mgaughan/mw-lifecycle-analysis
1
0
Fork 0
Code
7a28e0e079
mw-lifecycle-analysis/text_analysis/case3/050825_join_resolved_files.ipynb

1177 lines
53 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "fcc726a8-44a4-48cf-a1cd-937b05bd4d08",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1fceca29-48c1-4ba3-93ba-88724dea22a7",
"metadata": {},
"outputs": [],
"source": [
"first_resolved_path = \"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/0050825_coref-rel-first.csv\"\n",
"first_resolved_df = pd.read_csv(first_resolved_path)\n",
"second_resolved_path = \"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/050825_coref_rel_phab_stragglers.csv\"\n",
"second_resolved_df = pd.read_csv(second_resolved_path)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f26c31e7-bee1-4100-821f-769e5b1791bd",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>task_title</th>\n",
" <th>comment_text</th>\n",
" <th>date_created</th>\n",
" <th>speaker</th>\n",
" <th>meta.affil</th>\n",
" <th>conversation_id</th>\n",
" <th>comment_type</th>\n",
" <th>status</th>\n",
" <th>meta.gerrit</th>\n",
" <th>id</th>\n",
" <th>reply_to</th>\n",
" <th>timestamp</th>\n",
" <th>is_relevant</th>\n",
" <th>is_migrated</th>\n",
" <th>text</th>\n",
" <th>resolved_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Special:PasswordReset locks out of account: \"I...</td>\n",
" <td>[Backport was merged into 1.24wmf16 upon a tim...</td>\n",
" <td>1412717629</td>\n",
" <td>PHID-USER-hgn5uw2jafgjgfvxibhh</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-7ho223nxpxvlbbyd3ckz</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243500</td>\n",
" <td>243499.0</td>\n",
" <td>2014-10-07 21:33:49+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>[Backport was merged into 1.24wmf16 upon a tim...</td>\n",
" <td>[Backport was merged into 1.24wmf16 upon a tim...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>login busted</td>\n",
" <td>I guess this can be closed now as RESOLVED WOR...</td>\n",
" <td>1413464793</td>\n",
" <td>PHID-USER-hgn5uw2jafgjgfvxibhh</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-jekgcahti7tcon56pca2</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>250657</td>\n",
" <td>250656.0</td>\n",
" <td>2014-10-16 13:06:33+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>I guess this can be closed now as RESOLVED WOR...</td>\n",
" <td>I guess this can be closed now as RESOLVED WOR...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>SSLError on requesting data from Wikidata</td>\n",
" <td>The upstream issue is https://github.com/jcgre...</td>\n",
" <td>1417113110</td>\n",
" <td>PHID-USER-muirnivxp5hzppn2a3z7</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-w4js4xepsmk6fz75gkwe</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>250686</td>\n",
" <td>250685.0</td>\n",
" <td>2014-11-27 18:31:50+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>The upstream issue is https://github.com/jcgre...</td>\n",
" <td>The upstream issue is https://github.com/jcgre...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>SSLError on requesting data from Wikidata</td>\n",
" <td>An update on this. In Amsterdam we found at th...</td>\n",
" <td>1417110306</td>\n",
" <td>PHID-USER-uu7wg6g3b37dcktbje3a</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-w4js4xepsmk6fz75gkwe</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>250687</td>\n",
" <td>250686.0</td>\n",
" <td>2014-11-27 17:45:06+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>An update on this. In Amsterdam we found at th...</td>\n",
" <td>An update on this. In Amsterdam we found at th...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>SSLError on requesting data from Wikidata</td>\n",
" <td>Yes. It's used by people using pywikibot-as-a-...</td>\n",
" <td>1412595221</td>\n",
" <td>PHID-USER-muirnivxp5hzppn2a3z7</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-w4js4xepsmk6fz75gkwe</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>250688</td>\n",
" <td>250687.0</td>\n",
" <td>2014-10-06 11:33:41+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Yes. It's used by people using pywikibot-as-a-...</td>\n",
" <td>Yes. It's used by people using pywikibot-as-a-...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>857</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" <td>1434207367</td>\n",
" <td>PHID-USER-lhtlnmkdbzlz6pbxaqdd</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406640</td>\n",
" <td>406639.0</td>\n",
" <td>2015-06-13 14:56:07+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>858</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>1434140114</td>\n",
" <td>PHID-USER-wrimmmr5w2zt7nk2t753</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406641</td>\n",
" <td>406640.0</td>\n",
" <td>2015-06-12 20:15:14+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>859</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>1434116915</td>\n",
" <td>PHID-USER-wrimmmr5w2zt7nk2t753</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406642</td>\n",
" <td>406641.0</td>\n",
" <td>2015-06-12 13:48:35+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>860</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" <td>1434114623</td>\n",
" <td>PHID-USER-sx63fwaih5kjt7bz4u6z</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406643</td>\n",
" <td>406642.0</td>\n",
" <td>2015-06-12 13:10:23+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>861</th>\n",
" <td>Allow login using mosh as an alternative to pl...</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" <td>1413537437</td>\n",
" <td>PHID-USER-2nnm76h4ykalvvref2ye</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-hnwvtmwgpm2oisoqaozt</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406877</td>\n",
" <td>406876.0</td>\n",
" <td>2014-10-17 09:17:17+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>862 rows × 16 columns</p>\n",
"</div>"
],
"text/plain": [
" task_title \\\n",
"0 Special:PasswordReset locks out of account: \"I... \n",
"1 login busted \n",
"2 SSLError on requesting data from Wikidata \n",
"3 SSLError on requesting data from Wikidata \n",
"4 SSLError on requesting data from Wikidata \n",
".. ... \n",
"857 text input history/autocomplete doesn't work w... \n",
"858 text input history/autocomplete doesn't work w... \n",
"859 text input history/autocomplete doesn't work w... \n",
"860 text input history/autocomplete doesn't work w... \n",
"861 Allow login using mosh as an alternative to pl... \n",
"\n",
" comment_text date_created \\\n",
"0 [Backport was merged into 1.24wmf16 upon a tim... 1412717629 \n",
"1 I guess this can be closed now as RESOLVED WOR... 1413464793 \n",
"2 The upstream issue is https://github.com/jcgre... 1417113110 \n",
"3 An update on this. In Amsterdam we found at th... 1417110306 \n",
"4 Yes. It's used by people using pywikibot-as-a-... 1412595221 \n",
".. ... ... \n",
"857 I amended the title to the range IE8-10 becaus... 1434207367 \n",
"858 If I remember correctly this problem was at le... 1434140114 \n",
"859 If I remember correctly this problem was at le... 1434116915 \n",
"860 After a quick test, autocomplete seems to work... 1434114623 \n",
"861 Still not merged, so we can't really do much. 1413537437 \n",
"\n",
" speaker meta.affil \\\n",
"0 PHID-USER-hgn5uw2jafgjgfvxibhh False \n",
"1 PHID-USER-hgn5uw2jafgjgfvxibhh False \n",
"2 PHID-USER-muirnivxp5hzppn2a3z7 False \n",
"3 PHID-USER-uu7wg6g3b37dcktbje3a False \n",
"4 PHID-USER-muirnivxp5hzppn2a3z7 False \n",
".. ... ... \n",
"857 PHID-USER-lhtlnmkdbzlz6pbxaqdd False \n",
"858 PHID-USER-wrimmmr5w2zt7nk2t753 False \n",
"859 PHID-USER-wrimmmr5w2zt7nk2t753 False \n",
"860 PHID-USER-sx63fwaih5kjt7bz4u6z False \n",
"861 PHID-USER-2nnm76h4ykalvvref2ye False \n",
"\n",
" conversation_id comment_type status meta.gerrit \\\n",
"0 PHID-TASK-7ho223nxpxvlbbyd3ckz task_subcomment NaN False \n",
"1 PHID-TASK-jekgcahti7tcon56pca2 task_subcomment NaN False \n",
"2 PHID-TASK-w4js4xepsmk6fz75gkwe task_subcomment NaN False \n",
"3 PHID-TASK-w4js4xepsmk6fz75gkwe task_subcomment NaN False \n",
"4 PHID-TASK-w4js4xepsmk6fz75gkwe task_subcomment NaN False \n",
".. ... ... ... ... \n",
"857 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"858 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"859 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"860 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"861 PHID-TASK-hnwvtmwgpm2oisoqaozt task_subcomment NaN False \n",
"\n",
" id reply_to timestamp is_relevant is_migrated \\\n",
"0 243500 243499.0 2014-10-07 21:33:49+00:00 True False \n",
"1 250657 250656.0 2014-10-16 13:06:33+00:00 True False \n",
"2 250686 250685.0 2014-11-27 18:31:50+00:00 True False \n",
"3 250687 250686.0 2014-11-27 17:45:06+00:00 True False \n",
"4 250688 250687.0 2014-10-06 11:33:41+00:00 True False \n",
".. ... ... ... ... ... \n",
"857 406640 406639.0 2015-06-13 14:56:07+00:00 True False \n",
"858 406641 406640.0 2015-06-12 20:15:14+00:00 True False \n",
"859 406642 406641.0 2015-06-12 13:48:35+00:00 True False \n",
"860 406643 406642.0 2015-06-12 13:10:23+00:00 True False \n",
"861 406877 406876.0 2014-10-17 09:17:17+00:00 True False \n",
"\n",
" text \\\n",
"0 [Backport was merged into 1.24wmf16 upon a tim... \n",
"1 I guess this can be closed now as RESOLVED WOR... \n",
"2 The upstream issue is https://github.com/jcgre... \n",
"3 An update on this. In Amsterdam we found at th... \n",
"4 Yes. It's used by people using pywikibot-as-a-... \n",
".. ... \n",
"857 I amended the title to the range IE8-10 becaus... \n",
"858 If I remember correctly this problem was at le... \n",
"859 If I remember correctly this problem was at le... \n",
"860 After a quick test, autocomplete seems to work... \n",
"861 Still not merged, so we can't really do much. \n",
"\n",
" resolved_text \n",
"0 [Backport was merged into 1.24wmf16 upon a tim... \n",
"1 I guess this can be closed now as RESOLVED WOR... \n",
"2 The upstream issue is https://github.com/jcgre... \n",
"3 An update on this. In Amsterdam we found at th... \n",
"4 Yes. It's used by people using pywikibot-as-a-... \n",
".. ... \n",
"857 I amended the title to the range IE8-10 becaus... \n",
"858 If I remember correctly this problem was at le... \n",
"859 If I remember correctly this problem was at le... \n",
"860 After a quick test, autocomplete seems to work... \n",
"861 Still not merged, so we can't really do much. \n",
"\n",
"[862 rows x 16 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(second_resolved_df)\n",
"second_resolved_df = second_resolved_df.drop(columns=['_merge'])\n",
"second_resolved_df"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "dfa81ca2-4d66-4679-bc3e-192d0cac67fa",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>task_title</th>\n",
" <th>comment_text</th>\n",
" <th>date_created</th>\n",
" <th>speaker</th>\n",
" <th>meta.affil</th>\n",
" <th>conversation_id</th>\n",
" <th>comment_type</th>\n",
" <th>status</th>\n",
" <th>meta.gerrit</th>\n",
" <th>id</th>\n",
" <th>reply_to</th>\n",
" <th>timestamp</th>\n",
" <th>is_relevant</th>\n",
" <th>is_migrated</th>\n",
" <th>text</th>\n",
" <th>resolved_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" <td>1411541280</td>\n",
" <td>PHID-USER-v7vgzvvcw7v2umf737ri</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_description</td>\n",
" <td>resolved</td>\n",
" <td>False</td>\n",
" <td>243215</td>\n",
" <td>NaN</td>\n",
" <td>2014-09-24 06:48:00+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>Revert has been deployed.</td>\n",
" <td>1411573104</td>\n",
" <td>PHID-USER-v7vgzvvcw7v2umf737ri</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243216</td>\n",
" <td>243215.0</td>\n",
" <td>2014-09-24 15:38:24+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Revert has been deployed.</td>\n",
" <td>Revert has been deployed.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" <td>1411572378</td>\n",
" <td>PHID-USER-ynivjflmc2dcl6w5ut5v</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243217</td>\n",
" <td>243216.0</td>\n",
" <td>2014-09-24 15:26:18+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" <td>1411545535</td>\n",
" <td>PHID-USER-v7bwpq3rs3zdxegibdbh</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243218</td>\n",
" <td>243217.0</td>\n",
" <td>2014-09-24 07:58:55+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" <td>1411542640</td>\n",
" <td>PHID-USER-ynivjflmc2dcl6w5ut5v</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243219</td>\n",
" <td>243218.0</td>\n",
" <td>2014-09-24 07:10:40+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13623</th>\n",
" <td>OAuth login refers to mediawiki.org:/ instead ...</td>\n",
" <td>&gt; When I registered, phabricator linked mediaw...</td>\n",
" <td>1413205650</td>\n",
" <td>PHID-USER-hgn5uw2jafgjgfvxibhh</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-yeaxsfxhhtbn26koo5fi</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>378799</td>\n",
" <td>378798.0</td>\n",
" <td>2014-10-13 13:07:30+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>&gt; When I registered, phabricator linked mediaw...</td>\n",
" <td>&gt; When I registered, phabricator linked mediaw...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13624</th>\n",
" <td>OAuth login refers to mediawiki.org:/ instead ...</td>\n",
" <td>See {T574} for a related discussion.</td>\n",
" <td>1412958953</td>\n",
" <td>PHID-USER-lluzkul4z7us4sxkayss</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-yeaxsfxhhtbn26koo5fi</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>378800</td>\n",
" <td>378799.0</td>\n",
" <td>2014-10-10 16:35:53+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>See {T574} for a related discussion.</td>\n",
" <td>See {T574} for a related discussion.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13625</th>\n",
" <td>Improvements to Wikimedia SUL login dialog UI:...</td>\n",
" <td>Some improvements to the Wikimedia SUL dialog:...</td>\n",
" <td>1412362816</td>\n",
" <td>PHID-USER-lluzkul4z7us4sxkayss</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-j6czqxlv5fzcx3tmq23n</td>\n",
" <td>task_description</td>\n",
" <td>declined</td>\n",
" <td>False</td>\n",
" <td>378858</td>\n",
" <td>NaN</td>\n",
" <td>2014-10-03 19:00:16+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Some improvements to the Wikimedia SUL dialog:...</td>\n",
" <td>Some improvements to the Wikimedia SUL dialog:...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13626</th>\n",
" <td>Improvements to Wikimedia SUL login dialog UI:...</td>\n",
" <td>I guess the same restrictions as in T543 apply...</td>\n",
" <td>1412415111</td>\n",
" <td>PHID-USER-lluzkul4z7us4sxkayss</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-j6czqxlv5fzcx3tmq23n</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>378860</td>\n",
" <td>378859.0</td>\n",
" <td>2014-10-04 09:31:51+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>I guess the same restrictions as in T543 apply...</td>\n",
" <td>I guess the same restrictions as in T543 apply...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13627</th>\n",
" <td>Improvements to Wikimedia SUL login dialog UI:...</td>\n",
" <td>It's not entirely trivial to change</td>\n",
" <td>1412366627</td>\n",
