cleaned dataset

NER.py

@@ -158,7 +158,7 @@ if __name__ == '__main__':
                      index_col=None,
                      engine='python',
                      # usecols=[1,2],
-                     nrows=100,
+                     # nrows=100,
                      quoting=csv.QUOTE_NONNUMERIC,
                      quotechar='\'')
     #print(df)

VisualizerNews.py

@@ -97,7 +97,7 @@ class VisualizerNews:
         # texts = df_hits['Title'] + '. ' + df_hits['Text']
         texts = df[1] + '. ' + df[2]
 
-        # dict: count articles with company names
+        # list: count articles with company names
         count_names = NER.count_companies(texts)
         
         # sort list in descending order
@@ -265,6 +265,11 @@ class VisualizerNews:
                     .format(VisualizerNews.datestring))
         plt.show()
 
+    def plot_hist_num_comp_per_art():
+        ''' open pkl file of dict, plot histogram of number of different
+        company names per article.
+        '''
+        
 if __name__ == '__main__':
     VisualizerNews.plot_wordcloud_dataset()
     # VisualizerNews.plot_histogram_companies()