In [23]:

    

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 [34]:

    

# Read the Titanic_train.csv file here


    

In [26]:

    

# Extract the pclass and sex into a new Dataframe


    

    
Out[26]:






  

    

      

      
pclass
      
sex
    
  
  

    

      
0
      
3rd
      
female
    
    

      
1
      
1st
      
male
    
    

      
2
      
2nd
      
male
    
    

      
3
      
1st
      
male
    
    

      
4
      
3rd
      
male
    
  

In [27]:

    

# Convert pclass to pure numbers


    

    
Out[27]:






  

    

      

      
pclass
      
sex
    
  
  

    

      
0
      
3
      
female
    
    

      
1
      
1
      
male
    
    

      
2
      
2
      
male
    
    

      
3
      
1
      
male
    
    

      
4
      
3
      
male
    
  

In [ ]:

    

# Replace the sex with 0 for female, 1 for male


    

In [29]:

    

# Create the expected result dataframe.


    

In [30]:

    

# Create test/train split


    

In [31]:

    

# Create the random forest instance, and train it with training data


    

    




C:\st\Anaconda3\lib\site-packages\ipykernel\__main__.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  from ipykernel import kernelapp as app






    
Out[31]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False)

In [32]:

    

# Get the accuracy of your model


    

    
Out[32]:





0.80263157894736847

In [33]:

    

# Write the model to a file called "titanic_model2"


    

    
Out[33]:





['titanic_model2']

In [ ]: