In [1]:

    

%matplotlib inline
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier as dt
from sklearn.cross_validation import ShuffleSplit, train_test_split
from sklearn.metrics import make_scorer,accuracy_score
from sklearn.grid_search import GridSearchCV


    

In [2]:

    

t_data = pd.read_csv('titanic_data.csv')
l_data = t_data.Survived
t_data = t_data.drop(['Name','PassengerId','Ticket','Cabin','Embarked'],axis=1)
def sexter(data): return 1 if data == 'female' else 0
t_data.Sex = t_data['Sex'].apply(sexter)
t_data.head()
t_data.fillna(0,inplace=True)


    

In [3]:

    

t_data.head()


    

    
Out[3]:






  

    

      

      
Survived
      
Pclass
      
Sex
      
Age
      
SibSp
      
Parch
      
Fare
    
  
  

    

      
0
      
0
      
3
      
0
      
22
      
1
      
0
      
7.2500
    
    

      
1
      
1
      
1
      
1
      
38
      
1
      
0
      
71.2833
    
    

      
2
      
1
      
3
      
1
      
26
      
0
      
0
      
7.9250
    
    

      
3
      
1
      
1
      
1
      
35
      
1
      
0
      
53.1000
    
    

      
4
      
0
      
3
      
0
      
35
      
0
      
0
      
8.0500
    
  

In [30]:

    

for group,data in t_data.groupby(['Pclass','Sex']):
    dead = data.Survived.value_counts()[0]
    dead_p = float(dead)/t_data.Survived.value_counts()[0]
    alive = data.Survived.value_counts()[1]
    alive_p = float(alive)/t_data.Survived.value_counts()[1]
    print ('Pclass %i, Sex, %i dead = %i, dead_p = %0.2f'% (group[0],group[1],dead,dead_p))
    print ('Pclass %i, Sex, %i alive = %i, alive_p = %0.2f' % (group[0],group[1],alive,alive_p))


    

    




Pclass 1, Sex, 0 dead = 77, dead_p = 0.14
Pclass 1, Sex, 0 alive = 45, alive_p = 0.13
Pclass 1, Sex, 1 dead = 3, dead_p = 0.01
Pclass 1, Sex, 1 alive = 91, alive_p = 0.27
Pclass 2, Sex, 0 dead = 91, dead_p = 0.17
Pclass 2, Sex, 0 alive = 17, alive_p = 0.05
Pclass 2, Sex, 1 dead = 6, dead_p = 0.01
Pclass 2, Sex, 1 alive = 70, alive_p = 0.20
Pclass 3, Sex, 0 dead = 300, dead_p = 0.55
Pclass 3, Sex, 0 alive = 47, alive_p = 0.14
Pclass 3, Sex, 1 dead = 72, dead_p = 0.13
Pclass 3, Sex, 1 alive = 72, alive_p = 0.21

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: