라이브러리와 app 데이터 세트 로딩¶
In [160]:
from IPython.core.display import display, HTML
display(HTML("<style>.container {width:90% !important;}</style>"))
C:\Users\82105\AppData\Local\Temp\ipykernel_19812\2892539641.py:1: DeprecationWarning: Importing display from IPython.core.display is deprecated since IPython 7.14, please import from IPython display
from IPython.core.display import display, HTML
In [ ]:
import numpy as np
import pandas as pd
import gc
import time
import matplotlib.pyplot as plt
import seaborn as sns
#import warning
%matplotlib inline
#warning.ignorewarning(...)
pd.set_option('display.max_rows', 100)
pd.set_option('display.max_columns', 200)
In [120]:
app_train = pd.read_csv('데이터셋/home-credit-default-risk/application_train.csv')
app_test = pd.read_csv('데이터셋/home-credit-default-risk/application_test.csv')
In [4]:
app_train.head()
Out[4]:
| SK_ID_CURR | TARGET | 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 | FLAG_PHONE | FLAG_EMAIL | OCCUPATION_TYPE | CNT_FAM_MEMBERS | REGION_RATING_CLIENT | REGION_RATING_CLIENT_W_CITY | WEEKDAY_APPR_PROCESS_START | HOUR_APPR_PROCESS_START | REG_REGION_NOT_LIVE_REGION | 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 | YEARS_BEGINEXPLUATATION_MODE | YEARS_BUILD_MODE | COMMONAREA_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 | DEF_30_CNT_SOCIAL_CIRCLE | OBS_60_CNT_SOCIAL_CIRCLE | DEF_60_CNT_SOCIAL_CIRCLE | DAYS_LAST_PHONE_CHANGE | FLAG_DOCUMENT_2 | FLAG_DOCUMENT_3 | FLAG_DOCUMENT_4 | FLAG_DOCUMENT_5 | FLAG_DOCUMENT_6 | FLAG_DOCUMENT_7 | FLAG_DOCUMENT_8 | FLAG_DOCUMENT_9 | FLAG_DOCUMENT_10 | FLAG_DOCUMENT_11 | FLAG_DOCUMENT_12 | FLAG_DOCUMENT_13 | FLAG_DOCUMENT_14 | FLAG_DOCUMENT_15 | FLAG_DOCUMENT_16 | FLAG_DOCUMENT_17 | FLAG_DOCUMENT_18 | FLAG_DOCUMENT_19 | FLAG_DOCUMENT_20 | FLAG_DOCUMENT_21 | AMT_REQ_CREDIT_BUREAU_HOUR | AMT_REQ_CREDIT_BUREAU_DAY | AMT_REQ_CREDIT_BUREAU_WEEK | AMT_REQ_CREDIT_BUREAU_MON | AMT_REQ_CREDIT_BUREAU_QRT | AMT_REQ_CREDIT_BUREAU_YEAR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100002 | 1 | Cash loans | M | N | Y | 0 | 202500.0 | 406597.5 | 24700.5 | 351000.0 | Unaccompanied | Working | Secondary / secondary special | Single / not married | House / apartment | 0.018801 | -9461 | -637 | -3648.0 | -2120 | NaN | 1 | 1 | 0 | 1 | 1 | 0 | Laborers | 1.0 | 2 | 2 | WEDNESDAY | 10 | 0 | 0 | 0 | 0 | 0 | 0 | Business Entity Type 3 | 0.083037 | 0.262949 | 0.139376 | 0.0247 | 0.0369 | 0.9722 | 0.6192 | 0.0143 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0369 | 0.0202 | 0.0190 | 0.0000 | 0.0000 | 0.0252 | 0.0383 | 0.9722 | 0.6341 | 0.0144 | 0.0000 | 0.0690 | 0.0833 | 0.1250 | 0.0377 | 0.022 | 0.0198 | 0.0 | 0.0 | 0.0250 | 0.0369 | 0.9722 | 0.6243 | 0.0144 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0375 | 0.0205 | 0.0193 | 0.0000 | 0.00 | reg oper account | block of flats | 0.0149 | Stone, brick | No | 2.0 | 2.0 | 2.0 | 2.0 | -1134.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 |
| 1 | 100003 | 0 | Cash loans | F | N | N | 0 | 270000.0 | 1293502.5 | 35698.5 | 1129500.0 | Family | State servant | Higher education | Married | House / apartment | 0.003541 | -16765 | -1188 | -1186.0 | -291 | NaN | 1 | 1 | 0 | 1 | 1 | 0 | Core staff | 2.0 | 1 | 1 | MONDAY | 11 | 0 | 0 | 0 | 0 | 0 | 0 | School | 0.311267 | 0.622246 | NaN | 0.0959 | 0.0529 | 0.9851 | 0.7960 | 0.0605 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0130 | 0.0773 | 0.0549 | 0.0039 | 0.0098 | 0.0924 | 0.0538 | 0.9851 | 0.8040 | 0.0497 | 0.0806 | 0.0345 | 0.2917 | 0.3333 | 0.0128 | 0.079 | 0.0554 | 0.0 | 0.0 | 0.0968 | 0.0529 | 0.9851 | 0.7987 | 0.0608 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0132 | 0.0787 | 0.0558 | 0.0039 | 0.01 | reg oper account | block of flats | 0.0714 | Block | No | 1.0 | 0.0 | 1.0 | 0.0 | -828.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2 | 100004 | 0 | Revolving loans | M | Y | Y | 0 | 67500.0 | 135000.0 | 6750.0 | 135000.0 | Unaccompanied | Working | Secondary / secondary special | Single / not married | House / apartment | 0.010032 | -19046 | -225 | -4260.0 | -2531 | 26.0 | 1 | 1 | 1 | 1 | 1 | 0 | Laborers | 1.0 | 2 | 2 | MONDAY | 9 | 0 | 0 | 0 | 0 | 0 | 0 | Government | NaN | 0.555912 | 0.729567 | 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 | NaN | NaN | 0.0 | 0.0 | 0.0 | 0.0 | -815.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3 | 100006 | 0 | Cash loans | F | N | Y | 0 | 135000.0 | 312682.5 | 29686.5 | 297000.0 | Unaccompanied | Working | Secondary / secondary special | Civil marriage | House / apartment | 0.008019 | -19005 | -3039 | -9833.0 | -2437 | NaN | 1 | 1 | 0 | 1 | 0 | 0 | Laborers | 2.0 | 2 | 2 | WEDNESDAY | 17 | 0 | 0 | 0 | 0 | 0 | 0 | Business Entity Type 3 | NaN | 0.650442 | 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 | NaN | NaN | NaN | 2.0 | 0.0 | 2.0 | 0.0 | -617.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | NaN | NaN | NaN | NaN | NaN | NaN |
| 4 | 100007 | 0 | Cash loans | M | N | Y | 0 | 121500.0 | 513000.0 | 21865.5 | 513000.0 | Unaccompanied | Working | Secondary / secondary special | Single / not married | House / apartment | 0.028663 | -19932 | -3038 | -4311.0 | -3458 | NaN | 1 | 1 | 0 | 1 | 0 | 0 | Core staff | 1.0 | 2 | 2 | THURSDAY | 11 | 0 | 0 | 0 | 0 | 1 | 1 | Religion | NaN | 0.322738 | 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 | NaN | NaN | NaN | 0.0 | 0.0 | 0.0 | 0.0 | -1106.0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
In [121]:
app_train.shape, app_test.shape
Out[121]:
((307511, 122), (48744, 121))TARGET 값 분포 및 AMT_INCOME_TOTAL 값 Histogram¶
- TARGET값 별 분포도, Pandas, Matplotlib, Seaborn으로 histogram 표현
In [6]:
app_train['TARGET'].value_counts()
Out[6]:
0 282686
1 24825
Name: TARGET, dtype: int64In [43]:
# AMT_CREDIT _ Credit amount of the loan, 대출 총액
app_train['AMT_CREDIT'].hist()
#app_train[app_train['AMT_CREDIT'] == 4050000]
#test_hist['AMT_CREDIT'].hist()
#히스토그램 y축은 금액에 해당하는 행 수
#x축은 금액을 소수점 단위로 변환해서 비율
Out[43]:
<AxesSubplot:>
In [8]:
# AMT_INCOME_TOTAL == 수입
plt.hist(app_train['AMT_INCOME_TOTAL'])
Out[8]:
(array([3.07508e+05, 2.00000e+00, 0.00000e+00, 0.00000e+00, 0.00000e+00,
0.00000e+00, 0.00000e+00, 0.00000e+00, 0.00000e+00, 1.00000e+00]),
array([2.56500000e+04, 1.17230850e+07, 2.34205200e+07, 3.51179550e+07,
4.68153900e+07, 5.85128250e+07, 7.02102600e+07, 8.19076950e+07,
9.36051300e+07, 1.05302565e+08, 1.17000000e+08]),
<BarContainer object of 10 artists>)
In [46]:
# 수입
sns.distplot(app_train['AMT_INCOME_TOTAL'])
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
Out[46]:
<AxesSubplot:xlabel='AMT_INCOME_TOTAL', ylabel='Density'>
In [11]:
# 수입
sns.boxplot(app_train['AMT_INCOME_TOTAL'])
C:\Users\82105\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
warnings.warn(
Out[11]:
<AxesSubplot:xlabel='AMT_INCOME_TOTAL'>
AMT_INCOME_TOTAL이 1000000 이하인 값에 대한 분포도¶
- boolean indexing으로 filtering 후 histogram 표현
In [ ]:
# boolean indexing 으로 filtering 적용
# AMT_INCOME_TOTAL == 수입
app_train[app_train['AMT_INCOME_TOTAL'] < 1000000]['AMT_INCOME_TOTAL'].hist()
#app_train[app_train['AMT_INCOME_TOTAL'] < 1000000].sum()
In [13]:
# distplot으로 histogram 표현
# 대출 총액
sns.distplot(app_train[app_train['AMT_CREDIT'] < 1000000]['AMT_CREDIT'])
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
Out[13]:
<AxesSubplot:xlabel='AMT_CREDIT', ylabel='Density'>
TARGET 값에 따른 AMT_INCOME_TOTAL값 분포도 비교¶
- distplot과 violinplot 시각화
- plt.subplots() 기반으로 seaborn의 distplot과 violinplot으로 분포도 비교 시각화
In [50]:
# TARGET값에 따른 Filtering 조건 각각 설정.
cond1 = (app_train['TARGET'] == 1) # 그짓말쟁이
cond0 = (app_train['TARGET'] == 0) # 착한 사람
# AMT_INCOME_TOTAL_(수입)은 매우 큰 값이 있으므로 이는 제외.
cond_amt = (app_train['AMT_INCOME_TOTAL'] < 500000)
# distplot으로 TARGET=1이면 빨간색으로, 0이면 푸른색으로 Histogram 표현
#cond_amt을 추가 안하면 y축이 50이상 가장 큰값까지 나오기 떄문에 제한을 두었다
sns.distplot(app_train[cond0 & cond_amt]['AMT_INCOME_TOTAL'], label='0', color='blue')
sns.distplot(app_train[cond1 & cond_amt]['AMT_INCOME_TOTAL'], label='1', color='red')
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
Out[50]:
<AxesSubplot:xlabel='AMT_INCOME_TOTAL', ylabel='Density'>
In [15]:
# violinplot을 이용하면 Category 값별로 연속형 값의 분포도를 알수 있음. x는 category컬럼, y는 연속형 컬럼
sns.violinplot(x='TARGET', y='AMT_INCOME_TOTAL', data=app_train[cond_amt]) # 수입이 500000 이하인것만
Out[15]:
<AxesSubplot:xlabel='TARGET', ylabel='AMT_INCOME_TOTAL'>
In [51]:
# 2개의 subplot을 생성
fig, axs = plt.subplots(figsize=(12, 4), nrows=1, ncols=2)
In [53]:
# TARGET 값 유형에 따른 Boolean Indexing 조건
cond1 = (app_train['TARGET'] == 1)
cond0 = (app_train['TARGET'] == 0)
cond_amt = (app_train['AMT_INCOME_TOTAL'] < 500000)
# 2개의 subplot을 생성하고 왼쪽에는 violinplot을 오른쪽에는 distplot을 표현
fig, axs = plt.subplots(figsize=(12, 4), nrows=1, ncols=2, squeeze=False)
# violin plot을 왼쪽 subplot에 그림.
sns.violinplot(x='TARGET', y='AMT_INCOME_TOTAL', data=app_train[cond_amt], ax=axs[0][0] )
# Histogram을 오른쪽 subplot에 그림.
sns.distplot(app_train[cond0 & cond_amt]['AMT_INCOME_TOTAL'], ax=axs[0][1], label='0', color='blue')
sns.distplot(app_train[cond1 & cond_amt]['AMT_INCOME_TOTAL'], ax=axs[0][1], label='1', color='red')
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
Out[53]:
<AxesSubplot:xlabel='AMT_INCOME_TOTAL', ylabel='Density'>
In [ ]:
##위에 코드 함수화
In [56]:
def show_column_hist_by_target(df, column, is_amt=False):
cond1 = (df['TARGET'] == 1)
cond0 = (df['TARGET'] == 0)
fig, axs = plt.subplots(figsize=(12, 4), nrows=1, ncols=2, squeeze=False)
# is_amt가 True이면 < 500000 조건으로 filtering
cond_amt = True
if is_amt:
cond_amt = df[column] < 500000
sns.violinplot(x='TARGET', y=column, data=df[cond_amt], ax=axs[0][0] )
sns.distplot(df[cond0 & cond_amt][column], ax=axs[0][1], label='0', color='blue')
sns.distplot(df[cond1 & cond_amt][column], ax=axs[0][1], label='1', color='red')
show_column_hist_by_target(app_train, 'AMT_CREDIT', is_amt=True)
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\82105\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
app_train과 app_test를 합쳐서 한번에 데이터 preprocessing 수행.¶
In [122]:
app_train.shape, app_test.shape
Out[122]:
((307511, 122), (48744, 121))In [123]:
# pandas의 concat()을 이용하여 app_train과 app_test를 결합
apps = pd.concat([app_train, app_test])
apps.shape
Out[123]:
(356255, 122)In [124]:
#널값이 있다.
