msb-public-java
/
AiLearning-Theory-Applying
mirror of https://github.com/ben1234560/AiLearning-Theory-Applying
2
6
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
AiLearning-Theory-Applying/机器学习竞赛实战_优胜解决方案/机器学习实战小项目/特征工程建模/.ipynb_checkpoints/特征工程建模-银行违约预测-checkpoint.ipynb

307 lines
16 KiB
Raw Permalink Blame History Escape

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import xgboost as xgb\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.metrics import roc_auc_score\n",
"from featexp import univariate_plotter # pip install featexp\n",
"from featexp import get_univariate_plots\n",
"from featexp import get_trend_stats"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-2-6bab406005e5>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mapplication_raw\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'data/application_train.csv'\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# 银行贷款数据，预测违约可能性0/1\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mapplication_raw\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mD:\\Anaconda3\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, delim_whitespace, low_memory, memory_map, float_precision)\u001b[0m\n\u001b[0;32m 700\u001b[0m skip_blank_lines=skip_blank_lines)\n\u001b[0;32m 701\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 702\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 703\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 704\u001b[0m \u001b[0mparser_f\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mD:\\Anaconda3\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m 433\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 434\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 435\u001b[1;33m \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 436\u001b[0m \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 437\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mD:\\Anaconda3\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36mread\u001b[1;34m(self, nrows)\u001b[0m\n\u001b[0;32m 1137\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1138\u001b[0m \u001b[0mnrows\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_validate_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'nrows'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1139\u001b[1;33m \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1140\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1141\u001b[0m \u001b[1;31m# May alter columns / col_dict\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mD:\\Anaconda3\\lib\\site-packages\\pandas\\io\\parsers.py\u001b[0m in \u001b[0;36mread\u001b[1;34m(self, nrows)\u001b[0m\n\u001b[0;32m 1993\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1994\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1995\u001b[1;33m \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_reader\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1996\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1997\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_first_chunk\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader.read\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_low_memory\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_rows\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_column_data\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_tokens\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_with_dtype\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mD:\\Anaconda3\\lib\\site-packages\\pandas\\core\\dtypes\\common.py\u001b[0m in \u001b[0;36mis_categorical_dtype\u001b[1;34m(arr_or_dtype)\u001b[0m\n\u001b[0;32m 570\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 571\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 572\u001b[1;33m \u001b[1;32mdef\u001b[0m \u001b[0mis_categorical_dtype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marr_or_dtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 573\u001b[0m \"\"\"\n\u001b[0;32m 574\u001b[0m \u001b[0mCheck\u001b[0m \u001b[0mwhether\u001b[0m \u001b[0man\u001b[0m \u001b[0marray\u001b[0m\u001b[1;33m-\u001b[0m\u001b[0mlike\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mdtype\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mof\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mCategorical\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"application_raw = pd.read_csv('data/application_train.csv') # 银行贷款数据，预测违约可能性0/1\n",
"application_raw.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 数据预处理\n",
"def get_nonull_dummy_data(application_train_raw, dummy_drop=['ORGANIZATION_TYPE']):\n",
" # 缺失值填充\n",
" nulls = pd.isnull(application_train_raw).sum()\n",
" less_nulls = nulls[(nulls<3075)&(nulls!=0)].index\n",
" less_nulls_float = []\n",
" for i in range(len(less_nulls)):\n",
" if application_train_raw[less_nulls[i]].dtype != 'O':\n",
" less_nulls_float.append(less_nulls[i])\n",
" \n",
