process github link

.gitignore

@@ -12,3 +12,5 @@
 aclImdb/README
 
 *.csv
+
+*.json

add_group_project_name.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+group_names = []
+project_names = []
+for i in range(len(csv['project path'])):
+    group_names.append(csv['project path'][i].split('/')[3])
+    project_names.append(csv['project path'][i].split('/')[4])
+
+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

delete_grouplink.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+delete_group_row = []
+for i in range(len(csv)):
+    if len(csv['project path'].loc[i].split('/')) <= 4:
+        delete_group_row.append(i)
+
+for index in delete_group_row:
+    csv.drop(index=index, inplace=True)
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

delete_login_settings.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+delete_rows = []
+for i in range(len(csv)):
+    if 'login' in csv['project path'][i] or 'settings' in csv['project path'][i]:
+        delete_rows.append(i)
+
+for index in delete_rows:
+    csv.drop(index=index, inplace=True)
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

delete_not_githublink.py

+import pandas as pd
+
+csv = pd.read_csv('/home/mao/Documents/githublinks.csv')
+print(len(csv))
+
+delete_rows_index = []
+for i in range(len(csv)):
+    if not 'github' in str(csv['project path'].loc[i]):
+        delete_rows_index.append(i)
+
+for index in delete_rows_index:
+    csv.drop(index=index, inplace=True)
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

drop_duplicates.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+
+csv_drop_duplicates = csv.drop_duplicates(subset=['project_name'])
+
+csv_drop_duplicates.to_csv('test.csv', columns=['project path', 'visits', 'group_name', 'project_name'], index=False)
+print(len(csv_drop_duplicates))
\ No newline at end of file

replace_#.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_tree_row = []
+for i in range(len(csv)):
+    if '#' in csv['project path'][i]:
+        replace_tree_row.append(i)
+
+for index in replace_tree_row:
+    for index_, item in enumerate(csv['project path'][index].split('#')):
+        csv['project path'][index] = csv['project path'][21].split('#')[0]
+        break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_%.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_tree_row = []
+for i in range(len(csv)):
+    if '%' in csv['project path'][i]:
+        replace_tree_row.append(i)
+
+for index in replace_tree_row:
+    for index_, item in enumerate(csv['project path'][index].split('%')):
+        csv['project path'][index] = csv['project path'][index].split('%')[0]
+        break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_.git.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+for i in range(len(csv)):
+    if '.git' in csv['project path'][i]:
+        csv['project path'][i] = str(csv['project path'][i]).replace('.git', '')
+    elif ';' in csv['project path'][i]:
+        csv['project path'][i] = str(csv['project path'][i]).replace(';', '')
+
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))

replace_archive.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_archive_row = []
+for i in range(len(csv)):
+    if 'archive' in csv['project path'][i]:
+        replace_archive_row.append(i)
+
+for index in replace_archive_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if 'archive' in item:
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_blob.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_blob_row = []
+for i in range(len(csv)):
+    if 'blob' in csv['project path'][i]:
+        replace_blob_row.append(i)
+
+
+for index in replace_blob_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if item == 'blob':
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_issues.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_tree_row = []
+for i in range(len(csv)):
+    if 'issues' in csv['project path'][i]:
+        replace_tree_row.append(i)
+
+for index in replace_tree_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if 'issues' in item:
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_release.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_release_row = []
+for i in range(len(csv)):
+    if 'release' in csv['project path'][i]:
+        replace_release_row.append(i)
+
+for index in replace_release_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if item == 'releases':
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_tree.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_tree_row = []
+for i in range(len(csv)):
+    if 'tree' in csv['project path'][i]:
+        replace_tree_row.append(i)
+
+for index in replace_tree_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if item == 'tree':
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file

replace_wiki.py

+import pandas as pd
+
+csv = pd.read_csv('test.csv')
+print(len(csv))
+
+replace_wiki_row = []
+for i in range(len(csv)):
+    if 'wiki' in csv['project path'][i]:
+        replace_wiki_row.append(i)
+
+
+for index in replace_wiki_row:
+    for index_, item in enumerate(csv['project path'][index].split('/')):
+        if item == 'wiki':
+            csv['project path'][index] = '/'.join(csv['project path'][index].split('/')[0:index_])
+            break
+
+
+csv.to_csv('test.csv', columns=['project path', 'visits'], index=False)
+print(len(csv))
\ No newline at end of file