWPW;h$0^ZjlHO*T=Ti zAjbR(lb={;?AU?#JV@d@K|~{`SFYJtT4YfmdVJ!`jXw1krsPc((Gbaa7nZr#e^`1>*g8oY>OF7QdaB4m3{?pLl~i z5?K_8gPw4rhq@Vl7a)lr1@WLC z=*RLqeMX^?BS(Rl_=po<=@;R<4k=ckByJzOtAG|+6o|$*IPqwhF(UR}Hw&O5(do(fHR-lE|V!d>qD!O>gbScUDrYSV=TJ^9es&$x$GN?%~9J zL!FZ8R{f$RUcR_&}iAh`A4o5Z0Q6M_{apI>@noDW%o02%DblwJ9WKkgYSjUOkp_A|z38Vx4 zE{JHB+v=-xl@?hPh>KQn;<_4E_$$+r_(MtDS9K)*cDEb_;*Q0f*g9A}iEh=ON}|cT zi};HKlE|V!+~UKD@hL79Y4MkmsL>^F9o?!d3dHcaoapqtBi{2M9q4aCL}!Q2q{DbW zxf}&z+Eh;5((knJ_jFWe#~(pNBj;3Z%09YA76syxNt}2(Vc$Rcu~ZOIjmJux;5%fg zMivEPpW&QXv~7d1zN)IROc2c?z?@@ttP%bui6pWp5O4M6MBA3j@s1!V=Bti>QG!H$ z<59w|^;HMUqCnhZ&WSH>tlEUeYMd&zTuD5C#}>c0lA}QU*^?9dl)V!61ggXpN@A0i zVZxf#-zX51O*pYA_>l0uM^$X4AU?ee`cWrqA--BkHL@rW?=2|&>L#4%;F+9Hi>sByX=e)X>WU{I)-!unW+@K^zm)mVli!2Jn zhi|wV?Gi_L(W0LqzHSH3j`PMd@XCYKAuI~S`stkL(0p1YTHGjz>-qrEIKr#49iGyE&;tSQLo5!JK&7+(T6C+jC=jptbK+C8{MB@gJCwx1 z<(v~~kwt-cX9FibC_nTmEd~l=t5u-Jepj>coFg?4ivrPa9Ve#5y=p^?L4x?~91ykb z60GSOSrmvlb2-uH#oBgAG*``XI|Z@k5g=|<55xOc{C@1Vwr zH4eRLkwt;H#Do*IPP_l3#yx_FTD3&`rxq=;C=gF{=EN`kvi?!yUO_}PYG!>+r$rV8 zqD6a7jEg&n?>eM@+@~Zarr-R>*}i$cF9eOH}MS*yuA}4wdsf)izAc=tx@jZYX1>zVD zPONGD8LuHru_J<5xfKvM`?w2V?NimrqCm9!c36IXtopoY4&AC@g6QZ7=A2COjMl#P`>A<7tsafw=e+C+?pANsq4as37iI18S_he+k~Z zBGt&EK%AAsiJc73*P+E@f|wi##BTem;@{~=B8vi1E1eV1ls_Qs?NqhuaY5{w2)=5& zM1A8kx>Z>eh{uvSF`_{={H|O&&=Z2F`2&0pdHJ~ImuQhifmrhjCr;lIdY^992qp2% zsb)pA$f7{p8Ow=jt*-Q-#YjO+X#-l-A|&GlEwU&O-A{7jlU^m)kr=1y$CFB;^RHX@ z?SmWz;_om{9Bi*AtahrzC_#)c05vu$UONlbD2Xfz#5spJvEPBRdvuMb1o38FaCSr$ zM&nsd5?K_8UqU!>wobJ(w0K$&zqA6P$Frttbd4+u#E8|LSX$dVlNQeiVkJ``+7Ev| zpB7mZh;FkvapF$D*R*(6NlYDmuoo?|C=gFh=EP{bSYh9zYUD&KiEcN`;lEHI^&^V{ zQGXIAM(i1mpUS1!IYCVK1!J|#>4V+r8d(&GQ(ZXme3Sn8&9x++R}w3ZFNgP8$x$Fa z9m|PMo`ZySa#gEdP!cDeh!(zq@HYy?>@l49k-bHvN6tk-bO->g`m}sp3EiqJ3PcYF zPK*g{6iJIQN}|_E7kgS{Q6TCJ5wfg_9Jzf&Tllwu94KDRBMxq=AVweRd z1|&N!Ks8FSSV1g01;n0K-kWKWMS*Bz%84;8{tTkU%Sz(=w2scS$f7`uZ^Mb98%Da* z;uS#*@c^^j$vUeW(;|xkaY|E8tPvDYoffYuiAz?!xJ`>J3dGKhIq`te0{qnlsUPD6 z5%ptCzP$@AvM3OB^f<9i*txcJjqyt2lzlbvcgduKWlw> zSo<0ntKR~O@qLaYvM3Py=W?Qpdzi4BR3%~wp4 zPcFrt2;$B@K&%w;1-}iHqd-j3=EUAx6WY-=rV8S%rJz-<0}VT(^HCC66o_5bIPu%r z#QwCHCWtnBfcV_*Y$z?VC=d&a4$Aj(t$W&M)8bP>bh`}1+M|1aphXr1Vq7jKMlG$5 zzcDK{O}diU{N|Liw8)}B+>*+PZyKJ#D-V*Gp(LL9ylxXMvM3N+CUN3^1GlxPRpV6i z>N6#=dcbZ^B+5}B_Pxc4RdR*<94Yo(5F0!P{g_aA%77MG6o@|OIdRIzq4Ve(GX-&T zdmtvCnvUNENC(TJKs1a;5TJbEK3mYHUgrFx8YH`MivEP-NT%i+(#phuJMH+ z7V84h{zuG8T4Yfm8U=A;*}%#8UQVjDBipRO*Z#n*zkNE2K; zt`BYanig3UhYsa)!eH-Z@d z2#DTwyGPJ9vM3NMIdEdpyUnGjMzse2t&-&m;=n>6daXRQ5Q%aWh|~IW;(hn8MYQ-< z5UXVa@%~ANd$h=+KIBZ~s@QzuRw?6qPUExs4T z8Kpqnp%cHKu8~E7=wr-@UJZxgcLCCYeozwCKRDyBzROV{elz66+*;%CEGNbCl*EoE z74aIf90g)hJx=tP;~Y)5YQ7+zv;wXAD<$?K-Ks1K#12(B(e~5VpS1W<5c>`TqE1r% zBeck(K+G&XAm7XBKA3rz77GONstXXueRRi9tWvA8C=fF~b7HzvfBgPYihUA9qhK(T zw{=|DoUV~Yf$0B^6YDQph0oxoTehEQlegKrE@>#UF`s6o~t-bK);Me;YJ%q*$>a Z?rQ?Xr1h>|w8)}B>>9<1-G^Ln@jsaIk30YX literal 22556 zcmajmd0b6-9|!OvOGJb$Stc55WE)G0k_ttMBqLcuwrH_Op%RsnLP(J%St6A+#V{D_ zlzohO#!eZdEW=oy^SI~9{e6C)d5!;gy*}Re^F6=cx#!$_ZfhOQpU*Rm2kPtS*z}94 zeA~8dlWHc_^j!lcjGr7hd4^xTv<9vESbqI`uj9vucTjVu&wIT8nrl(bw3>lkz>L5^ zd%vK788heAbD69}g@5{f=jMZL)%4z&Rj}SLR;nPMa(y~+vL4Fa5(IhP60^Zv)+6$x8~Px>csns3U8(3T&{xhl%_t~@`Szz zn{&AekyFCofZWBP>yS|tWV?<^`C&8pVh*KcdmwV_O&tEa=WW;{#>p`j za(e@Ec~aibcODdhyxhCgn#(m&KKP>`S1S&P<8n>XIk4gtkiDKp_u;Z3%I3#~bJ#jP z%R^i?By!TY3m_l0A3Kf9wNSQ<6V74N%*WQ@axEe+^F0T$zwW#cF4smmYT6|2UG-_m z9!DJLey!ZG`gf2}0+}d(ThdvJsJ6HaG>c{ng(3ymK9t^#Z4Bcead~ zo6Y4qM1HyA1jz3{B^=>$U6dV1_-V_#9(=Ipa$O=PM&*O-pVZzRWF7neUH#Rnhw|<8 z8QSvA4i&vYE>Ft)IeJVU$X713sKI69f06fQ=jm|Sm~=iKc@*T3hhkV9PhH}D< zncBzs*zd2>xZI4$z3T6W&c8m6f5+u-P;N8SUt2zW>bwb;zaetp7nvXj#~=QI%cdxo z4j0ZOuFq|!bJ>*0zV%U#ZW9#9<>n}-?G)Db?LRl%=5li)C)@0W&hOkjW^uU%$}z_T zxoGCcU0iNK3mJLA;)tpIMq8zeD=%|K1 zRbKl(@8xnU(mD1)2FO3s`M`ZoPbm%;8j^RIaHb;5!FyXx_Jm21s%jQI`+YIGqW&QE)Mx9xElqXLRWZNNQ z+H$!)k>|wkfX+)=PfLPn7iji#2b4cQ66Ca|-LP|cQr^#heAo`MZdJRgT(&^j+DzD0 z-!?tA2|BB?1?hZdp(Njm#P=#S-x1}Di9+Y76TX64bmbEkiihdX;X zbGZ|dgLiC$Y4^;#Q;*A?QLgb&xZZBP&&rO=or&z{h4O`8>KJpm3(C$F1^Joz$?v(` zg~+-$wnFEY)#Hk|+!f`GcZGKhyCfg!&Rw%Bx)Rwe808}OkWF0v4&~Bkf}DOa%AI%q zj>rXOC?C16i?WWxmpk`vC`bP-OxvSZ-FG0DC*}RTW>FeUJ7au@XV6*AcSpJLggM$* zy&pPH9m3`Aq;sq}%9jipcyPG~%DMA}tKKJn{3YGRYNpkL$jb`1KxdD?#wByPC(8M| zh0gXJTcq>OJ&7FUiSn}_e|XJhOO(BC2*=qo&fbB`mP9^X3uRZg$vRx_g>s92!n9-8 znwE087m@#t-VD=rpOlipWh<1AhY51(pxZuNwjy#;QA;Da> zCi2gxQlWF>clw_}w$ZH6-YEP1BFN)fuU-doc~aib5n(8|u(B@Zavzk(wG!mO#MrG| z?n63Tw?Mgi#afrRY=iQadV<_@!JUs>wjr|j)fAX^hV%7aT$aA~ZZ%MlEqxyjrV);GO%S?B89GEBNP}<#InFS8+i(v4+(tF59ELq}g2U_o~99p^dm~PvpTLlVRGq z_067w9IDyR4k*_x70%ml?COmMxjZTF=g!MfZa?$41zdJSdCWaw+Hr27Yq{)5Iv+Z@ z5jwv&=+K|b{ZXzJBXmA@BB~FU`x7}i9OZcs~~%}~z$ z)$Kl)2cmprkkGmBrrXuHJdnu!cW!`bhv@d&!(}IwA5RtJ@Df}6Bu-snPDEbegYr(V z{1aSuMtS>dVcMSI}^F(Hz@z^{BjtV2chg{Aar){sNRsvgNVHF*m{`uqqxYL zAQx!%^I(+WI?Q5-%|npOlk$Gfo`~`v=0+#E?1J*H3}M=nPx?sTd~05_3+Wut0p;RL z(fB!u`pR8VZv0%3Jw2BN@y@P9zETn8O0j8p9j3}dP|m9_9Ot8EcRF)<2$7$jNrL12 zSAz33K5aLYO>70(N8iev%Wg!DOGbI+h=IqsJQU@7j)L4pr!1MvLx~(e24(-HN2Kqc zHS1&;%6&cv@_+`V(Oe!zv$-a7 z**qIpE{{a{T5X|o=NQXeE{`PggEc5O$(dQe}=eURx`E_)H#X$i`;x8|pV zY@^xFqfzejQIM@m57h;^JSp$zZ39qt*c6VRZ>xE4l&wsJ<809@^BR}EN$0Tbi7@R` z&5qaRoyVYDqm>}1FRA&7%VUUa))nRGG&?+#sGY~6eD_yD-ra2pJ`-1-l&8J?KMBzJ zsZ*BpnStgwk3)H*cnuWY?0_Fzt*DDdBvDO+b0Q_&G`Xxuc7D=LtlP zN{lQ`A zT%MHWt?N zClk4`A&uZd35(RiCmtEvfgq*t{1xtf90fho=Iez53w-qj7mK&bJ-u|-B*R;Q1S6JmOC>yoZD{iO$mN>%X2dDr2mROSym41f&F;AeIO>7s| zNsT5iUHVjr%Jzr}Xz%HD){onZC0j>Fu*;roc*bodD%&qRqdom%?T6f6BH32rC6UFm z1Nq!mqO#q{5N-Dg%iX!XRI)7>3ca6xei6@YB`Vu)xhr6$^)%jS%WdUTX!yB%U-4#R z-~NCj+*YEp9Xtc=k@G)J;&!-XFNhR+FD`xjncGTKwtF;2J9CfoY;H$L_RQXb9dyDAIpuTj}Wjik#ZKv;EEaP^xWVg={Y>(O& z`?#${WxHe)+FhosL=UqRdA=x=!KpbjoxvMr(nyIP$# zow%(;WjlB`+E=zVTg-c}mTdQRg59)dBA#2+m#su)`^Px6>loXw=5~T)$G#P8-xJ;r zytfjS?KhLrem(S!6}J;5`|}vV_R3E&;kFW$ZR5IV-%34K$n7?Y`&VVm>+iN8|CP>)dzrD*T1^a7MwhhD3Uf9OGF}K%Awt1*v7dx!R znX9%Em2KNmXs6iCI?L@O$&Oel*hS+FYw_MnRJNy>p?&iDR=iGCU;KK>J~TkEYaecs z&TSolggwLZ<6dv#|2wA)#x3!m8fi& z6)lD1?NInQ1#BD5{!Wo>1AoCz`P}dZ*k7Zv?KvCm3RYEpxt%K6Bh3YSZ2cE2xUEEG zyMr;>wtoHgaeK359}E+0>#Q?fxvfNHTc=3y}7MK zWqVBpv^~y*Rp&F`CfQf_2)3P(ZwR-QsB9P9UJS?E{^b*WZf}?DBZmb$bVlYlZYxpQ zJ{64ie%~8^fE}vY-#a9GN1kB!d$g?{*k7ZvJ>3ayofFI3a64VHSKb%a`OE18qqwa^ zW!tj`+Ee2zzu@*x$#y9b?4#NbWnUvCm+q)#&s*iBIGwqTma$AYY_Wr?WXBO={!|mOY-NjqzopSrd9BwO7*{;_X z?ZLPF@$)rxvF?%Vs7%2gFnVMjx0R@DyBnbG*E}8X1yy^mWKZoZ*zNrCf9AFlmF?WP z5Ljz>&)iFgnHOmGccx?)T^H=+KRf>j_SdLvUo=6xJ6%sWw_G37>=n0_ zsBGt$p`ATwff2WJBs+4uV88IS*W1&XsHjAHhz!zDN3;NwdzC usBF8uTL5kRyI|9w!h<30%XUGK}5(EDptw$B|wJEC;7?|%WnwhtNr diff --git a/main/train/catboost_info/learn_error.tsv b/main/train/catboost_info/learn_error.tsv index a3f7037..147bb20 100644 --- a/main/train/catboost_info/learn_error.tsv +++ b/main/train/catboost_info/learn_error.tsv @@ -1,185 +1,501 @@ -iter Precision CrossEntropy -0 0.6527196653 0.6539506586 -1 0.7857142857 0.62 -2 0.7876106195 0.5895233377 -3 0.8407079646 0.5620427264 -4 0.8421052632 0.5384506159 -5 0.8854166667 0.5166076215 -6 0.9069767442 0.4981064667 -7 0.8910891089 0.4814881886 -8 0.8727272727 0.466400298 -9 0.8679245283 0.4533062343 -10 0.8782608696 0.4415312072 -11 0.8740740741 0.4312919494 -12 0.8689655172 0.4220624715 -13 0.8721804511 0.413855426 -14 0.8741258741 0.406276303 -15 0.8857142857 0.3991897383 -16 0.9084507042 0.3933755916 -17 0.904 0.3882018776 -18 0.9078014184 0.3829967282 -19 0.9275362319 0.3780131586 -20 0.9310344828 0.3741117915 -21 0.9361702128 0.3698772169 -22 0.9361702128 0.3662776217 -23 0.9481481481 0.3634891081 -24 0.9618320611 0.3606119554 -25 0.9562043796 0.3583850365 -26 0.958041958 0.3559227803 -27 0.9507042254 0.3537762674 -28 0.9503546099 0.3512843579 -29 0.9473684211 0.3493274549 -30 0.9480519481 0.3476888615 -31 0.9407894737 0.3458803675 -32 0.9426751592 0.3436222628 -33 0.9622641509 0.3419754362 -34 0.9518072289 0.3403367002 -35 0.9520958084 0.3387332487 -36 0.95 0.3373228288 -37 0.9451219512 0.3361083272 -38 0.9515151515 0.3348690907 -39 0.9553072626 0.33377502 -40 0.9516129032 0.3329283688 -41 0.9441624365 0.3318725764 -42 0.945 0.3308382043 -43 0.95 0.3292620538 -44 0.9466019417 0.3283621194 -45 0.9468599034 0.3272893262 -46 0.9488372093 0.3261484589 -47 0.9497716895 0.3251783474 -48 0.9475982533 0.3244344848 -49 0.9475982533 0.323543425 -50 0.9605263158 0.3229784443 -51 0.9570815451 0.3219528399 -52 0.9565217391 0.3212596231 -53 0.9567099567 0.3205928875 -54 0.9608695652 0.3193251383 -55 0.9663865546 0.3186993185 -56 0.9628099174 0.3180124458 -57 0.9674796748 0.3170894161 -58 0.9603174603 0.3165342011 -59 0.9619771863 0.3155287337 -60 0.962962963 0.3146865733 -61 0.9635036496 0.3140015896 -62 0.9642857143 0.313511063 -63 0.9615384615 0.3127688398 -64 0.9612676056 0.312167149 -65 0.9620689655 0.3110078553 -66 0.9632107023 0.3105276289 -67 0.9636963696 0.3099715585 -68 0.9617834395 0.3091966882 -69 0.9692307692 0.3085731852 -70 0.9607250755 0.3076873289 -71 0.9643916914 0.3061730868 -72 0.9591836735 0.3057069029 -73 0.9548022599 0.3049678518 -74 0.9582172702 0.3040258967 -75 0.958677686 0.3035014399 -76 0.9568733154 0.3029796561 -77 0.9572192513 0.3022192917 -78 0.9603174603 0.3015648167 -79 0.9557291667 0.3011355925 -80 0.9567430025 0.300810333 -81 0.9573934837 0.3003533089 -82 0.9580246914 0.3000302235 -83 0.9581280788 0.2995648951 -84 0.9608801956 0.2991294337 -85 0.9591346154 0.2989826642 -86 0.9578454333 0.2979737041 -87 0.9627039627 0.2973494526 -88 0.9608294931 0.2969713019 -89 0.9567198178 0.2965064011 -90 0.9573033708 0.2960730782 -91 0.9577777778 0.2954965678 -92 0.9558498896 0.2948055607 -93 0.9564270153 0.2939628122 -94 0.9569892473 0.293530612 -95 0.9574468085 0.2922860473 -96 0.9576271186 0.2914134138 -97 0.9604166667 0.2907755653 -98 0.9608247423 0.2901806284 -99 0.9633401222 0.2895748745 -100 0.9618473896 0.288912309 -101 0.9620758483 0.2882808223 -102 0.9608610568 0.2876833728 -103 0.9610136452 0.286969306 -104 0.9619771863 0.286024464 -105 0.961038961 0.2852715307 -106 0.9616087751 0.284758176 -107 0.9616087751 0.2843796868 -108 0.9583333333 0.2836953446 -109 0.9584837545 0.2826532918 -110 0.9625 0.2820946196 -111 0.9625668449 0.2815772197 -112 0.963028169 0.2812213803 -113 0.9602763385 0.280713746 -114 0.9605488851 0.280147518 -115 0.9641638225 0.2793720062 -116 0.9642248722 0.2788365363 -117 0.9644067797 0.278158057 -118 0.9646464646 0.2771244333 -119 0.9647058824 0.2767586322 -120 0.9648241206 0.2761904796 -121 0.9633943428 0.2758859632 -122 0.9636963696 0.2752923094 -123 0.9623567921 0.2747471808 -124 0.9627831715 0.2743734318 -125 0.9632 0.2735782462 -126 0.9634920635 0.273085884 -127 0.9636650869 0.2727205285 -128 0.963836478 0.2722575701 -129 0.9609375 0.2718730397 -130 0.9625585023 0.2715995844 -131 0.9628482972 0.2709222457 -132 0.9615975422 0.2703818039 -133 0.9630200308 0.2697465393 -134 0.9618902439 0.2693822351 -135 0.9653614458 0.269036197 -136 0.9654654655 0.2682332416 -137 0.9689349112 0.2676281471 -138 0.9693877551 0.2671804609 -139 0.969740634 0.2666987376 -140 0.9713467049 0.2663339523 -141 0.9715099715 0.2655467324 -142 0.9702549575 0.2647545941 -143 0.9664335664 0.264308494 -144 0.9705469846 0.2636648359 -145 0.9694019471 0.2633127388 -146 0.9708737864 0.2630347036 -147 0.9710743802 0.2628232814 -148 0.9725274725 0.2625271762 -149 0.9702300406 0.2618719883 -150 0.9689608637 0.261406945 -151 0.9666221629 0.2607731595 -152 0.9667994688 0.2604694628 -153 0.9670184697 0.2600434285 -154 0.9659685864 0.259592499 -155 0.9676165803 0.25914132 -156 0.9664516129 0.2588320099 -157 0.9715394567 0.2581554017 -158 0.9716494845 0.2574764235 -159 0.9704749679 0.2567622854 -160 0.9694267516 0.2560285805 -161 0.9707750953 0.2553710938 -162 0.9721518987 0.2546564924 -163 0.9738480697 0.2542799634 -164 0.973880597 0.2539259773 -165 0.975308642 0.2536220667 -166 0.9754901961 0.2529050061 -167 0.9755501222 0.2525285841 -168 0.9722222222 0.2520549512 -169 0.9723557692 0.2518949055 -170 0.972322503 0.2511279119 -171 0.9736211031 0.2506003543 -172 0.9702026222 0.2503210538 -173 0.9714285714 0.2500940743 -174 0.9695193435 0.2495754626 -175 0.972027972 0.2491294872 -176 0.9699769053 0.2486089152 -177 0.9711316397 0.2481818652 -178 0.9711981567 0.247761373 -179 0.9726339795 0.2473678789 -180 0.9727272727 0.2472103459 -181 0.9751972943 0.2463777729 -182 0.9741863075 0.2460682311 -183 0.9765100671 0.2458297217 +iter Precision Logloss +0 0.6593406593 0.68530972 +1 0.722972973 0.6775917398 +2 0.8018018018 0.6700164661 +3 0.8288288288 0.6627022981 +4 0.828125 0.6555495837 +5 0.8529411765 0.6486192689 +6 0.8526315789 0.6416034871 +7 0.8571428571 0.6349575872 +8 0.8928571429 0.62841526 +9 0.925 0.6219793568 +10 0.9012345679 0.6156481666 +11 0.8974358974 0.6094561188 +12 0.8915662651 0.6034505446 +13 0.8717948718 0.5977210809 +14 0.8888888889 0.5921640839 +15 0.8815789474 0.5866051979 +16 0.8783783784 0.5813390311 +17 0.8658536585 0.5761386576 +18 0.875 0.5708657191 +19 0.8717948718 0.5658757342 +20 0.8734177215 0.5609954166 +21 0.8780487805 0.5562411254 +22 0.9054054054 0.5516046276 +23 0.904109589 0.5470313569 +24 0.904109589 0.5426306241 +25 0.9066666667 0.5382543054 +26 0.9066666667 0.5339250684 +27 0.9090909091 0.5298334854 +28 0.9090909091 0.5258193858 +29 0.9230769231 0.521902693 +30 0.9358974359 0.5180032861 +31 0.9259259259 0.5142040303 +32 0.9277108434 0.5104505018 +33 0.9285714286 0.5068626326 +34 0.9318181818 0.50327708 +35 0.9342105263 0.4999440793 +36 0.9342105263 0.4965771484 +37 0.9444444444 0.4933516766 +38 0.9452054795 0.4901509395 +39 0.9459459459 0.4870445797 +40 0.9452054795 0.4840240078 +41 0.9444444444 0.4811060105 +42 0.9333333333 0.478205406 +43 0.9358974359 0.4753474281 +44 0.9358974359 0.472622997 +45 0.9605263158 0.4699823577 +46 0.9459459459 0.467461187 +47 0.92 0.4648738666 +48 0.9230769231 0.4623380831 +49 0.9444444444 0.4599138914 +50 0.9452054795 0.4574885236 +51 0.9459459459 0.4551268818 +52 0.9459459459 0.4528412266 +53 0.9444444444 0.4505661211 +54 0.9342105263 0.448414868 +55 0.9452054795 0.4462228059 +56 0.9189189189 0.4441773352 +57 0.92 0.4420920535 +58 0.925 0.440192283 +59 0.9024390244 0.4382421875 +60 0.9024390244 0.4363475493 +61 0.9024390244 0.4345450787 +62 0.9036144578 0.4326472685 +63 0.8977272727 0.4308568801 +64 0.9 0.4291056256 +65 0.902173913 0.4273129562 +66 0.9090909091 0.4256047559 +67 0.8988764045 0.4240742972 +68 0.8941176471 0.4224448991 +69 0.8953488372 0.4209080249 +70 0.8988764045 0.4193174398 +71 0.9 0.4177749344 +72 0.8988764045 0.4162908445 +73 0.9 0.4148385464 +74 0.9032258065 0.4133756629 +75 0.9052631579 0.4120514941 +76 0.8958333333 0.4107138529 +77 0.89 0.409451735 +78 0.8932038835 0.4082081147 +79 0.8921568627 0.4069098212 +80 0.8952380952 0.4056634566 +81 0.9134615385 0.4043676936 +82 0.9038461538 0.4031632071 +83 0.9065420561 0.4020146057 +84 0.9065420561 0.4008684991 +85 0.9082568807 0.3996890682 +86 0.9174311927 0.3986428633 +87 0.9181818182 0.3975681455 +88 0.9026548673 0.3964486984 +89 0.9099099099 0.3954416272 +90 0.9115044248 0.3943964915 +91 0.9107142857 0.3933641152 +92 0.9026548673 0.3924092937 +93 0.8947368421 0.3914568602 +94 0.8965517241 0.390547374 +95 0.8965517241 0.3896693944 +96 0.8728813559 0.3887562728 +97 0.8760330579 0.3878669594 +98 0.8813559322 0.3870453995 +99 0.868852459 0.386205128 +100 0.8833333333 0.385424377 +101 0.8833333333 0.3846496137 +102 0.9043478261 0.3838790559 +103 0.906779661 0.3831366546 +104 0.8974358974 0.3823459597 +105 0.905982906 0.3816439396 +106 0.8925619835 0.3809453054 +107 0.9043478261 0.380220974 +108 0.9130434783 0.3795425482 +109 0.9130434783 0.3788851149 +110 0.8947368421 0.3782476049 +111 0.9026548673 0.377613659 +112 0.9008264463 0.3769072551 +113 0.8991596639 0.3762798315 +114 0.8991596639 0.3756611399 +115 0.8976377953 0.3750953752 +116 0.9032258065 0.374501169 +117 0.905511811 0.3739479856 +118 0.8947368421 0.3733265497 +119 0.890625 0.3727895116 +120 0.9 0.3722381815 +121 0.9076923077 0.371693837 +122 0.9076923077 0.3711173443 +123 0.9090909091 0.3705372163 +124 0.9083969466 0.3700201728 +125 0.9090909091 0.3695156393 +126 0.9104477612 0.3690077198 +127 0.9124087591 0.3685299883 +128 0.9117647059 0.3680443801 +129 0.9124087591 0.3676033944 +130 0.9117647059 0.367166757 +131 0.897810219 0.3667144374 +132 0.9 0.3662658959 +133 0.9057971014 0.3658401645 +134 0.9084507042 0.3653852076 +135 0.9078014184 0.3649000627 +136 0.9014084507 0.364462855 +137 0.8958333333 0.3640970005 +138 0.8958333333 0.3636442533 +139 0.88 0.363245217 +140 0.8823529412 0.3628620409 +141 0.8881578947 0.3624502809 +142 0.8896103896 0.3620806127 +143 0.891025641 0.3617276959 +144 0.8917197452 0.3613753136 +145 0.8853503185 0.3610250342 +146 0.8917197452 0.3606988481 +147 0.8860759494 0.3602493442 +148 0.88125 0.3599184891 +149 0.8765432099 0.3596188911 +150 0.8773006135 0.3592183936 +151 0.8780487805 0.3588919223 +152 0.8711656442 0.3585073563 +153 0.8711656442 0.3581781763 +154 0.8773006135 0.3578482479 +155 0.8734939759 0.3575392763 +156 0.875 0.3572412466 +157 0.8787878788 0.3568917156 +158 0.8773006135 0.3565857023 +159 0.8848484848 0.3563088076 +160 0.8855421687 0.3559962007 +161 0.8902439024 0.3556571125 +162 0.8855421687 0.35543956 +163 0.8848484848 0.3551621664 +164 0.8902439024 0.354874722 +165 0.896969697 0.3545863509 +166 0.8963414634 0.3542585253 +167 0.8963414634 0.3539345489 +168 0.8909090909 0.3536960039 +169 0.8963414634 0.3534498674 +170 0.875739645 0.353215635 +171 0.8848484848 0.3529295806 +172 0.8915662651 0.352638679 +173 0.8902439024 0.3523191934 +174 0.8963414634 0.3520754448 +175 0.8982035928 0.3518537936 +176 0.8941176471 0.3516214145 +177 0.8888888889 0.3513249886 +178 0.8982035928 0.3511203738 +179 0.9 0.3509067775 +180 0.9053254438 0.3507023765 +181 0.9053254438 0.350465578 +182 0.9101796407 0.3502760749 +183 0.9058823529 0.3500263743 +184 0.9058823529 0.3498100693 +185 0.9117647059 0.3496086978 +186 0.9117647059 0.3494197651 +187 0.9122807018 0.349233042 +188 0.9075144509 0.3489871194 +189 0.9132947977 0.3487706361 +190 0.9142857143 0.3485947836 +191 0.9248554913 0.3483899193 +192 0.9248554913 0.3482065109 +193 0.9142857143 0.3479946966 +194 0.9147727273 0.3477309535 +195 0.9147727273 0.3474873475 +196 0.9147727273 0.3472967396 +197 0.9157303371 0.347078902 +198 0.9157303371 0.34688056 +199 0.9162011173 0.3466977575 +200 0.9116022099 0.3465445013 +201 0.912568306 0.3462837876 +202 0.912568306 0.346108149 +203 0.9086021505 0.3459622348 +204 0.9081081081 0.3457472129 +205 0.9086021505 0.3455854742 +206 0.9095744681 0.345429937 +207 0.9100529101 0.3452428932 +208 0.9114583333 0.3450315423 +209 0.9109947644 0.3448759694 +210 0.90625 0.3446913136 +211 0.90625 0.3444859503 +212 0.90625 0.3442730668 +213 0.9057591623 0.3440894089 +214 0.9067357513 0.3439525833 +215 0.9114583333 0.3438305486 +216 0.9114583333 0.3436801437 +217 0.9119170984 0.3435236442 +218 0.9114583333 0.3433478273 +219 0.9119170984 0.3432052991 +220 0.9072164948 0.3430779183 +221 0.9081632653 0.342938277 +222 0.9086294416 0.3427751126 +223 0.9086294416 0.3426143719 +224 0.9086294416 0.3423794266 +225 0.9095477387 0.3422408902 +226 0.9090909091 0.3420682453 +227 0.9145728643 0.3419356966 +228 0.9191919192 0.3417886419 +229 0.9191919192 0.3416593721 +230 0.923857868 0.3415157034 +231 0.923857868 0.3413484047 +232 0.9246231156 0.3412097613 +233 0.9303482587 0.3410308437 +234 0.9306930693 0.3408708514 +235 0.935 0.3407408688 +236 0.9310344828 0.3405847613 +237 0.9359605911 0.3404300083 +238 0.9362745098 0.3402643134 +239 0.9317073171 0.3401302321 +240 0.9323671498 0.3399919451 +241 0.9414634146 0.3398047588 +242 0.9371980676 0.3396306883 +243 0.9375 0.339554773 +244 0.9375 0.3394041187 +245 0.9380952381 0.3392554246 +246 0.9339622642 0.3388922787 +247 0.9342723005 0.3387117216 +248 0.9339622642 0.3385895087 +249 0.9386792453 0.3385190465 +250 0.9348837209 0.3382733377 +251 0.9345794393 0.3381529425 +252 0.9348837209 0.3380619155 +253 0.9348837209 0.3378854927 +254 0.9348837209 0.3377540132 +255 0.9302325581 0.3375425197 +256 0.9302325581 0.3374556983 +257 0.9299065421 0.3373343408 +258 0.9389671362 0.3372118071 +259 0.930875576 0.3370945484 +260 0.935483871 0.3369541942 +261 0.9400921659 0.3368692618 +262 0.9400921659 0.3367536425 +263 0.9403669725 0.3366149279 +264 0.9406392694 0.3365411511 +265 0.9406392694 0.3363912095 +266 0.9403669725 0.3363007527 +267 0.9411764706 0.3361698078 +268 0.9447004608 0.3360679103 +269 0.9417040359 0.3358984375 +270 0.9459459459 0.3357251155 +271 0.9414414414 0.3356337677 +272 0.9424778761 0.335546376 +273 0.9424778761 0.3353878094 +274 0.9424778761 0.3352970318 +275 0.9424778761 0.3351617031 +276 0.9424778761 0.3350522497 +277 0.9429824561 0.3349684934 +278 0.9429824561 0.3347801309 +279 0.943231441 0.3346032448 +280 0.9429824561 0.334415203 +281 0.9427312775 0.334342638 +282 0.9429824561 0.3341694229 +283 0.9388646288 0.3340826015 +284 0.9391304348 0.3339726491 +285 0.9396551724 0.333826343 +286 0.9393939394 0.3336900875 +287 0.9396551724 0.3335809549 +288 0.9393939394 0.333442062 +289 0.9396551724 0.3333525676 +290 0.9396551724 0.3332697023 +291 0.9401709402 0.3331760379 +292 0.9399141631 0.3330947765 +293 0.9358974359 0.3329954451 +294 0.9358974359 0.3329106552 +295 0.936440678 0.3327866603 +296 0.9361702128 0.3327275319 +297 0.9404255319 0.3326225336 +298 0.9411764706 0.3324805757 +299 0.9377593361 0.3323966768 +300 0.9341563786 0.3322237825 +301 0.9377593361 0.3321659016 +302 0.9380165289 0.3320394474 +303 0.9380165289 0.3319693773 +304 0.9377593361 0.3318825202 +305 0.9382716049 0.3317774863 +306 0.9382716049 0.3316979713 +307 0.9346938776 0.3315895515 +308 0.9346938776 0.3315500257 +309 0.9390243902 0.3314697978 +310 0.939516129 0.3314249615 +311 0.939516129 0.3312820769 +312 0.9357429719 0.3311679901 +313 0.939516129 0.3311195184 +314 0.939516129 0.3310690152 +315 0.939516129 0.3309855084 +316 0.939516129 0.3309401731 +317 0.9357429719 0.330802492 +318 0.9357429719 0.3307062614 +319 0.9357429719 0.330692005 +320 0.9357429719 0.3306368684 +321 0.9282868526 0.3305426337 +322 0.9282868526 0.3305008269 +323 0.9282868526 0.3303075459 +324 0.932 0.3302724396 +325 0.932 0.3301259552 +326 0.9288537549 0.3300699989 +327 0.9288537549 0.3299974339 +328 0.9288537549 0.3298813512 +329 0.9288537549 0.3298155936 +330 0.9288537549 0.3297789191 +331 0.9288537549 0.3297477332 +332 0.9291338583 0.3296651888 +333 0.93359375 0.3295453638 +334 0.93359375 0.3294967495 +335 0.9375 0.3294302079 +336 0.9375 0.3294071838 +337 0.9375 0.3293788136 +338 0.9338521401 0.3292367487 +339 0.9338521401 0.3291954408 +340 0.9338521401 0.3290744754 +341 0.9338521401 0.3290348426 +342 0.9338521401 0.329009288 +343 0.9338521401 0.3289871906 +344 0.9302325581 0.3289021869 +345 0.9299610895 0.3288670806 +346 0.9302325581 0.3287844648 +347 0.9305019305 0.3286397625 +348 0.9307692308 0.3286172018 +349 0.9307692308 0.3285155894 +350 0.9305019305 0.328492102 +351 0.9302325581 0.3284671889 +352 0.9307692308 0.3284392108 +353 0.9307692308 0.3283767678 +354 0.9307692308 0.3283334284 +355 0.9310344828 0.3283064482 +356 0.9310344828 0.3282412252 +357 0.9310344828 0.328229535 +358 0.9310344828 0.3281949276 +359 0.9312977099 0.3280923885 +360 0.9310344828 0.3279984389 +361 0.9315589354 0.3279718151 +362 0.928030303 0.3279480782 +363 0.9353612167 0.3278811445 +364 0.9353612167 0.3277992059 +365 0.9318181818 0.3277876226 +366 0.9318181818 0.3276685105 +367 0.9318181818 0.3275194956 +368 0.9318181818 0.3275007485 +369 0.9318181818 0.3274810034 +370 0.9318181818 0.3274523124 +371 0.9318181818 0.3273819928 +372 0.9318181818 0.3273513415 +373 0.9320754717 0.3272574276 +374 0.9320754717 0.3272349025 +375 0.9320754717 0.3272111656 +376 0.9318181818 0.3271826172 +377 0.9318181818 0.3271223483 +378 0.9318181818 0.3270916971 +379 0.9318181818 0.3270695284 +380 0.9320754717 0.3269869839 +381 0.9318181818 0.3269538022 +382 0.9320754717 0.3268146242 +383 0.9323308271 0.3266813626 +384 0.9323308271 0.3266648609 +385 0.9323308271 0.3266294694 +386 0.9323308271 0.3265899079 +387 0.9325842697 0.3264602461 +388 0.9328358209 0.3264275989 +389 0.9328358209 0.3261832801 +390 0.9293680297 0.3261257912 +391 0.9328358209 0.3261000585 +392 0.9296296296 0.3260115263 +393 0.9296296296 0.3260047901 +394 0.9296296296 0.3259721074 +395 0.9304029304 0.3258751639 +396 0.9306569343 0.3258094064 +397 0.9306569343 0.3257776859 +398 0.9306569343 0.3256861599 +399 0.9306569343 0.3256791386 +400 0.9306569343 0.3255725365 +401 0.9306569343 0.3254692133 +402 0.9306569343 0.325401745 +403 0.9309090909 0.3253311759 +404 0.9275362319 0.3253155295 +405 0.9275362319 0.3252776788 +406 0.9277978339 0.3252604998 +407 0.9285714286 0.3251181854 +408 0.9283154122 0.3250225607 +409 0.9290780142 0.3249287893 +410 0.9288256228 0.3247705078 +411 0.9293286219 0.3247093123 +412 0.9293286219 0.3246648323 +413 0.9295774648 0.3246344662 +414 0.9293286219 0.3246129747 +415 0.9295774648 0.3245792584 +416 0.9295774648 0.3245577312 +417 0.9298245614 0.3244512717 +418 0.9300699301 0.3243873674 +419 0.9300699301 0.3243661967 +420 0.9300699301 0.3242703581 +421 0.9305555556 0.3242519674 +422 0.9303135889 0.3241523865 +423 0.9270833333 0.3241283289 +424 0.9270833333 0.3240927592 +425 0.9278350515 0.3240085039 +426 0.9280821918 0.3239215043 +427 0.9249146758 0.3238194642 +428 0.9217687075 0.3237158203 +429 0.9217687075 0.3237044865 +430 0.9225589226 0.3236037651 +431 0.9225589226 0.3235472385 +432 0.9222972973 0.323520294 +433 0.9261744966 0.3234630902 +434 0.9264214047 0.3232854913 +435 0.9266666667 0.3231383654 +436 0.9266666667 0.3230566763 +437 0.9266666667 0.3230444871 +438 0.9238410596 0.3230088461 +439 0.9238410596 0.3229739536 +440 0.9238410596 0.3229666472 +441 0.9240924092 0.3228943673 +442 0.9240924092 0.3228382328 +443 0.9243421053 0.3227665232 +444 0.9245901639 0.3227103173 +445 0.9245901639 0.3226070655 +446 0.9273927393 0.3225281207 +447 0.9273927393 0.3225112982 +448 0.9245901639 0.322388123 +449 0.9245901639 0.3222409615 +450 0.9248366013 0.3220693858 +451 0.9248366013 0.3219415773 +452 0.9248366013 0.3219059364 +453 0.9248366013 0.3217937742 +454 0.9250814332 0.3216357065 +455 0.9225806452 0.3216104371 +456 0.9223300971 0.3215952184 +457 0.9258064516 0.3214618855 +458 0.9258064516 0.3213783788 +459 0.9260450161 0.3212732736 +460 0.9260450161 0.3211840286 +461 0.9260450161 0.3211772211 +462 0.9260450161 0.3210794936 +463 0.9260450161 0.3209590271 +464 0.9260450161 0.3208823991 +465 0.9262820513 0.3208157861 +466 0.9262820513 0.3206734717 +467 0.923566879 0.32060415 +468 0.9265175719 0.3205238509 +469 0.9267515924 0.3204176765 +470 0.9238095238 0.3203140682 +471 0.9242902208 0.3202052207 +472 0.9247648903 0.3201198606 +473 0.9247648903 0.3199963646 +474 0.9247648903 0.319894075 +475 0.9247648903 0.319887232 +476 0.9252336449 0.3197591383 +477 0.9226006192 0.3196688598 +478 0.9223602484 0.3196189624 +479 0.9221183801 0.3195125741 +480 0.9221183801 0.3194593622 +481 0.9228395062 0.3193807738 +482 0.9230769231 0.3193528313 +483 0.9259259259 0.3192504705 +484 0.9287925697 0.3191515668 +485 0.9290123457 0.3189851947 +486 0.9294478528 0.3189042541 +487 0.9292307692 0.3188111599 +488 0.9263803681 0.3187479685 +489 0.9296636086 0.3186910142 +490 0.9296636086 0.318641402 +491 0.9296636086 0.3185637403 +492 0.9268292683 0.3184447351 +493 0.9270516717 0.3183507142 +494 0.9272727273 0.3182590457 +495 0.9242424242 0.3181805286 +496 0.9246987952 0.3181252851 +497 0.9244712991 0.318031585 +498 0.9251497006 0.3178987511 +499 0.9223880597 0.3177505916 diff --git a/main/train/catboost_info/test/events.out.tfevents b/main/train/catboost_info/test/events.out.tfevents index e0cb7f4d95d1a3fca5f5d898bfe012f58b982209..bc38dfd92d797fc241a285812a98dbde8f545ff0 100644 GIT binary patch literal 56740 zcmajocU({J`v>qyMx?AFvT9oc)6 z-~Ii(@1JvB*M0Rk{`1G{@jTak-{(H}xz9Q8su&sm{qeGFm(R$^xo~{$v}U%YO-q{Q z>pXs_yXOSYv15uA_%Wx6llK43raOjKkh$j7d^>8n5~fzBc{+?8K5FcQ3B_86**A6i z|Njm8

QuGf_*HfBu`X$U(Kt1GAxat^9=4NZJ9A(HSd{FZ_WbbJxxij&3h);8}X#F=KUIU%Zm4MQ_tyH zC~VIg&cBB7UT*AF@vWqJmtAi@=e;~S-qI4|^YUIE>|J_aLGvbB$A2cC?|MPBNW z_8fTBH-UJ6lW2UVg_YO5BZV>>^Iksc4KBU_wr7`-mJfL^AFj{GuAJsgp5t1S_e`l* zvF!@zEp2?up7%_#cl78#nm4v!a97^TPrWA&OQDxz@5CRxmmhl>^U7#mNba<+yjOsF z8TD2|&oT4zN!}}fy*K4-G%q#z6rEpWubWYCdw+lEU7QX^#|{nQ_slA7uIM0z5ij}Gsm7wu(jqTCEd#Ae6UbG zFX%n8DKwthX9>--zc#WEUtb~WIWBdFUdE`#Ie4!S_8eLk*Su8%|vm(?RxCD*Q&o9<*B;Ma7n$PmPSZZGMzvrxZ zuPF86$D!-Py@icTc&{j~Z(-+Rnm49jJy+f7YdNfMcVflKyk~{IU+#r9uj_~XcDz@d zdPYWp&^vc&R5tBd9DA?371F#Jlb;viy%MUo0eU-TOwHo!D}lX~t`?eids=TgU&~Q# zO}%d^!O)9!ah*4Vq~Wv+RN85INg`btvodBkGqoe2od&3h%W*C?={=9wI*XTp1> zsCRzs8tCn`YPpQ}N@34urJ3d}t`?m{JfkB2yH~L&O+B)n=-9R>T`&DjqWLBIQUT2~ z^Rr*Wdp6V?U&;^GmoR;c1*uPZHn_g(_w#FB=9(!EyjO;L^Dm?Oqq9w&ck^Bu?0u*J zyorr}l;pjCsFyx)5v;GB@yuzw_Yd~6Tuin4yiNE2=Do5yo|Ws{61-Oyd#U5|Y2J^( zjxBhv9QDY0@aEl9PkFB#_SzlHt9eG#9X)xkJoO$8N9)1j=iHz3UU}?w%E+U6qg&TA z=DiBkBj-c!_gSI5R{?t?I|A=(#<4NHSCM+;`d912&J(;>5qsU217Lj%PEJbX>#Ksj^#QrG`YI>5x)aaYFn?C1-oC*3&}-;m)1G*LlW6|jn`*3i zK9$o`c+Zx43;odidBu59JKnR!^?5Y_Uft>TUwE$?^~m}qGR1u)?^VOz+U+^D`Yt@0 zu#NZZsAq1z47TSkV-rW-v%}t+(!g_^7f;u_vKOjTkIXMqO1bsmz3SN87nnnYpZm_djblHhIB&wWvqNXN}H%GkLET_7a<9X!jK?iVv@m^i*S>6Akc^!Tqf53b7s7L0{YG>W%@?JgcmBb2O5_Urn*cud#V@<<)97he^41>480;yp*|k@IhEY?CQ`eU8}s z)9s5^-_~kp=>4=jN+;@tPeT1yBk%-WU;j;_{=3`zv*v}T1kvk*Of{sQ|3Y;Bo&UC; zo)3SM$m`Mdlji;WUbq|Io{gxt``0{pzBlkaR-JFpMz}p)dwtZr3@3{Qyw{j|k9MK` ztnP9BvgyCZ*lRf8gXVo&SNtE|YeK!(B~W|%74i4s>uZ8NhdJ*x&#CdcW4zatdgT6n z#k!nBc&{n;t~_|Bd8f*HXYigg^;%3@0{idXbPIYtlHNXDgS}5uNn5tX9KTLnKBJYeKCglvpKDgcqNA{DMP%!NpwDZ%6OyIXR)gbeI6iF zEp)u6uWaae`I|)EK^x$0tT*)xUtde=k^YNq(}wQPORptv&qDsMwfd^>wQ%OWR@B>g z5}ofZHsh83Rzpv;!d{uvc1cGz3h|G8G*(fqQr9q^imuS@4WR~_&1xN3pC=Zfol68u!Fulk`>x<49Q!lP2x?gcH+9waS`g)XH zHk8ySQ+=rC&=>80e)e4N#e02leG_^CuR-j@K;G-C<5hWEurTlS#a^AC548H~?+xF_ zd;O?4e;!&7u54vS=TF%({jgVUG4KY>_n^;HWvV~*$onYA>=wV|>+6rblSP1+=jZ3g ze0>9SyaI>ox$@os>`mHqUu(}dWQ6<_PZ%((!tw#ai;-AnXPD0B`KZaqoCHAr-JqKg&Yzg3v{#;@P@3~WttS2fa7N+}k(sRdN%d6>HdnV=2r0WS^!+bV`dR6sPbQ65bm| zJ@S6RL(c&Vd2bl@+Hbn6wWryR#VdGkIQ7W&Z&LDi`n*cE%y8`OY6U#U6;361&x3m8 zdB^IK1?l_H((}Mx*~~jyeY-mc)A>cFJgL{C2YP?$WznLu`1bU~UazUZ`xz7O#Md`M z$6LQ5>JIOXz@9~6;Q6*R?ZA5@sW<(`I=G+JYu7ks|JraSjl|xp%V}DBmaTG9*}pcV zMp2L4|4r-WI*_k#6!to9176&(;jQ@kM(cQIv+kebz0ug~H5z!w%`@Nd-WckU`K3dn zmQQ$Z4EFX_1K!c)k@S6bIX=fyk34_hTquz~-~5|I^Vz_(+gktC%jJ+s>WeY-pBMGW z`ys1u8AXu#{w9$ZJ0EyUGskb?y>Zkd@7tW5=wFNX#^Lr%uLQhsw~NYtouR(*)FbZ~ z)HWSajQ7T4ul~7PT6zj(} z>)#T18K*40d2br^$ou6_+q;(Ly=mCnVFA4MNkR8{Z#wnJe)+uHH^1}VbnNwhld6rE zR-xsxh-Xynzx}}()Fb;Lqsq7^6Yp;l_1~CS;MI(|e~$OOsaNG8dVbWSUT0;0&~T*Q zxIVjCzJsqzij<_dL-YT zv#@t_DDVbEe4y(=>G@EPtUn(&nO}wXe6ZKHB=Anv8)sKdepR=iWL$gkRh{&Fl@IdB z1hXsI=1*lAJ^nDdHHxAUC8=(h04$tMq*?QtE7nj|&&e^cuEh`+vLhqKG2#TT>u*&Xw~vFV0iM z#BFFJ^k@C3g}f-DNc{LMS?fn@kLp`^alW2d_3^i^yeOhb9B>ziRsnHWd2xZB7;awT zH7|-N5}l)fSjnsHD9=;84E0YUBOV@C0! zh$694Paq!Zk^F%d{S}eC(sX0wvnXB^Q6v_!0%GLLjXijAks^{BSI@qkhZjW@iCNcg zXk)c^rb#niT&##a|3PQRwh3M#yeOhbj9Cvvr+1D+cric`ckVzJsu?wNj^;%XMPj5c z5VLNMrt_*Ca7z^N^IY^QRdlLlLtYe7ByMgF#JXp{J>zR!s)%H<_^w4@GB1iK5}#QD z(W>suk-WG}5lM~3#zd#`qKG1K^v@)1=mFtbmx#WGS#E`%IILg;dbQG`NPIH^h>lZ>y6|F< zo|rsm^deHD6h#z?4lRKA$)%D9FRoNXvXK#0x`_iXiYO8%I04aX{+ji?xJpm-9_KNP z7ey3_Xa51>t&!GCcyYC!XxhsE4ljx*63e~6uALn_S2p~}i)-}6;wB zbGCtFoS zk@&_2h#%vg(lvmLZPpWQ?WTqDHHs(_-7J7uf7r!r#4UPa=)&O5yeOhb+?#b(J3A6v z7obIv_-_&r zQ?Fbe#*5n(k&K*&XWo9{YZOr=o<0r4N&P0r^5PCfB z#hrShPxAdMyeOhb91#MM>t z#KB#G==`QAU6aeE*{dhck4fpsiz13d*SIo1rbr^P-3%G1&r$!SC{4;l+cBNY0LWA^jflqKG1KQpOeS zYGpsX_$gjIq=;nXl>Khz%Znn4#EEBsnCiBCD=!{aM6#B9*Cxq>7ey3_b4~$qUs}gG zym&-UT$#3DE-#8G61~EJIDG4$^SpRe5y{o6(xYu7c~L}>_-q3Zo$O=F^Wrf@B==T7 znjN7#4|14`C=x6C12JalQ#P)1>oGzQ&V^NcI69eO&c|uTeyixUwM-4>;HjB%-fjmOG^z} zVw@t9v6}X!oF^}eC=$zC0Wo=JY&tKVRYWp!R@)w0&Wj?7#9iMnYgenlb_3q=;yFEW z)8u!3c~L}>81ov4br&|;z>DVrkKW z1Zq(vo>~vYD@B@Rks4*}q9T$Sy@nZ&AvJ1IBvxAh#N74j_2I=tMI1x9DQ=FMUmKcG!Wmqjor`Jcv(;Uej)rmU!#a3aeH?l zo}T*pBrjf3#6|0a;aGj!ck5?f6j3A=ZV1GV;cH9r;#EbgbYKk>*X%W(#ET+|#Hp2m zIMg~SlNYZkVr;%pC_V`dqvxaSM-fG$)sIWsyy}^&NhSHwHT*Fy21;kg#@HHs(_ zQ@;bTO-l4yUQAL%@*`iJ_F5S6qKG1~k>4%(jtQuMUxA&N$C#D9iszO99ibU6VAl9Dh z{)4otjHN1K=sNWBy?<()7cYt^5>qY!v4_!x`Mh{j5lKIm?GkW-7ey3_32{JdvoEwO6j3COJ_N)?rMqR*k7;`1 z($qiIc~L}>n6(>-i;bQ%3ZU#u5Qu1D56L#ya&`+^yZ!ee2w=M(fkGavD?5a z{;|9$qDXXz2I3Qs=HGbnzMdG-{LV{W6j3B@hW)sGbmHvGoQ}V_45St$FdGB9d0UocePlMKgf&teu~D zQAClLV-*lhD!VHCa)wrYtcc`lb!_pXXS^t)NE{jj#92RP(LH2Y;}box@$wwXTZo2( z6;UKUUkJp&khx9ye#}rrx18u|m9KqP1Ye_wB60L0AR5^ed&`SY6_Jcpk8*A4(+Al+ zB8o&~KOowyax~+`XNpL!9bYFkpT*ZGqDb7h9EijA9SrBiOg%BE!sKvX6j3C8m<~jT zA|>5<@wp;?aohxFfRKQorMxJjNPIp9i236qs`BCsJ<;A{@=;zCQ6zrp3&gZxqj&S- zOFi-T{+f?@QAClrr2`Q6%{tzOh`xrC>Xn|jHN%5GW7VQaeAfVobE12W=f&50;wr}` zNu)+8iYOAN*#Xh*VS^&P_(l=Qs-yju0-JbIM3Fet9*6~Q&ZAFQ^*Z4tCd~KULfEPs+iOX^Vu}6}%GcSHrL=XFoaL#d!O36kPQ6#qd zm8jj7NB0S%Z$8VB^GOkV4M(%wfQ^YC_!>nNiOKJPc&OaboP3R+74cXmS|J~O(?!`Q zHw*z0MPl8DK&%iPkTV~BlKMAE8# zM-2BNt*S+ln0_3Hd!`*2z>D7$G2d%^r?bKSI4_DQ5(~uuG56`&ro8xF5lM~JhfM3t ziz14|_E21zxU3^D{!m0xqsxVrbe$txRYZ|^YAdL*t$&^oy!ca3OzW03kFQZgk(jj} zhy$-HPm$z-{!+vO(dg`$-tWvQUKCLz9u5Gab3?Ode2u>qk@RD!rEjwtIUryt>Eg-fg~BMHGoo;K;H2 z_%k;z`YL}Qkce;0W9T|Z4gnEGV&-;GV@UoFhj?+ep4iCy=@q_45k+D`7!bF`*+ui> z97Rku+X7qFwD2#w&XF~WC=x410MTRomOMl>D*oTz<6K2tQDHk2E2RtxCN*kNB;JDO zSh5mdqlh9g zataV%Idy%=*SJtmJZ|5s4KIo)5>3YfG2veBy1eMGCwks7Tg8haibS)aKrD2rj4LlL z(i87nzS_ZyB8tQ!gMb+Hr`mO1T&yQ{oO_HuVUa^XM3HFI1&9S3^i}rB4KqN1o_Nv! z`aZr!5k=yL_CQRil}_hXXM?yzPkdSR5xsxZqDVZ|5Qq=2Orl>R$kc)#Aio_MQ zfH-iR*HXS!SLunp-}%sItny$*6p5`W0NY~_26j3C;D-6WU zn$zgBIT>4{h&N`T8DLnIe)PUWiz2a;DG&qv{TGr}^)=KOtS6S)T)8{xM=grPtlU5x zT&~y(UJTI_&Axln@2#XLqDXvO0EkPvIC}BoT0L>b$iYOAjvMy@7WP87UkK)B}MJ(D7 ztyeAQzo+j5$W|3mB(D1cL?h3T%DlKiPdqaI5qqozip1(y zfq1vy$yt1jJM_c>I}7CG`%y%ZxDbk;X7+2ui#rvuXj^0{y(6C!Qsa9jABYS`>*^`+-;> zDrb8#a*Rs+w-dNm5qIv`0cY~USyh$qAOA*?7|MdIVlK#ZU9 z={YYRP(-qN>{8V8J71%SA~Aj=5I=tK$j^%h6_JdbS{_g7_g1n-5k+FT2p}4b?zoW` z4=EyfI$!2)8+vagMG-}!H*D2{`!8lw<6%9~tY&F?ZzV+$MdFe5pvIWpdCKrL9#KS- z>1bZfQES3)z8^&tiFXzP@vyrK-LsMhdQ?xWlU{2NFN!DYS@hXA@D2BJp?t5N|ANc9*oOj2%}*lgDUhzOeZ_`t(7IV$lzX^Y1u@^5O|S zah2H``i`y?MHGqQvw=7{c!=`Wlc7~l>WN!tU#8E>r6{6EEIJE__mjWV_mE}mlp@o+4r^18ib7U!=))TGUx!>YN5k+EE*s7&&^rtg`6k`;T%yJ*B ze}3Ub5k+FmB2eRUtGe_FixguOkvzA0)~8VkUKCLzZkq?hNn_@0;m7J3J#pNc^cuV< zqDag!7l@^g+V`UkiL8@LU$hI5D-x$E|~_zO{E9XH)eeeGr)O0@nqt8Wq0Lo6p6zp0kPeY z4hu+)QjAwbGFHbvs!i`Zv?vlkP6lG0GR`e{@q!|zmcZAJbHkUBew3n!BJqv~5Nk}l z{EHV86p_4vU{Z7reV<&4B8o(li9js6)`QLfGImiB$(*zBY)iT`uSJn~cN7p`+;ye1 zoQx&viEDe8qfZ~SC=%Cu0&&;W`WAevUQ)z6htL&yscUum?Sm9W6p3j|f!MiHR0CeT ztS5$^nL@vPkfMkpu`Qg*FCGl=;l(R@qV1Oux?Yu{h$68Ttg)h7apmcQ;WWOgh(2x5 zUdMng3+X#ZQWQ}nR$2jC)&Ko#`n83OUDFd+Mzm7)kPQbbqDVA?HI7?-l|Ivv;&nZ7 z%Nv^?{0tzXNc_D3)Hr#5NEYeG7{h@k>4}jC_s=Av7DZy-`9R$4oI-ysT*hwbiOW6T z+w-D`BC#&K3y9debS__GvLcf6(JSEI16~wSB-VjzfTK~%=-DA_Owkk17%epAMG-|} zUbuSPmKaCBev)FUp4k0>XFXmNQ6v_Gt4EUxPiFG1dQ(q)I=msh?~n&8qDb^XHNNg{ z%!{}5#5u>NDDMOshPj9$@iZK(i;l0Q&vfL0-d04i&Z%JTO6OHAio~+Z!Pzl0{k*b= zY&g&~MI2QH&2kYXEvxYTD56L#z6^-=dlnDoTlJ12k{W#*e9xv;MHGq0;n~r=;CXsQ zmQ8b45vy-OPdtZs%n#*j6j3BrgLmbV85b{O)MukoRt*wSo_883<`5|=Cit-8CLuM00eQpAG? z(DTPjpL5ck2iZI#ibRi9Ks>&q^9P5c)HOc zxKIA{@_yxwS;H_FQ6#p7HGW)bMCTlNpc#5%_vY`L^Zh8INPG!v>|^GWkFW8mo_J=m zg|hc(s8K|b_$U~(s%4&j6?yTQp6F%UQ`vhoh$4!_Qn1FvyALbzVx}VIT7>#>wXcsI z->M>t#2C1voA7#j1tK~d4)nR6*r1G82O?@wBpzD}TD9e+?0fR>YZ!=$(i69qg315Dh~>M3HC>pCS#3YDAwS%NpM(qF>N4IOjY_?KF(9 zQACmWBpTG1V}9q=e2s4vF{IN;C~ldaN`L1;9;}EW@zQo6`Ze;&%Zu;y#7k|h=-r$Y zMHGokVL$$BcAnlN%h-E8aX?B(ddI3ok=P3MV-Byt1$>Pk6fyt$SlFs9pJjaI`%y%Z z*zW*n)rU5&^xjGy=to6N@H_>@yaV&k;zbcfVwrT#q()zZ_(c&(t6G*YqGyK| zMdFY|Am$rqO8?f3jD1zahG{2YtA5$*MV|#|Q6!pO1mYq0mRI>2zv+o9{;lwdw5k+E z6p0&d0x>-N!b@KKu85>n$NL?~&x<08#9--$9bGpNdHOF;~#Jj(m+Gip2h~#%E2-XESns>4|egPWkboh$6AwT~OmPhb7(k ze*CS7c3qCcvAXfg(PO+QqDZWf0Yo3;;+=UhOA)=_qN~-&SILKXQACk=2EL&;aPYun zUi_noh3BGK?tRWF`FK%8k=P#A7-Adzh!=g0=^vaVV#%at*_<6Bio|&@K&yTlz9X23 zF@{-gww^e>R&8ZJ=Wi5=iLZe8yYEYS$124+ia5{W3>-O=-#XCuSG6b-S3U)z`P#i( z_!{Rb;=7;d`na`d8lB~&D56NLau0}mL%Y(Q2N|2EC;np{O}~B6qDU+cYb+aGlHLW# z*nCAKBWJPSkuWk=wI~w(;4Js}yeYkZl(7YR;%{5G?Yt-l{2QP{!5??~Gon@W#e2t6r#Lb?CTzFALk!TD1u||%4qj_<$B9gJ%c>WIMd52-n z5m6+D!5RyHc38uU0g6awfEEkF=-r&`5D`V9Bdl@Mp2GBZSBy&jx7)cy5p&N)cLDcz z8~-A$szs5Q7m9P&<)_z28C$A|WUN*^-Y*X?iYO8fz_r}ZNqw4=R+Zv1J<+O@X$mij zC=&DB0%ymo!;NV_N-K=g6{oL==hV;TI*x)_y<7*BGRTq{g?~yq)+OMHGo6 z;X0@N$a*HcxKdB_h&1-*MG-|}pEqFSBpxtH<;7KsIKEUoY}Gd7Q!n$Ph$1od8xTvU z`qAI(ke#twPrTl`&O}}mQ6#Q62H%uzz29XmU*j4*(LHUPEiZ~F5}on^G3R+Nb0Rt$ zX1QQRBy-M^KPPSyQHvt6v1KJ>l=!xNrpPBHYh$8VY?8lUA^_9I2gSb{t ztUBD3t~z9mB8tRH@aw0$4ZEG>TXmfxlJn8WG-T;rEaB$1OVXts16?WM0io zu6}~AQACj#0KZ3GVN$UUFNW)hPHm^q?*e3vB8tS|VxU#uwRl0F&B@pXJ#l3X7Z1Kh z5k+D27;tcW7fw+0X$(!J>2oQ!Q##HDvHz_D7# zsvW&rX;CD4*#YtM?(@pG^M;YLT@fc*u~ipXta0-Jyu& zeDpYNO;;US6p0@8K&-Q_LP>tC?o>o0Bh;!-7dE6%b)_hxNGu9}J!53>bNbekjP24B z2hD9cf^St3MWPWDCxp-R;%nTkC*H6sSC6p68QK&uXjwanzjC_S;&oj+#0D56L_ z2E{t9yS*b~jA5+q(G!O>diR=$S`>*PuvMMv6e+-qd-cSnBdgQzJESP0NZbd1Kc|O@ zJKaN;v1mnH)kt(lzRu%^x_eIW96P4el_A&o8buU|-Qlkije60l6kp>$MYJ6$Zdf$Y zzG?#fEVv223!HmRY;gL>jVi}+B!MiE7#ds`q*El}($U*jP~ z9KA0A)_CRVlLEXbqDV}KqFcxH6L|5kB3{0935qwuORnHW5k=yGPN2rnbw>1xEIZ?f zp4i}h&yl<+qDahu;#FghMtqG&^+c2PX7sl#c73m#b@bOw;3h$1l+{%YUjnD!2QjVJX)ivkO$@imGl5-o>;8mmSurN4qA5A>9t zxFFM$&g5DYiTUC01b(d5;u2ruX+f=906ZjfM6p7}rRTl?tp>LAN1C3F{x(~0y zkz;4qoxW?WMUiOd0a~?3ls{eP$XKi*_MdniieY8?()Z=GC=xeA@x)L+`m9{W&L|?8 zS2ris&ZZwl6p3-3pvJ=eCr;)2F-{T5n!M$LMi2RZ6j3B@fi|S8*JyN34*Ics&sy|-0AE9^Ueyy#ERMwyQHvtcq&EIJ*}RCmdQqe_29`*A+3t7wvT<_4# zXI_2Fiz14|TYW%{6=(fJe_29`Hx!ZVJ%;x2@5_rKio_cIfVjPBe)_hI6q6N^)Og70 z4Sh#fiz4v{ybE}-H6j;3a#9rW`3W@3?Y#9njjvHek=U~bs4=Wg%2r-X)e}pXDm9cB zMHGqYU4WRo_d&XPludI}5%07_*N)StUz+oxh$8V1yqmKvo=Ja~Op3P@@xx=ZqdT;8 z9DVwrMUi+L_T!8f&U7Z1vD552Nb#dO>vw2ZOk=T475dA`e=+3;X@t&Ued*{{jyeOhbJPc>K z$ulzPZ&^t3z9Q}}iB^x72F{{icxh22j)DD{oUqQDZ`B8iNLqDJw=HY=8buU|51`n7 zXNO6=_)rnOjnQ7m*_;pZ@}h_$@iP<;A00vOSY^{ZQpAE=&=uLuFYP%miYO8{_6H-U z#&xemzQ)IjNY0Lh_aX=LqKG1K2wVfWlrX2ytz?Z)6tUJ|v_dX*FTXJ_iYOBM!8s@0 zayZ@VkYa`+ruw1PE=X&A`_s4X-Di2mfk?0IZ&g_;+{dw_)p4cxiH(dirQACm04z5?n zJeYQu7hfu3WIB2)IP_S*+hWR!jE`##wk%M7xU zt;ATeHJGohZ1cP0bANsAeVx}ln*YA@c)Y&P&->hS&OPVc)3nlP|M@4ZPM<0ojYH4G zig$lBYgn~G)hhib1^AB*9~&A{JHj=+o1N}|e>Dv~+E&h;$sYVkmuptFNmV_^NulB4 zP9YJKLc^xj{GmJjOrlAZ*KD=$g$shSB(lNXWJ($YYuGo`7p>O zNwKxtJ+1=sq)pXaxLgtCc?k(hd1CY5XK=Y9skvZH1(3(}UlPLQN+=JtO;gHg0j(-? zxe}3o|4;_xl;~UoE>}i5FmR(%Hmp?dDwiu0Il1^tH}!b#G9#xGm#d%*ecPm4%&%Oo zLgd7DA3;udsehBpRZ-4-woX~|)qgxF zi0pjiFOXAi6p!Sx9?FYNHY??`Sxwq-S&ztR?Vp4E*ga$s$XVL)tdBB0=Y{h-JOa5S zDUN5a4o^US`EGiBE>}nSroO6g&+5L*jLX$Y%?GU>f?O1|y)l;!P<|Mcs%-5cee%M% zY(QiSulpdoE*yWF%Qa9wuz$Z&PHbKa-;#1`*C4Xnojj0xTIoOMa!r(z+GZ-{6P^qD z@S1B9c|+H`ARlg4IG)RfC_@ixJ@IT3mko(r!|gW6%`*FCaoGsva_)zeHIH=u9LHrN zBI~!f3G!acj0i5*LK)`mUs7F%aJd$dbAoPw9GS0&?<$SczpK9*wNW+;Qq?>m^wG~C zmn6mUT=3U5kbkw`-3)4$^L0?R*tk#G+86Fz-pA!Sq~@jJS3#crYX5aE*G0Mhs9%+G z#`F_|xLlXWj)qr2HZ;GL%jJ3~Px0HNl+A|sKE~yGL@p?M8RV(<_V2lDjB?a<)vEV& z;Q4NzXbY?)Gi z;xzjZuekw{Q%7Ean(c4jIK<^2P=L8aS#qm5n`#i{(HY{qyWfPQ59aZv|!M3?vHX$|t)F0)i-rX*8xe>}snx9kF z9CSwS3zr)adDT2AtlGs+p4v2q%Z*WPmvKfZ4@tRR%;m;J-cc6iz>3#*bGZr1lYaO^ zDG$tFcZ$nRh&+AqS*ZC;%u_QiH%0ko{O?LRFLOD*tK=Tml*lJ-QNB|Acnp`Dq1-6$ zrBY7bGuDLH+>FS!$E5~SJ?BcT-+bh9bCh4ddZm=zDisEBxjB)`jzanMu)6oS+ydo8 z6LOVu_1#UUbGZeP9rRJw|0NMuy|LPv#1!R=7o-VLcQRDIo5ly^lB773IK7fOiK?}0 z#hQ(Sn&o^;ltXeqC}qP*2S0MTC8_y*6v~#(4*PSt70MqCrG=}m=IB3S@q|YH&8>*+ zY>4t--izCCxi!iiQ*SBdLeux{dCjef?DbBXhE%P+Y)j5gE}Nk|ZjQ7m)75O})npcz z&4|2mJ<7`q2IG2LZnHKhZ=Z2WDYtBVX*-wO5PAJvl)qUW?!{|1M;ZF|-QjUZxol2k zkI^X4?^|7u%N8hG4b?G3e#rEuAr$Swy_ z&Kh+USG{sSu_;9!VsH7D%Qi$FI2Yxvx2$}4&FxW!J;t@Y-VM0ip2$NYQJ$N2do`Ck zpj^Rnld`q%UcHT{k8*2uAac)Fs z$}G#BQEsQFdRGOHU38qwor!#BI?7@9+B@>rwnKSXQI4{;(?{=Y&Sg6y4~#`w&$-?X zE_XrMH$pmO(aqcMgFklTau*^uABytr=v!^M+!bZl9nz7OPIjDbF`mm^iG0Ew<-U){ zrEu9EWdpBEO4)AeuCH9SCvuuI%5TbTI|H(Vc06}OdH4&}E;irM6~B~~B*pQZ*$w5^ z6OxW{xjV{_JE>}RPpO;_HOq2$Qge(0%3pGiyymh4%14JvN7TCK{8RLAIFrb-1CgEG zQI0>d2WJvFFMRigeU+iro!-3WABlXkAId)F+4zl4mV02$AfMhB`i#pxh8TsBHMbSY^|5uhs!-t-jjD-DW5LdkjUkpL_RSEWzz#a z|6^1+q5Q~LIyBYQ+}mK;FfKb0*`S_E?J|0l)qTqLXv zx~_>B1+6XTol%C??sKt?374Ho&540nbLC=JD=xdB3^kvA85PWB7b0hRqP+Eeei)Z~ zqYO3oFsfOW%e{%bQW#ZhKAL~vavzjoFFE0_vFEwmhsY^{>@j?}7nfa8hBJfYB_0>J z>`LUf_So8ePP^h)V7Z6&McKQm>izu4@NIuC_a*WzUz9CszZA|%v}3~!<-4xWl;b&D z??WJ$-H6;E0A&Nm@=Kw$v$S$Qlr1yW@|F|pKrTs&vc2iVI@gX zu5W=g7rZs92CXgUy-~KYd8>TRZ7QtPz;iB1it-$5l+XNP@`%erP(IVIP$^HmdJ7MkzOZx~~eChZ1?N@SGRk=u*sU_CXnHzFXFRG?#sd z>^}r+wp~2Zp3B2f4t}p{?Lqw}|HpG4Mr6$-lrwY7SLL!V%DZ|>*V=UJ?Qs2j!hI6$ zc=RQ5d=$zC@zdLZ?4ZpLFGcp77Cr%5yCf<0?a9LXIja4f3tS$7@~xq&?~;#}c)sNF z2vYO?Agp=ht%|q~lYjY0lxMD2J?9EX%hloXNFtlZpqzg8@^N1CD3qV3t7a0P`M0gO zJc`IGrlK5itePK}{YsH7zD_jYvLBK4qfs8wWAzIz`=k72i*#93*SC*sNKNIkKatyp zqwIIkMmVj|_U+Lq+h10-_P|N4BDp-8$Ug{g$v06^PkGG&C_~@YjA>xZ9+aw5Yd?*F28MH&&xuFMe4tuX#Mm8jW;WR3}f4 zt}~L$g9_5*}{P0$XTyrqWUVr2(<;AnhKjd;Sk*~y}e5&BuNM7>fD*j6NsF?0A&l)rB)zkY5PeC${NjMWz99y?z@9rk`zaksW5NPDmJOY3Do>$v%PvdeJ%AFTHQr6sk!am{twzjpxh}=PF?QO-gO}IP}W#pTsYC!^diRkZ@No3s`0hsmRAGLemL zp`2Op&6UejP<9)pdd@#v&aJ>}o4N+|X~zvNN0lP`WYxXRvIT#hDk?!T9gRCnS& zyoeHRj%$0^bd;MEtJd4rmwMsaQ~u4c?OaH zXN>p5D!J(!aXAL%h>NOI=Ck!egm3QJ)`}tW2vd~ZItA|r*+HA1i87q5pSDQAFDNBR zaXdRZp**UB!NE52-xAMlaLV=Hza`envBIArFYT@>I_>MAA?@U7#_ZY8RZ-D?;fnS) zGv5qu|0LK6`~IhVQJS=v7{_fXD%vK(T|k@pfycN#ORx=cRMUz6>HW6cmZGAa)Di2h z)Y>MV+p`6`ufFP)^`YK|y4;qcqMgtQ?T7u(b>{XQ!G^AOVxQLsZc9R9|`iWCKxGhCR`;YgI|^W#+?&Z1-dHh`^*inf0fv=jH*z2$a7Y4-hUbU`#u;zA>V8fC7>P8WRxh+LS`%E<2ZJ#F$;dZiM!<>4f_vIjN zOHtA8H4*KUEIuqdwTj@<+cJrOo>5tDOHt7_@J8F@uLwVGFBa_Zd#a_{_?4~B zb6bjv_JRRuuQHw!$n7P9y`;>0<@lasYTBFIQdG2`3`aZi;=Og;P7&;xyH#~JEm}X0 z+fr1tZAPNqy&&y8w^Ich+WhRf$2i91z9vOQ`}qX4=h(#Sb9-rN_RxVRabA;cDJt5@ zacG}9`SU(*FDuP1Tr)zCx49G*?Ulmc%6N=D+X8G&@9(?q<%0e0t!gv$Q@@LrVC$ly zy-Ao;$M0B}$n7-2)=O25Z}YXr4Y@5vMZ3}*Z1XkiSIp=33c(IARIO7tI3F6uZ7C|+ zZmEK8;hV$lp9LG%scDa6@OjH^E=5Iqo$yy#_j{fh!R?iTtU-VdM=M=f(+#=U4MMXPwE83fH6uWUdL$EJiP(AO_A*;{ux}~US zzuSX$SJMwQxV=iS%Xz5w2ICHW3jdHbx(JqNafc6_fEY^eMC^NHzT>!PB4 zG#%@H(B9XX+iL`S*d5h6H7sLd8n>mWXg^(nc1xS20o-0I*sV=f`x4{3U7fitMMb+{ z7uv}$x)gJJonQw%P(ANc0m(SNM|w2e2T z{n4=J25xT(LQwy>%MTa zHttJgd!u0Y@=~qOryYADoHJ>MrxX?KK^M^8-OJ=Gw0W%d|6r3~yB|{RL$Cc^bPDR$ zMMb;LL$vc(#|!&!t-V>WBU`A>*LEIASk7%JD%wx4qg~m5_f=l^7Qu#h=+>pH{^Yh4 z747g`v|CkrFYLdyb#E2y{4uJ!@4jpv#%(Do+V$?D{pirVOkVdk!M00O%`IDgYgmKZ zQdG2W6rr8b)Tjryw+r@KOVynE&#&wMqi!iG+C9FZ9Tt8B&ot%ExJw$%zs0!3a9fIs_5yvh&Dxq(<@O%I*1N5m z*M1&&qL|xKRJ6C7q8%6H-I3dSOS8?_`t|3w6cuevN3>VC{^rZ=eS*ECwd!4xROsi= zZ7C|+Gn~=RnRqLT+xrC@p7)jZ4{LH;ii&o!Biiw!BaFCxK(Jwq)z}fSi`!CEw9N*i z{drFZJYSOs%0a=-e5M-T(TO!5a9fIscCJ6#CoSBcLfx7^-}m2#1bh5P)pfKr@zqkm P)