logistic regression

log_reg.py

def logistic_regression(feature_matrix, sentiment, initial_coefficients, step_size, max_iter):
    coefficients = np.array(initial_coefficients) # make sure it's a numpy array
    for itr in xrange(max_iter):

        # Predict P(y_i = +1|x_i,w) using your predict_probability() function
        # YOUR CODE HERE
        predictions = predict_probability(feature_matrix, coefficients)
        
        # Compute indicator value for (y_i = +1)
        indicator = (sentiment==+1)
        
        # Compute the errors as indicator - predictions
        errors = indicator - predictions
        for j in xrange(len(coefficients)): # loop over each coefficient
            
            # Recall that feature_matrix[:,j] is the feature column associated with coefficients[j].
            # Compute the derivative for coefficients[j]. Save it in a variable called derivative
            # YOUR CODE HERE
            derivative = feature_derivative(errors, feature_matrix[:,j])
            
            # add the step size times the derivative to the current coefficient
            ## YOUR CODE HERE
            coefficients = coefficients + (step_size * derivative)
        
        # Checking whether log likelihood is increasing
        if itr <= 15 or (itr <= 100 and itr % 10 == 0) or (itr <= 1000 and itr % 100 == 0) \
        or (itr <= 10000 and itr % 1000 == 0) or itr % 10000 == 0:
            lp = compute_log_likelihood(feature_matrix, sentiment, coefficients)
            print 'iteration %*d: log likelihood of observed labels = %.8f' % \
                (int(np.ceil(np.log10(max_iter))), itr, lp)
    return coefficients