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     "import matplotlib.pyplot as plt\n",
  11     "print(platform.python_version())"
  12    ]
  13   },
  14   {
  15    "cell_type": "markdown",
  16    "metadata": {},
  17    "source": []
  18   },
  19   {
  20    "cell_type": "markdown",
  21    "metadata": {},
  22    "source": [
  23     "# Todo List\n",
  24     "\n",
  25     "- [x] add calculated year to the metadata\n",
  26     "- [ ] make one chart per year\n",
  27     "- [x] make sure all the data files are getting loaded"
  28    ]
  29   },
  30   {
  31    "cell_type": "code",
  32    "execution_count": null,
  33    "metadata": {},
  34    "outputs": [],
  35    "source": [
  36     "# Get ye data\n",
  37     "import glob\n",
  38     "import os\n",
  39     "\n",
  40     "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\n",
  41     "\n",
  42     "for file in data_files:\n",
  43     "\tprint(f\"{file}\", os.path.getsize(file))\n",
  44     "\n"
  45    ]
  46   },
  47   {
  48    "cell_type": "code",
  49    "execution_count": null,
  50    "metadata": {},
  51    "outputs": [],
  52    "source": [
  53     "import pandas as pd\n",
  54     "\n",
  55     "data_frames = []\n",
  56     "for file in data_files:\n",
  57     "\n",
  58     "\tf = open(file, encoding='utf-8')\n",
  59     "\tdf_temp = pd.read_json(f)\n",
  60     "\tdata_frames.append(df_temp)\n",
  61     "\n",
  62     "df = pd.concat(data_frames, ignore_index=True)"
  63    ]
  64   },
  65   {
  66    "cell_type": "code",
  67    "execution_count": null,
  68    "metadata": {},
  69    "outputs": [],
  70    "source": [
  71     "import numpy as np\n",
  72     "df['count'] = np.zeros(len(df))\n",
  73     "\n"
  74    ]
  75   },
  76   {
  77    "cell_type": "markdown",
  78    "metadata": {},
  79    "source": [
  80     "#### Pie Chart"
  81    ]
  82   },
  83   {
  84    "cell_type": "code",
  85    "execution_count": null,
  86    "metadata": {},
  87    "outputs": [],
  88    "source": [
  89     "\n",
  90     "dfp = df\n",
  91     "# dfp['mile'] = [m.get('title') if m else None for m in dfp.milestone]\n",
  92     "dfp['mile'] = [m.get('title') if hasattr(m, 'get') else None for m in dfp['milestone']]\n"
  93    ]
  94   },
  95   {
  96    "cell_type": "code",
  97    "execution_count": null,
  98    "metadata": {},
  99    "outputs": [],
 100    "source": [
 101     "closed_dates = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
 102     "dfp['year'] = closed_dates.dt.year\n",
 103     "\n",
 104     "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)\n",
 105     "print(dfp)"
 106    ]
 107   },
 108   {
 109    "cell_type": "code",
 110    "execution_count": null,
 111    "metadata": {},
 112    "outputs": [],
 113    "source": [
 114     "\n",
 115     "mile_counts = dfp.groupby('mile')['title'].nunique()\n",
 116     "dfp['count'] = dfp['mile'].map(mile_counts)\n",
 117     "# dfp.drop(columns=['title'], inplace=True)\n",
 118     "dfp['mile'] = df['mile'].drop_duplicates()\n",
 119     "dfp.dropna(inplace=True)\n",
 120     "dfp = dfp[dfp['count'] > 5]\n",
 121     "print(dfp)"
 122    ]
 123   },
 124   {
 125    "cell_type": "code",
 126    "execution_count": null,
 127    "metadata": {},
 128    "outputs": [],
 129    "source": [
 130     "mile_counts = df.groupby('mile')['count'].sum()\n",
 131     "mile_counts = mile_counts.loc[lambda x: x > 5]\n",
 132     "\n",
 133     "\n",
 134     "print(mile_counts)"
 135    ]
 136   },
 137   {
 138    "cell_type": "code",
 139    "execution_count": null,
 140    "metadata": {},
 141    "outputs": [],
 142    "source": [
 143     "\n",
 144     "plt.pie(mile_counts, labels=mile_counts.index, autopct='%0.1f%%')\n",
 145     "plt.title(f\"Tasks by Milestone\")\n",
 146     "plt.axis('equal')\n",
 147     "plt.show()"
 148    ]
 149   },
 150   {
 151    "cell_type": "code",
 152    "execution_count": null,
 153    "metadata": {},
 154    "outputs": [],
 155    "source": [
 156     "type(mile_counts)"
 157    ]
 158   },
 159   {
 160    "cell_type": "markdown",
 161    "metadata": {},
 162    "source": [
 163     "#### Plot of closed issues by month and milestone for one project\n"
 164    ]
 165   },
 166   {
 167    "cell_type": "code",
 168    "execution_count": null,
 169    "metadata": {},
 170    "outputs": [],
 171    "source": [
 172     "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
 173     "df['closed_month'] = closed_months.dt.month\n",
 174     "df.drop(columns=['closedAt'], inplace=True)"
 175    ]
 176   },
 177   {
 178    "cell_type": "code",
 179    "execution_count": null,
 180    "metadata": {},
 181    "outputs": [],
 182    "source": [
 183     "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
 184    ]
 185   },
 186   {
 187    "cell_type": "code",
 188    "execution_count": null,
 189    "metadata": {},
 190    "outputs": [],
 191    "source": [
 192     "\n",
 193     "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
 194     "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\n"
 195    ]
 196   },
 197   {
 198    "cell_type": "code",
 199    "execution_count": null,
 200    "metadata": {},
 201    "outputs": [],
 202    "source": [
 203     "exclude_from_chart = [\n",
 204     "\t'Job Aid Ideas']\n",
 205     "\n",
 206     "for ex in exclude_from_chart:\n",
 207     "\tdfg = dfg[dfg['mile'] != ex]\n"
 208    ]
 209   },
 210   {
 211    "cell_type": "code",
 212    "execution_count": null,
 213    "metadata": {},
 214    "outputs": [],
 215    "source": [
 216     "import seaborn as sns\n",
 217     "import matplotlib.pyplot as plt\n",
 218     "sns.set_theme()"
 219    ]
 220   },
 221   {
 222    "cell_type": "code",
 223    "execution_count": null,
 224    "metadata": {},
 225    "outputs": [],
 226    "source": [
 227     "plt.figure(figsize=(10, 6))\n",
 228     "sns.pie(x='closed_month', y='count', hue='mile', data=dfg)\n",
 229     "plt.pie(dfg, )\n",
 230     "plt.xlabel('Closed Month')\n",
 231     "plt.ylabel('ClosedAt')\n",
 232     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",
 233     "plt.xticks(rotation=45)\n",
 234     "plt.legend(title='Mile', loc='upper left')\n",
 235     "plt.show()"
 236    ]
 237   }
 238  ],
 239  "metadata": {
 240   "kernelspec": {
 241    "display_name": "Python 3",
 242    "language": "python",
 243    "name": "python3"
 244   },
 245   "language_info": {
 246    "codemirror_mode": {
 247     "name": "ipython",
 248     "version": 3
 249    },
 250    "file_extension": ".py",
 251    "mimetype": "text/x-python",
 252    "name": "python",
 253    "nbconvert_exporter": "python",
 254    "pygments_lexer": "ipython3",
 255    "version": "3.12.2"
 256   }
 257  },
 258  "nbformat": 4,
 259  "nbformat_minor": 2
 260 }