DOC Better documentation

Author: luispedro

ch07/boston1.py

@@ -5,19 +5,26 @@
 #
 # It is made available under the MIT License
 
+# This script shows an example of simple (ordinary) linear regression
+
 import numpy as np
 from sklearn.datasets import load_boston
 import pylab as plt
 
 boston = load_boston()
 x = np.array([np.concatenate((v, [1])) for v in boston.data])
 y = boston.target
+
+# np.linal.lstsq implements least-squares linear regression
 s, total_error, _, _ = np.linalg.lstsq(x, y)
 
 rmse = np.sqrt(total_error[0] / len(x))
 print('Residual: {}'.format(rmse))
 
+# Plot the prediction versus real:
 plt.plot(np.dot(x, s), boston.target, 'ro')
+
+# Plot a diagonal (for reference):
 plt.plot([0, 50], [0, 50], 'g-')
 plt.xlabel('predicted')
 plt.ylabel('real')

ch07/boston_cv10_penalized.py

@@ -5,6 +5,8 @@
 #
 # It is made available under the MIT License
 
+# This script fits several forms of penalized regression
+
 from __future__ import print_function
 from sklearn.cross_validation import KFold
 from sklearn.linear_model import ElasticNet, Lasso, Ridge
@@ -20,12 +22,18 @@
         ('lasso(.5)', Lasso(fit_intercept=True, alpha=0.5)),
         ('ridge(.5)', Ridge(fit_intercept=True, alpha=0.5)),
 ]:
+    # Fit on the whole data:
     met.fit(x, y)
+
+    # Predict on the whole data:
     p = np.array([met.predict(xi) for xi in x])
+
     e = p - y
+    # np.dot(e, e) == sum(ei**2 for ei in e) but faster
     total_error = np.dot(e, e)
     rmse_train = np.sqrt(total_error / len(p))
 
+    # Now, we use 10 fold cross-validation to estimate generalization error
     kf = KFold(len(x), n_folds=10)
     err = 0
     for train, test in kf:

ch07/predict10k_en.py

@@ -11,10 +11,10 @@
 from sklearn.linear_model import ElasticNet, LinearRegression
 
 data, target = load_svmlight_file('data/E2006.train')
-lr = LinearRegression(fit_intercept=True)
-en = ElasticNet(fit_intercept=True, alpha=.1)
 
-met = en
+# Edit the lines below if you want to switch method:
+# met = LinearRegression(fit_intercept=True)
+met = ElasticNet(fit_intercept=True, alpha=.1)
 
 kf = KFold(len(target), n_folds=10)
 err = 0

ch07/usermodel.py

@@ -22,7 +22,9 @@
 
 
 def movie_norm(xc):
+    '''Normalize per movie'''
     xc = xc.copy().toarray()
+    # x1 is the mean of the positive items
     x1 = np.array([xi[xi > 0].mean() for xi in xc])
     x1 = np.nan_to_num(x1)