{ "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/case3/051725_coref_rel_phab_comments_to_2014.csv\"\n", "first_resolved_df = pd.read_csv(first_resolved_path)\n", "second_resolved_path = \"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/051725_coref_rel_phab_comments_2014_to_2015.csv\"\n", "second_resolved_df = pd.read_csv(second_resolved_path)" ] }, { "cell_type": "code", "execution_count": 3, "id": "f26c31e7-bee1-4100-821f-769e5b1791bd", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "8621" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(second_resolved_df)" ] }, { "cell_type": "code", "execution_count": 4, "id": "dfa81ca2-4d66-4679-bc3e-192d0cac67fa", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "5007" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(first_resolved_df)" ] }, { "cell_type": "code", "execution_count": 5, "id": "6dc11bda-f0f6-4eb6-96f5-02ed9a3492ba", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "13628" ] }, "execution_count": 5, "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": 6, "id": "0c903199-8159-455c-aa7f-e57ef07ce03e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | task_title | \n", "comment_text | \n", "date_created | \n", "speaker | \n", "meta.affil | \n", "conversation_id | \n", "comment_type | \n", "status | \n", "meta.gerrit | \n", "id | \n", "reply_to | \n", "timestamp | \n", "is_relevant | \n", "is_migrated | \n", "text | \n", "resolved_text | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "User with unattached accounts unable to login ... | \n", "User:NickK reported in IRC that they're gettin... | \n", "1411541280 | \n", "PHID-USER-v7vgzvvcw7v2umf737ri | \n", "False | \n", "PHID-TASK-mio2uq45ny7mms72syut | \n", "task_description | \n", "resolved | \n", "False | \n", "243215 | \n", "NaN | \n", "2014-09-24 06:48:00+00:00 | \n", "True | \n", "False | \n", "User:NickK reported in IRC that they're gettin... | \n", "User:NickK reported in IRC that they're gettin... | \n", "
1 | \n", "User with unattached accounts unable to login ... | \n", "Revert has been deployed. | \n", "1411573104 | \n", "PHID-USER-v7vgzvvcw7v2umf737ri | \n", "False | \n", "PHID-TASK-mio2uq45ny7mms72syut | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "243216 | \n", "243215.0 | \n", "2014-09-24 15:38:24+00:00 | \n", "True | \n", "False | \n", "Revert has been deployed. | \n", "Revert has been deployed. | \n", "
2 | \n", "User with unattached accounts unable to login ... | \n", "**gerritadmin** wrote:\\n\\nChange 162550 merged... | \n", "1411572378 | \n", "PHID-USER-ynivjflmc2dcl6w5ut5v | \n", "False | \n", "PHID-TASK-mio2uq45ny7mms72syut | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "243217 | \n", "243216.0 | \n", "2014-09-24 15:26:18+00:00 | \n", "True | \n", "False | \n", "**gerritadmin** wrote:\\n\\nChange 162550 merged... | \n", "**gerritadmin** wrote:\\n\\nChange 162550 merged... | \n", "
3 | \n", "User with unattached accounts unable to login ... | \n", "(In reply to Kunal Mehta (Legoktm) from commen... | \n", "1411545535 | \n", "PHID-USER-v7bwpq3rs3zdxegibdbh | \n", "False | \n", "PHID-TASK-mio2uq45ny7mms72syut | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "243218 | \n", "243217.0 | \n", "2014-09-24 07:58:55+00:00 | \n", "True | \n", "False | \n", "(In reply to Kunal Mehta (Legoktm) from commen... | \n", "(In reply to Kunal Mehta (Legoktm) from commen... | \n", "
4 | \n", "User with unattached accounts unable to login ... | \n", "**gerritadmin** wrote:\\n\\nChange 162549 merged... | \n", "1411542640 | \n", "PHID-USER-ynivjflmc2dcl6w5ut5v | \n", "False | \n", "PHID-TASK-mio2uq45ny7mms72syut | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "243219 | \n", "243218.0 | \n", "2014-09-24 07:10:40+00:00 | \n", "True | \n", "False | \n", "**gerritadmin** wrote:\\n\\nChange 162549 merged... | \n", "**gerritadmin** wrote:\\n\\nChange 162549 merged... | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
8616 | \n", "OAuth login refers to mediawiki.org:/ instead ... | \n", "> When I registered, phabricator linked mediaw... | \n", "1413205650 | \n", "PHID-USER-hgn5uw2jafgjgfvxibhh | \n", "False | \n", "PHID-TASK-yeaxsfxhhtbn26koo5fi | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "378799 | \n", "378798.0 | \n", "2014-10-13 13:07:30+00:00 | \n", "True | \n", "False | \n", "> When I registered, phabricator linked mediaw... | \n", "> When I registered, phabricator linked mediaw... | \n", "
8617 | \n", "OAuth login refers to mediawiki.org:/ instead ... | \n", "See {T574} for a related discussion. | \n", "1412958953 | \n", "PHID-USER-lluzkul4z7us4sxkayss | \n", "False | \n", "PHID-TASK-yeaxsfxhhtbn26koo5fi | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "378800 | \n", "378799.0 | \n", "2014-10-10 16:35:53+00:00 | \n", "True | \n", "False | \n", "See {T574} for a related discussion. | \n", "See {T574} for a related discussion. | \n", "
8618 | \n", "Improvements to Wikimedia SUL login dialog UI:... | \n", "Some improvements to the Wikimedia SUL dialog:... | \n", "1412362816 | \n", "PHID-USER-lluzkul4z7us4sxkayss | \n", "False | \n", "PHID-TASK-j6czqxlv5fzcx3tmq23n | \n", "task_description | \n", "declined | \n", "False | \n", "378858 | \n", "NaN | \n", "2014-10-03 19:00:16+00:00 | \n", "True | \n", "False | \n", "Some improvements to the Wikimedia SUL dialog:... | \n", "Some improvements to the Wikimedia SUL dialog:... | \n", "
8619 | \n", "Improvements to Wikimedia SUL login dialog UI:... | \n", "I guess the same restrictions as in T543 apply... | \n", "1412415111 | \n", "PHID-USER-lluzkul4z7us4sxkayss | \n", "False | \n", "PHID-TASK-j6czqxlv5fzcx3tmq23n | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "378860 | \n", "378859.0 | \n", "2014-10-04 09:31:51+00:00 | \n", "True | \n", "False | \n", "I guess the same restrictions as in T543 apply... | \n", "I guess the same restrictions as in T543 apply... | \n", "
8620 | \n", "Improvements to Wikimedia SUL login dialog UI:... | \n", "It's not entirely trivial to change | \n", "1412366627 | \n", "PHID-USER-fn7qnpccfbitivgtw2rt | \n", "False | \n", "PHID-TASK-j6czqxlv5fzcx3tmq23n | \n", "task_subcomment | \n", "NaN | \n", "False | \n", "378861 | \n", "378860.0 | \n", "2014-10-03 20:03:47+00:00 | \n", "True | \n", "False | \n", "It's not entirely trivial to change | \n", "It's not entirely trivial to change | \n", "
13628 rows × 16 columns
\n", "