visuals.py

###########################################
# Suppress matplotlib user warnings
# Necessary for newer version of matplotlib
import warnings
warnings.filterwarnings("ignore", category = UserWarning, module = "matplotlib")
#
# Display inline matplotlib plots with IPython
from IPython import get_ipython
get_ipython().run_line_magic('matplotlib', 'inline')
###########################################

import matplotlib.pyplot as pl
import numpy as np
import sklearn.learning_curve as curves
from sklearn.tree import DecisionTreeRegressor
from sklearn.cross_validation import ShuffleSplit, train_test_split

def ModelLearning(X, y):
    """ Calculates the performance of several models with varying sizes of training data.
        The learning and testing scores for each model are then plotted. """
    
    # Create 10 cross-validation sets for training and testing
    cv = ShuffleSplit(X.shape[0], n_iter = 10, test_size = 0.2, random_state = 0)

    # Generate the training set sizes increasing by 50
    train_sizes = np.rint(np.linspace(1, X.shape[0]*0.8 - 1, 9)).astype(int)

    # Create the figure window
    fig = pl.figure(figsize=(10,7))

    # Create three different models based on max_depth
    for k, depth in enumerate([1,3,6,10]):
        
        # Create a Decision tree regressor at max_depth = depth
        regressor = DecisionTreeRegressor(max_depth = depth)

        # Calculate the training and testing scores
        sizes, train_scores, test_scores = curves.learning_curve(regressor, X, y, \
            cv = cv, train_sizes = train_sizes, scoring = 'r2')
        
        # Find the mean and standard deviation for smoothing
        train_std = np.std(train_scores, axis = 1)
        train_mean = np.mean(train_scores, axis = 1)
        test_std = np.std(test_scores, axis = 1)
        test_mean = np.mean(test_scores, axis = 1)

        # Subplot the learning curve 
        ax = fig.add_subplot(2, 2, k+1)
        ax.plot(sizes, train_mean, 'o-', color = 'r', label = 'Training Score')
        ax.plot(sizes, test_mean, 'o-', color = 'g', label = 'Testing Score')
        ax.fill_between(sizes, train_mean - train_std, \
            train_mean + train_std, alpha = 0.15, color = 'r')
        ax.fill_between(sizes, test_mean - test_std, \
            test_mean + test_std, alpha = 0.15, color = 'g')
        
        # Labels
        ax.set_title('max_depth = %s'%(depth))
        ax.set_xlabel('Number of Training Points')
        ax.set_ylabel('Score')
        ax.set_xlim([0, X.shape[0]*0.8])
        ax.set_ylim([-0.05, 1.05])
    
    # Visual aesthetics
    ax.legend(bbox_to_anchor=(1.05, 2.05), loc='lower left', borderaxespad = 0.)
    fig.suptitle('Decision Tree Regressor Learning Performances', fontsize = 16, y = 1.03)
    fig.tight_layout()
    fig.show()


def ModelComplexity(X, y):
    """ Calculates the performance of the model as model complexity increases.
        The learning and testing errors rates are then plotted. """
    
    # Create 10 cross-validation sets for training and testing
    cv = ShuffleSplit(X.shape[0], n_iter = 10, test_size = 0.2, random_state = 0)

    # Vary the max_depth parameter from 1 to 10
    max_depth = np.arange(1,11)

    # Calculate the training and testing scores
    train_scores, test_scores = curves.validation_curve(DecisionTreeRegressor(), X, y, \
        param_name = "max_depth", param_range = max_depth, cv = cv, scoring = 'r2')

    # Find the mean and standard deviation for smoothing
    train_mean = np.mean(train_scores, axis=1)
    train_std = np.std(train_scores, axis=1)
    test_mean = np.mean(test_scores, axis=1)
    test_std = np.std(test_scores, axis=1)

    # Plot the validation curve
    pl.figure(figsize=(7, 5))
    pl.title('Decision Tree Regressor Complexity Performance')
    pl.plot(max_depth, train_mean, 'o-', color = 'r', label = 'Training Score')
    pl.plot(max_depth, test_mean, 'o-', color = 'g', label = 'Validation Score')
    pl.fill_between(max_depth, train_mean - train_std, \
        train_mean + train_std, alpha = 0.15, color = 'r')
    pl.fill_between(max_depth, test_mean - test_std, \
        test_mean + test_std, alpha = 0.15, color = 'g')
    
    # Visual aesthetics
    pl.legend(loc = 'lower right')
    pl.xlabel('Maximum Depth')
    pl.ylabel('Score')
    pl.ylim([-0.05,1.05])
    pl.show()


def PredictTrials(X, y, fitter, data):
    """ Performs trials of fitting and predicting data. """

    # Store the predicted prices
    prices = []

    for k in range(10):
        # Split the data
        X_train, X_test, y_train, y_test = train_test_split(X, y, \
            test_size = 0.2, random_state = k)
        
        # Fit the data
        reg = fitter(X_train, y_train)
        
        # Make a prediction
        pred = reg.predict([data[0]])[0]
        prices.append(pred)
        
        # Result
        print "Trial {}: ${:,.2f}".format(k+1, pred)

    # Display price range
    print "\nRange in prices: ${:,.2f}".format(max(prices) - min(prices))