" <td>PHID-USER-fn7qnpccfbitivgtw2rt</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-j6czqxlv5fzcx3tmq23n</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>378861</td>\n",
" <td>378860.0</td>\n",
" <td>2014-10-03 20:03:47+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>It's not entirely trivial to change</td>\n",
" <td>It's not entirely trivial to change</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>13628 rows × 16 columns</p>\n",
"</div>"
],
"text/plain": [
" task_title \\\n",
"0 User with unattached accounts unable to login ... \n",
"1 User with unattached accounts unable to login ... \n",
"2 User with unattached accounts unable to login ... \n",
"3 User with unattached accounts unable to login ... \n",
"4 User with unattached accounts unable to login ... \n",
"... ... \n",
"13623 OAuth login refers to mediawiki.org:/ instead ... \n",
"13624 OAuth login refers to mediawiki.org:/ instead ... \n",
"13625 Improvements to Wikimedia SUL login dialog UI:... \n",
"13626 Improvements to Wikimedia SUL login dialog UI:... \n",
"13627 Improvements to Wikimedia SUL login dialog UI:... \n",
"\n",
" comment_text date_created \\\n",
"0 User:NickK reported in IRC that they're gettin... 1411541280 \n",
"1 Revert has been deployed. 1411573104 \n",
"2 **gerritadmin** wrote:\\n\\nChange 162550 merged... 1411572378 \n",
"3 (In reply to Kunal Mehta (Legoktm) from commen... 1411545535 \n",
"4 **gerritadmin** wrote:\\n\\nChange 162549 merged... 1411542640 \n",
"... ... ... \n",
"13623 > When I registered, phabricator linked mediaw... 1413205650 \n",
"13624 See {T574} for a related discussion. 1412958953 \n",
"13625 Some improvements to the Wikimedia SUL dialog:... 1412362816 \n",
"13626 I guess the same restrictions as in T543 apply... 1412415111 \n",
"13627 It's not entirely trivial to change 1412366627 \n",
"\n",
" speaker meta.affil \\\n",
"0 PHID-USER-v7vgzvvcw7v2umf737ri False \n",
"1 PHID-USER-v7vgzvvcw7v2umf737ri False \n",
"2 PHID-USER-ynivjflmc2dcl6w5ut5v False \n",
"3 PHID-USER-v7bwpq3rs3zdxegibdbh False \n",
"4 PHID-USER-ynivjflmc2dcl6w5ut5v False \n",
"... ... ... \n",
"13623 PHID-USER-hgn5uw2jafgjgfvxibhh False \n",
"13624 PHID-USER-lluzkul4z7us4sxkayss False \n",
"13625 PHID-USER-lluzkul4z7us4sxkayss False \n",
"13626 PHID-USER-lluzkul4z7us4sxkayss False \n",
"13627 PHID-USER-fn7qnpccfbitivgtw2rt False \n",
"\n",
" conversation_id comment_type status \\\n",
"0 PHID-TASK-mio2uq45ny7mms72syut task_description resolved \n",
"1 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN \n",
"2 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN \n",
"3 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN \n",
"4 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN \n",
"... ... ... ... \n",
"13623 PHID-TASK-yeaxsfxhhtbn26koo5fi task_subcomment NaN \n",
"13624 PHID-TASK-yeaxsfxhhtbn26koo5fi task_subcomment NaN \n",
"13625 PHID-TASK-j6czqxlv5fzcx3tmq23n task_description declined \n",
"13626 PHID-TASK-j6czqxlv5fzcx3tmq23n task_subcomment NaN \n",
"13627 PHID-TASK-j6czqxlv5fzcx3tmq23n task_subcomment NaN \n",
"\n",
" meta.gerrit id reply_to timestamp is_relevant \\\n",
"0 False 243215 NaN 2014-09-24 06:48:00+00:00 True \n",
"1 False 243216 243215.0 2014-09-24 15:38:24+00:00 True \n",
"2 False 243217 243216.0 2014-09-24 15:26:18+00:00 True \n",
"3 False 243218 243217.0 2014-09-24 07:58:55+00:00 True \n",
"4 False 243219 243218.0 2014-09-24 07:10:40+00:00 True \n",
"... ... ... ... ... ... \n",
"13623 False 378799 378798.0 2014-10-13 13:07:30+00:00 True \n",
"13624 False 378800 378799.0 2014-10-10 16:35:53+00:00 True \n",
"13625 False 378858 NaN 2014-10-03 19:00:16+00:00 True \n",
"13626 False 378860 378859.0 2014-10-04 09:31:51+00:00 True \n",
"13627 False 378861 378860.0 2014-10-03 20:03:47+00:00 True \n",
"\n",
" is_migrated text \\\n",
"0 False User:NickK reported in IRC that they're gettin... \n",
"1 False Revert has been deployed. \n",
"2 False **gerritadmin** wrote:\\n\\nChange 162550 merged... \n",
"3 False (In reply to Kunal Mehta (Legoktm) from commen... \n",
"4 False **gerritadmin** wrote:\\n\\nChange 162549 merged... \n",
"... ... ... \n",
"13623 False > When I registered, phabricator linked mediaw... \n",
"13624 False See {T574} for a related discussion. \n",
"13625 False Some improvements to the Wikimedia SUL dialog:... \n",
"13626 False I guess the same restrictions as in T543 apply... \n",
"13627 False It's not entirely trivial to change \n",
"\n",
" resolved_text \n",
"0 User:NickK reported in IRC that they're gettin... \n",
"1 Revert has been deployed. \n",
"2 **gerritadmin** wrote:\\n\\nChange 162550 merged... \n",
"3 (In reply to Kunal Mehta (Legoktm) from commen... \n",
"4 **gerritadmin** wrote:\\n\\nChange 162549 merged... \n",
"... ... \n",
"13623 > When I registered, phabricator linked mediaw... \n",
"13624 See {T574} for a related discussion. \n",
"13625 Some improvements to the Wikimedia SUL dialog:... \n",
"13626 I guess the same restrictions as in T543 apply... \n",
"13627 It's not entirely trivial to change \n",
"\n",
"[13628 rows x 16 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(first_resolved_df)\n",
"first_resolved_df"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "6dc11bda-f0f6-4eb6-96f5-02ed9a3492ba",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"14490"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"combined_df = pd.concat([first_resolved_df, second_resolved_df])\n",
"unique_df = combined_df.drop_duplicates()\n",
"len(unique_df)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "0c903199-8159-455c-aa7f-e57ef07ce03e",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>task_title</th>\n",
" <th>comment_text</th>\n",
" <th>date_created</th>\n",
" <th>speaker</th>\n",
" <th>meta.affil</th>\n",
" <th>conversation_id</th>\n",
" <th>comment_type</th>\n",
" <th>status</th>\n",
" <th>meta.gerrit</th>\n",
" <th>id</th>\n",
" <th>reply_to</th>\n",
" <th>timestamp</th>\n",
" <th>is_relevant</th>\n",
" <th>is_migrated</th>\n",
" <th>text</th>\n",
" <th>resolved_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" <td>1411541280</td>\n",
" <td>PHID-USER-v7vgzvvcw7v2umf737ri</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_description</td>\n",
" <td>resolved</td>\n",
" <td>False</td>\n",
" <td>243215</td>\n",
" <td>NaN</td>\n",
" <td>2014-09-24 06:48:00+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" <td>User:NickK reported in IRC that they're gettin...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>Revert has been deployed.</td>\n",
" <td>1411573104</td>\n",
" <td>PHID-USER-v7vgzvvcw7v2umf737ri</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243216</td>\n",
" <td>243215.0</td>\n",
" <td>2014-09-24 15:38:24+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Revert has been deployed.</td>\n",
" <td>Revert has been deployed.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" <td>1411572378</td>\n",
" <td>PHID-USER-ynivjflmc2dcl6w5ut5v</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243217</td>\n",
" <td>243216.0</td>\n",
" <td>2014-09-24 15:26:18+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162550 merged...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" <td>1411545535</td>\n",
" <td>PHID-USER-v7bwpq3rs3zdxegibdbh</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243218</td>\n",
" <td>243217.0</td>\n",
" <td>2014-09-24 07:58:55+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" <td>(In reply to Kunal Mehta (Legoktm) from commen...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>User with unattached accounts unable to login ...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" <td>1411542640</td>\n",
