Titanic:disaster_1

import pandas as pd
import numpy as np
pd.options.display.max_columns=15
pd.set_option('expand_frame_repr', False)
data=pd.read_csv("path of your train data set")
data=data.fillna(0)


Pclass=data.groupby(['Pclass','Survived'])['PassengerId'].count()
print pd.DataFrame({"Frequency":Pclass,"Percentage":Pclass.apply(lambda xx: 100*xx/float(Pclass.sum())),'Cumulative_Frequency':Pclass.cumsum(),'Cumulative_percentage':Pclass.cumsum().apply(lambda xx: 100*xx/float(Pclass.sum()))})#.value_counts(sort=False,normalize=True)#.plot(kind='barh')


x = data[(data['Age']<=25)]
y = pd.merge(data[(data['Age']<=50)],data[(data['Age']>25)],how='inner',on='PassengerId')
z = data[(data['Age']>50)]
x=x.groupby(['Sex','Survived'])['PassengerId'].count()
y=y.groupby(['Sex_x','Survived_x'])['PassengerId'].count()
z=z.groupby(['Sex','Survived'])['PassengerId'].count()
print pd.DataFrame({'for age<=25':x,'for 25<age<=50':y,'for age>=50':z})#.plot(kind='barh')


x=data.groupby(['SibSp','Survived'])['PassengerId'].count()
y=data.groupby(['Parch','Survived'])['PassengerId'].count()
z=pd.DataFrame({'SibSp':x,'Parch':y,'SibSp_cumulative':x.cumsum()\
,'SibSp_freq_dist':x.apply(lambda xx: 100*xx/float(x.sum()))\
,'Parch_cumulative':y.cumsum(),'Parch_freq_dist':y.apply(lambda xx: 100*xx/float(x.sum()))}).fillna(0)
print z