data/issues.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": 2,
   6    "metadata": {},
   7    "outputs": [],
   8    "source": [
   9     "# Get ye data\n",
  10     "import glob\n",
  11     "import os\n",
  12     "\n",
  13     "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\n"
  14    ]
  15   },
  16   {
  17    "cell_type": "code",
  18    "execution_count": null,
  19    "metadata": {},
  20    "outputs": [],
  21    "source": [
  22     "import os\n",
  23     "\n",
  24     "for file in data_files:\n",
  25     "\tprint(f\"{file}\", os.path.getsize(file))\n"
  26    ]
  27   },
  28   {
  29    "cell_type": "code",
  30    "execution_count": 5,
  31    "metadata": {},
  32    "outputs": [
  33     {
  34      "name": "stdout",
  35      "output_type": "stream",
  36      "text": [
  37       "3.12.2\n"
  38      ]
  39     }
  40    ],
  41    "source": [
  42     "import platform\n",
  43     "print(platform.python_version())"
  44    ]
  45   },
  46   {
  47    "cell_type": "code",
  48    "execution_count": null,
  49    "metadata": {},
  50    "outputs": [],
  51    "source": [
  52     "import pandas as pd\n",
  53     "\n",
  54     "data_sets = []\n",
  55     "\n",
  56     "file = data_files[6]\n",
  57     "print(file)\n",
  58     "\n",
  59     "f = open(file, encoding='utf-16')\n",
  60     "df = pd.read_json(f)"
  61    ]
  62   },
  63   {
  64    "cell_type": "code",
  65    "execution_count": 26,
  66    "metadata": {},
  67    "outputs": [
  68     {
  69      "name": "stdout",
  70      "output_type": "stream",
  71      "text": [
  72       "<class 'pandas._libs.tslibs.timestamps.Timestamp'>\n"
  73      ]
  74     }
  75    ],
  76    "source": [
  77     "print(type(df.closed[0]))"
  78    ]
  79   },
  80   {
  81    "cell_type": "code",
  82    "execution_count": null,
  83    "metadata": {},
  84    "outputs": [],
  85    "source": [
  86     "import numpy as np\n",
  87     "df['count'] = np.zeros(len(df))\n",
  88     "\n"
  89    ]
  90   },
  91   {
  92    "cell_type": "code",
  93    "execution_count": null,
  94    "metadata": {},
  95    "outputs": [],
  96    "source": [
  97     "print(df.milestone[22].get('title'))"
  98    ]
  99   },
 100   {
 101    "cell_type": "code",
 102    "execution_count": 68,
 103    "metadata": {},
 104    "outputs": [],
 105    "source": [
 106     "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
 107     "df['closed_month'] = closed_months.dt.month"
 108    ]
 109   },
 110   {
 111    "cell_type": "code",
 112    "execution_count": 69,
 113    "metadata": {},
 114    "outputs": [],
 115    "source": [
 116     "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
 117    ]
 118   },
 119   {
 120    "cell_type": "code",
 121    "execution_count": 39,
 122    "metadata": {},
 123    "outputs": [],
 124    "source": [
 125     "for_plot = df.groupby(df.closed.dt.month)['url'].count()"
 126    ]
 127   },
 128   {
 129    "cell_type": "code",
 130    "execution_count": 70,
 131    "metadata": {},
 132    "outputs": [],
 133    "source": [
 134     "\n",
 135     "grp_df = df.groupby(['mile', 'closed_month']).count().reset_index()"
 136    ]
 137   },
 138   {
 139    "cell_type": "code",
 140    "execution_count": null,
 141    "metadata": {},
 142    "outputs": [],
 143    "source": [
 144     "print(grp_df)"
 145    ]
 146   },
 147   {
 148    "cell_type": "markdown",
 149    "metadata": {},
 150    "source": [
 151     "#### Plot of closed issues by month for one project\n"
 152    ]
 153   },
 154   {
 155    "cell_type": "code",
 156    "execution_count": null,
 157    "metadata": {},
 158    "outputs": [],
 159    "source": [
 160     "for_plot.plot(kind='bar')"
 161    ]
 162   },
 163   {
 164    "cell_type": "code",
 165    "execution_count": 75,
 166    "metadata": {},
 167    "outputs": [],
 168    "source": [
 169     "import seaborn as sns\n",
 170     "import matplotlib.pyplot as plt\n",
 171     "sns.set_theme()"
 172    ]
 173   },
 174   {
 175    "cell_type": "code",
 176    "execution_count": null,
 177    "metadata": {},
 178    "outputs": [],
 179    "source": [
 180     "plt.figure(figsize=(10, 6))\n",
 181     "sns.lineplot(x='closed_month', y='url', hue='mile', data=grp_df, marker='o', ci=None)\n",
 182     "plt.xlabel('Closed Month')\n",
 183     "plt.ylabel('ClosedAt')\n",
 184     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",
 185     "plt.xticks(rotation=45)\n",
 186     "plt.legend(title='Mile', loc='upper left')\n",
 187     "plt.show()"
 188    ]
 189   }
 190  ],
 191  "metadata": {
 192   "kernelspec": {
 193    "display_name": "Python 3",
 194    "language": "python",
 195    "name": "python3"
 196   },
 197   "language_info": {
 198    "codemirror_mode": {
 199     "name": "ipython",
 200     "version": 3
 201    },
 202    "file_extension": ".py",
 203    "mimetype": "text/x-python",
 204    "name": "python",
 205    "nbconvert_exporter": "python",
 206    "pygments_lexer": "ipython3",
 207    "version": "3.12.2"
 208   }
 209  },
 210  "nbformat": 4,
 211  "nbformat_minor": 2
 212 }