#위에 356255보다 작다
# app_test셋은 테스트 셋이기 떄문에 tarfet컬럼이 없다.
apps['TARGET'].value_counts().sum()
Out[124]:
307511In [125]:
# app_train의 TARGET 값을 Null로 입력됨.
apps['TARGET'].value_counts(dropna=False)
#target컬럼의 범주별 수와 널값을 한번에 알수 있다.
Out[125]:
0.0 282686
NaN 48744
1.0 24825
Name: TARGET, dtype: int64In [126]:
# 널을 안없애는 이유는 test셋을 이용하기 위함이다.
#test셋은 target컬럼을 제외한 컬럼들만 존재하기 때문에
# train 셋을 통해 학습시켜 test셋을 예측 하려 한다,
apps['TARGET'].isnull().sum()
Out[126]:
48744Object feature들을 Label Encoding¶
- pandas의 factorize()를 이용
In [99]:
apps.info()
<class 'pandas.core.frame.DataFrame'>
Int64Index: 356255 entries, 0 to 48743
Columns: 122 entries, SK_ID_CURR to AMT_REQ_CREDIT_BUREAU_YEAR
dtypes: float64(66), int64(40), object(16)
memory usage: 334.3+ MB
In [127]:
len(pd.factorize(apps['CODE_GENDER'])[1])
# [1]은 인코딩이 안된 것을 모아둔거 같다 길이도 3밖에 되지 않는다.
Out[127]:
3In [129]:
# pdapps.factorize()는 편리하게 Category(범주형) 컬럼을 Label인코딩 수행.
# pd.factorize(Category컬럼 Series)는 Label인코딩된 Series와 uniq한 Category값을 반환함. [0]을 이용하여 Label인코딩 Series만 취함.
#0과 1로 인코딩된 시리즈만 옭기기
# CODE_GENDER == 성별
apps['CODE_GENDER'] = pd.factorize(apps['CODE_GENDER'])[0]
# 문자형 범주형이 CODE_GENDER뿐이다.
In [130]:
pd.factorize(apps['CODE_GENDER'])#두개를 반환한다..그래서 첫번째만 반환해라 해서, [0]을 넣는다.
# 2가 있는것은 성별 범주가 [F/M/XNA] 3가지라서 그렇다
Out[130]:
(array([0, 1, 0, ..., 1, 0, 1], dtype=int64),
Int64Index([0, 1, 2], dtype='int64'))In [131]:
apps['CODE_GENDER'].value_counts()
Out[131]:
1 235126
0 121125
2 4
Name: CODE_GENDER, dtype: int64In [132]:
apps.info()
#오브젝트 컬럼이 하나 줄었다,
#int는 1 추가 되었다.
<class 'pandas.core.frame.DataFrame'>
Int64Index: 356255 entries, 0 to 48743
Columns: 122 entries, SK_ID_CURR to AMT_REQ_CREDIT_BUREAU_YEAR
dtypes: float64(66), int64(41), object(15)
memory usage: 334.3+ MB
In [135]:
# Label 인코딩을 위해 object 유형의 컬럼만 추출
object_columns = apps.dtypes[apps.dtypes == 'object'].index.tolist()
# 범주형 문자컬럼이 아닌 컬럼들을 한번에 레이블화 시켜본다
In [136]:
object_columns
# 이렇게 많은 문자형 컬럼이 있었다
Out[136]:
['NAME_CONTRACT_TYPE',
'FLAG_OWN_CAR',
'FLAG_OWN_REALTY',
'NAME_TYPE_SUITE',
'NAME_INCOME_TYPE',
'NAME_EDUCATION_TYPE',
'NAME_FAMILY_STATUS',
'NAME_HOUSING_TYPE',
'OCCUPATION_TYPE',
'WEEKDAY_APPR_PROCESS_START',
'ORGANIZATION_TYPE',
'FONDKAPREMONT_MODE',
'HOUSETYPE_MODE',
'WALLSMATERIAL_MODE',
'EMERGENCYSTATE_MODE']In [137]:
# pd.factorize()는 한개의 컬럼만 Label 인코딩이 가능하므로 object형 컬럼들을 iteration하면서 변환 수행.
# 문자형 컬럼들을 인트로 lable화 시켰다
#factorize 함수는 factorize와 다르게 한번에 인코딩이 안대서 하나씩 해야 하므로 for문을 썻다.
for column in object_columns:
apps[column] = pd.factorize(apps[column])[0]
In [139]:
apps.head()
# 컬럼에 문자가 없다.
Out[139]:
| SK_ID_CURR | TARGET | 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 | FLAG_PHONE | FLAG_EMAIL | OCCUPATION_TYPE | CNT_FAM_MEMBERS | REGION_RATING_CLIENT | REGION_RATING_CLIENT_W_CITY | WEEKDAY_APPR_PROCESS_START | HOUR_APPR_PROCESS_START | REG_REGION_NOT_LIVE_REGION | 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 | YEARS_BEGINEXPLUATATION_MODE | YEARS_BUILD_MODE | COMMONAREA_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 | DEF_30_CNT_SOCIAL_CIRCLE | OBS_60_CNT_SOCIAL_CIRCLE | DEF_60_CNT_SOCIAL_CIRCLE | DAYS_LAST_PHONE_CHANGE | FLAG_DOCUMENT_2 | FLAG_DOCUMENT_3 | FLAG_DOCUMENT_4 | FLAG_DOCUMENT_5 | FLAG_DOCUMENT_6 | FLAG_DOCUMENT_7 | FLAG_DOCUMENT_8 | FLAG_DOCUMENT_9 | FLAG_DOCUMENT_10 | FLAG_DOCUMENT_11 | FLAG_DOCUMENT_12 | FLAG_DOCUMENT_13 | FLAG_DOCUMENT_14 | FLAG_DOCUMENT_15 | FLAG_DOCUMENT_16 | FLAG_DOCUMENT_17 | FLAG_DOCUMENT_18 | FLAG_DOCUMENT_19 | FLAG_DOCUMENT_20 | FLAG_DOCUMENT_21 | AMT_REQ_CREDIT_BUREAU_HOUR | AMT_REQ_CREDIT_BUREAU_DAY | AMT_REQ_CREDIT_BUREAU_WEEK | AMT_REQ_CREDIT_BUREAU_MON | AMT_REQ_CREDIT_BUREAU_QRT | AMT_REQ_CREDIT_BUREAU_YEAR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100002 | 1.0 | 0 | 0 | 0 | 0 | 0 | 202500.0 | 406597.5 | 24700.5 | 351000.0 | 0 | 0 | 0 | 0 | 0 | 0.018801 | -9461 | -637 | -3648.0 | -2120 | NaN | 1 | 1 | 0 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 0 | 10 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.083037 | 0.262949 | 0.139376 | 0.0247 | 0.0369 | 0.9722 | 0.6192 | 0.0143 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0369 | 0.0202 | 0.0190 | 0.0000 | 0.0000 | 0.0252 | 0.0383 | 0.9722 | 0.6341 | 0.0144 | 0.0000 | 0.0690 | 0.0833 | 0.1250 | 0.0377 | 0.022 | 0.0198 | 0.0 | 0.0 | 0.0250 | 0.0369 | 0.9722 | 0.6243 | 0.0144 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0375 | 0.0205 | 0.0193 | 0.0000 | 0.00 | 0 | 0 | 0.0149 | 0 | 0 | 2.0 | 2.0 | 2.0 | 2.0 | -1134.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 |
| 1 | 100003 | 0.0 | 0 | 1 | 0 | 1 | 0 | 270000.0 | 1293502.5 | 35698.5 | 1129500.0 | 1 | 1 | 1 | 1 | 0 | 0.003541 | -16765 | -1188 | -1186.0 | -291 | NaN | 1 | 1 | 0 | 1 | 1 | 0 | 1 | 2.0 | 1 | 1 | 1 | 11 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.311267 | 0.622246 | NaN | 0.0959 | 0.0529 | 0.9851 | 0.7960 | 0.0605 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0130 | 0.0773 | 0.0549 | 0.0039 | 0.0098 | 0.0924 | 0.0538 | 0.9851 | 0.8040 | 0.0497 | 0.0806 | 0.0345 | 0.2917 | 0.3333 | 0.0128 | 0.079 | 0.0554 | 0.0 | 0.0 | 0.0968 | 0.0529 | 0.9851 | 0.7987 | 0.0608 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0132 | 0.0787 | 0.0558 | 0.0039 | 0.01 | 0 | 0 | 0.0714 | 1 | 0 | 1.0 | 0.0 | 1.0 | 0.0 | -828.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2 | 100004 | 0.0 | 1 | 0 | 1 | 0 | 0 | 67500.0 | 135000.0 | 6750.0 | 135000.0 | 0 | 0 | 0 | 0 | 0 | 0.010032 | -19046 | -225 | -4260.0 | -2531 | 26.0 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 1 | 9 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | NaN | 0.555912 | 0.729567 | 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 | -1 | NaN | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -815.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3 | 100006 | 0.0 | 0 | 1 | 0 | 0 | 0 | 135000.0 | 312682.5 | 29686.5 | 297000.0 | 0 | 0 | 0 | 2 | 0 | 0.008019 | -19005 | -3039 | -9833.0 | -2437 | NaN | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 2.0 | 2 | 2 | 0 | 17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | NaN | 0.650442 | 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 | -1 | NaN | -1 | -1 | 2.0 | 0.0 | 2.0 | 0.0 | -617.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | NaN | NaN | NaN | NaN | NaN | NaN |
| 4 | 100007 | 0.0 | 0 | 0 | 0 | 0 | 0 | 121500.0 | 513000.0 | 21865.5 | 513000.0 | 0 | 0 | 0 | 0 | 0 | 0.028663 | -19932 | -3038 | -4311.0 | -3458 | NaN | 1 | 1 | 0 | 1 | 0 | 0 | 1 | 1.0 | 2 | 2 | 2 | 11 | 0 | 0 | 0 | 0 | 1 | 1 | 3 | NaN | 0.322738 | 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 | -1 | NaN | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -1106.0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
Null값 일괄 변환¶
In [140]:
apps.isnull().sum().head(100)
#은행가면 형관펜 표시된것만 적는것과 같다,
#중요하지 않은것은 널값이 많다.
Out[140]:
SK_ID_CURR 0
TARGET 48744
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 36
AMT_GOODS_PRICE 278
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 235241
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 0
CNT_FAM_MEMBERS 2
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_1 193910
EXT_SOURCE_2 668
EXT_SOURCE_3 69633
APARTMENTS_AVG 179948
BASEMENTAREA_AVG 207584
YEARS_BEGINEXPLUATATION_AVG 172863
YEARS_BUILD_AVG 236306
COMMONAREA_AVG 248360
ELEVATORS_AVG 189080
ENTRANCES_AVG 178407
FLOORSMAX_AVG 176341
FLOORSMIN_AVG 241108
LANDAREA_AVG 210844
LIVINGAPARTMENTS_AVG 242979
LIVINGAREA_AVG 177902
NONLIVINGAPARTMENTS_AVG 246861
NONLIVINGAREA_AVG 195766
APARTMENTS_MODE 179948
BASEMENTAREA_MODE 207584
YEARS_BEGINEXPLUATATION_MODE 172863
YEARS_BUILD_MODE 236306
COMMONAREA_MODE 248360
ELEVATORS_MODE 189080
ENTRANCES_MODE 178407
FLOORSMAX_MODE 176341
FLOORSMIN_MODE 241108
LANDAREA_MODE 210844
LIVINGAPARTMENTS_MODE 242979
LIVINGAREA_MODE 177902
NONLIVINGAPARTMENTS_MODE 246861
NONLIVINGAREA_MODE 195766
APARTMENTS_MEDI 179948
BASEMENTAREA_MEDI 207584
YEARS_BEGINEXPLUATATION_MEDI 172863
YEARS_BUILD_MEDI 236306
COMMONAREA_MEDI 248360
ELEVATORS_MEDI 189080
ENTRANCES_MEDI 178407
FLOORSMAX_MEDI 176341
FLOORSMIN_MEDI 241108
LANDAREA_MEDI 210844
LIVINGAPARTMENTS_MEDI 242979
LIVINGAREA_MEDI 177902
NONLIVINGAPARTMENTS_MEDI 246861
NONLIVINGAREA_MEDI 195766
FONDKAPREMONT_MODE 0
HOUSETYPE_MODE 0
TOTALAREA_MODE 171055
WALLSMATERIAL_MODE 0
EMERGENCYSTATE_MODE 0
OBS_30_CNT_SOCIAL_CIRCLE 1050
DEF_30_CNT_SOCIAL_CIRCLE 1050
OBS_60_CNT_SOCIAL_CIRCLE 1050
DEF_60_CNT_SOCIAL_CIRCLE 1050
DAYS_LAST_PHONE_CHANGE 1
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
dtype: int64In [141]:
# -999로 모든 컬럼들의 Null값 변환
#모든 컬럼의 널값을 -999로 바꾼다.
apps = apps.fillna(-999)
In [142]:
apps.isnull().sum().head(100)
Out[142]:
SK_ID_CURR 0
TARGET 0
NAME_CONTRACT_TYPE 0
CODE_GENDER 0
FLAG_OWN_CAR 0
FLAG_OWN_REALTY 0
CNT_CHILDREN 0
AMT_INCOME_TOTAL 0
AMT_CREDIT 0
AMT_ANNUITY 0
AMT_GOODS_PRICE 0
NAME_TYPE_SUITE 0
NAME_INCOME_TYPE 0
NAME_EDUCATION_TYPE 0
NAME_FAMILY_STATUS 0
NAME_HOUSING_TYPE 0
REGION_POPULATION_RELATIVE 0
DAYS_BIRTH 0
DAYS_EMPLOYED 0
DAYS_REGISTRATION 0
DAYS_ID_PUBLISH 0
OWN_CAR_AGE 0
FLAG_MOBIL 0
FLAG_EMP_PHONE 0
FLAG_WORK_PHONE 0
FLAG_CONT_MOBILE 0
FLAG_PHONE 0
FLAG_EMAIL 0
OCCUPATION_TYPE 0
CNT_FAM_MEMBERS 0
REGION_RATING_CLIENT 0
REGION_RATING_CLIENT_W_CITY 0
WEEKDAY_APPR_PROCESS_START 0
HOUR_APPR_PROCESS_START 0
REG_REGION_NOT_LIVE_REGION 0
REG_REGION_NOT_WORK_REGION 0
LIVE_REGION_NOT_WORK_REGION 0
REG_CITY_NOT_LIVE_CITY 0
REG_CITY_NOT_WORK_CITY 0
LIVE_CITY_NOT_WORK_CITY 0
ORGANIZATION_TYPE 0
EXT_SOURCE_1 0
EXT_SOURCE_2 0
EXT_SOURCE_3 0
APARTMENTS_AVG 0
BASEMENTAREA_AVG 0
YEARS_BEGINEXPLUATATION_AVG 0
YEARS_BUILD_AVG 0
COMMONAREA_AVG 0
ELEVATORS_AVG 0
ENTRANCES_AVG 0
FLOORSMAX_AVG 0
FLOORSMIN_AVG 0
LANDAREA_AVG 0
LIVINGAPARTMENTS_AVG 0
LIVINGAREA_AVG 0
NONLIVINGAPARTMENTS_AVG 0
NONLIVINGAREA_AVG 0
APARTMENTS_MODE 0
BASEMENTAREA_MODE 0
YEARS_BEGINEXPLUATATION_MODE 0
YEARS_BUILD_MODE 0
COMMONAREA_MODE 0
ELEVATORS_MODE 0
ENTRANCES_MODE 0
FLOORSMAX_MODE 0
FLOORSMIN_MODE 0
LANDAREA_MODE 0
LIVINGAPARTMENTS_MODE 0
LIVINGAREA_MODE 0
NONLIVINGAPARTMENTS_MODE 0
NONLIVINGAREA_MODE 0
APARTMENTS_MEDI 0
BASEMENTAREA_MEDI 0
YEARS_BEGINEXPLUATATION_MEDI 0
YEARS_BUILD_MEDI 0
COMMONAREA_MEDI 0
ELEVATORS_MEDI 0
ENTRANCES_MEDI 0
FLOORSMAX_MEDI 0
FLOORSMIN_MEDI 0
LANDAREA_MEDI 0
LIVINGAPARTMENTS_MEDI 0
LIVINGAREA_MEDI 0
NONLIVINGAPARTMENTS_MEDI 0
NONLIVINGAREA_MEDI 0
FONDKAPREMONT_MODE 0
HOUSETYPE_MODE 0
TOTALAREA_MODE 0
WALLSMATERIAL_MODE 0
EMERGENCYSTATE_MODE 0
OBS_30_CNT_SOCIAL_CIRCLE 0
DEF_30_CNT_SOCIAL_CIRCLE 0
OBS_60_CNT_SOCIAL_CIRCLE 0
DEF_60_CNT_SOCIAL_CIRCLE 0
DAYS_LAST_PHONE_CHANGE 0
FLAG_DOCUMENT_2 0
FLAG_DOCUMENT_3 0
FLAG_DOCUMENT_4 0
FLAG_DOCUMENT_5 0
dtype: int64학습 데이터와 테스트 데이터 다시 분리¶
In [143]:
# 왜 target컬럼의 널을 제거 하지 않았냐
# >>> target값이 널인 행을 가지고 돈을 값을 것인지 안값을 것인지를 예측하기 위해서다.
# app_test의 TARGET 컬럼은 원래 null이었는데 앞에서 fillna(-999)로 -999로 변환됨. 이를 추출함.
# TARGETdl -999값이 아닌 행만 모두 app_test로 넣기
app_train = apps[apps['TARGET'] != -999]
#TARGET이 -999값이 있는 행만 모두 app_test로 넣기
app_test = apps[apps['TARGET']== -999]
app_train.shape, app_test.shape
# app_train, app_test에 원래 있던 데이터는 없어진것 같다
# shape시 새로 넣은 데이터만 있다
Out[143]:
((307511, 122), (48744, 122))In [144]:
# app_test의 TARGET컬럼을 Drop
app_test = app_test.drop('TARGET', axis=1)
# test셋이라 타켓값컬럼을 삭제
In [145]:
app_test.shape
Out[145]:
(48744, 121)In [146]:
app_test.dtypes
Out[146]:
SK_ID_CURR int64
NAME_CONTRACT_TYPE int64
CODE_GENDER int64
FLAG_OWN_CAR int64
FLAG_OWN_REALTY int64
...
AMT_REQ_CREDIT_BUREAU_DAY float64
AMT_REQ_CREDIT_BUREAU_WEEK float64
AMT_REQ_CREDIT_BUREAU_MON float64
AMT_REQ_CREDIT_BUREAU_QRT float64
AMT_REQ_CREDIT_BUREAU_YEAR float64
Length: 121, dtype: object학습 데이터를 검증 데이터로 분리하고 LGBM Classifier로 학습 수행.¶
- 피처용 데이터와 타겟 데이터 분리
- 학습용/검증용 데이터 세트 분리
In [147]:
app_train.head()
Out[147]:
| SK_ID_CURR | TARGET | 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 | FLAG_PHONE | FLAG_EMAIL | OCCUPATION_TYPE | CNT_FAM_MEMBERS | REGION_RATING_CLIENT | REGION_RATING_CLIENT_W_CITY | WEEKDAY_APPR_PROCESS_START | HOUR_APPR_PROCESS_START | REG_REGION_NOT_LIVE_REGION | 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 | YEARS_BEGINEXPLUATATION_MODE | YEARS_BUILD_MODE | COMMONAREA_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 | DEF_30_CNT_SOCIAL_CIRCLE | OBS_60_CNT_SOCIAL_CIRCLE | DEF_60_CNT_SOCIAL_CIRCLE | DAYS_LAST_PHONE_CHANGE | FLAG_DOCUMENT_2 | FLAG_DOCUMENT_3 | FLAG_DOCUMENT_4 | FLAG_DOCUMENT_5 | FLAG_DOCUMENT_6 | FLAG_DOCUMENT_7 | FLAG_DOCUMENT_8 | FLAG_DOCUMENT_9 | FLAG_DOCUMENT_10 | FLAG_DOCUMENT_11 | FLAG_DOCUMENT_12 | FLAG_DOCUMENT_13 | FLAG_DOCUMENT_14 | FLAG_DOCUMENT_15 | FLAG_DOCUMENT_16 | FLAG_DOCUMENT_17 | FLAG_DOCUMENT_18 | FLAG_DOCUMENT_19 | FLAG_DOCUMENT_20 | FLAG_DOCUMENT_21 | AMT_REQ_CREDIT_BUREAU_HOUR | AMT_REQ_CREDIT_BUREAU_DAY | AMT_REQ_CREDIT_BUREAU_WEEK | AMT_REQ_CREDIT_BUREAU_MON | AMT_REQ_CREDIT_BUREAU_QRT | AMT_REQ_CREDIT_BUREAU_YEAR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100002 | 1.0 | 0 | 0 | 0 | 0 | 0 | 202500.0 | 406597.5 | 24700.5 | 351000.0 | 0 | 0 | 0 | 0 | 0 | 0.018801 | -9461 | -637 | -3648.0 | -2120 | -999.0 | 1 | 1 | 0 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 0 | 10 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.083037 | 0.262949 | 0.139376 | 0.0247 | 0.0369 | 0.9722 | 0.6192 | 0.0143 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0369 | 0.0202 | 0.0190 | 0.0000 | 0.0000 | 0.0252 | 0.0383 | 0.9722 | 0.6341 | 0.0144 | 0.0000 | 0.0690 | 0.0833 | 0.1250 | 0.0377 | 0.022 | 0.0198 | 0.0 | 0.0 | 0.0250 | 0.0369 | 0.9722 | 0.6243 | 0.0144 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0375 | 0.0205 | 0.0193 | 0.0000 | 0.00 | 0 | 0 | 0.0149 | 0 | 0 | 2.0 | 2.0 | 2.0 | 2.0 | -1134.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 |
| 1 | 100003 | 0.0 | 0 | 1 | 0 | 1 | 0 | 270000.0 | 1293502.5 | 35698.5 | 1129500.0 | 1 | 1 | 1 | 1 | 0 | 0.003541 | -16765 | -1188 | -1186.0 | -291 | -999.0 | 1 | 1 | 0 | 1 | 1 | 0 | 1 | 2.0 | 1 | 1 | 1 | 11 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.311267 | 0.622246 | -999.000000 | 0.0959 | 0.0529 | 0.9851 | 0.7960 | 0.0605 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0130 | 0.0773 | 0.0549 | 0.0039 | 0.0098 | 0.0924 | 0.0538 | 0.9851 | 0.8040 | 0.0497 | 0.0806 | 0.0345 | 0.2917 | 0.3333 | 0.0128 | 0.079 | 0.0554 | 0.0 | 0.0 | 0.0968 | 0.0529 | 0.9851 | 0.7987 | 0.0608 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0132 | 0.0787 | 0.0558 | 0.0039 | 0.01 | 0 | 0 | 0.0714 | 1 | 0 | 1.0 | 0.0 | 1.0 | 0.0 | -828.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2 | 100004 | 0.0 | 1 | 0 | 1 | 0 | 0 | 67500.0 | 135000.0 | 6750.0 | 135000.0 | 0 | 0 | 0 | 0 | 0 | 0.010032 | -19046 | -225 | -4260.0 | -2531 | 26.0 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 1 | 9 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | -999.000000 | 0.555912 | 0.729567 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -815.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3 | 100006 | 0.0 | 0 | 1 | 0 | 0 | 0 | 135000.0 | 312682.5 | 29686.5 | 297000.0 | 0 | 0 | 0 | 2 | 0 | 0.008019 | -19005 | -3039 | -9833.0 | -2437 | -999.0 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 2.0 | 2 | 2 | 0 | 17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -999.000000 | 0.650442 | -999.000000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 2.0 | 0.0 | 2.0 | 0.0 | -617.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 |
| 4 | 100007 | 0.0 | 0 | 0 | 0 | 0 | 0 | 121500.0 | 513000.0 | 21865.5 | 513000.0 | 0 | 0 | 0 | 0 | 0 | 0.028663 | -19932 | -3038 | -4311.0 | -3458 | -999.0 | 1 | 1 | 0 | 1 | 0 | 0 | 1 | 1.0 | 2 | 2 | 2 | 11 | 0 | 0 | 0 | 0 | 1 | 1 | 3 | -999.000000 | 0.322738 | -999.000000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -1106.0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
In [148]:
# SK_ID_CURR' == 대출 id , 'TARGET == 0,1 사기구분
# 학습시키기 위해서 트레인에는 타켓값과 타켓값과 유사한 SK_ID_CURR도 같이 제외
ftr_app = app_train.drop(['SK_ID_CURR', 'TARGET'], axis=1) #prime key값도 제외 시키자
target_app = app_train['TARGET'] # 사기인지 알수 있는 기준인 타켓값만 넣기
In [149]:
from sklearn.model_selection import train_test_split
train_x, valid_x, train_y, valid_y = train_test_split(ftr_app, target_app, test_size=0.3, random_state=2020)
train_x.shape, valid_x.shape
Out[149]:
((215257, 120), (92254, 120))In [ ]:
In [150]:
from lightgbm import LGBMClassifier
clf = LGBMClassifier(
n_jobs=-1,
n_estimators=1000,
learning_rate=0.02,
num_leaves=32,
subsample=0.8,
max_depth=12,
silent=-1,
verbose=-1
)
clf.fit(train_x, train_y, eval_set=[(train_x, train_y), (valid_x, valid_y)],
eval_metric= 'auc', verbose= 100, early_stopping_rounds= 50)
# early_stopping_rounds 최고 성능이 나오고 50번 더 돌렸는데 더 좋은 성능이 안나오면 기존 최고 성능이 최고 성능이 된다
C:\Users\82105\anaconda3\lib\site-packages\lightgbm\sklearn.py:598: UserWarning: 'silent' argument is deprecated and will be removed in a future release of LightGBM. Pass 'verbose' parameter via keyword arguments instead.
_log_warning("'silent' argument is deprecated and will be removed in a future release of LightGBM. "
C:\Users\82105\anaconda3\lib\site-packages\lightgbm\sklearn.py:726: UserWarning: 'early_stopping_rounds' argument is deprecated and will be removed in a future release of LightGBM. Pass 'early_stopping()' callback via 'callbacks' argument instead.
_log_warning("'early_stopping_rounds' argument is deprecated and will be removed in a future release of LightGBM. "
C:\Users\82105\anaconda3\lib\site-packages\lightgbm\sklearn.py:736: UserWarning: 'verbose' argument is deprecated and will be removed in a future release of LightGBM. Pass 'log_evaluation()' callback via 'callbacks' argument instead.
_log_warning("'verbose' argument is deprecated and will be removed in a future release of LightGBM. "
[100] training's auc: 0.752205 training's binary_logloss: 0.250372 valid_1's auc: 0.744317 valid_1's binary_logloss: 0.251593
[200] training's auc: 0.771473 training's binary_logloss: 0.243554 valid_1's auc: 0.754053 valid_1's binary_logloss: 0.247539
[300] training's auc: 0.784885 training's binary_logloss: 0.239292 valid_1's auc: 0.757737 valid_1's binary_logloss: 0.246203
[400] training's auc: 0.796336 training's binary_logloss: 0.235948 valid_1's auc: 0.758946 valid_1's binary_logloss: 0.245732
[500] training's auc: 0.806016 training's binary_logloss: 0.233017 valid_1's auc: 0.759411 valid_1's binary_logloss: 0.24555
Out[150]:
LGBMClassifier(learning_rate=0.02, max_depth=12, n_estimators=1000,
num_leaves=32, silent=-1, subsample=0.8, verbose=-1)On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LGBMClassifier(learning_rate=0.02, max_depth=12, n_estimators=1000,
num_leaves=32, silent=-1, subsample=0.8, verbose=-1)Feature importance 시각화¶
In [151]:
from lightgbm import plot_importance
plot_importance(clf, figsize=(16, 32))
#EXT_SOURCE_3 Normalized score from external data source,normalized
# DAYS_BIRTH == 신청날 고객 나이
# EXT_SOURCE_3 == 정규화 점수
Out[151]:
<AxesSubplot:title={'center':'Feature importance'}, xlabel='Feature importance', ylabel='Features'>
학습된 Classifier를 이용하여 테스트 데이터을 예측하고 결과를 Kaggle로 Submit 수행.¶
In [152]:
#학습된 classifier의 predict_proba()를 이용하여 binary classification에서 1이될 확률만 추출
preds = clf.predict_proba(app_test.drop(['SK_ID_CURR'], axis=1))[:, 1 ]
In [153]:
clf.predict_proba(app_test.drop(['SK_ID_CURR'],axis=1)) #0과 1이 될 확룔이 두개다 표시가 된다.
Out[153]:
array([[0.97246502, 0.02753498],
[0.87904013, 0.12095987],
[0.98381082, 0.01618918],
...,
[0.96802646, 0.03197354],
[0.94283805, 0.05716195],
[0.82020099, 0.17979901]])In [154]:
app_test['TARGET'] = preds
app_test['TARGET'].head(10)
Out[154]:
0 0.027535
1 0.120960
2 0.016189
3 0.037421
4 0.146077
5 0.036411
6 0.017445
7 0.041752
8 0.016933
9 0.087198
Name: TARGET, dtype: float64In [155]:
# SK_ID_CURR과 TARGET 값만 csv 형태로 생성.
app_test[['SK_ID_CURR', 'TARGET']].to_csv('app_baseline_01.csv', index=False)
In [156]:
app_test.head()
Out[156]:
| 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 | FLAG_PHONE | FLAG_EMAIL | OCCUPATION_TYPE | CNT_FAM_MEMBERS | REGION_RATING_CLIENT | REGION_RATING_CLIENT_W_CITY | WEEKDAY_APPR_PROCESS_START | HOUR_APPR_PROCESS_START | REG_REGION_NOT_LIVE_REGION | 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 | YEARS_BEGINEXPLUATATION_MODE | YEARS_BUILD_MODE | COMMONAREA_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 | DEF_30_CNT_SOCIAL_CIRCLE | OBS_60_CNT_SOCIAL_CIRCLE | DEF_60_CNT_SOCIAL_CIRCLE | DAYS_LAST_PHONE_CHANGE | FLAG_DOCUMENT_2 | FLAG_DOCUMENT_3 | FLAG_DOCUMENT_4 | FLAG_DOCUMENT_5 | FLAG_DOCUMENT_6 | FLAG_DOCUMENT_7 | FLAG_DOCUMENT_8 | FLAG_DOCUMENT_9 | FLAG_DOCUMENT_10 | FLAG_DOCUMENT_11 | FLAG_DOCUMENT_12 | FLAG_DOCUMENT_13 | FLAG_DOCUMENT_14 | FLAG_DOCUMENT_15 | FLAG_DOCUMENT_16 | FLAG_DOCUMENT_17 | FLAG_DOCUMENT_18 | FLAG_DOCUMENT_19 | FLAG_DOCUMENT_20 | FLAG_DOCUMENT_21 | AMT_REQ_CREDIT_BUREAU_HOUR | AMT_REQ_CREDIT_BUREAU_DAY | AMT_REQ_CREDIT_BUREAU_WEEK | AMT_REQ_CREDIT_BUREAU_MON | AMT_REQ_CREDIT_BUREAU_QRT | AMT_REQ_CREDIT_BUREAU_YEAR | TARGET | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100001 | 0 | 1 | 0 | 0 | 0 | 135000.0 | 568800.0 | 20560.5 | 450000.0 | 0 | 0 | 1 | 1 | 0 | 0.018850 | -19241 | -2329 | -5170.0 | -812 | -999.0 | 1 | 1 | 0 | 1 | 0 | 1 | -1 | 2.0 | 2 | 2 | 6 | 18 | 0 | 0 | 0 | 0 | 0 | 0 | 13 | 0.752614 | 0.789654 | 0.159520 | 0.0660 | 0.0590 | 0.9732 | -999.0000 | -999.0000 | -999.00 | 0.1379 | 0.125 | -999.0000 | -999.0000 | -999.0000 | 0.0505 | -999.0000 | -999.00 | 0.0672 | 0.0612 | 0.9732 | -999.0000 | -999.0000 | -999.0000 | 0.1379 | 0.125 | -999.0000 | -999.0000 | -999.0000 | 0.0526 | -999.0000 | -999.0000 | 0.0666 | 0.0590 | 0.9732 | -999.0000 | -999.0000 | -999.00 | 0.1379 | 0.125 | -999.0000 | -999.0000 | -999.0000 | 0.0514 | -999.0000 | -999.0000 | -1 | 0 | 0.0392 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | -1740.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.027535 |
| 1 | 100005 | 0 | 0 | 0 | 0 | 0 | 99000.0 | 222768.0 | 17370.0 | 180000.0 | 0 | 0 | 0 | 1 | 0 | 0.035792 | -18064 | -4469 | -9118.0 | -1623 | -999.0 | 1 | 1 | 0 | 1 | 0 | 0 | 13 | 2.0 | 2 | 2 | 5 | 9 | 0 | 0 | 0 | 0 | 0 | 0 | 9 | 0.564990 | 0.291656 | 0.432962 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3.0 | 0.120960 |
| 2 | 100013 | 0 | 0 | 1 | 0 | 0 | 202500.0 | 663264.0 | 69777.0 | 630000.0 | -1 | 0 | 1 | 1 | 0 | 0.019101 | -20038 | -4458 | -2175.0 | -3503 | 5.0 | 1 | 1 | 0 | 1 | 0 | 0 | 4 | 2.0 | 2 | 2 | 1 | 14 | 0 | 0 | 0 | 0 | 0 | 0 | 25 | -999.000000 | 0.699787 | 0.610991 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -856.0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 4.0 | 0.016189 |
| 3 | 100028 | 0 | 1 | 0 | 0 | 2 | 315000.0 | 1575000.0 | 49018.5 | 1575000.0 | 0 | 0 | 0 | 1 | 0 | 0.026392 | -13976 | -1866 | -2000.0 | -4208 | -999.0 | 1 | 1 | 0 | 1 | 1 | 0 | 5 | 4.0 | 2 | 2 | 0 | 11 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.525734 | 0.509677 | 0.612704 | 0.3052 | 0.1974 | 0.9970 | 0.9592 | 0.1165 | 0.32 | 0.2759 | 0.375 | 0.0417 | 0.2042 | 0.2404 | 0.3673 | 0.0386 | 0.08 | 0.3109 | 0.2049 | 0.9970 | 0.9608 | 0.1176 | 0.3222 | 0.2759 | 0.375 | 0.0417 | 0.2089 | 0.2626 | 0.3827 | 0.0389 | 0.0847 | 0.3081 | 0.1974 | 0.9970 | 0.9597 | 0.1173 | 0.32 | 0.2759 | 0.375 | 0.0417 | 0.2078 | 0.2446 | 0.3739 | 0.0388 | 0.0817 | 0 | 0 | 0.3700 | 2 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | -1805.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 3.0 | 0.037421 |
| 4 | 100038 | 0 | 0 | 1 | 1 | 1 | 180000.0 | 625500.0 | 32067.0 | 625500.0 | 0 | 0 | 0 | 1 | 0 | 0.010032 | -13040 | -2191 | -4000.0 | -4262 | 16.0 | 1 | 1 | 1 | 1 | 0 | 0 | -1 | 3.0 | 2 | 2 | 5 | 5 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0.202145 | 0.425687 | -999.000000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -821.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 | 0.146077 |
In [157]:
app_train.head()
Out[157]:
| SK_ID_CURR | TARGET | 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 | FLAG_PHONE | FLAG_EMAIL | OCCUPATION_TYPE | CNT_FAM_MEMBERS | REGION_RATING_CLIENT | REGION_RATING_CLIENT_W_CITY | WEEKDAY_APPR_PROCESS_START | HOUR_APPR_PROCESS_START | REG_REGION_NOT_LIVE_REGION | 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 | YEARS_BEGINEXPLUATATION_MODE | YEARS_BUILD_MODE | COMMONAREA_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 | DEF_30_CNT_SOCIAL_CIRCLE | OBS_60_CNT_SOCIAL_CIRCLE | DEF_60_CNT_SOCIAL_CIRCLE | DAYS_LAST_PHONE_CHANGE | FLAG_DOCUMENT_2 | FLAG_DOCUMENT_3 | FLAG_DOCUMENT_4 | FLAG_DOCUMENT_5 | FLAG_DOCUMENT_6 | FLAG_DOCUMENT_7 | FLAG_DOCUMENT_8 | FLAG_DOCUMENT_9 | FLAG_DOCUMENT_10 | FLAG_DOCUMENT_11 | FLAG_DOCUMENT_12 | FLAG_DOCUMENT_13 | FLAG_DOCUMENT_14 | FLAG_DOCUMENT_15 | FLAG_DOCUMENT_16 | FLAG_DOCUMENT_17 | FLAG_DOCUMENT_18 | FLAG_DOCUMENT_19 | FLAG_DOCUMENT_20 | FLAG_DOCUMENT_21 | AMT_REQ_CREDIT_BUREAU_HOUR | AMT_REQ_CREDIT_BUREAU_DAY | AMT_REQ_CREDIT_BUREAU_WEEK | AMT_REQ_CREDIT_BUREAU_MON | AMT_REQ_CREDIT_BUREAU_QRT | AMT_REQ_CREDIT_BUREAU_YEAR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100002 | 1.0 | 0 | 0 | 0 | 0 | 0 | 202500.0 | 406597.5 | 24700.5 | 351000.0 | 0 | 0 | 0 | 0 | 0 | 0.018801 | -9461 | -637 | -3648.0 | -2120 | -999.0 | 1 | 1 | 0 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 0 | 10 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.083037 | 0.262949 | 0.139376 | 0.0247 | 0.0369 | 0.9722 | 0.6192 | 0.0143 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0369 | 0.0202 | 0.0190 | 0.0000 | 0.0000 | 0.0252 | 0.0383 | 0.9722 | 0.6341 | 0.0144 | 0.0000 | 0.0690 | 0.0833 | 0.1250 | 0.0377 | 0.022 | 0.0198 | 0.0 | 0.0 | 0.0250 | 0.0369 | 0.9722 | 0.6243 | 0.0144 | 0.00 | 0.0690 | 0.0833 | 0.1250 | 0.0375 | 0.0205 | 0.0193 | 0.0000 | 0.00 | 0 | 0 | 0.0149 | 0 | 0 | 2.0 | 2.0 | 2.0 | 2.0 | -1134.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 |
| 1 | 100003 | 0.0 | 0 | 1 | 0 | 1 | 0 | 270000.0 | 1293502.5 | 35698.5 | 1129500.0 | 1 | 1 | 1 | 1 | 0 | 0.003541 | -16765 | -1188 | -1186.0 | -291 | -999.0 | 1 | 1 | 0 | 1 | 1 | 0 | 1 | 2.0 | 1 | 1 | 1 | 11 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.311267 | 0.622246 | -999.000000 | 0.0959 | 0.0529 | 0.9851 | 0.7960 | 0.0605 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0130 | 0.0773 | 0.0549 | 0.0039 | 0.0098 | 0.0924 | 0.0538 | 0.9851 | 0.8040 | 0.0497 | 0.0806 | 0.0345 | 0.2917 | 0.3333 | 0.0128 | 0.079 | 0.0554 | 0.0 | 0.0 | 0.0968 | 0.0529 | 0.9851 | 0.7987 | 0.0608 | 0.08 | 0.0345 | 0.2917 | 0.3333 | 0.0132 | 0.0787 | 0.0558 | 0.0039 | 0.01 | 0 | 0 | 0.0714 | 1 | 0 | 1.0 | 0.0 | 1.0 | 0.0 | -828.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2 | 100004 | 0.0 | 1 | 0 | 1 | 0 | 0 | 67500.0 | 135000.0 | 6750.0 | 135000.0 | 0 | 0 | 0 | 0 | 0 | 0.010032 | -19046 | -225 | -4260.0 | -2531 | 26.0 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 1.0 | 2 | 2 | 1 | 9 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | -999.000000 | 0.555912 | 0.729567 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -815.0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3 | 100006 | 0.0 | 0 | 1 | 0 | 0 | 0 | 135000.0 | 312682.5 | 29686.5 | 297000.0 | 0 | 0 | 0 | 2 | 0 | 0.008019 | -19005 | -3039 | -9833.0 | -2437 | -999.0 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 2.0 | 2 | 2 | 0 | 17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -999.000000 | 0.650442 | -999.000000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 2.0 | 0.0 | 2.0 | 0.0 | -617.0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 | -999.0 |
| 4 | 100007 | 0.0 | 0 | 0 | 0 | 0 | 0 | 121500.0 | 513000.0 | 21865.5 | 513000.0 | 0 | 0 | 0 | 0 | 0 | 0.028663 | -19932 | -3038 | -4311.0 | -3458 | -999.0 | 1 | 1 | 0 | 1 | 0 | 0 | 1 | 1.0 | 2 | 2 | 2 | 11 | 0 | 0 | 0 | 0 | 1 | 1 | 3 | -999.000000 | 0.322738 | -999.000000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.000 | -999.0000 | -999.0 | -999.0 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.0000 | -999.00 | -1 | -1 | -999.0000 | -1 | -1 | 0.0 | 0.0 | 0.0 | 0.0 | -1106.0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
'사기 예측 (언발란스 데이터)' 카테고리의 다른 글
| 10_prev_baseline_01_exercise_pandas_대출상환 예측_피처 엔지니어링_2단계(판다스 고급기술 활용) (0) | 2022.11.03 |
|---|---|
| 09_4_app_baseline_02_exercise_피처 엔지니어_1단계 (0) | 2022.11.03 |
