In [2]:

    

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import train_test_split
pd.options.mode.chained_assignment = None
from sklearn.externals import joblib


    

In [3]:

    

# Read the file titanic_test.csv, into a variable called data
print(len(data))


    

    




394

In [4]:

    

# Extract class and sex


    

    
Out[4]:






  

    

      

      
pclass
      
sex
    
  
  

    

      
0
      
3rd
      
male
    
    

      
1
      
1st
      
female
    
    

      
2
      
1st
      
male
    
    

      
3
      
3rd
      
female
    
    

      
4
      
2nd
      
male
    
  

In [5]:

    

# Replace class with humber


    

    
Out[5]:






  

    

      

      
pclass
      
sex
    
  
  

    

      
0
      
3
      
male
    
    

      
1
      
1
      
female
    
    

      
2
      
1
      
male
    
    

      
3
      
3
      
female
    
    

      
4
      
2
      
male
    
  

In [6]:

    

# Replace sex with number


    

    
Out[6]:






  

    

      

      
pclass
      
sex
    
  
  

    

      
0
      
3
      
1
    
    

      
1
      
1
      
0
    
    

      
2
      
1
      
1
    
    

      
3
      
3
      
0
    
    

      
4
      
2
      
1
    
  

In [7]:

    

rf = joblib.load("titanic_model2")


    

In [8]:

    

pred = rf.predict()# ADD YOUR DATA VARIABLE HERE)


    

In [9]:

    

pred


    

    
Out[9]:





array([0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
       0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1,
       0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
       0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,
       1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
       0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0,
       0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0,
       0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0,
       0, 1, 0], dtype=int64)

In [10]:

    

def find_err(pred):
    titanic_data = np.loadtxt("titanic_results.txt", dtype="int32")
    diff_arr = np.equal(titanic_data, pred)
    correct_answers = np.sum(diff_arr)
    percent_diff = correct_answers / len(pred) * 100
    print("Titanic: Percentage Match is: ", percent_diff)
    
find_err(pred)


    

    




Titanic: Percentage Match is:  82.7411167513