gitee count and fix code

gitee_tags_count.py

+import pandas as pd
+from collections import Counter
+
+filenameStr = '/home/mao/Documents/GiTeeData.csv'
+csv = pd.read_csv(filenameStr, encoding='utf-8', dtype=str, usecols=['tags'])
+print(len(csv))
+
+
+tags = csv['tags']
+tags = tags.dropna(how='any')
+tags_list = []
+
+
+for index, string in enumerate(tags):
+    if len(string.split(',')) >=2:
+        # print(index)
+        tags_list += [tag.strip() for tag in string.split(',')]
+    else:
+        tags_list.append(string.strip())
+
+
+tags_count = Counter(tags_list)
+tags_dict = dict(reversed(sorted(tags_count.items(), key=lambda item: int(item[1]))))
+pd.DataFrame.from_dict({'tags': list(tags_dict.keys()), 'count': list(tags_dict.values())}).to_csv('gitee_tags.csv', index=False)
\ No newline at end of file

githublink_process/add_group_project_name.py

@@ -14,5 +14,6 @@ for index, project in enumerate(project_path):
 csv['group_name'] = group_names
 csv['project_name'] = project_names
 
-csv.to_csv('test.csv', columns=['project path', 'visits', 'group_name', 'project_name'], index=False)
-print(len(csv))
\ No newline at end of file
+drop_none = csv.dropna(how='any')
+drop_none.to_csv('test.csv', columns=['project path', 'visits', 'group_name', 'project_name'], index=False)
+print(len(drop_none))
\ No newline at end of file

githublink_process/csv_split_80%.py

@@ -3,25 +3,26 @@ import pandas as pd
 csv = pd.read_csv('test.csv')
 print(len(csv))
 
-visists = csv['visits'].to_numpy(dtype=float)
+# visists = csv['visits'].to_numpy(dtype=float)
+#
+# sum = 0
+# for index, visit in enumerate(visists):
+#     sum += visit
+#     if sum > visists.sum() * 0.6:
+#         print(index)
+#         break
+#
+# csv_split = csv[:index+1]
+# csv_split.to_csv('csv_split.csv', columns=['project path', 'group_name', 'project_name', 'visits'], index=False)
+# print(len(csv_split))
+
 
-sum = 0
-for index, visit in enumerate(visists):
-    sum += visit
-    if sum > visists.sum() * 0.6:
+visists = csv['visits'].to_numpy(dtype=float)
+for index, num in enumerate(visists):
+    if num < 60:
         print(index)
         break
 
-csv_split = csv[:index+1]
+csv_split = csv[:index]
 csv_split.to_csv('csv_split.csv', columns=['project path', 'group_name', 'project_name', 'visits'], index=False)
-print(len(csv_split))
-
-
-# visists = csv['visits'].to_numpy(dtype=float)
-# for index, num in enumerate(visists):
-#     if num < 60:
-#         print(index)
-#         break
-#
-# csv_split = csv[:index]
-# csv_split.to_csv('csv_split.csv', columns=['project path', 'group_name', 'project_name', 'visits'], index=False)
\ No newline at end of file
+print(len(csv_split))
\ No newline at end of file