Cleanup unused columns

[dotfiles.git] / data / issues.ipynb

diff --git a/data/issues.ipynb b/data/issues.ipynb
index 3ffa40cc4173e730ff39f7e396c276988f8d78ae..7608fd74725e3d5037de9943f4c5765fdc252ef7 100644 (file)
--- a/data/issues.ipynb
+++ b/data/issues.ipynb
@@ -2,7 +2,17 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import platform\n",
+    "print(platform.python_version())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,20 +25,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3.12.2\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "import platform\n",
-    "print(platform.python_version())"
+    "import os\n",
+    "\n",
+    "for file in data_files:\n",
+    "\tprint(f\"{file}\", os.path.getsize(file))\n"
    ]
   },
   {
@@ -41,13 +45,81 @@
     "\n",
     "data_sets = []\n",
     "\n",
-    "file = data_files[0]\n",
+    "file = data_files[2]\n",
     "print(file)\n",
     "\n",
-    "f = open(file, encoding='utf-16')\n",
-    "data = pd.read_json(f)\n",
+    "f = open(file, encoding='utf-8')\n",
+    "df = pd.read_json(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "df['count'] = np.zeros(len(df))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
+    "df['closed_month'] = closed_months.dt.month\n",
+    "df.drop(columns=['closedAt'], inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "\n",
-    "print(data)\n"
+    "grp_df = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
+    "grp_df.drop(columns=['milestone', 'title', 'url'], inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "print(grp_df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Plot of closed issues by month and milestone for one project\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "sns.set_theme()"
    ]
   },
   {
@@ -56,9 +128,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import maptploglib.pyplot as platform\n",
-    "# TODO: Get ye data into scatter plot\n",
-    "plt.scatter(x, y)\n",
+    "plt.figure(figsize=(10, 6))\n",
+    "sns.barplot(x='closed_month', y='url', hue='mile', data=grp_df)\n",
+    "plt.xlabel('Closed Month')\n",
+    "plt.ylabel('ClosedAt')\n",
+    "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",
+    "plt.xticks(rotation=45)\n",
+    "plt.legend(title='Mile', loc='upper left')\n",
     "plt.show()"
    ]
   }