data/issues.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": null,
   6    "metadata": {},
   7    "outputs": [],
   8    "source": [
   9     "import platform\n",
  10     "print(platform.python_version())"
  11    ]
  12   },
  13   {
  14    "cell_type": "code",
  15    "execution_count": null,
  16    "metadata": {},
  17    "outputs": [],
  18    "source": [
  19     "# Get ye data\n",
  20     "import glob\n",
  21     "import os\n",
  22     "\n",
  23     "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\n"
  24    ]
  25   },
  26   {
  27    "cell_type": "code",
  28    "execution_count": null,
  29    "metadata": {},
  30    "outputs": [],
  31    "source": [
  32     "import os\n",
  33     "\n",
  34     "for file in data_files:\n",
  35     "\tprint(f\"{file}\", os.path.getsize(file))\n"
  36    ]
  37   },
  38   {
  39    "cell_type": "code",
  40    "execution_count": null,
  41    "metadata": {},
  42    "outputs": [],
  43    "source": [
  44     "import pandas as pd\n",
  45     "\n",
  46     "data_sets = []\n",
  47     "\n",
  48     "# file = data_files[6]  # CLI Tools\n",
  49     "file = data_files[2]  # Job Aids\n",
  50     "print(file)\n",
  51     "\n",
  52     "f = open(file, encoding='utf-8')\n",
  53     "df = pd.read_json(f)"
  54    ]
  55   },
  56   {
  57    "cell_type": "code",
  58    "execution_count": null,
  59    "metadata": {},
  60    "outputs": [],
  61    "source": [
  62     "import numpy as np\n",
  63     "df['count'] = np.zeros(len(df))\n",
  64     "\n"
  65    ]
  66   },
  67   {
  68    "cell_type": "markdown",
  69    "metadata": {},
  70    "source": [
  71     "#### Pie Chart"
  72    ]
  73   },
  74   {
  75    "cell_type": "code",
  76    "execution_count": null,
  77    "metadata": {},
  78    "outputs": [],
  79    "source": [
  80     "dfp = df\n",
  81     "dfp['mile'] = [d.get('title') if d else None for d in dfp.milestone]\n",
  82     "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)"
  83    ]
  84   },
  85   {
  86    "cell_type": "code",
  87    "execution_count": null,
  88    "metadata": {},
  89    "outputs": [],
  90    "source": [
  91     "\n",
  92     "mile_counts = dfp.groupby('mile')['title'].nunique()\n",
  93     "dfp['count'] = dfp['mile'].map(mile_counts)\n",
  94     "# dfp.drop(columns=['title'], inplace=True)\n",
  95     "dfp['mile'] = df['mile'].drop_duplicates()\n",
  96     "dfp.dropna(inplace=True)\n",
  97     "dfp = dfp[dfp['count'] > 5]\n",
  98     "print(dfp)"
  99    ]
 100   },
 101   {
 102    "cell_type": "code",
 103    "execution_count": null,
 104    "metadata": {},
 105    "outputs": [],
 106    "source": [
 107     "mile_counts = df.groupby('mile')['count'].sum()\n",
 108     "mile_counts = mile_counts.loc[lambda x: x > 5]\n",
 109     "plt.pie(mile_counts, labels=mile_counts.index, autopct='%1.1f%%')\n",
 110     "plt.title(f\"Tasks by Milestone\")\n",
 111     "plt.axis('equal')\n",
 112     "plt.show()"
 113    ]
 114   },
 115   {
 116    "cell_type": "markdown",
 117    "metadata": {},
 118    "source": [
 119     "#### Plot of closed issues by month and milestone for one project\n"
 120    ]
 121   },
 122   {
 123    "cell_type": "code",
 124    "execution_count": null,
 125    "metadata": {},
 126    "outputs": [],
 127    "source": [
 128     "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
 129     "df['closed_month'] = closed_months.dt.month\n",
 130     "df.drop(columns=['closedAt'], inplace=True)"
 131    ]
 132   },
 133   {
 134    "cell_type": "code",
 135    "execution_count": null,
 136    "metadata": {},
 137    "outputs": [],
 138    "source": [
 139     "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
 140    ]
 141   },
 142   {
 143    "cell_type": "code",
 144    "execution_count": null,
 145    "metadata": {},
 146    "outputs": [],
 147    "source": [
 148     "\n",
 149     "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
 150     "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\n"
 151    ]
 152   },
 153   {
 154    "cell_type": "code",
 155    "execution_count": null,
 156    "metadata": {},
 157    "outputs": [],
 158    "source": [
 159     "exclude_from_chart = [\n",
 160     "\t'Job Aid Ideas']\n",
 161     "\n",
 162     "for ex in exclude_from_chart:\n",
 163     "\tdfg = dfg[dfg['mile'] != ex]\n"
 164    ]
 165   },
 166   {
 167    "cell_type": "code",
 168    "execution_count": null,
 169    "metadata": {},
 170    "outputs": [],
 171    "source": [
 172     "import seaborn as sns\n",
 173     "import matplotlib.pyplot as plt\n",
 174     "sns.set_theme()"
 175    ]
 176   },
 177   {
 178    "cell_type": "code",
 179    "execution_count": null,
 180    "metadata": {},
 181    "outputs": [],
 182    "source": [
 183     "plt.figure(figsize=(10, 6))\n",
 184     "sns.pie(x='closed_month', y='count', hue='mile', data=dfg)\n",
 185     "plt.pie(dfg, )\n",
 186     "plt.xlabel('Closed Month')\n",
 187     "plt.ylabel('ClosedAt')\n",
 188     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",
 189     "plt.xticks(rotation=45)\n",
 190     "plt.legend(title='Mile', loc='upper left')\n",
 191     "plt.show()"
 192    ]
 193   }
 194  ],
 195  "metadata": {
 196   "kernelspec": {
 197    "display_name": "Python 3",
 198    "language": "python",
 199    "name": "python3"
 200   },
 201   "language_info": {
 202    "codemirror_mode": {
 203     "name": "ipython",
 204     "version": 3
 205    },
 206    "file_extension": ".py",
 207    "mimetype": "text/x-python",
 208    "name": "python",
 209    "nbconvert_exporter": "python",
 210    "pygments_lexer": "ipython3",
 211    "version": "3.12.2"
 212   }
 213  },
 214  "nbformat": 4,
 215  "nbformat_minor": 2
 216 }