Add year metadata column

[dotfiles.git] / data / issues.ipynb

diff --git a/data/issues.ipynb b/data/issues.ipynb
index 735326e771234919ff27dd251456e45fbfdf1a3c..08d596b1b3916d78e94e01406fa07061b98c190d 100644 (file)
--- a/data/issues.ipynb
+++ b/data/issues.ipynb
@@ -2,7 +2,34 @@
  "cells": [
   {
    "cell_type": "code",
  "cells": [
   {
    "cell_type": "code",

-   "execution_count": 2,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import platform\n",
+    "import matplotlib.pyplot as plt\n",
+    "print(platform.python_version())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Todo List\n",
+    "\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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,

    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [


@@ -10,7 +37,11 @@
     "import glob\n",
     "import os\n",
     "\n",
     "import glob\n",
     "import os\n",
     "\n",

-    "data_files = glob.glob(os.path.expanduser('~\\\\Data\\\\*.json'))\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",
+    "\n"

    ]
   },
   {
    ]
   },
   {


@@ -19,28 +50,34 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "import os\n",
+    "import pandas as pd\n",

     "\n",
     "\n",

+    "data_frames = []\n",

     "for file in data_files:\n",
     "for file in data_files:\n",

-    "\tprint(f\"{file}\", os.path.getsize(file))\n"
+    "\n",
+    "\tf = open(file, encoding='utf-8')\n",
+    "\tdf_temp = pd.read_json(f)\n",
+    "\tdata_frames.append(df_temp)\n",
+    "\n",
+    "df = pd.concat(data_frames, ignore_index=True)"

    ]
   },
   {
    "cell_type": "code",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 5,
+   "execution_count": null,

    "metadata": {},
    "metadata": {},

-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3.12.2\n"
-     ]
-    }
-   ],
+   "outputs": [],

    "source": [
    "source": [

-    "import platform\n",
-    "print(platform.python_version())"
+    "import numpy as np\n",
+    "df['count'] = np.zeros(len(df))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Pie Chart"

    ]
   },
   {
    ]
   },
   {


@@ -49,32 +86,23 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "import pandas as pd\n",
-    "\n",
-    "data_sets = []\n",
-    "\n",
-    "file = data_files[6]\n",
-    "print(file)\n",

     "\n",
     "\n",

-    "f = open(file, encoding='utf-16')\n",
-    "df = pd.read_json(f)"
+    "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",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 26,
+   "execution_count": null,

    "metadata": {},
    "metadata": {},

-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas._libs.tslibs.timestamps.Timestamp'>\n"
-     ]
-    }
-   ],
+   "outputs": [],

    "source": [
    "source": [

-    "print(type(df.closed[0]))"
+    "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)"

    ]
   },
   {
    ]
   },
   {


@@ -83,9 +111,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "import numpy as np\n",
-    "df['count'] = np.zeros(len(df))\n",
-    "\n"
+    "\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)"

    ]
   },
   {
    ]
   },
   {


@@ -94,45 +127,51 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "print(df.milestone[22].get('title'))"
+    "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",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 68,
+   "execution_count": null,

    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
-    "df['closed_month'] = closed_months.dt.month"
+    "\n",
+    "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()"

    ]
   },
   {
    "cell_type": "code",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 69,
+   "execution_count": null,

    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "df['mile'] = [d.get('title') if d else None for d in df.milestone]"
+    "type(mile_counts)"

    ]
   },
   {
    ]
   },
   {

-   "cell_type": "code",
-   "execution_count": 39,
+   "cell_type": "markdown",

    "metadata": {},
    "metadata": {},

-   "outputs": [],

    "source": [
    "source": [

-    "for_plot = df.groupby(df.closed.dt.month)['url'].count()"
+    "#### Plot of closed issues by month and milestone for one project\n"

    ]
   },
   {
    "cell_type": "code",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 70,
+   "execution_count": null,

    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "\n",
-    "grp_df = df.groupby(['mile', 'closed_month']).count().reset_index()"
+    "closed_months = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
+    "df['closed_month'] = closed_months.dt.month\n",
+    "df.drop(columns=['closedAt'], inplace=True)"

    ]
   },
   {
    ]
   },
   {


@@ -141,14 +180,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "print(grp_df)"
+    "df['mile'] = [d.get('title') if d else None for d in df.milestone]"

    ]
   },
   {
    ]
   },
   {

-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,

    "metadata": {},
    "metadata": {},

+   "outputs": [],

    "source": [
    "source": [

-    "#### Plot of closed issues by month for one project\n"
+    "\n",
+    "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n",
+    "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\n"

    ]
   },
   {
    ]
   },
   {


@@ -157,12 +200,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [

-    "for_plot.plot(kind='bar')"
+    "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",
    ]
   },
   {
    "cell_type": "code",

-   "execution_count": 75,
+   "execution_count": null,

    "metadata": {},
    "outputs": [],
    "source": [
    "metadata": {},
    "outputs": [],
    "source": [


@@ -178,7 +225,8 @@
    "outputs": [],
    "source": [
     "plt.figure(figsize=(10, 6))\n",
    "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",
     "plt.xlabel('Closed Month')\n",
     "plt.ylabel('ClosedAt')\n",
     "plt.title('Stacked Line Chart: Milestone Effort by Issue Close Date')\n",