Add 'Year' column

[dotfiles.git] / data / issues.ipynb

diff --git a/data/issues.ipynb b/data/issues.ipynb
index 6c081fe64749a4425fa37c90d998997534d7692f..7b7f1beab3c807dd91a58881b2290d99bdbb5ba1 100644 (file)
--- a/data/issues.ipynb
+++ b/data/issues.ipynb
@@ -7,9 +7,21 @@
    "outputs": [],
    "source": [
     "import platform\n",
    "outputs": [],
    "source": [
     "import platform\n",

+    "import matplotlib.pyplot as plt\n",

     "print(platform.python_version())"
    ]
   },
     "print(platform.python_version())"
    ]
   },

+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Todo List\n",
+    "\n",
+    "- [ ] trim each chart to just a single, selected year\n",
+    "- [ ] make one chart per year\n",
+    "- [x] make sure all the data files are getting loaded"
+   ]
+  },

   {
    "cell_type": "code",
    "execution_count": null,
   {
    "cell_type": "code",
    "execution_count": null,


@@ -43,14 +55,14 @@
    "source": [
     "import pandas as pd\n",
     "\n",
    "source": [
     "import pandas as pd\n",
     "\n",

-    "data_sets = []\n",
+    "data_frames = []\n",
+    "for file in data_files:\n",

     "\n",
     "\n",

-    "# file = data_files[6]  # CLI Tools\n",
-    "file = data_files[2]  # Job Aids\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",
     "\n",

-    "f = open(file, encoding='utf-8')\n",
-    "df = pd.read_json(f)"
+    "df = pd.concat(data_frames, ignore_index=True)"

    ]
   },
   {
    ]
   },
   {


@@ -79,7 +91,12 @@
    "source": [
     "dfp = df\n",
     "dfp['mile'] = [d.get('title') if d else None for d in dfp.milestone]\n",
    "source": [
     "dfp = df\n",
     "dfp['mile'] = [d.get('title') if d else None for d in dfp.milestone]\n",

-    "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)"
+    "closed_dates = pd.to_datetime(df['closedAt'], format='ISO8601')\n",
+    "dfp['year'] = closed_dates.dt.year\n",
+    "\n",
+    "# TODO: Split by YEAR before dropping 'closedAt'\n",
+    "dfp.drop(columns=['closedAt','milestone', 'url'], inplace=True)\n",
+    "print(dfp)"

    ]
   },
   {
    ]
   },
   {


@@ -106,12 +123,33 @@
    "source": [
     "mile_counts = df.groupby('mile')['count'].sum()\n",
     "mile_counts = mile_counts.loc[lambda x: x > 5]\n",
    "source": [
     "mile_counts = df.groupby('mile')['count'].sum()\n",
     "mile_counts = mile_counts.loc[lambda x: x > 5]\n",

-    "plt.pie(mile_counts, labels=mile_counts.index, autopct='%1.1f%%')\n",
+    "\n",
+    "\n",
+    "print(mile_counts)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\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()"
    ]
   },
     "plt.title(f\"Tasks by Milestone\")\n",
     "plt.axis('equal')\n",
     "plt.show()"
    ]
   },

+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "type(mile_counts)"
+   ]
+  },

   {
    "cell_type": "markdown",
    "metadata": {},
   {
    "cell_type": "markdown",
    "metadata": {},