remove debugging stuff

Author: wrichert

ch03/plot_kmeans_example.py

@@ -102,7 +102,7 @@ def plot_clustering(x, y, title, mx=None, ymax=None, xmin=None, km=None):
 c2a, c2b, c2c = km.cluster_centers_
 pylab.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
               marker='x', linewidth=2, s=100, color='black')
-# import pdb;pdb.set_trace()
+
 pylab.gca().add_patch(
     pylab.Arrow(c1a[0], c1a[1], c2a[0] - c1a[0], c2a[1] - c1a[1], width=0.1))
 pylab.gca().add_patch(

ch03/rel_post_mlcomp_01.py

@@ -77,8 +77,6 @@ def build_analyzer(self):
     similar.append((dist, dataset.data[i]))
 
 similar = sorted(similar)
-import pdb
-pdb.set_trace()
 
 show_at_1 = similar[0]
 show_at_2 = similar[len(similar) / 2]

ch05/PosTagFreqVectorizer.py

@@ -46,7 +46,6 @@ def update(self, other):
             for sent in other:
                 self.n_sents += 1
 
-                # import pdb;pdb.set_trace()
                 if self.poscache is not None:
                     if sent in self.poscache:
                         tags = self.poscache[sent]

ch05/so_xml_to_tsv.py

@@ -96,10 +96,6 @@ def parsexml(filename):
         if elem.tag == 'row':
             creation_date = dateparser.parse(elem.get('CreationDate'))
 
-            # import pdb;pdb.set_trace()
-            # if creation_date.year < 2011:
-            #    continue
-
             Id = int(elem.get('Id'))
             PostTypeId = int(elem.get('PostTypeId'))
             Score = int(elem.get('Score'))

ch06/04_sent.py

@@ -60,7 +60,6 @@ def fit(self, documents, y=None):
 
     def _get_sentiments(self, d):
         # http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
-        #import pdb;pdb.set_trace()
         sent = tuple(nltk.word_tokenize(d))
         if poscache is not None:
             if d in poscache:
@@ -106,7 +105,7 @@ def _get_sentiments(self, d):
         l = len(sent)
         avg_pos_val = np.mean(pos_vals)
         avg_neg_val = np.mean(neg_vals)
-        #import pdb;pdb.set_trace()
+
         return [1 - avg_pos_val - avg_neg_val, avg_pos_val, avg_neg_val,
                 nouns / l, adjectives / l, verbs / l, adverbs / l]
 

ch06/utils.py

@@ -46,7 +46,6 @@ def load_sanders_data(dirname=".", line_count=-1):
 
             topic, label, tweet_id = line
 
-            # import vimpdb;vimpdb.set_trace()
             tweet_fn = os.path.join(
                 DATA_DIR, dirname, 'rawdata', '%s.json' % tweet_id)
             tweet = json.load(open(tweet_fn, "r"))
@@ -157,7 +156,6 @@ def plot_feat_importance(feature_names, clf, name):
 
 def plot_feat_hist(data_name_list, filename=None):
     pylab.clf()
-    # import pdb;pdb.set_trace()
     num_rows = 1 + (len(data_name_list) - 1) / 2
     num_cols = 1 if len(data_name_list) == 1 else 2
     pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

ch09/utils.py

@@ -119,7 +119,6 @@ def plot_feat_importance(feature_names, clf, name):
 
 def plot_feat_hist(data_name_list, filename=None):
     pylab.clf()
-    # import pdb;pdb.set_trace()
     num_rows = 1 + (len(data_name_list) - 1) / 2
     num_cols = 1 if len(data_name_list) == 1 else 2
     pylab.figure(figsize=(5 * num_cols, 4 * num_rows))