In [1]:

    

import numpy as np
import pandas as pd

# RMS Titanic data visualization code 
from titanic_visualizations import survival_stats
from IPython.display import display
%matplotlib inline

# Load the dataset
in_file = 'titanic_data.csv'
full_data = pd.read_csv(in_file)

# Print the first few entries of the RMS Titanic data
display(full_data.head())


    

    




/home/josh/anaconda2/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.
  warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')






    







  

    

      

      
PassengerId
      
Survived
      
Pclass
      
Name
      
Sex
      
Age
      
SibSp
      
Parch
      
Ticket
      
Fare
      
Cabin
      
Embarked
    
  
  

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
    
    

      
3
      
4
      
1
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
    
    

      
4
      
5
      
0
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
    
  

In [2]:

    

# Store the 'Survived' feature in a new variable and remove it from the dataset
outcomes = full_data['Survived']
data = full_data.drop('Survived', axis = 1)

# Show the new dataset with 'Survived' removed
display(data.head())


    

    







  

    

      

      
PassengerId
      
Pclass
      
Name
      
Sex
      
Age
      
SibSp
      
Parch
      
Ticket
      
Fare
      
Cabin
      
Embarked
    
  
  

    

      
0
      
1
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
    
    

      
1
      
2
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
    
    

      
2
      
3
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
    
    

      
3
      
4
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
    
    

      
4
      
5
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
    
  

In [3]:

    

data = full_data.drop(['Survived','Name','Ticket','Cabin','Embarked','PassengerId'], axis = 1)
data['Sex'] = data['Sex'].apply(lambda x: 1. if x == 'female' else 0.)
display(data.head())


    

    







  

    

      

      
Pclass
      
Sex
      
Age
      
SibSp
      
Parch
      
Fare
    
  
  

    

      
0
      
3
      
0.0
      
22.0
      
1
      
0
      
7.2500
    
    

      
1
      
1
      
1.0
      
38.0
      
1
      
0
      
71.2833
    
    

      
2
      
3
      
1.0
      
26.0
      
0
      
0
      
7.9250
    
    

      
3
      
1
      
1.0
      
35.0
      
1
      
0
      
53.1000
    
    

      
4
      
3
      
0.0
      
35.0
      
0
      
0
      
8.0500
    
  

In [26]:

    

data = data.fillna( data.mean() )
data["Age"] = np.floor(data["Age"]/10)*10


    

In [27]:

    

from sklearn import tree
clf = tree.DecisionTreeClassifier(min_samples_split=20,min_samples_leaf=6)


    

In [28]:

    

clf = clf.fit(data, outcomes)
predictions = clf.predict(data)
from sklearn.metrics import accuracy_score
print "Accuracy Score:", accuracy_score(outcomes, predictions)


    

    




Accuracy Score: 0.863075196409

In [29]:

    

from sklearn.externals.six import StringIO
with open("data.dot", 'w') as f:
    f = tree.export_graphviz(clf, out_file=f)


    

In [30]:

    

from sklearn.externals.six import StringIO  
import pydot 
dot_data = StringIO() 
tree.export_graphviz(clf, out_file=dot_data) 
graph = pydot.graph_from_dot_data(dot_data.getvalue()) 
graph[0].write_pdf("data.pdf")


    

    
Out[30]:





True

In [37]:

    




    

    




---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-37-6e025b99bcf3> in <module>()
----> 1 graph[0].write_pdf("data.pdf")

C:\ProgrameFiles\Anaconda\lib\site-packages\pydot.pyc in <lambda>(path, f, prog)
   1683                 'write_'+frmt,
   1684                 lambda path, f=frmt, prog=self.prog:
-> 1685                     self.write(path, format=f, prog=prog))
   1686 
   1687             f = self.__dict__['write_'+frmt]

C:\ProgrameFiles\Anaconda\lib\site-packages\pydot.pyc in write(self, path, prog, format)
   1766                 s = unicode(s)
   1767         else:
-> 1768             s = self.create(prog, format)
   1769             mode = 'wb'
   1770         with io.open(path, mode=mode) as f:

C:\ProgrameFiles\Anaconda\lib\site-packages\pydot.pyc in create(self, prog, format)
   1874                 raise Exception(
   1875                     '"{prog}" not found in path.'.format(
-> 1876                         prog=prog))
   1877             else:
   1878                 raise

Exception: "dot.exe" not found in path.

In [ ]: