{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"papermill": {
"duration": 0.717985,
"end_time": "2019-08-01T17:02:19.271138",
"exception": false,
"start_time": "2019-08-01T17:02:18.553153",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import altair as alt\n",
"\n",
"from datetime import timedelta\n",
"import pytz\n",
"\n",
"import sys\n",
"sys.path.append('../')\n",
"from mod import load_data, alt_theme"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"papermill": {
"duration": 2.901151,
"end_time": "2019-08-01T17:02:22.184707",
"exception": false,
"start_time": "2019-08-01T17:02:19.283556",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"comments, issues, prs = load_data('../../data/')\n",
"bot_names = pd.read_csv('../bot_names.csv')\n",
"comments = comments.query('author not in @bot_names')\n",
"issues = issues.query('author not in @bot_names')\n",
"prs = prs.query('author not in @bot_names')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"papermill": {
"duration": 0.028441,
"end_time": "2019-08-01T17:02:22.226844",
"exception": false,
"start_time": "2019-08-01T17:02:22.198403",
"status": "completed"
},
"tags": [
"parameters"
]
},
"outputs": [],
"source": [
"renderer = \"jupyterlab\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"papermill": {
"duration": 0.022358,
"end_time": "2019-08-01T17:02:22.261871",
"exception": false,
"start_time": "2019-08-01T17:02:22.239513",
"status": "completed"
},
"tags": [
"injected-parameters"
]
},
"outputs": [],
"source": [
"# Parameters\n",
"renderer = \"kaggle\"\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"papermill": {
"duration": 0.030317,
"end_time": "2019-08-01T17:02:22.305717",
"exception": false,
"start_time": "2019-08-01T17:02:22.275400",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"ThemeRegistry.enable('my_theme')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"alt.renderers.enable(renderer);\n",
"alt.themes.register('my_theme', alt_theme)\n",
"alt.themes.enable(\"my_theme\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"papermill": {
"duration": 0.494666,
"end_time": "2019-08-01T17:02:22.814065",
"exception": false,
"start_time": "2019-08-01T17:02:22.319399",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"use_data = prs # comments\n",
"seen_times = use_data.groupby(['org', 'author']).agg({'updatedAt': ['min', 'max']})['updatedAt']"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"papermill": {
"duration": 0.038162,
"end_time": "2019-08-01T17:02:22.863528",
"exception": false,
"start_time": "2019-08-01T17:02:22.825366",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"seen_times = seen_times.rename(columns={'min': 'first_seen', 'max': 'last_seen'})\n",
"for col in seen_times.columns:\n",
" seen_times[col] = pd.to_datetime(seen_times[col], utc=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"papermill": {
"duration": 0.538181,
"end_time": "2019-08-01T17:02:23.413123",
"exception": false,
"start_time": "2019-08-01T17:02:22.874942",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/choldgraf/anaconda/envs/dev/lib/python3.6/site-packages/ipykernel_launcher.py:9: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
" if __name__ == '__main__':\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
"HConcatChart({\n",
" hconcat: [Chart({\n",
" data: date kind count date_name\n",
" 0 2017-10-31 00:00:00+00:00 first_seen 3 2017-10\n",
" 1 2017-11-30 00:00:00+00:00 first_seen 2 2017-11\n",
" 2 2017-12-31 00:00:00+00:00 first_seen 0 2017-12\n",
" 3 2018-01-31 00:00:00+00:00 first_seen 0 2018-01\n",
" 4 2018-02-28 00:00:00+00:00 first_seen 1 2018-02\n",
" 5 2018-03-31 00:00:00+00:00 first_seen 0 2018-03\n",
" 6 2018-04-30 00:00:00+00:00 first_seen 0 2018-04\n",
" 7 2018-05-31 00:00:00+00:00 first_seen 0 2018-05\n",
" 8 2018-06-30 00:00:00+00:00 first_seen 0 2018-06\n",
" 9 2018-07-31 00:00:00+00:00 first_seen 1 2018-07\n",
" 10 2018-08-31 00:00:00+00:00 first_seen 2 2018-08\n",
" 11 2018-09-30 00:00:00+00:00 first_seen 2 2018-09\n",
" 12 2018-10-31 00:00:00+00:00 first_seen 4 2018-10\n",
" 13 2018-11-30 00:00:00+00:00 first_seen 2 2018-11\n",
" 14 2018-12-31 00:00:00+00:00 first_seen 1 2018-12\n",
" 15 2019-01-31 00:00:00+00:00 first_seen 0 2019-01\n",
" 16 2019-02-28 00:00:00+00:00 first_seen 2 2019-02\n",
" 17 2019-03-31 00:00:00+00:00 first_seen 3 2019-03\n",
" 18 2019-04-30 00:00:00+00:00 first_seen 0 2019-04\n",
" 19 2019-05-31 00:00:00+00:00 first_seen 4 2019-05\n",
" 20 2017-10-31 00:00:00+00:00 seen_recently False 2017-10\n",
" 21 2017-11-30 00:00:00+00:00 seen_recently False 2017-11\n",
" 22 2017-12-31 00:00:00+00:00 seen_recently False 2017-12\n",
" 23 2018-01-31 00:00:00+00:00 seen_recently False 2018-01\n",
" 24 2018-02-28 00:00:00+00:00 seen_recently False 2018-02\n",
" 25 2018-03-31 00:00:00+00:00 seen_recently False 2018-03\n",
" 26 2018-04-30 00:00:00+00:00 seen_recently False 2018-04\n",
" 27 2018-05-31 00:00:00+00:00 seen_recently False 2018-05\n",
" 28 2018-06-30 00:00:00+00:00 seen_recently False 2018-06\n",
" 29 2018-07-31 00:00:00+00:00 seen_recently False 2018-07\n",
" 30 2018-08-31 00:00:00+00:00 seen_recently False 2018-08\n",
" 31 2018-09-30 00:00:00+00:00 seen_recently True 2018-09\n",
" 32 2018-10-31 00:00:00+00:00 seen_recently False 2018-10\n",
" 33 2018-11-30 00:00:00+00:00 seen_recently False 2018-11\n",
" 34 2018-12-31 00:00:00+00:00 seen_recently False 2018-12\n",
" 35 2019-01-31 00:00:00+00:00 seen_recently False 2019-01\n",
" 36 2019-02-28 00:00:00+00:00 seen_recently False 2019-02\n",
" 37 2019-03-31 00:00:00+00:00 seen_recently False 2019-03\n",
" 38 2019-04-30 00:00:00+00:00 seen_recently False 2019-04\n",
" 39 2019-05-31 00:00:00+00:00 seen_recently False 2019-05,\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'binder-examples'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2015-01-31 00:00:00+00:00 first_seen 27.0 2015-01\n",
" 1 2015-02-28 00:00:00+00:00 first_seen 11.0 2015-02\n",
" 2 2015-03-31 00:00:00+00:00 first_seen 30.0 2015-03\n",
" 3 2015-04-30 00:00:00+00:00 first_seen 6.0 2015-04\n",
" 4 2015-05-31 00:00:00+00:00 first_seen 4.0 2015-05\n",
" 5 2015-06-30 00:00:00+00:00 first_seen 6.0 2015-06\n",
" 6 2015-07-31 00:00:00+00:00 first_seen 9.0 2015-07\n",
" 7 2015-08-31 00:00:00+00:00 first_seen 25.0 2015-08\n",
" 8 2015-09-30 00:00:00+00:00 first_seen 11.0 2015-09\n",
" 9 2015-10-31 00:00:00+00:00 first_seen 15.0 2015-10\n",
" 10 2015-11-30 00:00:00+00:00 first_seen 10.0 2015-11\n",
" 11 2015-12-31 00:00:00+00:00 first_seen 7.0 2015-12\n",
" 12 2016-01-31 00:00:00+00:00 first_seen 8.0 2016-01\n",
" 13 2016-02-29 00:00:00+00:00 first_seen 8.0 2016-02\n",
" 14 2016-03-31 00:00:00+00:00 first_seen 6.0 2016-03\n",
" 15 2016-04-30 00:00:00+00:00 first_seen 11.0 2016-04\n",
" 16 2016-05-31 00:00:00+00:00 first_seen 8.0 2016-05\n",
" 17 2016-06-30 00:00:00+00:00 first_seen 8.0 2016-06\n",
" 18 2016-07-31 00:00:00+00:00 first_seen 6.0 2016-07\n",
" 19 2016-08-31 00:00:00+00:00 first_seen 17.0 2016-08\n",
" 20 2016-09-30 00:00:00+00:00 first_seen 9.0 2016-09\n",
" 21 2016-10-31 00:00:00+00:00 first_seen 8.0 2016-10\n",
" 22 2016-11-30 00:00:00+00:00 first_seen 8.0 2016-11\n",
" 23 2016-12-31 00:00:00+00:00 first_seen 6.0 2016-12\n",
" 24 2017-01-31 00:00:00+00:00 first_seen 6.0 2017-01\n",
" 25 2017-02-28 00:00:00+00:00 first_seen 4.0 2017-02\n",
" 26 2017-03-31 00:00:00+00:00 first_seen 8.0 2017-03\n",
" 27 2017-04-30 00:00:00+00:00 first_seen 5.0 2017-04\n",
" 28 2017-05-31 00:00:00+00:00 first_seen 23.0 2017-05\n",
" 29 2017-06-30 00:00:00+00:00 first_seen 7.0 2017-06\n",
" .. ... ... ... ...\n",
" 82 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 83 2017-04-30 00:00:00+00:00 seen_recently 0.0 2017-04\n",
" 84 2017-05-31 00:00:00+00:00 seen_recently 0.0 2017-05\n",
" 85 2017-06-30 00:00:00+00:00 seen_recently 1.0 2017-06\n",
" 86 2017-07-31 00:00:00+00:00 seen_recently 0.0 2017-07\n",
" 87 2017-08-31 00:00:00+00:00 seen_recently 0.0 2017-08\n",
" 88 2017-09-30 00:00:00+00:00 seen_recently 0.0 2017-09\n",
" 89 2017-10-31 00:00:00+00:00 seen_recently 0.0 2017-10\n",
" 90 2017-11-30 00:00:00+00:00 seen_recently 1.0 2017-11\n",
" 91 2017-12-31 00:00:00+00:00 seen_recently 0.0 2017-12\n",
" 92 2018-01-31 00:00:00+00:00 seen_recently 0.0 2018-01\n",
" 93 2018-02-28 00:00:00+00:00 seen_recently 0.0 2018-02\n",
" 94 2018-03-31 00:00:00+00:00 seen_recently 0.0 2018-03\n",
" 95 2018-04-30 00:00:00+00:00 seen_recently 0.0 2018-04\n",
" 96 2018-05-31 00:00:00+00:00 seen_recently 1.0 2018-05\n",
" 97 2018-06-30 00:00:00+00:00 seen_recently 1.0 2018-06\n",
" 98 2018-07-31 00:00:00+00:00 seen_recently 1.0 2018-07\n",
" 99 2018-08-31 00:00:00+00:00 seen_recently 0.0 2018-08\n",
" 100 2018-09-30 00:00:00+00:00 seen_recently 0.0 2018-09\n",
" 101 2018-10-31 00:00:00+00:00 seen_recently 1.0 2018-10\n",
" 102 2018-11-30 00:00:00+00:00 seen_recently 0.0 2018-11\n",
" 103 2018-12-31 00:00:00+00:00 seen_recently 0.0 2018-12\n",
" 104 2019-01-31 00:00:00+00:00 seen_recently 1.0 2019-01\n",
" 105 2019-02-28 00:00:00+00:00 seen_recently 0.0 2019-02\n",
" 106 2019-03-31 00:00:00+00:00 seen_recently 0.0 2019-03\n",
" 107 2019-04-30 00:00:00+00:00 seen_recently 0.0 2019-04\n",
" 108 2019-05-31 00:00:00+00:00 seen_recently 1.0 2019-05\n",
" 109 2019-06-30 00:00:00+00:00 seen_recently 1.0 2019-06\n",
" 110 2019-07-31 00:00:00+00:00 seen_recently 11.0 2019-07\n",
" 111 2019-08-31 00:00:00+00:00 seen_recently 1.0 2019-08\n",
" \n",
" [112 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'ipython'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2015-01-31 00:00:00+00:00 first_seen 8.0 2015-01\n",
" 1 2015-02-28 00:00:00+00:00 first_seen 8.0 2015-02\n",
" 2 2015-03-31 00:00:00+00:00 first_seen 2.0 2015-03\n",
" 3 2015-04-30 00:00:00+00:00 first_seen 11.0 2015-04\n",
" 4 2015-05-31 00:00:00+00:00 first_seen 12.0 2015-05\n",
" 5 2015-06-30 00:00:00+00:00 first_seen 9.0 2015-06\n",
" 6 2015-07-31 00:00:00+00:00 first_seen 19.0 2015-07\n",
" 7 2015-08-31 00:00:00+00:00 first_seen 17.0 2015-08\n",
" 8 2015-09-30 00:00:00+00:00 first_seen 22.0 2015-09\n",
" 9 2015-10-31 00:00:00+00:00 first_seen 32.0 2015-10\n",
" 10 2015-11-30 00:00:00+00:00 first_seen 13.0 2015-11\n",
" 11 2015-12-31 00:00:00+00:00 first_seen 26.0 2015-12\n",
" 12 2016-01-31 00:00:00+00:00 first_seen 21.0 2016-01\n",
" 13 2016-02-29 00:00:00+00:00 first_seen 25.0 2016-02\n",
" 14 2016-03-31 00:00:00+00:00 first_seen 15.0 2016-03\n",
" 15 2016-04-30 00:00:00+00:00 first_seen 18.0 2016-04\n",
" 16 2016-05-31 00:00:00+00:00 first_seen 14.0 2016-05\n",
" 17 2016-06-30 00:00:00+00:00 first_seen 15.0 2016-06\n",
" 18 2016-07-31 00:00:00+00:00 first_seen 11.0 2016-07\n",
" 19 2016-08-31 00:00:00+00:00 first_seen 11.0 2016-08\n",
" 20 2016-09-30 00:00:00+00:00 first_seen 17.0 2016-09\n",
" 21 2016-10-31 00:00:00+00:00 first_seen 7.0 2016-10\n",
" 22 2016-11-30 00:00:00+00:00 first_seen 9.0 2016-11\n",
" 23 2016-12-31 00:00:00+00:00 first_seen 24.0 2016-12\n",
" 24 2017-01-31 00:00:00+00:00 first_seen 24.0 2017-01\n",
" 25 2017-02-28 00:00:00+00:00 first_seen 21.0 2017-02\n",
" 26 2017-03-31 00:00:00+00:00 first_seen 14.0 2017-03\n",
" 27 2017-04-30 00:00:00+00:00 first_seen 12.0 2017-04\n",
" 28 2017-05-31 00:00:00+00:00 first_seen 14.0 2017-05\n",
" 29 2017-06-30 00:00:00+00:00 first_seen 14.0 2017-06\n",
" .. ... ... ... ...\n",
" 80 2017-02-28 00:00:00+00:00 seen_recently 0.0 2017-02\n",
" 81 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 82 2017-04-30 00:00:00+00:00 seen_recently 1.0 2017-04\n",
" 83 2017-05-31 00:00:00+00:00 seen_recently 0.0 2017-05\n",
" 84 2017-06-30 00:00:00+00:00 seen_recently 0.0 2017-06\n",
" 85 2017-07-31 00:00:00+00:00 seen_recently 1.0 2017-07\n",
" 86 2017-08-31 00:00:00+00:00 seen_recently 2.0 2017-08\n",
" 87 2017-09-30 00:00:00+00:00 seen_recently 1.0 2017-09\n",
" 88 2017-10-31 00:00:00+00:00 seen_recently 3.0 2017-10\n",
" 89 2017-11-30 00:00:00+00:00 seen_recently 1.0 2017-11\n",
" 90 2017-12-31 00:00:00+00:00 seen_recently 0.0 2017-12\n",
" 91 2018-01-31 00:00:00+00:00 seen_recently 0.0 2018-01\n",
" 92 2018-02-28 00:00:00+00:00 seen_recently 2.0 2018-02\n",
" 93 2018-03-31 00:00:00+00:00 seen_recently 2.0 2018-03\n",
" 94 2018-04-30 00:00:00+00:00 seen_recently 0.0 2018-04\n",
" 95 2018-05-31 00:00:00+00:00 seen_recently 1.0 2018-05\n",
" 96 2018-06-30 00:00:00+00:00 seen_recently 0.0 2018-06\n",
" 97 2018-07-31 00:00:00+00:00 seen_recently 1.0 2018-07\n",
" 98 2018-08-31 00:00:00+00:00 seen_recently 1.0 2018-08\n",
" 99 2018-09-30 00:00:00+00:00 seen_recently 0.0 2018-09\n",
" 100 2018-10-31 00:00:00+00:00 seen_recently 1.0 2018-10\n",
" 101 2018-11-30 00:00:00+00:00 seen_recently 0.0 2018-11\n",
" 102 2018-12-31 00:00:00+00:00 seen_recently 1.0 2018-12\n",
" 103 2019-01-31 00:00:00+00:00 seen_recently 0.0 2019-01\n",
" 104 2019-02-28 00:00:00+00:00 seen_recently 1.0 2019-02\n",
" 105 2019-03-31 00:00:00+00:00 seen_recently 1.0 2019-03\n",
" 106 2019-04-30 00:00:00+00:00 seen_recently 3.0 2019-04\n",
" 107 2019-05-31 00:00:00+00:00 seen_recently 4.0 2019-05\n",
" 108 2019-06-30 00:00:00+00:00 seen_recently 6.0 2019-06\n",
" 109 2019-07-31 00:00:00+00:00 seen_recently 38.0 2019-07\n",
" \n",
" [110 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'jupyter'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2015-05-31 00:00:00+00:00 first_seen 4.0 2015-05\n",
" 1 2015-06-30 00:00:00+00:00 first_seen 1.0 2015-06\n",
" 2 2015-07-31 00:00:00+00:00 first_seen 1.0 2015-07\n",
" 3 2015-08-31 00:00:00+00:00 first_seen 4.0 2015-08\n",
" 4 2015-09-30 00:00:00+00:00 first_seen 2.0 2015-09\n",
" 5 2015-10-31 00:00:00+00:00 first_seen 4.0 2015-10\n",
" 6 2015-11-30 00:00:00+00:00 first_seen 1.0 2015-11\n",
" 7 2015-12-31 00:00:00+00:00 first_seen 1.0 2015-12\n",
" 8 2016-01-31 00:00:00+00:00 first_seen 6.0 2016-01\n",
" 9 2016-02-29 00:00:00+00:00 first_seen 1.0 2016-02\n",
" 10 2016-03-31 00:00:00+00:00 first_seen 2.0 2016-03\n",
" 11 2016-04-30 00:00:00+00:00 first_seen 3.0 2016-04\n",
" 12 2016-05-31 00:00:00+00:00 first_seen 2.0 2016-05\n",
" 13 2016-06-30 00:00:00+00:00 first_seen 0.0 2016-06\n",
" 14 2016-07-31 00:00:00+00:00 first_seen 1.0 2016-07\n",
" 15 2016-08-31 00:00:00+00:00 first_seen 0.0 2016-08\n",
" 16 2016-09-30 00:00:00+00:00 first_seen 3.0 2016-09\n",
" 17 2016-10-31 00:00:00+00:00 first_seen 2.0 2016-10\n",
" 18 2016-11-30 00:00:00+00:00 first_seen 0.0 2016-11\n",
" 19 2016-12-31 00:00:00+00:00 first_seen 0.0 2016-12\n",
" 20 2017-01-31 00:00:00+00:00 first_seen 0.0 2017-01\n",
" 21 2017-02-28 00:00:00+00:00 first_seen 12.0 2017-02\n",
" 22 2017-03-31 00:00:00+00:00 first_seen 0.0 2017-03\n",
" 23 2017-04-30 00:00:00+00:00 first_seen 3.0 2017-04\n",
" 24 2017-05-31 00:00:00+00:00 first_seen 4.0 2017-05\n",
" 25 2017-06-30 00:00:00+00:00 first_seen 2.0 2017-06\n",
" 26 2017-07-31 00:00:00+00:00 first_seen 0.0 2017-07\n",
" 27 2017-08-31 00:00:00+00:00 first_seen 5.0 2017-08\n",
" 28 2017-09-30 00:00:00+00:00 first_seen 2.0 2017-09\n",
" 29 2017-10-31 00:00:00+00:00 first_seen 5.0 2017-10\n",
" .. ... ... ... ...\n",
" 72 2017-02-28 00:00:00+00:00 seen_recently 3.0 2017-02\n",
" 73 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 74 2017-04-30 00:00:00+00:00 seen_recently 0.0 2017-04\n",
" 75 2017-05-31 00:00:00+00:00 seen_recently 0.0 2017-05\n",
" 76 2017-06-30 00:00:00+00:00 seen_recently 1.0 2017-06\n",
" 77 2017-07-31 00:00:00+00:00 seen_recently 0.0 2017-07\n",
" 78 2017-08-31 00:00:00+00:00 seen_recently 0.0 2017-08\n",
" 79 2017-09-30 00:00:00+00:00 seen_recently 0.0 2017-09\n",
" 80 2017-10-31 00:00:00+00:00 seen_recently 0.0 2017-10\n",
" 81 2017-11-30 00:00:00+00:00 seen_recently 0.0 2017-11\n",
" 82 2017-12-31 00:00:00+00:00 seen_recently 0.0 2017-12\n",
" 83 2018-01-31 00:00:00+00:00 seen_recently 0.0 2018-01\n",
" 84 2018-02-28 00:00:00+00:00 seen_recently 1.0 2018-02\n",
" 85 2018-03-31 00:00:00+00:00 seen_recently 0.0 2018-03\n",
" 86 2018-04-30 00:00:00+00:00 seen_recently 0.0 2018-04\n",
" 87 2018-05-31 00:00:00+00:00 seen_recently 0.0 2018-05\n",
" 88 2018-06-30 00:00:00+00:00 seen_recently 0.0 2018-06\n",
" 89 2018-07-31 00:00:00+00:00 seen_recently 1.0 2018-07\n",
" 90 2018-08-31 00:00:00+00:00 seen_recently 0.0 2018-08\n",
" 91 2018-09-30 00:00:00+00:00 seen_recently 0.0 2018-09\n",
" 92 2018-10-31 00:00:00+00:00 seen_recently 0.0 2018-10\n",
" 93 2018-11-30 00:00:00+00:00 seen_recently 1.0 2018-11\n",
" 94 2018-12-31 00:00:00+00:00 seen_recently 1.0 2018-12\n",
" 95 2019-01-31 00:00:00+00:00 seen_recently 0.0 2019-01\n",
" 96 2019-02-28 00:00:00+00:00 seen_recently 0.0 2019-02\n",
" 97 2019-03-31 00:00:00+00:00 seen_recently 0.0 2019-03\n",
" 98 2019-04-30 00:00:00+00:00 seen_recently 0.0 2019-04\n",
" 99 2019-05-31 00:00:00+00:00 seen_recently 0.0 2019-05\n",
" 100 2019-06-30 00:00:00+00:00 seen_recently 2.0 2019-06\n",
" 101 2019-07-31 00:00:00+00:00 seen_recently 17.0 2019-07\n",
" \n",
" [102 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'jupyter-widgets'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2016-02-29 00:00:00+00:00 first_seen 1.0 2016-02\n",
" 1 2016-03-31 00:00:00+00:00 first_seen 1.0 2016-03\n",
" 2 2016-04-30 00:00:00+00:00 first_seen 59.0 2016-04\n",
" 3 2016-05-31 00:00:00+00:00 first_seen 4.0 2016-05\n",
" 4 2016-06-30 00:00:00+00:00 first_seen 4.0 2016-06\n",
" 5 2016-07-31 00:00:00+00:00 first_seen 4.0 2016-07\n",
" 6 2016-08-31 00:00:00+00:00 first_seen 5.0 2016-08\n",
" 7 2016-09-30 00:00:00+00:00 first_seen 5.0 2016-09\n",
" 8 2016-10-31 00:00:00+00:00 first_seen 5.0 2016-10\n",
" 9 2016-11-30 00:00:00+00:00 first_seen 16.0 2016-11\n",
" 10 2016-12-31 00:00:00+00:00 first_seen 3.0 2016-12\n",
" 11 2017-01-31 00:00:00+00:00 first_seen 8.0 2017-01\n",
" 12 2017-02-28 00:00:00+00:00 first_seen 3.0 2017-02\n",
" 13 2017-03-31 00:00:00+00:00 first_seen 5.0 2017-03\n",
" 14 2017-04-30 00:00:00+00:00 first_seen 10.0 2017-04\n",
" 15 2017-05-31 00:00:00+00:00 first_seen 13.0 2017-05\n",
" 16 2017-06-30 00:00:00+00:00 first_seen 5.0 2017-06\n",
" 17 2017-07-31 00:00:00+00:00 first_seen 11.0 2017-07\n",
" 18 2017-08-31 00:00:00+00:00 first_seen 27.0 2017-08\n",
" 19 2017-09-30 00:00:00+00:00 first_seen 11.0 2017-09\n",
" 20 2017-10-31 00:00:00+00:00 first_seen 14.0 2017-10\n",
" 21 2017-11-30 00:00:00+00:00 first_seen 19.0 2017-11\n",
" 22 2017-12-31 00:00:00+00:00 first_seen 16.0 2017-12\n",
" 23 2018-01-31 00:00:00+00:00 first_seen 8.0 2018-01\n",
" 24 2018-02-28 00:00:00+00:00 first_seen 13.0 2018-02\n",
" 25 2018-03-31 00:00:00+00:00 first_seen 19.0 2018-03\n",
" 26 2018-04-30 00:00:00+00:00 first_seen 17.0 2018-04\n",
" 27 2018-05-31 00:00:00+00:00 first_seen 17.0 2018-05\n",
" 28 2018-06-30 00:00:00+00:00 first_seen 17.0 2018-06\n",
" 29 2018-07-31 00:00:00+00:00 first_seen 18.0 2018-07\n",
" .. ... ... ... ...\n",
" 54 2017-02-28 00:00:00+00:00 seen_recently 0.0 2017-02\n",
" 55 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 56 2017-04-30 00:00:00+00:00 seen_recently 2.0 2017-04\n",
" 57 2017-05-31 00:00:00+00:00 seen_recently 1.0 2017-05\n",
" 58 2017-06-30 00:00:00+00:00 seen_recently 0.0 2017-06\n",
" 59 2017-07-31 00:00:00+00:00 seen_recently 1.0 2017-07\n",
" 60 2017-08-31 00:00:00+00:00 seen_recently 0.0 2017-08\n",
" 61 2017-09-30 00:00:00+00:00 seen_recently 0.0 2017-09\n",
" 62 2017-10-31 00:00:00+00:00 seen_recently 0.0 2017-10\n",
" 63 2017-11-30 00:00:00+00:00 seen_recently 0.0 2017-11\n",
" 64 2017-12-31 00:00:00+00:00 seen_recently 2.0 2017-12\n",
" 65 2018-01-31 00:00:00+00:00 seen_recently 1.0 2018-01\n",
" 66 2018-02-28 00:00:00+00:00 seen_recently 2.0 2018-02\n",
" 67 2018-03-31 00:00:00+00:00 seen_recently 1.0 2018-03\n",
" 68 2018-04-30 00:00:00+00:00 seen_recently 2.0 2018-04\n",
" 69 2018-05-31 00:00:00+00:00 seen_recently 0.0 2018-05\n",
" 70 2018-06-30 00:00:00+00:00 seen_recently 0.0 2018-06\n",
" 71 2018-07-31 00:00:00+00:00 seen_recently 1.0 2018-07\n",
" 72 2018-08-31 00:00:00+00:00 seen_recently 2.0 2018-08\n",
" 73 2018-09-30 00:00:00+00:00 seen_recently 1.0 2018-09\n",
" 74 2018-10-31 00:00:00+00:00 seen_recently 0.0 2018-10\n",
" 75 2018-11-30 00:00:00+00:00 seen_recently 1.0 2018-11\n",
" 76 2018-12-31 00:00:00+00:00 seen_recently 0.0 2018-12\n",
" 77 2019-01-31 00:00:00+00:00 seen_recently 2.0 2019-01\n",
" 78 2019-02-28 00:00:00+00:00 seen_recently 1.0 2019-02\n",
" 79 2019-03-31 00:00:00+00:00 seen_recently 1.0 2019-03\n",
" 80 2019-04-30 00:00:00+00:00 seen_recently 0.0 2019-04\n",
" 81 2019-05-31 00:00:00+00:00 seen_recently 2.0 2019-05\n",
" 82 2019-06-30 00:00:00+00:00 seen_recently 1.0 2019-06\n",
" 83 2019-07-31 00:00:00+00:00 seen_recently 27.0 2019-07\n",
" \n",
" [84 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'jupyterhub'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2016-06-30 00:00:00+00:00 first_seen 15.0 2016-06\n",
" 1 2016-07-31 00:00:00+00:00 first_seen 8.0 2016-07\n",
" 2 2016-08-31 00:00:00+00:00 first_seen 6.0 2016-08\n",
" 3 2016-09-30 00:00:00+00:00 first_seen 7.0 2016-09\n",
" 4 2016-10-31 00:00:00+00:00 first_seen 6.0 2016-10\n",
" 5 2016-11-30 00:00:00+00:00 first_seen 5.0 2016-11\n",
" 6 2016-12-31 00:00:00+00:00 first_seen 2.0 2016-12\n",
" 7 2017-01-31 00:00:00+00:00 first_seen 2.0 2017-01\n",
" 8 2017-02-28 00:00:00+00:00 first_seen 4.0 2017-02\n",
" 9 2017-03-31 00:00:00+00:00 first_seen 3.0 2017-03\n",
" 10 2017-04-30 00:00:00+00:00 first_seen 1.0 2017-04\n",
" 11 2017-05-31 00:00:00+00:00 first_seen 11.0 2017-05\n",
" 12 2017-06-30 00:00:00+00:00 first_seen 7.0 2017-06\n",
" 13 2017-07-31 00:00:00+00:00 first_seen 2.0 2017-07\n",
" 14 2017-08-31 00:00:00+00:00 first_seen 12.0 2017-08\n",
" 15 2017-09-30 00:00:00+00:00 first_seen 7.0 2017-09\n",
" 16 2017-10-31 00:00:00+00:00 first_seen 2.0 2017-10\n",
" 17 2017-11-30 00:00:00+00:00 first_seen 3.0 2017-11\n",
" 18 2017-12-31 00:00:00+00:00 first_seen 7.0 2017-12\n",
" 19 2018-01-31 00:00:00+00:00 first_seen 10.0 2018-01\n",
" 20 2018-02-28 00:00:00+00:00 first_seen 15.0 2018-02\n",
" 21 2018-03-31 00:00:00+00:00 first_seen 16.0 2018-03\n",
" 22 2018-04-30 00:00:00+00:00 first_seen 6.0 2018-04\n",
" 23 2018-05-31 00:00:00+00:00 first_seen 5.0 2018-05\n",
" 24 2018-06-30 00:00:00+00:00 first_seen 18.0 2018-06\n",
" 25 2018-07-31 00:00:00+00:00 first_seen 20.0 2018-07\n",
" 26 2018-08-31 00:00:00+00:00 first_seen 12.0 2018-08\n",
" 27 2018-09-30 00:00:00+00:00 first_seen 10.0 2018-09\n",
" 28 2018-10-31 00:00:00+00:00 first_seen 17.0 2018-10\n",
" 29 2018-11-30 00:00:00+00:00 first_seen 11.0 2018-11\n",
" .. ... ... ... ...\n",
" 48 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 49 2017-04-30 00:00:00+00:00 seen_recently 0.0 2017-04\n",
" 50 2017-05-31 00:00:00+00:00 seen_recently 0.0 2017-05\n",
" 51 2017-06-30 00:00:00+00:00 seen_recently 0.0 2017-06\n",
" 52 2017-07-31 00:00:00+00:00 seen_recently 0.0 2017-07\n",
" 53 2017-08-31 00:00:00+00:00 seen_recently 1.0 2017-08\n",
" 54 2017-09-30 00:00:00+00:00 seen_recently 0.0 2017-09\n",
" 55 2017-10-31 00:00:00+00:00 seen_recently 1.0 2017-10\n",
" 56 2017-11-30 00:00:00+00:00 seen_recently 0.0 2017-11\n",
" 57 2017-12-31 00:00:00+00:00 seen_recently 1.0 2017-12\n",
" 58 2018-01-31 00:00:00+00:00 seen_recently 0.0 2018-01\n",
" 59 2018-02-28 00:00:00+00:00 seen_recently 2.0 2018-02\n",
" 60 2018-03-31 00:00:00+00:00 seen_recently 0.0 2018-03\n",
" 61 2018-04-30 00:00:00+00:00 seen_recently 2.0 2018-04\n",
" 62 2018-05-31 00:00:00+00:00 seen_recently 2.0 2018-05\n",
" 63 2018-06-30 00:00:00+00:00 seen_recently 1.0 2018-06\n",
" 64 2018-07-31 00:00:00+00:00 seen_recently 1.0 2018-07\n",
" 65 2018-08-31 00:00:00+00:00 seen_recently 2.0 2018-08\n",
" 66 2018-09-30 00:00:00+00:00 seen_recently 0.0 2018-09\n",
" 67 2018-10-31 00:00:00+00:00 seen_recently 1.0 2018-10\n",
" 68 2018-11-30 00:00:00+00:00 seen_recently 1.0 2018-11\n",
" 69 2018-12-31 00:00:00+00:00 seen_recently 1.0 2018-12\n",
" 70 2019-01-31 00:00:00+00:00 seen_recently 1.0 2019-01\n",
" 71 2019-02-28 00:00:00+00:00 seen_recently 1.0 2019-02\n",
" 72 2019-03-31 00:00:00+00:00 seen_recently 0.0 2019-03\n",
" 73 2019-04-30 00:00:00+00:00 seen_recently 3.0 2019-04\n",
" 74 2019-05-31 00:00:00+00:00 seen_recently 0.0 2019-05\n",
" 75 2019-06-30 00:00:00+00:00 seen_recently 3.0 2019-06\n",
" 76 2019-07-31 00:00:00+00:00 seen_recently 22.0 2019-07\n",
" 77 2019-08-31 00:00:00+00:00 seen_recently 1.0 2019-08\n",
" \n",
" [78 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'jupyterlab'\n",
" }), Chart({\n",
" data: date kind count date_name\n",
" 0 2015-05-31 00:00:00+00:00 first_seen 2.0 2015-05\n",
" 1 2015-06-30 00:00:00+00:00 first_seen 3.0 2015-06\n",
" 2 2015-07-31 00:00:00+00:00 first_seen 2.0 2015-07\n",
" 3 2015-08-31 00:00:00+00:00 first_seen 1.0 2015-08\n",
" 4 2015-09-30 00:00:00+00:00 first_seen 3.0 2015-09\n",
" 5 2015-10-31 00:00:00+00:00 first_seen 0.0 2015-10\n",
" 6 2015-11-30 00:00:00+00:00 first_seen 2.0 2015-11\n",
" 7 2015-12-31 00:00:00+00:00 first_seen 1.0 2015-12\n",
" 8 2016-01-31 00:00:00+00:00 first_seen 2.0 2016-01\n",
" 9 2016-02-29 00:00:00+00:00 first_seen 5.0 2016-02\n",
" 10 2016-03-31 00:00:00+00:00 first_seen 6.0 2016-03\n",
" 11 2016-04-30 00:00:00+00:00 first_seen 1.0 2016-04\n",
" 12 2016-05-31 00:00:00+00:00 first_seen 0.0 2016-05\n",
" 13 2016-06-30 00:00:00+00:00 first_seen 3.0 2016-06\n",
" 14 2016-07-31 00:00:00+00:00 first_seen 2.0 2016-07\n",
" 15 2016-08-31 00:00:00+00:00 first_seen 2.0 2016-08\n",
" 16 2016-09-30 00:00:00+00:00 first_seen 2.0 2016-09\n",
" 17 2016-10-31 00:00:00+00:00 first_seen 7.0 2016-10\n",
" 18 2016-11-30 00:00:00+00:00 first_seen 2.0 2016-11\n",
" 19 2016-12-31 00:00:00+00:00 first_seen 2.0 2016-12\n",
" 20 2017-01-31 00:00:00+00:00 first_seen 3.0 2017-01\n",
" 21 2017-02-28 00:00:00+00:00 first_seen 2.0 2017-02\n",
" 22 2017-03-31 00:00:00+00:00 first_seen 3.0 2017-03\n",
" 23 2017-04-30 00:00:00+00:00 first_seen 1.0 2017-04\n",
" 24 2017-05-31 00:00:00+00:00 first_seen 3.0 2017-05\n",
" 25 2017-06-30 00:00:00+00:00 first_seen 5.0 2017-06\n",
" 26 2017-07-31 00:00:00+00:00 first_seen 6.0 2017-07\n",
" 27 2017-08-31 00:00:00+00:00 first_seen 2.0 2017-08\n",
" 28 2017-09-30 00:00:00+00:00 first_seen 8.0 2017-09\n",
" 29 2017-10-31 00:00:00+00:00 first_seen 13.0 2017-10\n",
" .. ... ... ... ...\n",
" 72 2017-02-28 00:00:00+00:00 seen_recently 0.0 2017-02\n",
" 73 2017-03-31 00:00:00+00:00 seen_recently 0.0 2017-03\n",
" 74 2017-04-30 00:00:00+00:00 seen_recently 0.0 2017-04\n",
" 75 2017-05-31 00:00:00+00:00 seen_recently 0.0 2017-05\n",
" 76 2017-06-30 00:00:00+00:00 seen_recently 1.0 2017-06\n",
" 77 2017-07-31 00:00:00+00:00 seen_recently 0.0 2017-07\n",
" 78 2017-08-31 00:00:00+00:00 seen_recently 0.0 2017-08\n",
" 79 2017-09-30 00:00:00+00:00 seen_recently 1.0 2017-09\n",
" 80 2017-10-31 00:00:00+00:00 seen_recently 1.0 2017-10\n",
" 81 2017-11-30 00:00:00+00:00 seen_recently 1.0 2017-11\n",
" 82 2017-12-31 00:00:00+00:00 seen_recently 1.0 2017-12\n",
" 83 2018-01-31 00:00:00+00:00 seen_recently 0.0 2018-01\n",
" 84 2018-02-28 00:00:00+00:00 seen_recently 0.0 2018-02\n",
" 85 2018-03-31 00:00:00+00:00 seen_recently 0.0 2018-03\n",
" 86 2018-04-30 00:00:00+00:00 seen_recently 2.0 2018-04\n",
" 87 2018-05-31 00:00:00+00:00 seen_recently 0.0 2018-05\n",
" 88 2018-06-30 00:00:00+00:00 seen_recently 0.0 2018-06\n",
" 89 2018-07-31 00:00:00+00:00 seen_recently 0.0 2018-07\n",
" 90 2018-08-31 00:00:00+00:00 seen_recently 1.0 2018-08\n",
" 91 2018-09-30 00:00:00+00:00 seen_recently 0.0 2018-09\n",
" 92 2018-10-31 00:00:00+00:00 seen_recently 0.0 2018-10\n",
" 93 2018-11-30 00:00:00+00:00 seen_recently 0.0 2018-11\n",
" 94 2018-12-31 00:00:00+00:00 seen_recently 0.0 2018-12\n",
" 95 2019-01-31 00:00:00+00:00 seen_recently 0.0 2019-01\n",
" 96 2019-02-28 00:00:00+00:00 seen_recently 0.0 2019-02\n",
" 97 2019-03-31 00:00:00+00:00 seen_recently 0.0 2019-03\n",
" 98 2019-04-30 00:00:00+00:00 seen_recently 2.0 2019-04\n",
" 99 2019-05-31 00:00:00+00:00 seen_recently 1.0 2019-05\n",
" 100 2019-06-30 00:00:00+00:00 seen_recently 2.0 2019-06\n",
" 101 2019-07-31 00:00:00+00:00 seen_recently 8.0 2019-07\n",
" \n",
" [102 rows x 4 columns],\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" }),\n",
" row: Row({\n",
" field: 'date_name',\n",
" type: 'ordinal'\n",
" }),\n",
" x: X({\n",
" field: 'count',\n",
" type: 'quantitative'\n",
" }),\n",
" y: Y({\n",
" field: 'kind',\n",
" type: 'nominal'\n",
" })\n",
" }),\n",
" mark: 'bar',\n",
" title: 'nteract'\n",
" })]\n",
"})"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# \"recent\" defined as N days in the past\n",
"recently = pd.datetime.utcnow() - timedelta(days=30)\n",
"recently = pytz.utc.localize(recently)\n",
"\n",
"charts = []\n",
"for org, idata in seen_times.groupby('org'):\n",
" idata = idata.loc[org]\n",
"\n",
" idata['seen_recently'] = idata.eval('last_seen > @recently')\n",
"\n",
"\n",
" first_seen = idata.resample('M', on='first_seen').agg({'first_seen': 'count', 'seen_recently': 'sum'})\n",
" first_seen.index.name = 'date'\n",
"\n",
" first_seen = pd.melt(first_seen.reset_index(), id_vars='date', var_name='kind', value_name='count')\n",
"\n",
" first_seen['date_name'] = first_seen['date'].map(lambda a: \"{:%Y-%m}\".format(a))\n",
"\n",
" bar = alt.Chart(first_seen, title=org).mark_bar().encode(\n",
" x='count:Q',\n",
" y='kind',\n",
" color='kind',\n",
" row='date_name:O'\n",
" )\n",
" charts.append(bar)\n",
" \n",
"alt.hconcat(*charts)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"papermill": {
"duration": 0.042887,
"end_time": "2019-08-01T17:02:23.479838",
"exception": false,
"start_time": "2019-08-01T17:02:23.436951",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%%html\n",
""
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.6.5"
},
"papermill": {
"duration": 6.46796,
"end_time": "2019-08-01T17:02:24.008392",
"environment_variables": {},
"exception": null,
"input_path": "./stats/retention.ipynb",
"output_path": "../reports/summaries/retention.ipynb",
"parameters": {
"renderer": "kaggle"
},
"start_time": "2019-08-01T17:02:17.540432",
"version": "1.0.1"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}