" application_train_raw[less_nulls_float] = application_train_raw[less_nulls_float].fillna(application_train_raw[less_nulls_float].mean())\n",
" \n",
" # 缺失值填充\n",
" more_nulls = nulls[(nulls >= 3075)].index\n",
" more_nulls_float = []\n",
" for i in range(len(more_nulls)):\n",
" if application_train_raw[more_nulls[i]].dtype != 'O':\n",
" more_nulls_float.append(more_nulls[i])\n",
" \n",
" application_train_raw[more_nulls_float] = application_train_raw[more_nulls_float].fillna(application_train_raw[more_nulls_float].mean())\n",
" \n",
" # 特征编码\n",
" application_train_raw.drop(columns=dummy_drop, axis=1, inplace=True)\n",
" \n",
" all_cols = application_train_raw.columns\n",
" cat_cols = []\n",
" for col in all_cols:\n",
" if application_train_raw[col].dtype == 'O':\n",
" cat_cols.append(col)\n",
" \n",
" application_train_raw = pd.get_dummies(application_train_raw,columns=cat_cols, dummy_na=True)\n",
" \n",
" return application_train_raw\n",
"\n",
"\n",
"def import_and_create_train_test_data(test_size=0.33, random_state=42):\n",
" # 训练和验证集制作\n",
" application_raw = pd.read_csv('data/application_train.csv') \n",
" application = get_nonull_dummy_data(application_raw, dummy_drop=['ORGANIZATION_TYPE'])\n",
" \n",
" X = application.drop(['TARGET'],axis=1)\n",
" y = application['TARGET']\n",
" X_train, X_test,y_train,y_test = train_test_split(X, y, test_size=test_size,random_state=random_state)\n",
" \n",
" train_users = X_train[['SK_ID_CURR']]\n",
" train_users['TARGET'] = y_train\n",
" test_users = X_test[['SK_ID_CURR']]\n",
" test_users['TARGET'] = y_test\n",
" train_users.reset_index(drop=True, inplace=True)\n",
" test_users.reset_index(drop=True, inplace=True)\n",
" \n",
" return(X_train, X_test,y_train,y_test,train_users,test_users)\n",
"\n",
"\n",
"def import_and_create_TEST_data():\n",
" # 线上测试集\n",
" application_raw = pd.read_csv('data/application_test.csv') \n",
" application = get_nonull_dummy_data(application_raw, dummy_drop=['ORGANIZATION_TYPE'])\n",
" \n",
" X = application\n",
" users = X[['SK_ID_CURR']]\n",
" users.reset_index(drop=True, inplace=True)\n",
" \n",
" return(X, users)\n",
"\n",
"\n",
"def get_imp_df(xgb_model):\n",
"# 获取特征重要性\n",
" imp = pd.DataFrame(np.asarray(list(xgb_model.get_fscore().keys())))\n",
" imp.columns = ['Feature']\n",
" imp['importance'] = np.asarray(list(xgb_model.get_fscore().keys()))\n",
" imp = imp.sort_values(by=['importance'], ascending=False)\n",
" imp = imp.reset_index(drop=True)\n",
" \n",
" return (imp)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X_train.columns.values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 训练集和验证集"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train,y_test,train_users,test_users = import_and_create_train_test_data()\n",
"X_TEST,TEST_users = import_and_create_TEST_data()\n",
"\n",
"drop=['CODE_GENDER_XNA''NAME_INCOME_TYPE_Maternity leave',\n",
" 'NAME_FAMILY_STATUS_Unknown','SK_ID_CURR']\n",
"X_train = X_train.drop(drop, axis=1)\n",
"X_test = X_test.drop(drop, axis=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"data_train = X_train.reset_index(drop=True)\n",
"data_train['target'] = y_train.reset_index(drop=True)\n",
"data_test = X_test.reset_index(drop=True)\n",
"data_test['target'] = y_test.reset_index(drop=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 训练集与验证集特征趋势分析\n",
"\n",
"\n",
"get_univariate_plots(data=data_train,target_col='target',\n",
" features_list=data_train.columns[0:10],data_test=data_test)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"grouped_train,grouped_test = univariate_plotter(data=data_train,\n",
" target_col='target',\n",
" feature='AMT_INCOME_TOTAL',\n",
" data_test=data_test)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"grouped_train # 展示bin中数据信息"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 训练模型，使用全部特征"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dtrain = xgb.DMatrix(X_test,label=y_test,missing=np.nan)\n",
"dtest = xgb.DMatrix(X_train,label=y_train,missing=np.nan)\n",
"\n",
"params = {'max_depth':8,'learning_rate':0.1,'silent':0,\n",
" 'objective':'binary:logistic','min_child_weight':500,\n",
" 'eval_metric':'auc','nthread':8}\n",
"xgb_model = xgb.train(params, dtrain, 400, evals=[(dtrain,'train'),\n",
" (dtest,'test')],\n",
" early_stopping_rounds=25)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 提交结果\n",
"dTEST = xgb.DMatrix(X_TEST[X_test.columns], missing=np.nan)\n",
"y_TEST_pred = xgb_model.predict(dTEST)\n",
"submission_all_feats = pd.DataFrame({'SK_ID_CURR':TEST_users['SK_ID_CURR'],\n",
" 'TARGET':y_TEST_pred})\n",
"submission_all_feats.to_csv('data/submission_all_feats_1.csv',index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 计算训练集和验证集中特征的趋势"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"stats = get_trend_stats(data=data_train,target_col='target',data_test=data_test)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"submission_all_feats.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in new issue View Git Blame Copy Permalink