{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"papermill": {
"duration": 1.178838,
"end_time": "2019-08-20T23:09:03.949939",
"exception": false,
"start_time": "2019-08-20T23:09:02.771101",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"import seaborn as sns\n",
"import pandas as pd\n",
"import numpy as np\n",
"import altair as alt\n",
"from markdown import markdown\n",
"from IPython.display import Markdown\n",
"from ipywidgets.widgets import HTML, Tab\n",
"from ipywidgets import widgets\n",
"from datetime import timedelta\n",
"from matplotlib import pyplot as plt\n",
"from tqdm import tqdm\n",
"import os.path as op\n",
"\n",
"from mod import load_data, alt_theme\n",
"\n",
"from warnings import simplefilter\n",
"simplefilter('ignore')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"papermill": {
"duration": 0.020774,
"end_time": "2019-08-20T23:09:03.983366",
"exception": false,
"start_time": "2019-08-20T23:09:03.962592",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"def author_url(author):\n",
" return f\"https://github.com/{author}\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"papermill": {
"duration": 0.021081,
"end_time": "2019-08-20T23:09:04.015856",
"exception": false,
"start_time": "2019-08-20T23:09:03.994775",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"bot_names = pd.read_csv('./bot_names.csv')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"papermill": {
"duration": 0.019488,
"end_time": "2019-08-20T23:09:04.046387",
"exception": false,
"start_time": "2019-08-20T23:09:04.026899",
"status": "completed"
},
"tags": [
"parameters",
"hide_input"
]
},
"outputs": [],
"source": [
"fmt_date = \"{:%Y-%m-%d}\"\n",
"\n",
"start_date = None\n",
"end_date = None\n",
"\n",
"renderer = \"jupyterlab\"\n",
"github_orgs = [\"jupyterhub\", \"jupyter\", \"jupyterlab\", \"jupyter-widgets\", \"ipython\", \"binder-examples\", \"nteract\"]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"papermill": {
"duration": 0.017388,
"end_time": "2019-08-20T23:09:04.074697",
"exception": false,
"start_time": "2019-08-20T23:09:04.057309",
"status": "completed"
},
"tags": [
"injected-parameters"
]
},
"outputs": [],
"source": [
"# Parameters\n",
"renderer = \"kaggle\"\n",
"github_orgs = [\"jupyterhub\", \"jupyter\", \"jupyterlab\", \"jupyter-widgets\", \"ipython\", \"binder-examples\"]\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"papermill": {
"duration": 0.023179,
"end_time": "2019-08-20T23:09:04.109759",
"exception": false,
"start_time": "2019-08-20T23:09:04.086580",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"ThemeRegistry.enable('my_theme')"
]
},
"execution_count": 6,
"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": 7,
"metadata": {
"papermill": {
"duration": 2.582334,
"end_time": "2019-08-20T23:09:06.703108",
"exception": false,
"start_time": "2019-08-20T23:09:04.120774",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"comments, issues, prs = load_data('../data/', github_orgs=github_orgs)\n",
"comments = comments.query('author not in @bot_names').drop_duplicates()\n",
"issues = issues.query('author not in @bot_names').drop_duplicates()\n",
"prs = prs.query('author not in @bot_names').drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"papermill": {
"duration": 0.051011,
"end_time": "2019-08-20T23:09:06.768496",
"exception": false,
"start_time": "2019-08-20T23:09:06.717485",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"if start_date is None:\n",
" start_date = comments['updatedAt'].min()\n",
" \n",
"if end_date is None:\n",
" end_date = comments['updatedAt'].max()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"papermill": {
"duration": 0.031334,
"end_time": "2019-08-20T23:09:06.814377",
"exception": false,
"start_time": "2019-08-20T23:09:06.783043",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"# Information about out time window\n",
"time_delta = pd.to_datetime(end_date) - pd.to_datetime(start_date)\n",
"n_days = time_delta.days\n",
"\n",
"# Information about the data we loaded\n",
"github_orgs = comments['org'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"papermill": {
"duration": 0.043985,
"end_time": "2019-08-20T23:09:06.872612",
"exception": false,
"start_time": "2019-08-20T23:09:06.828627",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"def highlighted_line_plot(data, x, y, color, title, domain=[\"2019-05-01\", \"2019-08-01\"], legend=True):\n",
" ch = alt.Chart(data=data, width=1000, title=title)\n",
"\n",
" highlight = alt.selection(type='single', on='mouseover',\n",
" fields=[color], nearest=True)\n",
"\n",
" ln = ch.mark_line(clip=True).encode(\n",
" x=alt.X(x, scale=alt.Scale(domain=domain)),\n",
" y=y,\n",
" color=alt.Color(color, legend=legend),\n",
" opacity=alt.condition(~highlight, alt.value(.3), alt.value(1)),\n",
" size=alt.condition(~highlight, alt.value(2), alt.value(5))\n",
" )\n",
"\n",
" pt = ch.mark_point(clip=True).encode(\n",
" x=alt.X(x, scale=alt.Scale(domain=domain)),\n",
" y=y,\n",
" color=alt.Color(color, legend=legend),\n",
" tooltip=color,\n",
" size=alt.value(300),\n",
" opacity=alt.value(0)\n",
" ).add_selection(highlight).interactive()\n",
" return ln + pt"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"papermill": {
