クレジットカードユーザーが予測AI競争を滞納

1.テーマ

2.背景

3.大会説明

4.データ変数の説明

5.EDA、データプリプロセッシング

必要なlibrary import

import os, random
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.ensemble import VotingClassifier, RandomForestClassifier, BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from lightgbm import LGBMClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import log_loss
from tensorflow.keras.utils import to_categorical

データの読み込み

train = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/Prediction_of_default_rate/train.csv')
test = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/Prediction_of_default_rate/test.csv')
submission = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/Prediction_of_default_rate/sample_submission.csv')

データプリプロセッシング

train.info()

# 결측치 처리
train['occyp_type'] = train['occyp_type'].fillna('Null')
test['occyp_type'] = test['occyp_type'].fillna('Null')

# binary type (여성 - 0, 남성 - 1)
train['gender'] = train['gender'].replace({'F':0, 'M':1})
test['gender'] = test['gender'].replace({'F':0, 'M':1}) 


# 무의미한 변수 제거
train.drop('FLAG_MOBIL', axis=1, inplace=True) 
del train['index']

test.drop('FLAG_MOBIL', axis=1, inplace=True)
del test['index']

# one-hot encoding
train = pd.get_dummies(train)
test = pd.get_dummies(test)

# 수치형 데이터 전처리(0~1)
train_x['DAYS_BIRTH'] = train_x['DAYS_BIRTH'] / train_x['DAYS_BIRTH'].min()
test_x['DAYS_BIRTH'] = test_x['DAYS_BIRTH'] / test_x['DAYS_BIRTH'].min()
train_x['working_day'] = train_x['working_day'] / train_x['working_day'].min()
test_x['working_day'] = test_x['working_day'] / test_x['working_day'].min()
train_x['begin_month'] = train_x['begin_month'] / train_x['begin_month'].min()
test_x['begin_month'] = test_x['begin_month'] / test_x['begin_month'].min()

train_x['Annual_income'] = train_x['Annual_income'] / train_x['Annual_income'].max()
test_x['Annual_income'] = test_x['Annual_income'] / test_x['Annual_income'].max()

列車データと試験データを分離する

train_x = train.drop('credit', axis=1)
train_y = train[['credit']]
test_x = test
print(train_x.shape, train_y.shape, test_x.shape)

X_train, X_val, y_train, y_val = train_test_split(train_x, train_y, 
                                                    stratify=train_y,
                                                  test_size=0.2,
                                                    random_state = SEED)

6. Training

Randomforest Classifier

model_RF = RandomForestClassifier(n_estimators=500, max_features=16, random_state=SEED)
model_RF.fit(X_train, y_train)
y_pred = model_RF.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), y_pred)}")

Decision Tree Classifier

model_TREE = tree.DecisionTreeClassifier(criterion='entropy', max_depth=2, random_state=SEED)
model_TREE.fit(X_train, y_train)
y_pred = model_TREE.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), y_pred)}")

LGBNM Classifier

model_LGBM = LGBMClassifier(n_estimators=10000, num_leaves=50, subsample=0.8,learning_rate=0.01,
                      min_child_samples=60, max_depth=20)
evals = [(X_val, y_val)]
model_LGBM.fit(X_train, y_train, early_stopping_rounds=100,
                 eval_set=evals, eval_metric='logloss',verbose=False)
pred_y = model_LGBM.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), pred_y)}")

BaggingClassifier

model_BAG1 = BaggingClassifier(
    DecisionTreeClassifier(),
    n_estimators=600,
    max_samples=0.7,
    max_features=0.6, 
    bootstrap=True,
    n_jobs=-1 
)
model_BAG1.fit(X_train, y_train)
y_pred = model_BAG1.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), y_pred)}")

model_BAG2 = BaggingClassifier(
    DecisionTreeClassifier(),
    n_estimators=550,
    max_samples=0.7,
    max_features=0.6, 
    bootstrap=True,
    n_jobs=-1 
)
model_BAG2.fit(X_train, y_train)
y_pred = model_BAG2.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), y_pred)}")

VotingClassifier

model_VOTING = VotingClassifier(estimators=[('LGBM', model_LGBM),
                                      ('BAGClassifier1', model_BAG1),
                                      ('BAGlassifier2', model_BAG2),
                                      ('RF', model_RF),
                                      ('TREE', model_TREE)],
                         voting='soft')
model_VOTING.fit(X_train, y_train)
pred_y = model_VOTING.predict_proba(X_val)
print(f"log_loss: {log_loss(to_categorical(y_val['credit']), pred_y)}")

7. Test

pred = model_VOTING.predict_proba(test)
submission.loc[:,1:] = pred
submission.to_csv('/content/drive/MyDrive/Colab Notebooks/Prediction_of_default_rate/7120501821010008.csv',index=False)

8.感想