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]\n",
  49     "print(file)\n",
  50     "\n",
  51     "f = open(file, encoding='utf-8')\n",
  52     "df = pd.read_json(f)"
  53    ]
  54   },
  55   {
  56    "cell_type": "code",
  57    "execution_count": null,
  58    "metadata": {},
  59    "outputs": [],
  60    "source": [
  61     "import numpy as np\n",
  62     "df['count'] = np.zeros(len(df))\n",
  63     "\n"
  64    ]
  65   },
  66   {
  67    "cell_type": "code",
  68    "execution_count": null,
  69    "metadata": {},
  70    "outputs": [],
  71    "source": [
  72     "dfp = df\n",
  73     "dfp['mile'] = [d.get('title') if d else None for d in dfp.milestone]\n",
  74     "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)"
  75    ]
  76   },
  77   {
  78    "cell_type": "code",
  79    "execution_count": null,
  80    "metadata": {},
  81    "outputs": [],
  82    "source": [
  83     "\n",
  84     "mile_counts = dfp.groupby('mile')['title'].nunique()\n",
  85     "dfp['count'] = dfp['mile'].map(mile_counts)\n",
  86     "# dfp.drop(columns=['title'], inplace=True)\n",
  87     "dfp['mile'] = df['mile'].drop_duplicates()\n",
  88     "dfp.dropna(inplace=True)\n",
  89     "dfp = dfp[dfp['count'] > 5]\n",
  90     "print(dfp)"
  91    ]
  92   },
  93   {
  94    "cell_type": "code",
  95    "execution_count": null,
  96    "metadata": {},
  97    "outputs": [],
  98    "source": [
  99     "mile_counts = df.groupby('mile')['count'].sum()\n",
 100     "mile_counts = mile_counts.loc[lambda x: x > 5]\n",
 101     "plt.pie(mile_counts, labels=mile_counts.index, autopct='%1.1f%%')\n",
 102     "plt.title(f\"Tasks by Milestone\")\n",
 103     "plt.axis('equal')\n",
 104     "plt.show()"
 105    ]
 106   },
 107   {
 108    "cell_type": "code",
 109    "execution_count": null,
 110    "metadata": {},
 111    "outputs": [],
 112    "source": [
 113     "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
 114     "df['closed_month'] = closed_months.dt.month\n",
 115     "df.drop(columns=['closedAt'], inplace=True)"
 116    ]
 117   },
 118   {
 119    "cell_type": "code",
 120    "execution_count": null,
 121    "metadata": {},
 122    "outputs": [],
 123    "source": [
 124     "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
 125    ]
 126   },
 127   {
 128    "cell_type": "code",
 129    "execution_count": null,
 130    "metadata": {},
 131    "outputs": [],
 132    "source": [
 133     "\n",
 134     "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
 135     "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\n"
 136    ]
 137   },
 138   {
 139    "cell_type": "code",
 140    "execution_count": null,
 141    "metadata": {},
 142    "outputs": [],
 143    "source": [
 144     "\n",
 145     "print(dfg)"
 146    ]
 147   },
 148   {
 149    "cell_type": "markdown",
 150    "metadata": {},
 151    "source": [
 152     "#### Plot of closed issues by month and milestone for one project\n"
 153    ]
 154   },
 155   {
 156    "cell_type": "code",
 157    "execution_count": null,
 158    "metadata": {},
 159    "outputs": [],
 160    "source": [
 161     "exclude_from_chart = [\n",
 162     "\t'Job Aid Ideas']\n",
 163     "\n",
 164     "for ex in exclude_from_chart:\n",
 165     "\tdfg = dfg[dfg['mile'] != ex]\n"
 166    ]
 167   },
 168   {
 169    "cell_type": "code",
 170    "execution_count": null,
 171    "metadata": {},
 172    "outputs": [],
 173    "source": [
 174     "import seaborn as sns\n",
 175     "import matplotlib.pyplot as plt\n",
 176     "sns.set_theme()"
 177    ]
 178   },
 179   {
 180    "cell_type": "code",
 181    "execution_count": null,
 182    "metadata": {},
 183    "outputs": [],
 184    "source": [
 185     "plt.figure(figsize=(10, 6))\n",
 186     "sns.pie(x='closed_month', y='count', hue='mile', data=dfg)\n",
 187     "plt.pie(dfg, )\n",
 188     "plt.xlabel('Closed Month')\n",
 189     "plt.ylabel('ClosedAt')\n",
 190     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",
 191     "plt.xticks(rotation=45)\n",
 192     "plt.legend(title='Mile', loc='upper left')\n",
 193     "plt.show()"
 194    ]
 195   }
 196  ],
 197  "metadata": {
 198   "kernelspec": {
 199    "display_name": "Python 3",
 200    "language": "python",
 201    "name": "python3"
 202   },
 203   "language_info": {
 204    "codemirror_mode": {
 205     "name": "ipython",
 206     "version": 3
 207    },
 208    "file_extension": ".py",
 209    "mimetype": "text/x-python",
 210    "name": "python",
 211    "nbconvert_exporter": "python",
 212    "pygments_lexer": "ipython3",
 213    "version": "3.12.2"
 214   }
 215  },
 216  "nbformat": 4,
 217  "nbformat_minor": 2
 218 }