some updates

BagOfWords.py

@@ -13,12 +13,12 @@ also work => considered by 'rel_freq'(relative word frequencies) as parameter.
 '''
 from collections import OrderedDict
 import csv
+import pickle
 import re
 
 import numpy as np
 import pandas as pd
 from nltk.stem.porter import PorterStemmer
-import pickle
 
 class BagOfWords:
 

DecisionTree.py

@@ -19,7 +19,7 @@ import graphviz
 import numpy as np
 import pandas as pd
 from sklearn import tree
-# from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_selection import SelectPercentile
 from sklearn.metrics import f1_score
 from sklearn.model_selection import StratifiedKFold

FileHandler.py

@@ -110,6 +110,42 @@ class FileHandler:
                    quoting=csv.QUOTE_NONNUMERIC,
                    quotechar='\'')
 
+    def remove_duplicates():
+        '''remove articles with exactly same headline
+        '''
+        # read data set
+        file = 'data\\cleaned_data_set_without_header.csv'
+        df = pd.read_csv(file,
+                         delimiter='|',
+                         header=None,
+                         index_col=None,
+                         engine='python',
+                         #usecols=[1,2],
+                         #nrows=100,
+                         quoting=csv.QUOTE_NONNUMERIC,
+                         quotechar='\'')
+        print(type(df))
+
+        # for each article(row)
+        i = 1
+        while i < len(df):
+            # check if already in column
+            if df.iloc[i][1] in df.iloc[0:(i-1)][1]:
+                # remove duplicate
+                del df.iloc[i]
+            else:
+                i += 1
+
+        # save cleaned dataframe
+        df.to_csv('data\\cleaned_data_set_without_header.csv',
+                   header=False,
+                   index=False,
+                   sep='|',
+                   mode='a',
+                   encoding='utf-8',
+                   quoting=csv.QUOTE_NONNUMERIC,
+                   quotechar='\'')
+
     def write_articles_to_csv_files():
         '''read JSON files, select articles and write them to csv.
         '''
@@ -197,4 +233,4 @@ class FileHandler:
 if __name__ == '__main__':
     # FileHandler.write_articles_to_csv_files()
     # FileHandler.create_labeling_dataset()
-    FileHandler.clean_articles()
+    FileHandler.remove_duplicates()

NER.py

@@ -8,23 +8,24 @@ like persons, organizations and countries, e.g.
 from collections import OrderedDict
 import csv
 import os
+import pickle
+import re
 
 import numpy as np
 import pandas as pd
 from nltk.tag import StanfordNERTagger
 from nltk.tokenize import word_tokenize
-import pickle
-import re
 
 class NER:
 
     # common company abbreviations to be stripped
     company_abbrevs = ['Inc.', 'Inc', 'Corp', '& Co', 'Co', 'Ltd.', 'Ltd',
-                       'AG', 'LP', 'Limited', 'Tbk', 'Group', 'Co.', 'Groups'
+                       'AG', 'LP', 'Limited', 'Tbk', 'Group', 'Co.', 'Groups',
                        'LLC', 'LBO', 'IPO', 'HQ', 'CIO', 'NGO', 'AB', 'Plc',
                        's.r.l.', 'Holding', 'Holdings', 'GmbH', 'plc', 'Incs',
-                       'Plcs', 'PLC', 'Ltds', 'SA', 'Incs', 'S.A.R.L', 'LLC'
-                       'Company', '& Co.', 'Corporation', 'Pte', 'Pty', 'LLP']
+                       'Plcs', 'PLC', 'Ltds', 'SA', 'Incs', 'S.A.R.L', 'LLC',
+                       'Company', '& Co.', 'Corporation', 'Pte', 'Pty', 'LLP',
+                       'Corp.']
 
     # organizations that are no companies
     regex = r'.*Reuters.*|.*Ministry.*|.*Trump.*|.*Commission.*|.*BRIEF.*|\
@@ -153,20 +154,21 @@ class NER:
         print(n_dict)
 
 if __name__ == '__main__':
-    print('# starting NER...')
-    print()
-    # read data set
-    file = 'data\\cleaned_data_set_without_header.csv'
-    df = pd.read_csv(file,
-                     delimiter='|',
-                     header=None,
-                     index_col=None,
-                     engine='python',
-                     # usecols=[1,2],
-                     # nrows=100,
-                     quoting=csv.QUOTE_NONNUMERIC,
-                     quotechar='\'')
-    #print(df)
-    texts = df[1] + '. ' + df[2]
-    NER.count_companies(texts)
-    # NER.show_most_common_companies()
+    # print('# starting NER...')
+    # print()
+    # # read data set
+    # file = 'data\\cleaned_data_set_without_header.csv'
+    # df = pd.read_csv(file,
+                     # delimiter='|',
+                     # header=None,
+                     # index_col=None,
+                     # engine='python',
+                     # # usecols=[1,2],
+                     # # nrows=100,
+                     # quoting=csv.QUOTE_NONNUMERIC,
+                     # quotechar='\'')
+    # #print(df)
+    # texts = df[1] + '. ' + df[2]
+    # NER.count_companies(texts)
+    # # NER.show_most_common_companies()
+    #print(NER.tag_words('On Monday, Github and Microsoft announced their merger.'))

scheduler.py

@@ -1,16 +0,0 @@
-import schedule
-import time
-
-def job():
-   print("Starting whole process")
-    #collecting the data (requester.py) -> csv file with data
-    #model.py -> to be created, parameters of the pickled model should go here, to use for predictions (SVM)
-    #pushed through NER, output as pdf
-    #sent via email to telesales
-    
-
-schedule.every().day.at("10:30").do(job)
-
-while 1:
-   schedule.run_pending()
-   time.sleep(1)