diff --git a/机器学习竞赛实战_优胜解决方案/特征工程建模/.ipynb_checkpoints/特征工程建模-checkpoint.ipynb b/机器学习竞赛实战_优胜解决方案/特征工程建模/.ipynb_checkpoints/特征工程建模-checkpoint.ipynb
index 7d7b3c0..6452c75 100644
--- a/机器学习竞赛实战_优胜解决方案/特征工程建模/.ipynb_checkpoints/特征工程建模-checkpoint.ipynb
+++ b/机器学习竞赛实战_优胜解决方案/特征工程建模/.ipynb_checkpoints/特征工程建模-checkpoint.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -20,797 +20,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>SK_ID_CURR</th>\n",
-       "      <th>TARGET</th>\n",
-       "      <th>NAME_CONTRACT_TYPE</th>\n",
-       "      <th>CODE_GENDER</th>\n",
-       "      <th>FLAG_OWN_CAR</th>\n",
-       "      <th>FLAG_OWN_REALTY</th>\n",
-       "      <th>CNT_CHILDREN</th>\n",
-       "      <th>AMT_INCOME_TOTAL</th>\n",
-       "      <th>AMT_CREDIT</th>\n",
-       "      <th>AMT_ANNUITY</th>\n",
-       "      <th>AMT_GOODS_PRICE</th>\n",
-       "      <th>NAME_TYPE_SUITE</th>\n",
-       "      <th>NAME_INCOME_TYPE</th>\n",
-       "      <th>NAME_EDUCATION_TYPE</th>\n",
-       "      <th>NAME_FAMILY_STATUS</th>\n",
-       "      <th>NAME_HOUSING_TYPE</th>\n",
-       "      <th>REGION_POPULATION_RELATIVE</th>\n",
-       "      <th>DAYS_BIRTH</th>\n",
-       "      <th>DAYS_EMPLOYED</th>\n",
-       "      <th>DAYS_REGISTRATION</th>\n",
-       "      <th>DAYS_ID_PUBLISH</th>\n",
-       "      <th>OWN_CAR_AGE</th>\n",
-       "      <th>FLAG_MOBIL</th>\n",
-       "      <th>FLAG_EMP_PHONE</th>\n",
-       "      <th>FLAG_WORK_PHONE</th>\n",
-       "      <th>FLAG_CONT_MOBILE</th>\n",
-       "      <th>FLAG_PHONE</th>\n",
-       "      <th>FLAG_EMAIL</th>\n",
-       "      <th>OCCUPATION_TYPE</th>\n",
-       "      <th>CNT_FAM_MEMBERS</th>\n",
-       "      <th>REGION_RATING_CLIENT</th>\n",
-       "      <th>REGION_RATING_CLIENT_W_CITY</th>\n",
-       "      <th>WEEKDAY_APPR_PROCESS_START</th>\n",
-       "      <th>HOUR_APPR_PROCESS_START</th>\n",
-       "      <th>REG_REGION_NOT_LIVE_REGION</th>\n",
-       "      <th>REG_REGION_NOT_WORK_REGION</th>\n",
-       "      <th>LIVE_REGION_NOT_WORK_REGION</th>\n",
-       "      <th>REG_CITY_NOT_LIVE_CITY</th>\n",
-       "      <th>REG_CITY_NOT_WORK_CITY</th>\n",
-       "      <th>LIVE_CITY_NOT_WORK_CITY</th>\n",
-       "      <th>ORGANIZATION_TYPE</th>\n",
-       "      <th>EXT_SOURCE_1</th>\n",
-       "      <th>EXT_SOURCE_2</th>\n",
-       "      <th>EXT_SOURCE_3</th>\n",
-       "      <th>APARTMENTS_AVG</th>\n",
-       "      <th>BASEMENTAREA_AVG</th>\n",
-       "      <th>YEARS_BEGINEXPLUATATION_AVG</th>\n",
-       "      <th>YEARS_BUILD_AVG</th>\n",
-       "      <th>COMMONAREA_AVG</th>\n",
-       "      <th>ELEVATORS_AVG</th>\n",
-       "      <th>ENTRANCES_AVG</th>\n",
-       "      <th>FLOORSMAX_AVG</th>\n",
-       "      <th>FLOORSMIN_AVG</th>\n",
-       "      <th>LANDAREA_AVG</th>\n",
-       "      <th>LIVINGAPARTMENTS_AVG</th>\n",
-       "      <th>LIVINGAREA_AVG</th>\n",
-       "      <th>NONLIVINGAPARTMENTS_AVG</th>\n",
-       "      <th>NONLIVINGAREA_AVG</th>\n",
-       "      <th>APARTMENTS_MODE</th>\n",
-       "      <th>BASEMENTAREA_MODE</th>\n",
-       "      <th>...</th>\n",
-       "      <th>ELEVATORS_MODE</th>\n",
-       "      <th>ENTRANCES_MODE</th>\n",
-       "      <th>FLOORSMAX_MODE</th>\n",
-       "      <th>FLOORSMIN_MODE</th>\n",
-       "      <th>LANDAREA_MODE</th>\n",
-       "      <th>LIVINGAPARTMENTS_MODE</th>\n",