"duration": 0.264555,
"end_time": "2019-08-20T23:09:07.151241",
"exception": false,
"start_time": "2019-08-20T23:09:06.886686",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"date_fields = ['updatedAt', 'createdAt', 'closedAt']\n",
"for field in date_fields:\n",
" if field in comments.columns:\n",
" comments[field] = pd.to_datetime(comments[field])\n",
" if field in prs.columns:\n",
" prs[field] = pd.to_datetime(prs[field])\n",
" if field in issues.columns:\n",
" issues[field] = pd.to_datetime(issues[field])"
]
},
{
"cell_type": "markdown",
"metadata": {
"papermill": {
"duration": 0.011292,
"end_time": "2019-08-20T23:09:07.174968",
"exception": false,
"start_time": "2019-08-20T23:09:07.163676",
"status": "completed"
},
"tags": []
},
"source": [
"## Comments over time by people"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"papermill": {
"duration": 0.017849,
"end_time": "2019-08-20T23:09:07.206930",
"exception": false,
"start_time": "2019-08-20T23:09:07.189081",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"time_bin = '2W'\n",
"n_authors = 20\n",
"rolling_mean_amt = 4"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"papermill": {
"duration": 1.727669,
"end_time": "2019-08-20T23:09:08.946324",
"exception": false,
"start_time": "2019-08-20T23:09:07.218655",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterhub\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyter-widgets\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyter\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterlab\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ipython\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"binder-examples\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
"HConcatChart({\n",
" hconcat: [LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 Carreau 0 2015-03-08 00:00:00+00:00 NaN\n",
" 1 Carreau 1 2015-03-22 00:00:00+00:00 NaN\n",
" 2 Carreau 2 2015-04-05 00:00:00+00:00 NaN\n",
" 3 Carreau 3 2015-04-19 00:00:00+00:00 2.25\n",
" 4 Carreau 4 2015-05-03 00:00:00+00:00 1.25\n",
" ... ... ... ... ...\n",
" 1566 yuvipanda 1566 2019-05-26 00:00:00+00:00 53.75\n",
" 1567 yuvipanda 1567 2019-06-09 00:00:00+00:00 62.75\n",
" 1568 yuvipanda 1568 2019-06-23 00:00:00+00:00 65.00\n",
" 1569 yuvipanda 1569 2019-07-07 00:00:00+00:00 59.00\n",
" 1570 yuvipanda 1570 2019-07-21 00:00:00+00:00 26.00\n",
" \n",
" [1571 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector001'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector001'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-08-24', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyterhub',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-08-24', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector001': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector002': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyterhub',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 SylvainCorlay 0 2015-05-10 00:00:00+00:00 NaN\n",
" 1 SylvainCorlay 1 2015-05-24 00:00:00+00:00 NaN\n",
" 2 SylvainCorlay 2 2015-06-07 00:00:00+00:00 NaN\n",
" 3 SylvainCorlay 3 2015-06-21 00:00:00+00:00 6.50\n",
" 4 SylvainCorlay 4 2015-07-05 00:00:00+00:00 13.25\n",
" ... ... ... ... ...\n",
" 1467 willingc 1467 2017-03-12 00:00:00+00:00 0.00\n",
" 1468 willingc 1468 2017-03-26 00:00:00+00:00 0.00\n",
" 1469 willingc 1469 2017-04-09 00:00:00+00:00 0.00\n",
" 1470 willingc 1470 2017-04-23 00:00:00+00:00 0.25\n",
" 1471 willingc 1471 2017-05-07 00:00:00+00:00 0.50\n",
" \n",
" [1472 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector003'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector003'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-05-25', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyter-widgets',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-05-25', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector003': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector004': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyter-widgets',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 Carreau 0 2012-12-16 00:00:00+00:00 NaN\n",
" 1 Carreau 1 2012-12-30 00:00:00+00:00 NaN\n",
" 2 Carreau 2 2013-01-13 00:00:00+00:00 NaN\n",
" 3 Carreau 3 2013-01-27 00:00:00+00:00 0.75\n",
" 4 Carreau 4 2013-02-10 00:00:00+00:00 0.25\n",
" ... ... ... ... ...\n",
" 2440 yuvipanda 2440 2019-06-09 00:00:00+00:00 15.75\n",
" 2441 yuvipanda 2441 2019-06-23 00:00:00+00:00 15.25\n",
" 2442 yuvipanda 2442 2019-07-07 00:00:00+00:00 15.75\n",
" 2443 yuvipanda 2443 2019-07-21 00:00:00+00:00 9.75\n",
" 2444 yuvipanda 2444 2019-08-04 00:00:00+00:00 9.25\n",
" \n",
" [2445 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector005'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector005'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2012-12-16', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyter',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2012-12-16', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector005': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector006': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyter',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 BoPeng 0 2018-01-07 00:00:00+00:00 NaN\n",
" 1 BoPeng 1 2018-01-21 00:00:00+00:00 NaN\n",
" 2 BoPeng 2 2018-02-04 00:00:00+00:00 NaN\n",
" 3 BoPeng 3 2018-02-18 00:00:00+00:00 0.50\n",
" 4 BoPeng 4 2018-03-04 00:00:00+00:00 0.25\n",
" ... ... ... ... ...\n",
" 1297 vidartf 1297 2019-06-23 00:00:00+00:00 33.00\n",
" 1298 vidartf 1298 2019-07-07 00:00:00+00:00 39.00\n",
" 1299 vidartf 1299 2019-07-21 00:00:00+00:00 35.00\n",
" 1300 vidartf 1300 2019-08-04 00:00:00+00:00 32.50\n",
" 1301 vidartf 1301 2019-08-18 00:00:00+00:00 30.00\n",
" \n",
" [1302 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector007'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector007'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyterlab',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector007': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector008': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyterlab',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 Carreau 0 2011-12-04 00:00:00+00:00 NaN\n",
" 1 Carreau 1 2011-12-18 00:00:00+00:00 NaN\n",
" 2 Carreau 2 2012-01-01 00:00:00+00:00 NaN\n",
" 3 Carreau 3 2012-01-15 00:00:00+00:00 1.25\n",
" 4 Carreau 4 2012-01-29 00:00:00+00:00 1.00\n",
" ... ... ... ... ...\n",
" 2957 willingc 2957 2019-06-16 00:00:00+00:00 0.00\n",
" 2958 willingc 2958 2019-06-30 00:00:00+00:00 0.00\n",
" 2959 willingc 2959 2019-07-14 00:00:00+00:00 0.00\n",
" 2960 willingc 2960 2019-07-28 00:00:00+00:00 0.00\n",
" 2961 willingc 2961 2019-08-11 00:00:00+00:00 1.00\n",
" \n",
" [2962 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector009'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector009'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2010-10-10', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for ipython',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2010-10-10', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector009': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector010': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for ipython',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: author level_1 updatedAt id\n",
" 0 MatsGustavsson 0 2018-01-14 00:00:00+00:00 NaN\n",
" 1 RaoOfPhysics 1 2018-02-18 00:00:00+00:00 NaN\n",
" 2 RaoOfPhysics 2 2018-03-04 00:00:00+00:00 NaN\n",
" 3 RaoOfPhysics 3 2018-03-18 00:00:00+00:00 NaN\n",
" 4 RaoOfPhysics 4 2018-04-01 00:00:00+00:00 0.75\n",
" .. ... ... ... ...\n",
" 316 yuvipanda 316 2019-01-13 00:00:00+00:00 0.00\n",
" 317 yuvipanda 317 2019-01-27 00:00:00+00:00 0.00\n",
" 318 yuvipanda 318 2019-02-10 00:00:00+00:00 0.00\n",
" 319 yuvipanda 319 2019-02-24 00:00:00+00:00 0.00\n",
" 320 yuvipanda 320 2019-03-10 00:00:00+00:00 0.75\n",
" \n",
" [321 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector011'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector011'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-28']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for binder-examples',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'author',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'author',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-28']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector011': SelectionDef({\n",
" fields: ['author'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector012': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for binder-examples',\n",
" width: 1000\n",
" })]\n",
" })]\n",
"})"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"charts = []\n",
"for iorg in github_orgs:\n",
" print(iorg)\n",
" icomments = comments.query('org == @iorg')\n",
" authors = icomments.groupby(['author', 'updatedAt']).agg({'id': 'count'}).reset_index()\n",
"\n",
" top_authors = authors.groupby('author').sum()['id'].sort_values(ascending=False).head(n_authors).index\n",
" authors = authors.query('author in @top_authors')\n",
" authors = authors.groupby('author').resample(time_bin, on='updatedAt').sum().reset_index()\n",
" authors = authors.groupby('author').rolling(rolling_mean_amt, on='updatedAt').mean().reset_index()\n",
" domain = [fmt_date.format(authors['updatedAt'].min()), fmt_date.format(authors['updatedAt'].max())]\n",
" ch = highlighted_line_plot(authors, 'updatedAt', 'id', 'author', f\"Comments over time for {iorg}\",\n",
" legend=None, domain=domain)\n",
" charts.append(ch)\n",
"alt.hconcat(*charts)"
]
},
{
"cell_type": "markdown",
"metadata": {
"papermill": {
"duration": 0.02392,
"end_time": "2019-08-20T23:09:08.994837",
"exception": false,
"start_time": "2019-08-20T23:09:08.970917",
"status": "completed"
},
"tags": []
},
"source": [
"## Comments over time by repo"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"papermill": {
"duration": 0.030541,
"end_time": "2019-08-20T23:09:09.053219",
"exception": false,
"start_time": "2019-08-20T23:09:09.022678",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"time_bin = '2W'\n",
"n_repos = 30\n",
"rolling_mean_amt = 2"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"papermill": {
"duration": 1.877887,
"end_time": "2019-08-20T23:09:10.956534",
"exception": false,
"start_time": "2019-08-20T23:09:09.078647",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterhub\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyter-widgets\n",
