In [1]:

    

import pandas
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score


    

In [2]:

    

train = pandas.read_csv('data/titanic_train.csv')


    

In [3]:

    

train.shape


    

    
Out[3]:





(891, 12)

In [4]:

    

train.columns


    

    
Out[4]:





Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

In [5]:

    

train.head()


    

    
Out[5]:






  

    

      

      
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 [6]:

    

y, X = train['Survived'], train[['Age', 'SibSp', 'Fare']].fillna(0)


    

In [7]:

    

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)


    

In [8]:

    

lr = LogisticRegression()


    

In [9]:

    

lr.fit(X_train, y_train)


    

    
Out[9]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [10]:

    

print(accuracy_score(lr.predict(X_test), y_test))


    

    




0.664804469274

In [11]:

    

from tensorflow.contrib import skflow
import random


    

In [12]:

    

random.seed(42)


    

In [13]:

    

classifier = skflow.TensorFlowLinearClassifier(n_classes=2, batch_size=128, steps=500, learning_rate=0.05)


    

In [14]:

    

classifier.fit(X_train, y_train)


    

    




Step #100, epoch #16, avg. train loss: 0.68626
Step #200, epoch #33, avg. train loss: 0.63602
Step #300, epoch #50, avg. train loss: 0.63053
Step #400, epoch #66, avg. train loss: 0.62640
Step #500, epoch #83, avg. train loss: 0.62822






    
Out[14]:





TensorFlowLinearClassifier(batch_size=128, class_weight=None,
              clip_gradients=5.0, config=None, continue_training=False,
              learning_rate=0.05, n_classes=2, optimizer='Adagrad',
              steps=500, verbose=1)

In [15]:

    

print(accuracy_score(classifier.predict(X_test), y_test))


    

    




0.670391061453

In [ ]: