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