"jupyter\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterlab\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ipython\n",
"binder-examples\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
"HConcatChart({\n",
" hconcat: [LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 alabaster-jupyterhub 0 2018-10-21 00:00:00+00:00 NaN\n",
" 1 alabaster-jupyterhub 1 2018-11-04 00:00:00+00:00 4.0\n",
" 2 alabaster-jupyterhub 2 2018-11-18 00:00:00+00:00 0.0\n",
" 3 alabaster-jupyterhub 3 2018-12-02 00:00:00+00:00 0.0\n",
" 4 alabaster-jupyterhub 4 2018-12-16 00:00:00+00:00 0.0\n",
" ... ... ... ... ...\n",
" 2010 zero-to-jupyterhub-k8s 2010 2019-07-07 00:00:00+00:00 35.5\n",
" 2011 zero-to-jupyterhub-k8s 2011 2019-07-21 00:00:00+00:00 34.5\n",
" 2012 zero-to-jupyterhub-k8s 2012 2019-08-04 00:00:00+00:00 36.0\n",
" 2013 zero-to-jupyterhub-k8s 2013 2019-08-18 00:00:00+00:00 38.0\n",
" 2014 zero-to-jupyterhub-k8s 2014 2019-09-01 00:00:00+00:00 23.5\n",
" \n",
" [2015 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector013'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector013'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-08-24', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyterhub',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-08-24', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector013': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector014': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyterhub',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 ipyleaflet 0 2014-05-25 00:00:00+00:00 NaN\n",
" 1 ipyleaflet 1 2014-06-08 00:00:00+00:00 0.5\n",
" 2 ipyleaflet 2 2014-06-22 00:00:00+00:00 0.0\n",
" 3 ipyleaflet 3 2014-07-06 00:00:00+00:00 0.0\n",
" 4 ipyleaflet 4 2014-07-20 00:00:00+00:00 0.0\n",
" .. ... ... ... ...\n",
" 652 widget-ts-cookiecutter 652 2019-03-10 00:00:00+00:00 0.5\n",
" 653 widget-ts-cookiecutter 653 2019-03-24 00:00:00+00:00 4.5\n",
" 654 widget-ts-cookiecutter 654 2019-04-07 00:00:00+00:00 4.0\n",
" 655 widget-ts-cookiecutter 655 2019-04-21 00:00:00+00:00 0.0\n",
" 656 widget-ts-cookiecutter 656 2019-05-05 00:00:00+00:00 2.5\n",
" \n",
" [657 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector015'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector015'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-05-25', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyter-widgets',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2014-05-25', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector015': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector016': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyter-widgets',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 atom-notebook 0 2015-08-02 00:00:00+00:00 NaN\n",
" 1 atom-notebook 1 2015-08-16 00:00:00+00:00 6.0\n",
" 2 atom-notebook 2 2015-08-30 00:00:00+00:00 1.0\n",
" 3 atom-notebook 3 2015-09-13 00:00:00+00:00 0.0\n",
" 4 atom-notebook 4 2015-09-27 00:00:00+00:00 0.0\n",
" ... ... ... ... ...\n",
" 2954 tmpnb 2954 2017-12-10 00:00:00+00:00 0.0\n",
" 2955 tmpnb 2955 2017-12-24 00:00:00+00:00 0.5\n",
" 2956 tmpnb 2956 2018-01-07 00:00:00+00:00 0.5\n",
" 2957 tmpnb 2957 2018-01-21 00:00:00+00:00 5.0\n",
" 2958 tmpnb 2958 2018-02-04 00:00:00+00:00 6.5\n",
" \n",
" [2959 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector017'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector017'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2012-12-16', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyter',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2012-12-16', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector017': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector018': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyter',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 debugger 0 2019-08-11 00:00:00+00:00 NaN\n",
" 1 debugger 1 2019-08-25 00:00:00+00:00 10.5\n",
" 2 extension-cookiecutter-js 2 2016-09-25 00:00:00+00:00 NaN\n",
" 3 extension-cookiecutter-js 3 2016-10-09 00:00:00+00:00 13.5\n",
" 4 extension-cookiecutter-js 4 2016-10-23 00:00:00+00:00 6.5\n",
" ... ... ... ... ...\n",
" 1088 theme-cookiecutter 1088 2019-05-26 00:00:00+00:00 0.0\n",
" 1089 theme-cookiecutter 1089 2019-06-09 00:00:00+00:00 0.0\n",
" 1090 theme-cookiecutter 1090 2019-06-23 00:00:00+00:00 0.0\n",
" 1091 theme-cookiecutter 1091 2019-07-07 00:00:00+00:00 0.0\n",
" 1092 theme-cookiecutter 1092 2019-07-21 00:00:00+00:00 1.0\n",
" \n",
" [1093 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector019'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector019'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for jupyterlab',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector019': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector020': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for jupyterlab',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 disp 0 2017-06-11 00:00:00+00:00 NaN\n",
" 1 disp 1 2017-06-25 00:00:00+00:00 6.0\n",
" 2 disp 2 2017-07-09 00:00:00+00:00 2.5\n",
" 3 disp 3 2017-07-23 00:00:00+00:00 0.0\n",
" 4 disp 4 2017-08-06 00:00:00+00:00 0.0\n",
" ... ... ... ... ...\n",
