Add file count per commit distribution chart

Author: JohT

cypher/GitLog/List_git_files_per_commit_distribution.cypher

@@ -0,0 +1,6 @@
+// List how many git commits changed one file, how mandy changed two files, ....
+
+MATCH (git_commit:Git:Commit)-[:CONTAINS_CHANGE]->(git_change:Git:Change)-[]->(git_file:Git:File)
+ WITH git_commit, count(DISTINCT git_file.relativePath) AS filesPerCommit
+RETURN filesPerCommit, count(DISTINCT git_commit.sha)   AS commitCount
+ORDER BY filesPerCommit ASC

jupyter/GitHistoryGeneral.ipynb

@@ -197,9 +197,15 @@
    "source": [
     "# Base settings for Plotly Treemap\n",
     "\n",
-    "plotly_treemap_layout_base_settings = dict(\n",
+    "plotly_main_layout_base_settings = dict(\n",
     "    margin=dict(t=50, l=15, r=15, b=15),\n",
     ")\n",
+    "plotly_treemap_layout_base_settings = dict(\n",
+    "    **plotly_main_layout_base_settings\n",
+    ")\n",
+    "plotly_bar_layout_base_settings = dict(\n",
+    "    **plotly_main_layout_base_settings\n",
+    ")\n",
     "plotly_treemap_figure_show_settings = dict(\n",
     "    renderer=\"svg\" if is_command_line_execution() else None,\n",
     "    width=1000,\n",
@@ -512,6 +518,16 @@
    "id": "dc0c2d06",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "git_files_with_commit_statistics.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "053b448d",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "git_files_with_commit_statistics.head(30)"
    ]
@@ -913,6 +929,72 @@
     "figure.show(**plotly_treemap_figure_show_settings)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d8c6ccee",
+   "metadata": {},
+   "source": [
+    "## Filecount per commit\n",
+    "\n",
+    "Shows how many commits had changed one file, how many had changed two files, and so on.\n",
+    "The chart is limited to 30 lines for improved readability.\n",
+    "The data preview also includes overall statistics including the number of commits that are filtered out in the chart."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ed53b6e5",
+   "metadata": {},
+   "source": [
+    "### Preview data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5526e458",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "git_file_count_per_commit = query_cypher_to_data_frame(\"../cypher/GitLog/List_git_files_per_commit_distribution.cypher\")\n",
+    "\n",
+    "print(\"Sum of commits that changed more than 30 files (each) = \" + str(git_file_count_per_commit[git_file_count_per_commit['filesPerCommit'] > 30]['commitCount'].sum()))\n",
+    "print(\"Max changed files with one commit = \" + str(git_file_count_per_commit['filesPerCommit'].max()))\n",
+    "display(git_file_count_per_commit.describe())\n",
+    "display(git_file_count_per_commit.head(30))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dcea826e",
+   "metadata": {},
+   "source": [
+    "### Bar chart with the number of files per commit distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e9dbc57",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if git_file_count_per_commit.empty:\n",
+    "    print(\"No data to plot\")\n",
+    "else:\n",
+    "    figure = plotly_graph_objects.Figure(plotly_graph_objects.Bar(\n",
+    "        x=git_file_count_per_commit['filesPerCommit'].head(30), \n",
+    "        y=git_file_count_per_commit['commitCount'].head(30)),\n",
+    "    )\n",
+    "    figure.update_layout(\n",
+    "        **plotly_bar_layout_base_settings,\n",
+    "        title='Changed files per commit',\n",
+    "        xaxis_title='file count',\n",
+    "        yaxis_title='commit count'\n",
+    "    )\n",
+    "    figure.show(**plotly_treemap_figure_show_settings)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "14e87aff",
@@ -930,8 +1012,8 @@
    "source": [
     "# Query data from graph database\n",
     "git_author_words_with_frequency = query_cypher_to_data_frame(\"../cypher/Overview/Words_for_git_author_Wordcloud_with_frequency.cypher\")\n",
-    "# Debug \n",
-    "# display(git_author_words_with_frequency.head(10))"
+    "\n",
+    "git_author_words_with_frequency.sort_values(by='frequency', ascending=False).reset_index(drop=True).head(10)"
    ]
   },
   {