mgaughan/mw-convo-collections
1
0
Fork 0
Code

misc updates to phabricator cleaning script

Browse Source
This commit is contained in:
Matthew Gaughan 2025-06-03 16:47:33 -05:00
parent 2fd205a7bb
commit 21ce4f7854
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
data_cleaning/cleaning_phabricator.ipynb
View File

@ -12,22 +12,22 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"18152"
"4583"
]
},
"execution_count": 20,
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fp =\"/data/users/mgaughan/mw-repo-lifecycles/phab_data/http_phab_data/http_09-01-2013_12-01-2014_phab_data.json\"\n",
"fp =\"/data/users/mgaughan/mw-repo-lifecycles/phab_data/visualeditor/2012_1_1_to_2014_12_31.json\"\n",
"with open(fp, 'r') as file:\n",
" data1 = json.load(file)\n",
"len(data1)"
@ -104,11 +104,11 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"data_list = [data1, data3, data4]"
"#data_list = [data1, data3, data4]"
]
},
{
@ -21943,7 +21943,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
@ -22077,29 +22077,29 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"generate_csv(data, \"0402_https2_phab_comments.csv\")"
"generate_csv(data1, \"060325_c1_ve_phab_comments.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 25,
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Minimum date_created: 1378012620\n",
"Maximum date_created: 1745047564\n"
"Minimum date_created: 1325581020\n",
"Maximum date_created: 1735855955\n"
]
}
],
"source": [
"df = pd.read_csv('060325_c3_http_phab_comments.csv')\n",
"df = pd.read_csv('060325_c1_ve_phab_comments.csv')\n",
"# Convert the 'date_created' column to datetime format\n",
"\n",
"# Get the minimum and maximum date_created values\n",