In [1]:

    

import pandas as pd
titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')
titanic.head()


    

    
Out[1]:






  

    

      

      
row.names
      
pclass
      
survived
      
name
      
age
      
embarked
      
home.dest
      
room
      
ticket
      
boat
      
sex
    
  
  

    

      
0
      
1
      
1st
      
1
      
Allen, Miss Elisabeth Walton
      
29.0000
      
Southampton
      
St Louis, MO
      
B-5
      
24160 L221
      
2
      
female
    
    

      
1
      
2
      
1st
      
0
      
Allison, Miss Helen Loraine
      
2.0000
      
Southampton
      
Montreal, PQ / Chesterville, ON
      
C26
      
NaN
      
NaN
      
female
    
    

      
2
      
3
      
1st
      
0
      
Allison, Mr Hudson Joshua Creighton
      
30.0000
      
Southampton
      
Montreal, PQ / Chesterville, ON
      
C26
      
NaN
      
(135)
      
male
    
    

      
3
      
4
      
1st
      
0
      
Allison, Mrs Hudson J.C. (Bessie Waldo Daniels)
      
25.0000
      
Southampton
      
Montreal, PQ / Chesterville, ON
      
C26
      
NaN
      
NaN
      
female
    
    

      
4
      
5
      
1st
      
1
      
Allison, Master Hudson Trevor
      
0.9167
      
Southampton
      
Montreal, PQ / Chesterville, ON
      
C22
      
NaN
      
11
      
male
    
  

In [2]:

    

titanic.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 11 columns):
row.names    1313 non-null int64
pclass       1313 non-null object
survived     1313 non-null int64
name         1313 non-null object
age          633 non-null float64
embarked     821 non-null object
home.dest    754 non-null object
room         77 non-null object
ticket       69 non-null object
boat         347 non-null object
sex          1313 non-null object
dtypes: float64(1), int64(2), object(8)
memory usage: 112.9+ KB

In [3]:

    

X=titanic[['pclass','age','sex']]
y=titanic['survived']
X.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 3 columns):
pclass    1313 non-null object
age       633 non-null float64
sex       1313 non-null object
dtypes: float64(1), object(2)
memory usage: 30.8+ KB

In [5]:

    

X['age'].fillna(X['age'].mean(),inplace=True)
X.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 3 columns):
pclass    1313 non-null object
age       1313 non-null float64
sex       1313 non-null object
dtypes: float64(1), object(2)
memory usage: 30.8+ KB






    




/Users/ifeng/anaconda2/lib/python2.7/site-packages/pandas/core/generic.py:3295: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self._update_inplace(new_data)

In [6]:

    

from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=33)
from sklearn.feature_extraction import DictVectorizer
vec=DictVectorizer(sparse=False)
X_train=vec.fit_transform(X_train.to_dict(orient='record'))
print vec.feature_names_


    

    




['age', 'pclass=1st', 'pclass=2nd', 'pclass=3rd', 'sex=female', 'sex=male']

In [8]:

    

X_test=vec.transform(X_test.to_dict(orient='record'))
from sklearn.tree import DecisionTreeClassifier
dtc=DecisionTreeClassifier()
dtc.fit(X_train,y_train)
y_predict=dtc.predict(X_test)


    

In [9]:

    

from sklearn.metrics import classification_report
print dtc.score(X_test,y_test)
print classification_report(y_predict,y_test,target_names=['died','suivived'])


    

    




0.781155015198
             precision    recall  f1-score   support

       died       0.91      0.78      0.84       236
   suivived       0.58      0.80      0.67        93

avg / total       0.81      0.78      0.79       329