i2s-summer-school

# model formula
# here the ~ sign is an = sign, and the features of our dataset
# are written as a formula to predict survived. The C() lets our
# regression know that those variables are categorical.
# Ref: http://patsy.readthedocs.org/en/latest/formulas.html
formula = 'Survived ~ C(Pclass) + C(Sex) + Age + SibSp  + C(Embarked)'
# create a results dictionary to hold our regression results for easy analysis later
results = {}

# create a regression friendly dataframe using patsy's dmatrices function
y,x = dmatrices(formula, data=df, return_type='dataframe')

# instantiate our model
model = sm.Logit(y,x)

# fit our model to the training data
res = model.fit()

# save the result for outputing predictions later
results['Logit'] = [res, formula]
res.summary()