11_titanic.py

'''
EXERCISE: Predicting Survival on the Titanic
'''

# TASK 1: read the data from titanic.csv into a DataFrame
import pandas as pd
titanic = pd.read_csv('titanic.csv', index_col='PassengerId')

# TASK 2: define Pclass/Parch as the features and Survived as the response
feature_cols = ['Pclass', 'Parch']
X = titanic[feature_cols]
y = titanic.Survived

# TASK 3: split the data into training and testing sets
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)

# TASK 4: fit a logistic regression model and examine the coefficients
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression(C=1e9)
logreg.fit(X_train, y_train)
zip(feature_cols, logreg.coef_[0])

# TASK 5: make predictions on testing set and calculate accuracy
y_pred_class = logreg.predict(X_test)
from sklearn import metrics
print metrics.accuracy_score(y_test, y_pred_class)

# TASK 6 (BONUS): compare testing accuracy to null accuracy
1 - y_test.mean()

# TASK 7 (BONUS): add Age as a feature and calculate testing accuracy
titanic.Age.fillna(titanic.Age.mean(), inplace=True)
feature_cols = ['Pclass', 'Parch', 'Age']
X = titanic[feature_cols]
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
logreg.fit(X_train, y_train)
zip(feature_cols, logreg.coef_[0])
y_pred_class = logreg.predict(X_test)
print metrics.accuracy_score(y_test, y_pred_class)