7.変数値の変更

7.1女性値の指定

train['women'] = np.zeros(len(train))
train['women'][train['gender']=='F'] = 1

7.2不動産と自動車の価格設定

# 자동차
train['yesCar'] = np.zeros(len(train))
train['yesCar'][train['car']=='Y'] = 1
# 부동산
train['yesReality'] = np.zeros(len(train))
train['yesReality'][train['reality']=='Y'] = 1

7.2.1変数の削除

train.drop(columns=['gender', 'car', 'reality'], inplace=True)

7.3 4人または4人以上の子供に対する処理

train['child_num'][train['child_num'] > 3] = 4

7.4年齢グループの数値化

train['age_group'][train['age']<30] = 0

train['age_group'][(train['age']>=30) & (train['age']<40)] = 1

train['age_group'][(train['age']>=40) & (train['age']<50)] = 2

train['age_group'][(train['age']>=50) & (train['age']<60)] = 3

train['age_group'][train['age']>=60] = 4

train.describe(include='all')

8.テストセットデータの変換

8.1テストセットの読み込み

myfile2 = files.upload()

test = pd.read_csv('test.csv')

# 불필요한 변수 Drop
test.drop(columns=['index','FLAG_MOBIL','phone','email','work_phone', 'edu_type'], inplace=True)

8.2収益による変数の指定

# 4, 5 10 분위 지정시 test의 값이 아닌 training에 의한 4, 5, 10분위 지정을 해준다.
# variable 'income_quintile' 생성
test['income_quartile'] = np.zeros(10000)
# variable 'income_quintile' 생성
test['income_quintile'] = np.zeros(10000)
# variable 'income_decile' 생성
test['income_decile'] = np.zeros(10000)

# income_quartile에 값 할당하기
test['income_quartile'][test['income_total'] < train['income_total'].quantile(0.25)] = 1

test['income_quartile'][(test['income_total'] >= train['income_total'].quantile(0.25)) &
                       (test['income_total'] < train['income_total'].quantile(0.5))] = 2

test['income_quartile'][(test['income_total'] >= train['income_total'].quantile(0.5)) &
                       (test['income_total'] < train['income_total'].quantile(0.75))] = 3

test['income_quartile'][test['income_total'] >= train['income_total'].quantile(0.75)] = 4

# income_quintile에 값 할당하기
test['income_quintile'][test['income_total'] < train['income_total'].quantile(0.2)] = 1

test['income_quintile'][(test['income_total'] >= train['income_total'].quantile(0.2)) &
                       (test['income_total'] < train['income_total'].quantile(0.4))] = 2

test['income_quintile'][(test['income_total'] >= train['income_total'].quantile(0.4)) &
                       (test['income_total'] < train['income_total'].quantile(0.6))] = 3

test['income_quintile'][(test['income_total'] >= train['income_total'].quantile(0.6)) &
                       (test['income_total'] < train['income_total'].quantile(0.8))] = 4

test['income_quintile'][test['income_total'] >= train['income_total'].quantile(0.8)] = 5

# income_decile에 값 할당하기
test['income_decile'][test['income_total'] < train['income_total'].quantile(0.1)] = 1

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.1)) &
                       (test['income_total'] < train['income_total'].quantile(0.2))] = 2

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.2)) &
                       (test['income_total'] < train['income_total'].quantile(0.3))] = 3

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.3)) &
                       (test['income_total'] < train['income_total'].quantile(0.4))] = 4

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.4)) &
                       (test['income_total'] < train['income_total'].quantile(0.5))] = 5

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.5)) &
                       (test['income_total'] < train['income_total'].quantile(0.6))] = 6

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.6)) &
                       (test['income_total'] < train['income_total'].quantile(0.7))] = 7

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.7)) &
                       (test['income_total'] < train['income_total'].quantile(0.8))] = 8

test['income_decile'][(test['income_total'] >= train['income_total'].quantile(0.8)) &
                       (test['income_total'] < train['income_total'].quantile(0.9))] = 9

test['income_decile'][test['income_total'] >= train['income_total'].quantile(0.9)] = 10

8.3年齢層の設定

# age 변수 생성
# DAYS_BIRTH에 -1곱하고 365로 나누고 몫에다 +1
test['age'] = (test['DAYS_BIRTH'] * (-1))//365+1
# age_group 변수 생성
test['age_group'] = np.zeros(10000)

# 29Under, 30~39, 40~49, 50~64, 65+ 구간으로 나누어 주자
test['age_group'][test['age']<30] = 0

test['age_group'][(test['age']>=30) & (test['age']<40)] = 1

test['age_group'][(test['age']>=40) & (test['age']<50)] = 2

test['age_group'][(test['age']>=50) & (test['age']<60)] = 3

test['age_group'][test['age']>=60] = 4

8.4クレジットカード使用年数

# 신용카드 사용 연수 생성
# -1 곱해주고 12 나누고 내림
test['used_years'] = test['begin_month']*(-1)//12

8.5指定勤務年数

# worked_year 변수지정
test['worked_year'] = test['DAYS_EMPLOYED']*(-1)

# 취업되지 않은 사람들에 대해 -365 지정
test['worked_year'][test['worked_year']<0] = -365

# 근무연수를 구하기 위해 worked_year를 365로 나누고 몫만 지정
# 근무연수가 없는 사람들은 -1에 지정
test['worked_year'] = test['worked_year']//365

# 무직자와 연금수령자 중 무직자에 대해 Unempolyed 지정
test['occyp_type'][(test.worked_year==-1)&(test.income_type=='Pensioner')] = 'Unempolyed'
test['occyp_type'][test.worked_year==-1] = 'Unempolyed'
# 결측치 제거
test.dropna(axis=0, inplace=True)

8.6性別、自動車、不動産価格の変更と停止

# 성별
test['women'] = np.zeros(len(test))
test['women'][test['gender']=='F'] = 1
# 자동차
test['yesCar'] = np.zeros(len(test))
test['yesCar'][test['car']=='Y'] = 1
# 부동산
test['yesReality'] = np.zeros(len(test))
test['yesReality'][test['reality']=='Y'] = 1

# Drop
test.drop(columns=['gender', 'car', 'reality'], inplace=True)

8.7 4人または4人以上の子供を処理する

test['child_num'][test['child_num'] > 3] = 4

9.トレーニングおよびテストセットの保存

train.to_csv("newTrain.csv", sep=',',na_rep='NaN')
test.to_csv("newTest.csv", sep=',',na_rep='NaN')