moderne-visualizations-misc 0.58.0__tar.gz → 0.60.0__tar.gz

{moderne_visualizations_misc-0.58.0 → moderne_visualizations_misc-0.60.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: moderne_visualizations_misc
-Version: 0.58.0
+Version: 0.60.0
 Summary: Miscellaneous visualizations for the Moderne platform
 Author-email: Jonathan Schneider <jonathan@moderne.io>, Kyle Scully <kyle@moderne.io>
 License: Apache-2.0

moderne_visualizations_misc-0.60.0/moderne_visualizations_misc/composite_recipe_results_sankey.ipynb

@@ -0,0 +1,167 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "parameters"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "repository_filter: list[str] = []\n",
+        "count_threshold = \"0\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from code_data_science import data_table as dt\n",
+        "import warnings\n",
+        "\n",
+        "warnings.simplefilter(\"ignore\")\n",
+        "\n",
+        "df = dt.read_csv(\"../samples/composite_recipe_results_sankey.csv\")\n",
+        "\n",
+        "df[\"repositoryWithBranch\"] = df[\"repositoryPath\"] + \"/\" + df[\"repositoryBranch\"]\n",
+        "# Filter the data frame to only include rows where repositoryWithBranch contain\n",
+        "# a term in the repository_filter (case insensitive)\n",
+        "if len(repository_filter) > 0:\n",
+        "    df = df[\n",
+        "        df[\"repositoryWithBranch\"].str.contains(\"|\".join(repository_filter), case=False)\n",
+        "    ]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df = df[[\"parentRecipe\", \"recipe\"]].assign(count=lambda r: 1)\n",
+        "recipe_counts = (\n",
+        "    df[[\"parentRecipe\", \"recipe\", \"count\"]]\n",
+        "    .groupby(by=[\"parentRecipe\", \"recipe\"])[\"count\"]\n",
+        "    .count()\n",
+        "    .sort_values(ascending=False)\n",
+        "    .reset_index(name=\"count\")\n",
+        ")\n",
+        "recipe_counts[\"parentRecipe\"] = recipe_counts[\"parentRecipe\"].transform(\n",
+        "    lambda s: s.split(\".\")[-1]\n",
+        ")\n",
+        "recipe_counts[\"recipe\"] = recipe_counts[\"recipe\"].transform(lambda s: s.split(\".\")[-1])\n",
+        "\n",
+        "# sort recipe_counts by count\n",
+        "recipe_counts = recipe_counts.sort_values(by=[\"count\"], ascending=False)\n",
+        "\n",
+        "count_threshold_int = int(count_threshold)\n",
+        "\n",
+        "if count_threshold_int > 0:\n",
+        "    recipe_counts = recipe_counts[recipe_counts[\"count\"] > count_threshold_int]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import plotly.graph_objects as go\n",
+        "\n",
+        "# Extract all unique nodes (parent and child recipes)\n",
+        "all_nodes = list(set(recipe_counts[\"parentRecipe\"]).union(set(recipe_counts[\"recipe\"])))\n",
+        "\n",
+        "# Create node indices mapping for preparing for plotly\n",
+        "node_indices = {node: i for i, node in enumerate(all_nodes)}\n",
+        "\n",
+        "# iterates over each row in recipe_counts and find the index of the 'parentRecipe' in node_indices and adds it to the source list.\n",
+        "source = [node_indices[row[\"parentRecipe\"]] for _, row in recipe_counts.iterrows()]\n",
+        "\n",
+        "# iterates over each row in recipe_counts and find the index of the 'recipe' in node_indices and adds it to the target list.\n",
+        "target = [node_indices[row[\"recipe\"]] for _, row in recipe_counts.iterrows()]\n",
+        "\n",
+        "# convert the 'count' column to a list\n",
+        "value = list(recipe_counts[\"count\"])\n",
+        "\n",
+        "# Format labels with node names and counts\n",
+        "\n",
+        "\n",
+        "def getCount(node):\n",
+        "    left = recipe_counts[recipe_counts[\"recipe\"] == node][\"count\"].sum()\n",
+        "    if left == 0:\n",
+        "        return recipe_counts[recipe_counts[\"parentRecipe\"] == node][\"count\"].sum()\n",
+        "    else:\n",
+        "        return left\n",
+        "\n",
+        "\n",
+        "formatted_labels = [f\"{node} - {getCount(node)}\" for node in all_nodes]\n",
+        "base_colors= [\"#2f42ff\", \"#7e9bd2\", \"#27aa88\", \"#dcefde\", \"#84C9AA\", \"#ECB81F\", \"#F9A91B\", \"#DB4197\", \"#992FB9\", \"#D9D8E8\", \"#FF3232\"]\n",
+        "\n",
+        "# create a color palette for the nodes\n",
+        "# important that the number of colors is equal to the number of nodes\n",
+        "\n",
+        "colors = []\n",
+        "for i in range(len(all_nodes)):\n",
+        "    if i < len(base_colors):\n",
+        "        colors.append(base_colors[i])\n",
+        "    else:\n",
+        "        colors.append(base_colors[i % len(base_colors)])\n",
+        "\n",
+        "\n",
+        "# Create the Sankey diagram\n",
+        "fig = go.Figure(\n",
+        "    data=[\n",
+        "        go.Sankey(\n",
+        "            node=dict(\n",
+        "                pad=15,\n",
+        "                thickness=15,\n",
+        "                line=dict(color=\"black\", width=0.5),\n",
+        "                label=formatted_labels,\n",
+        "                color=colors\n",
+        "            ),\n",
+        "            link=dict(\n",
+        "                source=source,\n",
+        "                target=target,\n",
+        "                value=value,\n",
+        "            ),\n",
+        "        )\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "# Update layout\n",
+        "fig.update_layout(\n",
+        "    title_text=\"Recipes that made changes\",\n",
+        "    font_size=10,\n",
+        "    height=max(len(all_nodes) * 15, 400),\n",
+        ")\n",
+        "\n",
+        "fig.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.4"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}