" <td>PHID-USER-ynivjflmc2dcl6w5ut5v</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-mio2uq45ny7mms72syut</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>243219</td>\n",
" <td>243218.0</td>\n",
" <td>2014-09-24 07:10:40+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" <td>**gerritadmin** wrote:\\n\\nChange 162549 merged...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>857</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" <td>1434207367</td>\n",
" <td>PHID-USER-lhtlnmkdbzlz6pbxaqdd</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406640</td>\n",
" <td>406639.0</td>\n",
" <td>2015-06-13 14:56:07+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" <td>I amended the title to the range IE8-10 becaus...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>858</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>1434140114</td>\n",
" <td>PHID-USER-wrimmmr5w2zt7nk2t753</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406641</td>\n",
" <td>406640.0</td>\n",
" <td>2015-06-12 20:15:14+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>859</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>1434116915</td>\n",
" <td>PHID-USER-wrimmmr5w2zt7nk2t753</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406642</td>\n",
" <td>406641.0</td>\n",
" <td>2015-06-12 13:48:35+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" <td>If I remember correctly this problem was at le...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>860</th>\n",
" <td>text input history/autocomplete doesn't work w...</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" <td>1434114623</td>\n",
" <td>PHID-USER-sx63fwaih5kjt7bz4u6z</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-onqydqsd354curr7z7mb</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406643</td>\n",
" <td>406642.0</td>\n",
" <td>2015-06-12 13:10:23+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" <td>After a quick test, autocomplete seems to work...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>861</th>\n",
" <td>Allow login using mosh as an alternative to pl...</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" <td>1413537437</td>\n",
" <td>PHID-USER-2nnm76h4ykalvvref2ye</td>\n",
" <td>False</td>\n",
" <td>PHID-TASK-hnwvtmwgpm2oisoqaozt</td>\n",
" <td>task_subcomment</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>406877</td>\n",
" <td>406876.0</td>\n",
" <td>2014-10-17 09:17:17+00:00</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" <td>Still not merged, so we can't really do much.</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>14490 rows × 16 columns</p>\n",
"</div>"
],
"text/plain": [
" task_title \\\n",
"0 User with unattached accounts unable to login ... \n",
"1 User with unattached accounts unable to login ... \n",
"2 User with unattached accounts unable to login ... \n",
"3 User with unattached accounts unable to login ... \n",
"4 User with unattached accounts unable to login ... \n",
".. ... \n",
"857 text input history/autocomplete doesn't work w... \n",
"858 text input history/autocomplete doesn't work w... \n",
"859 text input history/autocomplete doesn't work w... \n",
"860 text input history/autocomplete doesn't work w... \n",
"861 Allow login using mosh as an alternative to pl... \n",
"\n",
" comment_text date_created \\\n",
"0 User:NickK reported in IRC that they're gettin... 1411541280 \n",
"1 Revert has been deployed. 1411573104 \n",
"2 **gerritadmin** wrote:\\n\\nChange 162550 merged... 1411572378 \n",
"3 (In reply to Kunal Mehta (Legoktm) from commen... 1411545535 \n",
"4 **gerritadmin** wrote:\\n\\nChange 162549 merged... 1411542640 \n",
".. ... ... \n",
"857 I amended the title to the range IE8-10 becaus... 1434207367 \n",
"858 If I remember correctly this problem was at le... 1434140114 \n",
