X-Git-Url: https://apps.delaporte.us/gitweb/dotfiles.git/blobdiff_plain/9cad6021b47e3b4d285c08a4f2e57cfd7b23cef0..2d0d87d37d5fa18c22a74f80bb8f90b2dd882b01:/data/issues.ipynb

diff --git a/data/issues.ipynb b/data/issues.ipynb
index 3340aaf..08d596b 100644
--- a/data/issues.ipynb
+++ b/data/issues.ipynb
@@ -2,33 +2,29 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3.12.2\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import platform\n",
+    "import matplotlib.pyplot as plt\n",
     "print(platform.python_version())"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 92,
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "# Get ye data\n",
-    "import glob\n",
-    "import os\n",
+    "# Todo List\n",
     "\n",
-    "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\n"
+    "- [x] add calculated year to the metadata\n",
+    "- [ ] make one chart per year\n",
+    "- [x] make sure all the data files are getting loaded"
    ]
   },
   {
@@ -37,10 +33,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Get ye data\n",
+    "import glob\n",
     "import os\n",
     "\n",
+    "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\n",
+    "\n",
     "for file in data_files:\n",
-    "\tprint(f\"{file}\", os.path.getsize(file))\n"
+    "\tprint(f\"{file}\", os.path.getsize(file))\n",
+    "\n"
    ]
   },
   {
@@ -51,18 +52,19 @@
    "source": [
     "import pandas as pd\n",
     "\n",
-    "data_sets = []\n",
+    "data_frames = []\n",
+    "for file in data_files:\n",
     "\n",
-    "file = data_files[6]\n",
-    "print(file)\n",
+    "\tf = open(file, encoding='utf-8')\n",
+    "\tdf_temp = pd.read_json(f)\n",
+    "\tdata_frames.append(df_temp)\n",
     "\n",
-    "f = open(file, encoding='utf-8')\n",
-    "df = pd.read_json(f)"
+    "df = pd.concat(data_frames, ignore_index=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -71,33 +73,78 @@
     "\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Pie Chart"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 95,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
-    "df['closed_month'] = closed_months.dt.month"
+    "\n",
+    "dfp = df\n",
+    "# dfp['mile'] = [m.get('title') if m else None for m in dfp.milestone]\n",
+    "dfp['mile'] = [m.get('title') if hasattr(m, 'get') else None for m in dfp['milestone']]\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
+    "closed_dates = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
+    "dfp['year'] = closed_dates.dt.year\n",
+    "\n",
+    "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)\n",
+    "print(dfp)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "mile_counts = dfp.groupby('mile')['title'].nunique()\n",
+    "dfp['count'] = dfp['mile'].map(mile_counts)\n",
+    "# dfp.drop(columns=['title'], inplace=True)\n",
+    "dfp['mile'] = df['mile'].drop_duplicates()\n",
+    "dfp.dropna(inplace=True)\n",
+    "dfp = dfp[dfp['count'] > 5]\n",
+    "print(dfp)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mile_counts = df.groupby('mile')['count'].sum()\n",
+    "mile_counts = mile_counts.loc[lambda x: x > 5]\n",
+    "\n",
+    "\n",
+    "print(mile_counts)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "\n",
-    "grp_df = df.groupby(['mile', 'closed_month']).count().reset_index()"
+    "plt.pie(mile_counts, labels=mile_counts.index, autopct='%0.1f%%')\n",
+    "plt.title(f\"Tasks by Milestone\")\n",
+    "plt.axis('equal')\n",
+    "plt.show()"
    ]
   },
   {
@@ -106,7 +153,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(grp_df)"
+    "type(mile_counts)"
    ]
   },
   {
@@ -118,7 +165,51 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "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",
+    "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
+    "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "exclude_from_chart = [\n",
+    "\t'Job Aid Ideas']\n",
+    "\n",
+    "for ex in exclude_from_chart:\n",
+    "\tdfg = dfg[dfg['mile'] != ex]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -134,7 +225,8 @@
    "outputs": [],
    "source": [
     "plt.figure(figsize=(10, 6))\n",
-    "sns.lineplot(x='closed_month', y='url', hue='mile', data=grp_df, marker='o', ci=None)\n",
+    "sns.pie(x='closed_month', y='count', hue='mile', data=dfg)\n",
+    "plt.pie(dfg, )\n",
     "plt.xlabel('Closed Month')\n",
     "plt.ylabel('ClosedAt')\n",
     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",