feat: Add unit measurement to language composition notebooks (#25)

moderne_visualizations_misc/language_composition.ipynb

@@ -14,6 +14,19 @@
     "This report shows the different languages that are used in the projects."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "parameters"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "unit: str = \"files\""
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -26,6 +39,7 @@
     "import code_data_science.palette as palette\n",
     "\n",
     "df = dt.read_csv(\"../samples/language_composition.csv\")\n",
+    "df[\"files\"] = 1\n",
     "\n",
     "# Exit early if there are no rows and render a plot with a message\n",
     "if len(df) == 0:\n",
@@ -65,16 +79,19 @@
     "        df[(df[\"hasParseFailures\"] == True) & (df[\"fileType\"] == \"java\")]\n",
     "    )\n",
     "\n",
-    "    # sum of lines of text in java files affected by parse failures\n",
+    "    # determine measurement field based on `unit`\n",
+    "    measurement_field = \"files\" if unit == \"files\" else \"linesOfText\"\n",
+    "\n",
+    "    # sum of unit in java files affected by parse failures\n",
     "    total_lines_of_java_affected_by_parse_failures = df[\n",
     "        (df[\"hasParseFailures\"] == True) & (df[\"fileType\"] == \"java\")\n",
-    "    ][\"linesOfText\"].sum()\n",
+    "    ][measurement_field].sum()\n",
     "\n",
     "    # Set the color palette\n",
     "    colors = palette.qualitative()\n",
     "\n",
     "    fig = px.treemap(\n",
-    "        df_file_grouped, path=path, values=\"linesOfText\", color_discrete_sequence=colors\n",
+    "        df_file_grouped, path=path, values=measurement_field, color_discrete_sequence=colors\n",
     "    )\n",
     "\n",
     "    fig.update_layout(\n",
@@ -136,7 +153,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

moderne_visualizations_misc/language_composition_by_repo.ipynb

@@ -14,6 +14,19 @@
     "This report shows the different languages that are used in each repository."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "parameters"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "unit: str = \"files\""
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -25,6 +38,7 @@
     "import code_data_science.palette as palette\n",
     "\n",
     "df = dt.read_csv(\"../samples/language_composition.csv\")\n",
+    "df[\"files\"] = 1\n",
     "\n",
     "# Exit early if there are no rows and render a plot with a message\n",
     "if len(df) == 0:\n",
@@ -72,16 +86,19 @@
     "        df[(df[\"hasParseFailures\"] == True) & (df[\"fileType\"] == \"java\")]\n",
     "    )\n",
     "\n",
+    "    # determine measurement field based on `unit`\n",
+    "    measurement_field = \"files\" if unit == \"files\" else \"linesOfText\"\n",
+    "\n",
     "    # sum of lines of text in java files affected by parse failures\n",
     "    total_lines_of_java_affected_by_parse_failures = df[\n",
     "        (df[\"hasParseFailures\"] == True) & (df[\"fileType\"] == \"java\")\n",
-    "    ][\"linesOfText\"].sum()\n",
+    "    ][measurement_field].sum()\n",
     "\n",
     "    # Set the color palette\n",
     "    colors = palette.qualitative()\n",
     "\n",
     "    fig = px.treemap(\n",
-    "        df_file_grouped, path=path, values=\"linesOfText\", color_discrete_sequence=colors\n",
+    "        df_file_grouped, path=path, values=measurement_field, color_discrete_sequence=colors\n",
     "    )\n",
     "\n",
     "    fig.update_layout(\n",
@@ -143,7 +160,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

moderne_visualizations_misc/specs/language_composition.yml

@@ -5,3 +5,19 @@ displayName: Language composition
 description: This report shows the different languages that are used in the projects.
 recipe: org.openrewrite.LanguageComposition
 dataTable: org.openrewrite.table.LanguageCompositionPerFile
+options:
+  - unit:
+      displayName: Unit
+      description: >
+        Which unit to use when measuring language compositions. Options include `lines` and `files`.
+
+        `lines` will measure language composition by lines of code. `files` will count the number of files with each language.
+
+        Because Moderne cannot parse all languages, you may want to know which files are not being parsed. Measuring by `lines` will
+        only show you successfully-parsed files, as unparseable files cannot have their lines of code counted.
+        
+        Defaults to `lines`.
+      valid:
+        - lines
+        - files
+      required: false

moderne_visualizations_misc/specs/language_composition_by_repo.yml

@@ -5,3 +5,19 @@ displayName: Language composition by repository
 description: This report shows the different languages that are used in each repository.
 recipe: org.openrewrite.LanguageComposition
 dataTable: org.openrewrite.table.LanguageCompositionPerFile
+options:
+  - unit:
+      displayName: Unit
+      description: >
+        Which unit to use when measuring language compositions. Options include `lines` and `files`.
+
+        `lines` will measure language composition by lines of code. `files` will count the number of files with each language.
+
+        Because Moderne cannot parse all languages, you may want to know which files are not being parsed. Measuring by `lines` will
+        only show you successfully-parsed files, as unparseable files cannot have their lines of code counted.
+        
+        Defaults to `lines`.
+      valid:
+        - lines
+        - files
+      required: false