"859 If I remember correctly this problem was at le... 1434116915 \n",
"860 After a quick test, autocomplete seems to work... 1434114623 \n",
"861 Still not merged, so we can't really do much. 1413537437 \n",
"\n",
" speaker meta.affil \\\n",
"0 PHID-USER-v7vgzvvcw7v2umf737ri False \n",
"1 PHID-USER-v7vgzvvcw7v2umf737ri False \n",
"2 PHID-USER-ynivjflmc2dcl6w5ut5v False \n",
"3 PHID-USER-v7bwpq3rs3zdxegibdbh False \n",
"4 PHID-USER-ynivjflmc2dcl6w5ut5v False \n",
".. ... ... \n",
"857 PHID-USER-lhtlnmkdbzlz6pbxaqdd False \n",
"858 PHID-USER-wrimmmr5w2zt7nk2t753 False \n",
"859 PHID-USER-wrimmmr5w2zt7nk2t753 False \n",
"860 PHID-USER-sx63fwaih5kjt7bz4u6z False \n",
"861 PHID-USER-2nnm76h4ykalvvref2ye False \n",
"\n",
" conversation_id comment_type status meta.gerrit \\\n",
"0 PHID-TASK-mio2uq45ny7mms72syut task_description resolved False \n",
"1 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN False \n",
"2 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN False \n",
"3 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN False \n",
"4 PHID-TASK-mio2uq45ny7mms72syut task_subcomment NaN False \n",
".. ... ... ... ... \n",
"857 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"858 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"859 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"860 PHID-TASK-onqydqsd354curr7z7mb task_subcomment NaN False \n",
"861 PHID-TASK-hnwvtmwgpm2oisoqaozt task_subcomment NaN False \n",
"\n",
" id reply_to timestamp is_relevant is_migrated \\\n",
"0 243215 NaN 2014-09-24 06:48:00+00:00 True False \n",
"1 243216 243215.0 2014-09-24 15:38:24+00:00 True False \n",
"2 243217 243216.0 2014-09-24 15:26:18+00:00 True False \n",
"3 243218 243217.0 2014-09-24 07:58:55+00:00 True False \n",
"4 243219 243218.0 2014-09-24 07:10:40+00:00 True False \n",
".. ... ... ... ... ... \n",
"857 406640 406639.0 2015-06-13 14:56:07+00:00 True False \n",
"858 406641 406640.0 2015-06-12 20:15:14+00:00 True False \n",
"859 406642 406641.0 2015-06-12 13:48:35+00:00 True False \n",
"860 406643 406642.0 2015-06-12 13:10:23+00:00 True False \n",
"861 406877 406876.0 2014-10-17 09:17:17+00:00 True False \n",
"\n",
" text \\\n",
"0 User:NickK reported in IRC that they're gettin... \n",
"1 Revert has been deployed. \n",
"2 **gerritadmin** wrote:\\n\\nChange 162550 merged... \n",
"3 (In reply to Kunal Mehta (Legoktm) from commen... \n",
"4 **gerritadmin** wrote:\\n\\nChange 162549 merged... \n",
".. ... \n",
"857 I amended the title to the range IE8-10 becaus... \n",
"858 If I remember correctly this problem was at le... \n",
"859 If I remember correctly this problem was at le... \n",
"860 After a quick test, autocomplete seems to work... \n",
"861 Still not merged, so we can't really do much. \n",
"\n",
" resolved_text \n",
"0 User:NickK reported in IRC that they're gettin... \n",
"1 Revert has been deployed. \n",
"2 **gerritadmin** wrote:\\n\\nChange 162550 merged... \n",
"3 (In reply to Kunal Mehta (Legoktm) from commen... \n",
"4 **gerritadmin** wrote:\\n\\nChange 162549 merged... \n",
".. ... \n",
"857 I amended the title to the range IE8-10 becaus... \n",
"858 If I remember correctly this problem was at le... \n",
"859 If I remember correctly this problem was at le... \n",
"860 After a quick test, autocomplete seems to work... \n",
"861 Still not merged, so we can't really do much. \n",
"\n",
"[14490 rows x 16 columns]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"unique_df"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "0c392d70-6236-4dfe-b6d4-bbe3f422b09e",
"metadata": {},
"outputs": [],
"source": [
"unique_df.to_csv(\"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/050825_coref-rel-final.csv\", index=False)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
View Git Blame Copy Permalink