some updates

CsvHandler.py

@@ -10,6 +10,12 @@ import csv
 import numpy as np
 import pandas as pd
 
+# todo: checken, wie groß ("Dataframe maximum size")
+# import sys
+# print(sys.getsizeof(OBEJCT_NAME_HERE))
+
+# beim selektieren (833 pro Monat) auf Duplikate in Überschrift prüfen!!!
+
 class CsvHandler:
 
     def read_csv(csv_file):
@@ -25,7 +31,8 @@ class CsvHandler:
         return df
 
     def write_csv(df, file_name):
-        df.to_csv(file_name, sep='|')
+        df.to_csv(file_name, 
+                  sep='|')
         print('# saved {} article(s) in {}'.format(len(df), file_name))
 
     def select_randoms(df, n):

NER.py

@@ -8,6 +8,7 @@ like persons, organizations and countries, e.g.
 import os
 
 import matplotlib.pyplot as plt
+import numpy as np
 from nltk.tag import StanfordNERTagger
 from nltk.tokenize import word_tokenize
 
@@ -53,19 +54,20 @@ class NER:
 
     def plot_histogram(count_names):
         '''pyplot diagram of company names distribution
-        in input news articles
-        x-axis:different company names (numbered consecutively)
-        y-axis:counts of company name
+        (probability density function)
+        x-axis: number of mentions of the company
+        y-axis: frequency
         '''
         # sort list in descending order
-        sorted = count_names.sort(reverse=True)
-        # plt.plot(range(len(count_names)), count_names, 'ro', ms = 5)
+        count_names.sort(reverse=True)
+        # convert list to array
+        names = np.asarray(count_names)
         plt.title('Company mentions in News Articles')
-        plt.xlabel('Number of mentions of the company')
+        plt.xlabel('Count of articles that mention a company')
         # Number of companies with this number of mentions
-        plt.ylabel('Frequency')
+        plt.ylabel('Number of companies with this number of articles')
         num_bins = 50
-        n, bins, patches = plt.hist(sorted, num_bins, facecolor='blue', alpha=0.5)
+        n, bins, patches = plt.hist(names, num_bins, facecolor='blue', alpha=0.5)
         # plt.grid(True)
         plt.show()
 
@@ -108,7 +110,7 @@ class NER:
                     dict_com[com] = 1
         # # print outlier
         # print(max(dict_com, key=dict_com.get))
-        return dict_com.values()
+        return list(dict_com.values())
 
 if __name__ == '__main__':