import numpy as np
import pandas as pd

#Print you can execute arbitrary python code
train = pd.read_csv("../input/train.csv", dtype={"Age": np.float64}, )
test = pd.read_csv("../input/test.csv", dtype={"Age": np.float64}, )

feature_cols = ['Pclass', 'Parch']
X = train.loc[:, feature_cols]
Y = train.Survived
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression()
logreg.fit(X,Y)

X_new = test.loc[:, feature_cols]
new_pred_class = logreg.predict(X_new)

sub=pd.DataFrame({'PassengerId':test.PassengerId, 'Survived':new_pred_class}).set_index('PassengerId')


#Print to standard output, and see the results in the "log" section below after running your script
print("\n\nTop of the training data:")
print(train.head())

print("\n\nSummary statistics of training data")
print(train.describe())

sub.to_csv('copy_of_the_training_data.csv', index=True)