" 1291 xkcd-font 1291 2018-12-02 00:00:00+00:00 0.0\n",
" 1292 xkcd-font 1292 2018-12-16 00:00:00+00:00 0.0\n",
" 1293 xkcd-font 1293 2018-12-30 00:00:00+00:00 0.0\n",
" 1294 xkcd-font 1294 2019-01-13 00:00:00+00:00 0.0\n",
" 1295 xkcd-font 1295 2019-01-27 00:00:00+00:00 0.5\n",
" \n",
" [1296 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector021'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector021'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2010-05-16', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for ipython',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2010-05-16', '2019-08-25']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector021': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector022': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for ipython',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo level_1 updatedAt id\n",
" 0 appmode 0 2017-12-17 00:00:00+00:00 NaN\n",
" 1 appmode 1 2017-12-31 00:00:00+00:00 2.5\n",
" 2 appmode 2 2018-01-14 00:00:00+00:00 11.5\n",
" 3 apt_install 3 2019-03-10 00:00:00+00:00 NaN\n",
" 4 bokeh 4 2019-06-23 00:00:00+00:00 NaN\n",
" .. ... ... ... ...\n",
" 350 setup.py 350 2018-11-11 00:00:00+00:00 0.0\n",
" 351 setup.py 351 2018-11-25 00:00:00+00:00 0.0\n",
" 352 setup.py 352 2018-12-09 00:00:00+00:00 0.0\n",
" 353 setup.py 353 2018-12-23 00:00:00+00:00 0.5\n",
" 354 stencila-r 354 2018-11-25 00:00:00+00:00 NaN\n",
" \n",
" [355 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector023'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector023'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Comments over time for binder-examples',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector023': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector024': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Comments over time for binder-examples',\n",
" width: 1000\n",
" })]\n",
" })]\n",
"})"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"charts = []\n",
"for iorg in github_orgs:\n",
" print(iorg)\n",
" icomments = comments.query('org == @iorg')\n",
" repos = icomments.groupby(['repo', 'updatedAt']).agg({'id': 'count'}).reset_index()\n",
"\n",
" top_repos = repos.groupby('repo').sum()['id'].sort_values(ascending=False).head(n_repos).index\n",
" repos = repos.query('repo in @top_repos')\n",
" repos = repos.groupby('repo').resample(time_bin, on='updatedAt').sum().reset_index()\n",
" repos = repos.groupby('repo').rolling(rolling_mean_amt, on='updatedAt').mean().reset_index()\n",
" domain = [fmt_date.format(repos['updatedAt'].min()), fmt_date.format(repos['updatedAt'].max())]\n",
" ch = highlighted_line_plot(repos, 'updatedAt', 'id', 'repo', f\"Comments over time for {iorg}\",\n",
" legend=None, domain=domain)\n",
" charts.append(ch)\n",
"alt.hconcat(*charts)"
]
},
{
"cell_type": "markdown",
"metadata": {
"papermill": {
"duration": 0.027687,
"end_time": "2019-08-20T23:09:11.012019",
"exception": false,
"start_time": "2019-08-20T23:09:10.984332",
"status": "completed"
},
"tags": []
},
"source": [
"### Activity over time in each organization"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"papermill": {
"duration": 1.237184,
"end_time": "2019-08-20T23:09:12.276007",
"exception": false,
"start_time": "2019-08-20T23:09:11.038823",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
"HConcatChart({\n",
" hconcat: [LayerChart({\n",
" data: org level_1 createdAt id\n",
" 0 binder-examples 0 2017-06-25 00:00:00+00:00 NaN\n",
" 1 binder-examples 1 2017-07-02 00:00:00+00:00 NaN\n",
" 2 binder-examples 2 2017-07-09 00:00:00+00:00 NaN\n",
" 3 binder-examples 3 2017-07-16 00:00:00+00:00 0.25\n",
" 4 binder-examples 4 2017-07-23 00:00:00+00:00 0.00\n",
" ... ... ... ... ...\n",
" 1646 jupyterlab 1646 2019-07-28 00:00:00+00:00 48.75\n",
" 1647 jupyterlab 1647 2019-08-04 00:00:00+00:00 43.75\n",
" 1648 jupyterlab 1648 2019-08-11 00:00:00+00:00 43.00\n",
" 1649 jupyterlab 1649 2019-08-18 00:00:00+00:00 43.75\n",
" 1650 jupyterlab 1650 2019-08-25 00:00:00+00:00 33.00\n",
" \n",
" [1651 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector025'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector025'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'issues over time',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'org',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector025': SelectionDef({\n",
" fields: ['org'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector026': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'issues over time',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: org level_1 createdAt id\n",
" 0 binder-examples 0 2017-10-22 00:00:00+00:00 NaN\n",
" 1 binder-examples 1 2017-10-29 00:00:00+00:00 NaN\n",
" 2 binder-examples 2 2017-11-05 00:00:00+00:00 NaN\n",
" 3 binder-examples 3 2017-11-12 00:00:00+00:00 1.00\n",
" 4 binder-examples 4 2017-11-19 00:00:00+00:00 0.75\n",
" ... ... ... ... ...\n",
" 1208 jupyterlab 1208 2019-08-04 00:00:00+00:00 29.50\n",
" 1209 jupyterlab 1209 2019-08-11 00:00:00+00:00 25.50\n",
" 1210 jupyterlab 1210 2019-08-18 00:00:00+00:00 26.00\n",
" 1211 jupyterlab 1211 2019-08-25 00:00:00+00:00 21.75\n",
" 1212 nteract 1212 2019-08-04 00:00:00+00:00 NaN\n",
" \n",
" [1213 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector027'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector027'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'prs over time',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'org',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector027': SelectionDef({\n",
" fields: ['org'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector028': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'prs over time',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: org level_1 createdAt id\n",
" 0 binder-examples 0 2017-06-25 00:00:00+00:00 NaN\n",
" 1 binder-examples 1 2017-07-02 00:00:00+00:00 NaN\n",
" 2 binder-examples 2 2017-07-09 00:00:00+00:00 NaN\n",
" 3 binder-examples 3 2017-07-16 00:00:00+00:00 0.50\n",
" 4 binder-examples 4 2017-07-23 00:00:00+00:00 0.00\n",
" ... ... ... ... ...\n",
" 1644 jupyterlab 1644 2019-07-28 00:00:00+00:00 258.25\n",
" 1645 jupyterlab 1645 2019-08-04 00:00:00+00:00 263.00\n",
" 1646 jupyterlab 1646 2019-08-11 00:00:00+00:00 298.25\n",
" 1647 jupyterlab 1647 2019-08-18 00:00:00+00:00 334.00\n",
" 1648 jupyterlab 1648 2019-08-25 00:00:00+00:00 239.75\n",
" \n",
" [1649 rows x 4 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector029'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector029'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'comments over time',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'org',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'org',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'createdAt',\n",
" scale: Scale({\n",
" domain: ['2017-06-25', '2019-07-21']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'id',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector029': SelectionDef({\n",
" fields: ['org'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector030': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'comments over time',\n",
" width: 1000\n",
" })]\n",
" })]\n",
"})"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"charts = []\n",
"\n",
"for kind, idata in [('issues', issues), ('prs', prs), ('comments', comments)]:\n",
" org_comments = idata.groupby('org').resample('W', on='createdAt').count()['id'].reset_index()\n",
" org_comments = org_comments.groupby('org').rolling(4, on='createdAt').mean().reset_index()\n",
"\n",
" ch = highlighted_line_plot(org_comments, 'createdAt', 'id', 'org', f\"{kind} over time\", legend=None, domain=domain)\n",
" charts.append(ch)\n",
"alt.hconcat(*charts)"
]
},
{
"cell_type": "markdown",
"metadata": {
"papermill": {
"duration": 0.035159,
"end_time": "2019-08-20T23:09:12.340116",
"exception": false,
"start_time": "2019-08-20T23:09:12.304957",
"status": "completed"
},
"tags": []
},
"source": [
"## Time to first response of issues"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"papermill": {
"duration": 0.079681,
"end_time": "2019-08-20T23:09:12.453581",
"exception": false,
"start_time": "2019-08-20T23:09:12.373900",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"first_comments = (\n",
" comments.groupby(['org', 'repo', 'issue_id'], as_index=False) \n",
" .agg({'id': 'first', 'createdAt': 'first'})\n",
" .rename(columns={'createdAt': 'firstResponse', 'issue_id': 'number'})\n",
" .drop(columns='id')\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"papermill": {
"duration": 0.085153,
"end_time": "2019-08-20T23:09:12.572126",
"exception": false,
"start_time": "2019-08-20T23:09:12.486973",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"issues_w_response = pd.merge(first_comments, issues, on=['org', 'repo', 'number'])\n",
"issues_w_response[['createdAt', 'firstResponse']] = issues_w_response[['createdAt', 'firstResponse']].apply(pd.to_datetime)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"papermill": {
"duration": 0.186074,
"end_time": "2019-08-20T23:09:12.797072",
"exception": false,
"start_time": "2019-08-20T23:09:12.610998",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"issues_w_response['time_to_first_response'] = issues_w_response['firstResponse'] - issues_w_response['createdAt']\n",
"issues_w_response['hours_to_first_response'] = issues_w_response['time_to_first_response'].map(lambda a: 24 * a.days + a.seconds / 60 / 60)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"papermill": {
"duration": 2.424111,
"end_time": "2019-08-20T23:09:15.249268",
"exception": false,
"start_time": "2019-08-20T23:09:12.825157",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterhub\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyter-widgets\n",
"jupyter\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"jupyterlab\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ipython\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"binder-examples\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
"HConcatChart({\n",
" hconcat: [LayerChart({\n",
" data: repo updatedAt \\\n",
" 4 batchspawner 2016-07-10 00:00:00+00:00 \n",
" 5 batchspawner 2016-07-24 00:00:00+00:00 \n",
" 6 batchspawner 2016-08-07 00:00:00+00:00 \n",
" 7 batchspawner 2016-08-21 00:00:00+00:00 \n",
" 8 batchspawner 2016-09-04 00:00:00+00:00 \n",
" ... ... ... \n",
" 2048 zero-to-jupyterhub-k8s 2019-07-07 00:00:00+00:00 \n",
" 2049 zero-to-jupyterhub-k8s 2019-07-21 00:00:00+00:00 \n",
" 2050 zero-to-jupyterhub-k8s 2019-08-04 00:00:00+00:00 \n",
" 2051 zero-to-jupyterhub-k8s 2019-08-18 00:00:00+00:00 \n",
" 2052 zero-to-jupyterhub-k8s 2019-09-01 00:00:00+00:00 \n",
" \n",
" hours_to_first_response \n",
" 4 NaN \n",
" 5 NaN \n",
" 6 NaN \n",
" 7 NaN \n",
" 8 22.398333 \n",
" ... ... \n",
" 2048 439.230917 \n",
" 2049 486.551833 \n",
" 2050 544.098639 \n",
" 2051 529.202972 \n",
" 2052 1147.504083 \n",
" \n",
" [1576 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector031'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector031'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-11', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for jupyterhub',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-11', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector031': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector032': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for jupyterhub',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo updatedAt hours_to_first_response\n",
" 0 ipyleaflet 2018-04-08 00:00:00+00:00 NaN\n",
" 1 ipyleaflet 2018-04-22 00:00:00+00:00 NaN\n",
" 2 ipyleaflet 2018-05-06 00:00:00+00:00 NaN\n",
" 3 ipyleaflet 2018-05-20 00:00:00+00:00 NaN\n",
" 4 ipyleaflet 2018-06-03 00:00:00+00:00 1657.512167\n",
" .. ... ... ...\n",
" 416 widget-ts-cookiecutter 2019-03-10 00:00:00+00:00 12.720000\n",
" 417 widget-ts-cookiecutter 2019-03-24 00:00:00+00:00 17.746722\n",
" 418 widget-ts-cookiecutter 2019-04-07 00:00:00+00:00 15.587778\n",
" 419 widget-ts-cookiecutter 2019-04-21 00:00:00+00:00 15.587778\n",
" 420 widget-ts-cookiecutter 2019-05-05 00:00:00+00:00 33.306778\n",
" \n",
" [421 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector033'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector033'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-05-10', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for jupyter-widgets',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-05-10', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector033': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector034': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for jupyter-widgets',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo updatedAt hours_to_first_response\n",
" 4 atom-notebook 2015-08-02 00:00:00+00:00 NaN\n",
" 5 atom-notebook 2015-08-16 00:00:00+00:00 NaN\n",
" 6 atom-notebook 2015-08-30 00:00:00+00:00 NaN\n",
" 7 atom-notebook 2015-09-13 00:00:00+00:00 NaN\n",
" 8 atom-notebook 2015-09-27 00:00:00+00:00 1.447583\n",
" ... ... ... ...\n",
" 3763 testpath 2019-05-12 00:00:00+00:00 0.000000\n",
" 3764 testpath 2019-05-26 00:00:00+00:00 0.000000\n",
" 3765 testpath 2019-06-09 00:00:00+00:00 0.000000\n",
" 3766 testpath 2019-06-23 00:00:00+00:00 0.000000\n",
" 3767 testpath 2019-07-07 00:00:00+00:00 8.398778\n",
" \n",
" [2182 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector035'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector035'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-11', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for jupyter',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-11', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector035': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector036': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for jupyter',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo updatedAt \\\n",
" 1 extension-cookiecutter-js 2016-10-02 00:00:00+00:00 \n",
" 2 extension-cookiecutter-js 2016-10-16 00:00:00+00:00 \n",
" 3 extension-cookiecutter-js 2016-10-30 00:00:00+00:00 \n",
" 4 extension-cookiecutter-js 2016-11-13 00:00:00+00:00 \n",
" 5 extension-cookiecutter-js 2016-11-27 00:00:00+00:00 \n",
" .. ... ... \n",
" 956 scipy2018-jupyterlab-tutorial 2019-05-12 00:00:00+00:00 \n",
" 957 scipy2018-jupyterlab-tutorial 2019-05-26 00:00:00+00:00 \n",
" 958 scipy2018-jupyterlab-tutorial 2019-06-09 00:00:00+00:00 \n",
" 959 scipy2018-jupyterlab-tutorial 2019-06-23 00:00:00+00:00 \n",
" 960 scipy2018-jupyterlab-tutorial 2019-07-07 00:00:00+00:00 \n",
" \n",
" hours_to_first_response \n",
" 1 NaN \n",
" 2 NaN \n",
" 3 NaN \n",
" 4 NaN \n",
" 5 0.250111 \n",
" .. ... \n",
" 956 0.000000 \n",
" 957 0.000000 \n",
" 958 0.000000 \n",
" 959 0.000000 \n",
" 960 181.427333 \n",
" \n",
" [926 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector037'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector037'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for jupyterlab',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2016-06-12', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector037': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector038': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for jupyterlab',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo updatedAt hours_to_first_response\n",
" 0 disp 2017-06-11 00:00:00+00:00 NaN\n",
" 1 disp 2017-06-25 00:00:00+00:00 NaN\n",
" 2 disp 2017-07-09 00:00:00+00:00 NaN\n",
" 3 disp 2017-07-23 00:00:00+00:00 NaN\n",
" 4 disp 2017-08-06 00:00:00+00:00 2.490667\n",
" .. ... ... ...\n",
" 893 xkcd-font 2018-12-02 00:00:00+00:00 0.000000\n",
" 894 xkcd-font 2018-12-16 00:00:00+00:00 0.000000\n",
" 895 xkcd-font 2018-12-30 00:00:00+00:00 0.000000\n",
" 896 xkcd-font 2019-01-13 00:00:00+00:00 0.000000\n",
" 897 xkcd-font 2019-01-27 00:00:00+00:00 6665.689722\n",
" \n",
" [898 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector039'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector039'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-04', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for ipython',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2015-01-04', '2019-09-01']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector039': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector040': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for ipython',\n",
" width: 1000\n",
" })]\n",
" }), LayerChart({\n",
" data: repo updatedAt hours_to_first_response\n",
" 2 apt_install 2019-03-10 00:00:00+00:00 NaN\n",
" 3 bokeh 2019-06-23 00:00:00+00:00 NaN\n",
" 4 conda 2018-12-16 00:00:00+00:00 NaN\n",
" 5 continuous-build 2018-07-22 00:00:00+00:00 NaN\n",
" 6 continuous-build 2018-08-05 00:00:00+00:00 NaN\n",
" .. ... ... ...\n",
" 216 requirements 2019-03-17 00:00:00+00:00 0.000000\n",
" 217 requirements 2019-03-31 00:00:00+00:00 0.000000\n",
" 218 requirements 2019-04-14 00:00:00+00:00 0.000000\n",
" 219 requirements 2019-04-28 00:00:00+00:00 1.530167\n",
" 220 setup.py 2018-12-23 00:00:00+00:00 NaN\n",
" \n",
" [218 rows x 3 columns],\n",
" layer: [Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: OpacityValue({\n",
" condition: OpacityValue({\n",
" selection: SelectionNot({\n",
" not: 'selector041'\n",
" }),\n",
" value: 0.3\n",
" }),\n",
" value: 1\n",
" }),\n",
" size: SizeValue({\n",
" condition: SizeValue({\n",
" selection: SelectionNot({\n",
" not: 'selector041'\n",
" }),\n",
" value: 2\n",
" }),\n",
" value: 5\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-11-19', '2019-07-28']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'line'\n",
" }),\n",
" title: 'Hours to first response for binder-examples',\n",
" width: 1000\n",
" }), Chart({\n",
" encoding: FacetedEncoding({\n",
" color: Color({\n",
" field: 'repo',\n",
" legend: None,\n",
" type: 'nominal'\n",
" }),\n",
" opacity: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 0\n",
" }),\n",
" size: ValueDefWithOptionalConditionMarkPropFieldDefnumber({\n",
" value: 300\n",
" }),\n",
" tooltip: Tooltip({\n",
" field: 'repo',\n",
" type: 'nominal'\n",
" }),\n",
" x: X({\n",
" field: 'updatedAt',\n",
" scale: Scale({\n",
" domain: ['2017-11-19', '2019-07-28']\n",
" }),\n",
" type: 'temporal'\n",
" }),\n",
" y: Y({\n",
" field: 'hours_to_first_response',\n",
" type: 'quantitative'\n",
" })\n",
" }),\n",
" mark: MarkDef({\n",
" clip: True,\n",
" type: 'point'\n",
" }),\n",
" selection: {'selector041': SelectionDef({\n",
" fields: ['repo'],\n",
" nearest: True,\n",
" on: 'mouseover',\n",
" type: 'single'\n",
" }), 'selector042': SelectionDef({\n",
" bind: 'scales',\n",
" encodings: ['x', 'y'],\n",
" type: 'interval'\n",
" })},\n",
" title: 'Hours to first response for binder-examples',\n",
" width: 1000\n",
" })]\n",
" })]\n",
"})"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"charts = []\n",
"for iorg in github_orgs:\n",
" print(iorg)\n",
" i_issues = issues_w_response.query('org == @iorg')\n",
" repo_comments = (\n",
" i_issues.groupby('repo')\n",
" .resample(time_bin, on='updatedAt').median()['hours_to_first_response']\n",
" .reset_index()\n",
" .replace(np.nan, 0)\n",
" .groupby('repo').rolling(5, on='updatedAt').mean().reset_index('repo')\n",
" )\n",
"\n",
" n_plot = 20\n",
" top_repos = repo_comments.groupby('repo').count()['hours_to_first_response'].sort_values(ascending=False).head(n_plot).index.values\n",
" repo_comments = repo_comments.query('repo in @top_repos')\n",
" domain = [fmt_date.format(repo_comments['updatedAt'].min()), fmt_date.format(repo_comments['updatedAt'].max())]\n",
" ch = highlighted_line_plot(repo_comments, 'updatedAt', 'hours_to_first_response', 'repo', f\"Hours to first response for {iorg}\",\n",
" legend=None, domain=domain)\n",
" charts.append(ch)\n",
"alt.hconcat(*charts)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"papermill": {
"duration": 0.061551,
"end_time": "2019-08-20T23:09:15.348647",
"exception": false,
"start_time": "2019-08-20T23:09:15.287096",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
""
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%%html\n",
""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"papermill": {
"duration": 0.047356,
"end_time": "2019-08-20T23:09:15.437163",
"exception": false,
"start_time": "2019-08-20T23:09:15.389807",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": []
}
],
"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": "3.7.3"
},
"papermill": {
"duration": 14.268804,
"end_time": "2019-08-20T23:09:15.888733",
"environment_variables": {},
"exception": null,
"input_path": "./time.ipynb",
"output_path": "../reports/summaries/time.ipynb",
"parameters": {
"github_orgs": [
"jupyterhub",
"jupyter",
"jupyterlab",
"jupyter-widgets",
"ipython",
"binder-examples"
],
"renderer": "kaggle"
},
"start_time": "2019-08-20T23:09:01.619929",
"version": "1.0.1"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}