sim10.py

#
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler, Imputer
from sklearn.linear_model import LogisticRegression

data = pd.read_csv('input/application_train.csv')
y_train = data['TARGET']
X_train = data.drop(columns = ['SK_ID_CURR', 'TARGET'])
test = pd.read_csv('input/application_test.csv')
submission = test[['SK_ID_CURR']]
X_test = test.drop(columns = ['SK_ID_CURR'])

# one-hot encoding
X_train = pd.get_dummies(X_train)
X_test = pd.get_dummies(X_test)

# align
X_train, X_test = X_train.align(X_test, join = 'inner', axis = 1)

# missing values
X_train = Imputer(strategy='median').fit_transform(X_train)
X_test = Imputer(strategy='median').fit_transform(X_test)

# Scaling
X_train = MinMaxScaler(feature_range = (0, 1)).fit_transform(X_train)
X_test = MinMaxScaler(feature_range = (0, 1)).fit_transform(X_test)

# train and predict
clf = LogisticRegression().fit(X_train, y_train)
y_pred = clf.predict_proba(X_test)[:, 1]

# submit
submission['TARGET'] = y_pred
print(submission.head())
submission.to_csv('benchmark.csv', index = False)