X-Git-Url: https://us-delaporte.pagekite.me/gitweb/dotfiles.git/blobdiff_plain/39aa091f5951f7dde7ae65831749d9c5d03b8b51..72a71a545ddfbb9250308146efdda18f8ebcdfc1:/data/issues.ipynb diff --git a/data/issues.ipynb b/data/issues.ipynb index 011beec..6c081fe 100644 --- a/data/issues.ipynb +++ b/data/issues.ipynb @@ -45,7 +45,8 @@ "\n", "data_sets = []\n", "\n", - "file = data_files[2]\n", + "# file = data_files[6] # CLI Tools\n", + "file = data_files[2] # Job Aids\n", "print(file)\n", "\n", "f = open(file, encoding='utf-8')\n", @@ -64,14 +65,10 @@ ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "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)" + "#### Pie Chart" ] }, { @@ -80,7 +77,9 @@ "metadata": {}, "outputs": [], "source": [ - "df['mile'] = [d.get('title') if d else None for d in df.milestone]" + "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)" ] }, { @@ -90,8 +89,13 @@ "outputs": [], "source": [ "\n", - "dfg = df.groupby(['mile', 'closed_month']).count().reset_index()\n", - "dfg.drop(columns=['milestone', 'title', 'url'], inplace=True)\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)" ] }, { @@ -100,8 +104,12 @@ "metadata": {}, "outputs": [], "source": [ - "\n", - "print(dfg)" + "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", + "plt.title(f\"Tasks by Milestone\")\n", + "plt.axis('equal')\n", + "plt.show()" ] }, { @@ -113,7 +121,38 @@ }, { "cell_type": "code", - "execution_count": 32, + "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": [ @@ -142,7 +181,8 @@ "outputs": [], "source": [ "plt.figure(figsize=(10, 6))\n", - "sns.barplot(x='closed_month', y='count', hue='mile', data=dfg)\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",