Pushing the docs to dev/ for branch: master, commit ec5a9fcf4f4e3cc4748f7145a58292be1e662edb

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -11,9 +11,6 @@
 The dataset used in this example is the 20 newsgroups dataset. It will be
 automatically downloaded, then cached.
 
-The bar plot indicates the accuracy, training time (normalized) and test time
-(normalized) of each classifier.
-
 """
 
 # Author: Peter Prettenhofer <[email protected]>
@@ -51,8 +48,6 @@
 logging.basicConfig(level=logging.INFO,
                     format='%(asctime)s %(levelname)s %(message)s')
 
-
-# parse commandline arguments
 op = OptionParser()
 op.add_option("--report",
               action="store_true", dest="print_report",
@@ -98,8 +93,12 @@ def is_interactive():
 print()
 
 
-# #############################################################################
-# Load some categories from the training set
+##############################################################################
+# Load data from the training set
+# ------------------------------------
+# Let's load data from the newsgroups dataset which comprises around 18000
+# newsgroups posts on 20 topics split in two subsets: one for training (or
+# development) and the other one for testing (or for performance evaluation).
 if opts.all_categories:
     categories = None
 else:
@@ -200,8 +199,11 @@ def trim(s):
     return s if len(s) <= 80 else s[:77] + "..."
 
 
-# #############################################################################
+##############################################################################
 # Benchmark classifiers
+# ------------------------------------
+# We train and test the datasets with 15 different classification models
+# and get performance results for each model.
 def benchmark(clf):
     print('_' * 80)
     print("Training: ")
@@ -294,8 +296,12 @@ def benchmark(clf):
                                                   tol=1e-3))),
   ('classification', LinearSVC(penalty="l2"))])))
 
-# make some plots
 
+##############################################################################
+# Add plots
+# ------------------------------------
+# The bar plot indicates the accuracy, training time (normalized) and test time
+# (normalized) of each classifier.
 indices = np.arange(len(results))
 
 results = [[x[i] for x in results] for i in range(4)]