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

def CleanData(data):
    data.fillna('0', inplace=True)
    # Sex
    data.drop(['Ticket', 'Name'], inplace=True, axis=1)
    data.loc[data.Sex != 'male', 'Sex'] = 0
    data.loc[data.Sex == 'male', 'Sex'] = 1
    # Cabin
    data.Cabin.fillna('0', inplace=True)
    data.loc[data.Cabin.str[0] == 'A', 'Cabin'] = 1
    data.loc[data.Cabin.str[0] == 'B', 'Cabin'] = 2
    data.loc[data.Cabin.str[0] == 'C', 'Cabin'] = 3
    data.loc[data.Cabin.str[0] == 'D', 'Cabin'] = 4
    data.loc[data.Cabin.str[0] == 'E', 'Cabin'] = 5
    data.loc[data.Cabin.str[0] == 'F', 'Cabin'] = 6
    data.loc[data.Cabin.str[0] == 'G', 'Cabin'] = 7
    data.loc[data.Cabin.str[0] == 'T', 'Cabin'] = 8
    # Embarked
    data.loc[data.Embarked == 'C', 'Embarked'] = 1
    data.loc[data.Embarked == 'Q', 'Embarked'] = 2
    data.loc[data.Embarked == 'S', 'Embarked'] = 3
    data.Embarked.fillna(0, inplace=True)
    data.fillna(-1, inplace=True)
    return data.astype(float)





#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}, )

trainData = CleanData(train)
testData = CleanData(test)


sns.countplot(train['Pclass'], hue=train['Survived'])
sns.plt.show()





#Any files you save will be available in the output tab below
#train.to_csv('copy_of_the_training_data.csv', index=False)