-       "      <th>LIVINGAREA_MODE</th>\n",
-       "      <th>NONLIVINGAPARTMENTS_MODE</th>\n",
-       "      <th>NONLIVINGAREA_MODE</th>\n",
-       "      <th>APARTMENTS_MEDI</th>\n",
-       "      <th>BASEMENTAREA_MEDI</th>\n",
-       "      <th>YEARS_BEGINEXPLUATATION_MEDI</th>\n",
-       "      <th>YEARS_BUILD_MEDI</th>\n",
-       "      <th>COMMONAREA_MEDI</th>\n",
-       "      <th>ELEVATORS_MEDI</th>\n",
-       "      <th>ENTRANCES_MEDI</th>\n",
-       "      <th>FLOORSMAX_MEDI</th>\n",
-       "      <th>FLOORSMIN_MEDI</th>\n",
-       "      <th>LANDAREA_MEDI</th>\n",
-       "      <th>LIVINGAPARTMENTS_MEDI</th>\n",
-       "      <th>LIVINGAREA_MEDI</th>\n",
-       "      <th>NONLIVINGAPARTMENTS_MEDI</th>\n",
-       "      <th>NONLIVINGAREA_MEDI</th>\n",
-       "      <th>FONDKAPREMONT_MODE</th>\n",
-       "      <th>HOUSETYPE_MODE</th>\n",
-       "      <th>TOTALAREA_MODE</th>\n",
-       "      <th>WALLSMATERIAL_MODE</th>\n",
-       "      <th>EMERGENCYSTATE_MODE</th>\n",
-       "      <th>OBS_30_CNT_SOCIAL_CIRCLE</th>\n",
-       "      <th>DEF_30_CNT_SOCIAL_CIRCLE</th>\n",
-       "      <th>OBS_60_CNT_SOCIAL_CIRCLE</th>\n",
-       "      <th>DEF_60_CNT_SOCIAL_CIRCLE</th>\n",
-       "      <th>DAYS_LAST_PHONE_CHANGE</th>\n",
-       "      <th>FLAG_DOCUMENT_2</th>\n",
-       "      <th>FLAG_DOCUMENT_3</th>\n",
-       "      <th>FLAG_DOCUMENT_4</th>\n",
-       "      <th>FLAG_DOCUMENT_5</th>\n",
-       "      <th>FLAG_DOCUMENT_6</th>\n",
-       "      <th>FLAG_DOCUMENT_7</th>\n",
-       "      <th>FLAG_DOCUMENT_8</th>\n",
-       "      <th>FLAG_DOCUMENT_9</th>\n",
-       "      <th>FLAG_DOCUMENT_10</th>\n",
-       "      <th>FLAG_DOCUMENT_11</th>\n",
-       "      <th>FLAG_DOCUMENT_12</th>\n",
-       "      <th>FLAG_DOCUMENT_13</th>\n",
-       "      <th>FLAG_DOCUMENT_14</th>\n",
-       "      <th>FLAG_DOCUMENT_15</th>\n",
-       "      <th>FLAG_DOCUMENT_16</th>\n",
-       "      <th>FLAG_DOCUMENT_17</th>\n",
-       "      <th>FLAG_DOCUMENT_18</th>\n",
-       "      <th>FLAG_DOCUMENT_19</th>\n",
-       "      <th>FLAG_DOCUMENT_20</th>\n",
-       "      <th>FLAG_DOCUMENT_21</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_HOUR</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_DAY</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_WEEK</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_MON</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_QRT</th>\n",
-       "      <th>AMT_REQ_CREDIT_BUREAU_YEAR</th>\n",
-       "      <th>DATE</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>145457</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Cash loans</td>\n",
-       "      <td>M</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>N</td>\n",
-       "      <td>0</td>\n",
-       "      <td>288000.0</td>\n",
-       "      <td>242595.0</td>\n",
-       "      <td>10813.5</td>\n",
-       "      <td>202500.0</td>\n",
-       "      <td>Unaccompanied</td>\n",
-       "      <td>Pensioner</td>\n",
-       "      <td>Secondary / secondary special</td>\n",
-       "      <td>Married</td>\n",
-       "      <td>Municipal apartment</td>\n",
-       "      <td>0.046220</td>\n",
-       "      <td>-22230</td>\n",
-       "      <td>365243</td>\n",
-       "      <td>-7689.0</td>\n",
-       "      <td>-4096</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>FRIDAY</td>\n",
-       "      <td>13</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>XNA</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.735594</td>\n",
-       "      <td>0.413597</td>\n",
-       "      <td>0.6113</td>\n",
-       "      <td>0.3295</td>\n",
-       "      <td>0.9871</td>\n",
-       "      <td>0.8232</td>\n",
-       "      <td>0.4761</td>\n",
-       "      <td>0.96</td>\n",
-       "      <td>0.4138</td>\n",
-       "      <td>0.4583</td>\n",
-       "      <td>0.5</td>\n",
-       "      <td>0.142</td>\n",
-       "      <td>0.453</td>\n",
-       "      <td>0.6385</td>\n",
-       "      <td>0.2085</td>\n",
-       "      <td>0.4423</td>\n",
-       "      <td>0.6229</td>\n",
-       "      <td>0.342</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.9667</td>\n",
-       "      <td>0.4138</td>\n",
-       "      <td>0.4583</td>\n",
-       "      <td>0.5</td>\n",
-       "      <td>0.1452</td>\n",
-       "      <td>0.4949</td>\n",
-       "      <td>0.6652</td>\n",
-       "      <td>0.2101</td>\n",
-       "      <td>0.4682</td>\n",
-       "      <td>0.6173</td>\n",
-       "      <td>0.3295</td>\n",
-       "      <td>0.9871</td>\n",
-       "      <td>0.8256</td>\n",
-       "      <td>0.4791</td>\n",
-       "      <td>0.96</td>\n",
-       "      <td>0.4138</td>\n",
-       "      <td>0.4583</td>\n",
-       "      <td>0.5</td>\n",
-       "      <td>0.1444</td>\n",
-       "      <td>0.4609</td>\n",
-       "      <td>0.65</td>\n",
-       "      <td>0.2096</td>\n",
-       "      <td>0.4516</td>\n",
-       "      <td>org spec account</td>\n",
-       "      <td>block of flats</td>\n",
-       "      <td>0.8750</td>\n",
-       "      <td>Stone, brick</td>\n",
-       "      <td>No</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>-1347.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2018-05</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>128979</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Cash loans</td>\n",
-       "      <td>F</td>\n",
-       "      <td>N</td>\n",
-       "      <td>N</td>\n",
-       "      <td>0</td>\n",
-       "      <td>94500.0</td>\n",
-       "      <td>646920.0</td>\n",
-       "      <td>20866.5</td>\n",
-       "      <td>540000.0</td>\n",
-       "      <td>Unaccompanied</td>\n",
-       "      <td>Pensioner</td>\n",
-       "      <td>Secondary / secondary special</td>\n",
-       "      <td>Married</td>\n",
-       "      <td>House / apartment</td>\n",
-       "      <td>0.018850</td>\n",
-       "      <td>-20599</td>\n",
-       "      <td>365243</td>\n",
-       "      <td>-784.0</td>\n",
-       "      <td>-2393</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2</td>\n",
-       "      <td>SUNDAY</td>\n",
-       "      <td>15</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>XNA</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.461944</td>\n",
-       "      <td>0.326475</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>-1273.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>2018-05</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>145448</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Cash loans</td>\n",
-       "      <td>M</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>1</td>\n",
-       "      <td>225000.0</td>\n",
-       "      <td>183294.0</td>\n",
-       "      <td>14823.0</td>\n",
-       "      <td>153000.0</td>\n",
-       "      <td>Unaccompanied</td>\n",
-       "      <td>Working</td>\n",
-       "      <td>Secondary / secondary special</td>\n",
-       "      <td>Married</td>\n",
-       "      <td>House / apartment</td>\n",
-       "      <td>0.020713</td>\n",
-       "      <td>-11070</td>\n",
-       "      <td>-1345</td>\n",
-       "      <td>-3463.0</td>\n",
-       "      <td>-3618</td>\n",
-       "      <td>19.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Drivers</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>3</td>\n",
-       "      <td>SATURDAY</td>\n",
-       "      <td>9</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Self-employed</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.374592</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>12.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>11.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>-1127.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>2018-03</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>294475</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Cash loans</td>\n",
-       "      <td>M</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>N</td>\n",
-       "      <td>0</td>\n",
-       "      <td>180000.0</td>\n",
-       "      <td>260640.0</td>\n",
-       "      <td>20169.0</td>\n",
-       "      <td>225000.0</td>\n",
-       "      <td>Family</td>\n",
-       "      <td>Working</td>\n",
-       "      <td>Secondary / secondary special</td>\n",
-       "      <td>Married</td>\n",
-       "      <td>House / apartment</td>\n",
-       "      <td>0.026392</td>\n",
-       "      <td>-15901</td>\n",
-       "      <td>-130</td>\n",
-       "      <td>-7799.0</td>\n",
-       "      <td>-4449</td>\n",
-       "      <td>12.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Security staff</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2</td>\n",
-       "      <td>THURSDAY</td>\n",
-       "      <td>18</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>Business Entity Type 3</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.712657</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.1031</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.9856</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.00</td>\n",
-       "      <td>0.2069</td>\n",
-       "      <td>0.1667</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.1050</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2069</td>\n",
-       "      <td>0.1667</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.1041</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.9856</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.00</td>\n",
-       "      <td>0.2069</td>\n",
-       "      <td>0.1667</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>block of flats</td>\n",
-       "      <td>0.0696</td>\n",
-       "      <td>Stone, brick</td>\n",
-       "      <td>No</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>-1768.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2018-04</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>216609</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Revolving loans</td>\n",
-       "      <td>M</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>Y</td>\n",
-       "      <td>1</td>\n",
-       "      <td>112500.0</td>\n",
-       "      <td>180000.0</td>\n",
-       "      <td>9000.0</td>\n",
-       "      <td>180000.0</td>\n",
-       "      <td>Unaccompanied</td>\n",
-       "      <td>State servant</td>\n",
-       "      <td>Higher education</td>\n",
-       "      <td>Married</td>\n",
-       "      <td>House / apartment</td>\n",
-       "      <td>0.007020</td>\n",
-       "      <td>-10234</td>\n",
-       "      <td>-1993</td>\n",
-       "      <td>-4040.0</td>\n",
-       "      <td>-2913</td>\n",
-       "      <td>6.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2</td>\n",
-       "      <td>WEDNESDAY</td>\n",
-       "      <td>11</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>Emergency</td>\n",
-       "      <td>0.405051</td>\n",
-       "      <td>0.528879</td>\n",
-       "      <td>0.604113</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>-429.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2018-03</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>5 rows × 123 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   SK_ID_CURR  TARGET NAME_CONTRACT_TYPE  ... AMT_REQ_CREDIT_BUREAU_QRT AMT_REQ_CREDIT_BUREAU_YEAR     DATE\n",
-       "0      145457       0         Cash loans  ...                       0.0                        2.0  2018-05\n",
-       "1      128979       0         Cash loans  ...                       0.0                        3.0  2018-05\n",
-       "2      145448       0         Cash loans  ...                       0.0                        5.0  2018-03\n",
-       "3      294475       0         Cash loans  ...                       0.0                        1.0  2018-04\n",
-       "4      216609       0    Revolving loans  ...                       0.0                        0.0  2018-03\n",
-       "\n",
-       "[5 rows x 123 columns]"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
+     "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('application_train.csv')  # 银行贷款数据，预测违约可能性0/1\n",
+    "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()"
    ]
   },
@@ -823,11 +60,11 @@
     "# 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",
+    "    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!='0':\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",
@@ -836,7 +73,7 @@
     "    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!='0':\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",
@@ -847,16 +84,17 @@
     "    all_cols = application_train_raw.columns\n",
     "    cat_cols = []\n",
     "    for col in all_cols:\n",
-    "        if application_train_raw[col].dtype!='0':\n",
-    "            more_nulls_float.append(col)\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, axis=1, dummy_na=True)\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",
-    "    application_raw = pd.read_csv('application_train.csv') \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",
@@ -874,14 +112,174 @@
     "\n",
     "\n",
     "def import_and_create_TEST_data():\n",
-    "    application_raw = pd.read_csv('test_data.csv') \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": {

	SK_ID_CURR	NAME_CONTRACT_TYPE	CODE_GENDER	FLAG_OWN_CAR	FLAG_OWN_REALTY	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT	AMT_ANNUITY	AMT_GOODS_PRICE	NAME_TYPE_SUITE	NAME_INCOME_TYPE	NAME_EDUCATION_TYPE	NAME_FAMILY_STATUS	NAME_HOUSING_TYPE	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	OWN_CAR_AGE	FLAG_MOBIL	FLAG_EMP_PHONE	FLAG_WORK_PHONE	FLAG_CONT_MOBILE	OCCUPATION_TYPE	CNT_FAM_MEMBERS	REGION_RATING_CLIENT	REGION_RATING_CLIENT_W_CITY	WEEKDAY_APPR_PROCESS_START	HOUR_APPR_PROCESS_START	REG_REGION_NOT_WORK_REGION	LIVE_REGION_NOT_WORK_REGION	REG_CITY_NOT_LIVE_CITY	REG_CITY_NOT_WORK_CITY	LIVE_CITY_NOT_WORK_CITY	ORGANIZATION_TYPE	EXT_SOURCE_1	EXT_SOURCE_2	EXT_SOURCE_3	APARTMENTS_AVG	BASEMENTAREA_AVG	YEARS_BEGINEXPLUATATION_AVG	YEARS_BUILD_AVG	COMMONAREA_AVG	ELEVATORS_AVG	ENTRANCES_AVG	FLOORSMAX_AVG	FLOORSMIN_AVG	LANDAREA_AVG	LIVINGAPARTMENTS_AVG	LIVINGAREA_AVG	NONLIVINGAPARTMENTS_AVG	NONLIVINGAREA_AVG	APARTMENTS_MODE	BASEMENTAREA_MODE	...	ELEVATORS_MODE	ENTRANCES_MODE	FLOORSMAX_MODE	FLOORSMIN_MODE	LANDAREA_MODE	LIVINGAPARTMENTS_MODE	LIVINGAREA_MODE	NONLIVINGAPARTMENTS_MODE	NONLIVINGAREA_MODE	APARTMENTS_MEDI	BASEMENTAREA_MEDI	YEARS_BEGINEXPLUATATION_MEDI	YEARS_BUILD_MEDI	COMMONAREA_MEDI	ELEVATORS_MEDI	ENTRANCES_MEDI	FLOORSMAX_MEDI	FLOORSMIN_MEDI	LANDAREA_MEDI	LIVINGAPARTMENTS_MEDI	LIVINGAREA_MEDI	NONLIVINGAPARTMENTS_MEDI	NONLIVINGAREA_MEDI	FONDKAPREMONT_MODE	HOUSETYPE_MODE	TOTALAREA_MODE	WALLSMATERIAL_MODE	EMERGENCYSTATE_MODE	OBS_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	FLAG_DOCUMENT_3	FLAG_DOCUMENT_6	FLAG_DOCUMENT_8	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_YEAR	DATE
0	145457	Cash loans	M	Y	N	0	288000.0	242595.0	10813.5	202500.0	Unaccompanied	Pensioner	Secondary / secondary special	Married	Municipal apartment	0.046220	-22230	365243	-7689.0	-4096	5.0	1	0	0	1	NaN	2.0	1	1	FRIDAY	13	0	0	0	0	0	XNA	NaN	0.735594	0.413597	0.6113	0.3295	0.9871	0.8232	0.4761	0.96	0.4138	0.4583	0.5	0.142	0.453	0.6385	0.2085	0.4423	0.6229	0.342	...	0.9667	0.4138	0.4583	0.5	0.1452	0.4949	0.6652	0.2101	0.4682	0.6173	0.3295	0.9871	0.8256	0.4791	0.96	0.4138	0.4583	0.5	0.1444	0.4609	0.65	0.2096	0.4516	org spec account	block of flats	0.8750	Stone, brick	No	0.0	0.0	-1347.0	0	1	0	0.0	0.0	2.0	2018-05
1	128979	Cash loans	F	N	N	0	94500.0	646920.0	20866.5	540000.0	Unaccompanied	Pensioner	Secondary / secondary special	Married	House / apartment	0.018850	-20599	365243	-784.0	-2393	NaN	1	0	0	1	NaN	2.0	2	2	SUNDAY	15	0	0	0	0	0	XNA	NaN	0.461944	0.326475	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0	0.0	-1273.0	1	0	0	0.0	0.0	3.0	2018-05
2	145448	Cash loans	M	Y	Y	1	225000.0	183294.0	14823.0	153000.0	Unaccompanied	Working	Secondary / secondary special	Married	House / apartment	0.020713	-11070	-1345	-3463.0	-3618	19.0	1	1	0	1	Drivers	3.0	3	3	SATURDAY	9	0	0	1	1	1	Self-employed	NaN	0.374592	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	12.0	11.0	-1127.0	0	0	1	0.0	0.0	5.0	2018-03
3	294475	Cash loans	M	Y	N	0	180000.0	260640.0	20169.0	225000.0	Family	Working	Secondary / secondary special	Married	House / apartment	0.026392	-15901	-130	-7799.0	-4449	12.0	1	1	1	1	Security staff	2.0	2	2	THURSDAY	18	1	1	0	1	1	Business Entity Type 3	NaN	0.712657	NaN	0.1031	NaN	0.9856	NaN	NaN	0.00	0.2069	0.1667	NaN	NaN	NaN	NaN	NaN	NaN	0.1050	NaN	...	0.0000	0.2069	0.1667	NaN	NaN	NaN	NaN	NaN	NaN	0.1041	NaN	0.9856	NaN	NaN	0.00	0.2069	0.1667	NaN	NaN	NaN	NaN	NaN	NaN	NaN	block of flats	0.0696	Stone, brick	No	0.0	0.0	-1768.0	1	0	0	0.0	1.0	1.0	2018-04
4	216609	Revolving loans	M	Y	Y	1	112500.0	180000.0	9000.0	180000.0	Unaccompanied	State servant	Higher education	Married	House / apartment	0.007020	-10234	-1993	-4040.0	-2913	6.0	1	1	0	1	NaN	3.0	2	2	WEDNESDAY	11	0	0	0	0	0	Emergency	0.405051	0.528879	0.604113	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	1.0	1.0	-429.0	0	0	0	1.0	0.0	0.0	2018-03