In [1]:

    

import numpy as np
import pandas as pd

#The Machine learning alogorithm
from sklearn.ensemble import RandomForestClassifier

# Test train split
from sklearn.cross_validation import train_test_split

# Just to switch off pandas warning
pd.options.mode.chained_assignment = None

# Used to write our model to a file
from sklearn.externals import joblib


    

In [2]:

    

data = pd.read_csv("titanic_train.csv")
data.head()


    

    
Out[2]:






  

    

      

      
Unnamed: 0
      
row.names
      
pclass
      
survived
      
name
      
age
      
embarked
      
home.dest
      
room
      
ticket
      
boat
      
sex
    
  
  

    

      
0
      
998
      
999
      
3rd
      
1
      
McCarthy, Miss Katie
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
female
    
    

      
1
      
179
      
180
      
1st
      
0
      
Millet, Mr Francis Davis
      
65
      
Southampton
      
East Bridgewater, MA
      
NaN
      
NaN
      
(249)
      
male
    
    

      
2
      
556
      
557
      
2nd
      
0
      
Sjostedt, Mr Ernst Adolf
      
59
      
Southampton
      
Sault St Marie, ON
      
NaN
      
NaN
      
NaN
      
male
    
    

      
3
      
174
      
175
      
1st
      
0
      
McCaffry, Mr Thomas Francis
      
46
      
Cherbourg
      
Vancouver, BC
      
NaN
      
NaN
      
(292)
      
male
    
    

      
4
      
1232
      
1233
      
3rd
      
0
      
Strilic, Mr Ivan
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
male
    
  

In [3]:

    

data.columns


    

    
Out[3]:





Index(['Unnamed: 0', 'row.names', 'pclass', 'survived', 'name', 'age',
       'embarked', 'home.dest', 'room', 'ticket', 'boat', 'sex'],
      dtype='object')

In [7]:

    

median_age = data['age'].median()
print("Median age is {}".format(median_age))


    

    




Median age is 29.0

In [8]:

    

data['age'].fillna(median_age, inplace = True)
data['age'].head()


    

    
Out[8]:





0    29
1    65
2    59
3    46
4    29
Name: age, dtype: float64

In [10]:

    

data_inputs = data[["pclass", "age", "sex"]]
data_inputs.head()


    

    
Out[10]:






  

    

      

      
pclass
      
age
      
sex
    
  
  

    

      
0
      
3rd
      
29
      
female
    
    

      
1
      
1st
      
65
      
male
    
    

      
2
      
2nd
      
59
      
male
    
    

      
3
      
1st
      
46
      
male
    
    

      
4
      
3rd
      
29
      
male
    
  

In [11]:

    

expected_output = data[["survived"]]
expected_output.head()


    

    
Out[11]:






  

    

      

      
survived
    
  
  

    

      
0
      
1
    
    

      
1
      
0
    
    

      
2
      
0
    
    

      
3
      
0
    
    

      
4
      
0
    
  

In [13]:

    

data_inputs["pclass"].replace("3rd", 3, inplace = True)
data_inputs["pclass"].replace("2nd", 2, inplace = True)
data_inputs["pclass"].replace("1st", 1, inplace = True)
data_inputs.head()


    

    
Out[13]:






  

    

      

      
pclass
      
age
      
sex
    
  
  

    

      
0
      
3
      
29
      
female
    
    

      
1
      
1
      
65
      
male
    
    

      
2
      
2
      
59
      
male
    
    

      
3
      
1
      
46
      
male
    
    

      
4
      
3
      
29
      
male
    
  

In [14]:

    

data_inputs["sex"] = np.where(data_inputs["sex"] == "female", 0, 1)
data_inputs.head()


    

    
Out[14]:






  

    

      

      
pclass
      
age
      
sex
    
  
  

    

      
0
      
3
      
29
      
0
    
    

      
1
      
1
      
65
      
1
    
    

      
2
      
2
      
59
      
1
    
    

      
3
      
1
      
46
      
1
    
    

      
4
      
3
      
29
      
1
    
  

In [21]:

    

inputs_train, inputs_test, expected_output_train, expected_output_test   = train_test_split (data_inputs, expected_output, test_size = 0.33, random_state = 42)

print(inputs_train.head())
print(expected_output_train.head())


    

    




     pclass  age  sex
618       3   19    1
169       3   29    1
830       1   54    1
140       3   29    1
173       2   28    1
     survived
618         0
169         0
830         1
140         0
173         0

In [22]:

    

rf = RandomForestClassifier (n_estimators=100)


    

In [23]:

    

rf.fit(inputs_train, expected_output_train)


    

    




C:\st\Anaconda3\lib\site-packages\ipykernel\__main__.py:1: 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().
  if __name__ == '__main__':






    
Out[23]:





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 [24]:

    

accuracy = rf.score(inputs_test, expected_output_test)
print("Accuracy = {}%".format(accuracy * 100))


    

    




Accuracy = 79.60526315789474%

In [20]:

    

joblib.dump(rf, "titanic_model1", compress=9)


    

    
Out[20]:





['titanic_model1']

In [ ]: