moderne-visualizations-misc 0.71.1__tar.gz → 0.72.0__tar.gz

{moderne_visualizations_misc-0.71.1 → moderne_visualizations_misc-0.72.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: moderne_visualizations_misc
-Version: 0.71.1
+Version: 0.72.0
 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-0.71.1 → moderne_visualizations_misc-0.72.0}/README.md

@@ -18,13 +18,17 @@ jupyter notebook
 
 ## Contributing
 
-Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
+* Install a Python version >= 3.9 and < 3.13 (3.9 recommended). [pyenv](https://github.com/pyenv/pyenv) makes this easy.
 
-Install development requirements:
+* Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
+
+* Install development requirements:
 
 ```bash
 uv sync --dev
 source .venv/bin/activate
+# or on Windows
+source .venv/Scripts/activate
 ```
 
 Run type checking:

{moderne_visualizations_misc-0.71.1 → moderne_visualizations_misc-0.72.0}/moderne_visualizations_misc/composite_recipe_results_sankey.ipynb

@@ -31,9 +31,8 @@
     "# 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",
-    "    ]"
+    "    df = df[df[\"repositoryWithBranch\"].str.contains(\n",
+    "        \"|\".join(repository_filter), case=False)]"
    ]
   },
   {
@@ -54,31 +53,6 @@
     "    .reset_index(name=\"count\")\n",
     ")\n",
     "\n",
-    "\n",
-    "def shorten_ids(df, cols):\n",
-    "    \"\"\"\n",
-    "    Shorten IDs in cols by using the artifact names if there are name collisions\n",
-    "    \"\"\"\n",
-    "    sep = \".\"\n",
-    "    df = df.copy()\n",
-    "    for col in cols:\n",
-    "        # count how many distinct IDs share each suffix\n",
-    "        unique_ids = df[col].unique()\n",
-    "        suffixes = pd.Series(unique_ids).str.rsplit(pat=sep, n=1).str[-1]\n",
-    "        suffix_counts = suffixes.value_counts()\n",
-    "\n",
-    "        # pick either full ID or suffix per row\n",
-    "        row_suffix = df[col].str.rsplit(pat=sep, n=1).str[-1]\n",
-    "        df[col] = np.where(\n",
-    "            row_suffix.map(suffix_counts) > 1,\n",
-    "            df[col],  # conflict → full ID\n",
-    "            row_suffix,  # unique  → artifact name\n",
-    "        )\n",
-    "    return df\n",
-    "\n",
-    "\n",
-    "recipe_counts = shorten_ids(recipe_counts, [\"parentRecipe\", \"recipe\"])\n",
-    "\n",
     "# sort recipe_counts by count\n",
     "recipe_counts = recipe_counts.sort_values(by=[\"count\"], ascending=False)\n",
     "\n",
@@ -111,9 +85,8 @@
     "# 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",
+    "# Format labels with node names and counts\n",
     "def getCount(node):\n",
     "    left = recipe_counts[recipe_counts[\"recipe\"] == node][\"count\"].sum()\n",
     "    if left == 0:\n",
@@ -122,7 +95,12 @@
     "        return left\n",
     "\n",
     "\n",
-    "formatted_labels = [f\"{node} - {getCount(node)}\" for node in all_nodes]\n",
+    "def short_name(node):\n",
+    "    return node.split(\".\")[-1]\n",
+    "\n",
+    "\n",
+    "formatted_labels = [f\"{short_name(node)} - {getCount(node)}\" for node in all_nodes]\n",
+    "\n",
     "base_colors = [\n",
     "    \"#2f42ff\",\n",
     "    \"#7e9bd2\",\n",
@@ -148,6 +126,13 @@
     "        colors.append(base_colors[i % len(base_colors)])\n",
     "\n",
     "\n",
+    "# Create custom data for links to show full node names\n",
+    "link_customdata = []\n",
+    "for i in range(len(source)):\n",
+    "    source_name = all_nodes[source[i]]\n",
+    "    target_name = all_nodes[target[i]]\n",
+    "    link_customdata.append([source_name, target_name])\n",
+    "\n",
     "# Create the Sankey diagram\n",
     "fig = go.Figure(\n",
     "    data=[\n",
@@ -158,11 +143,16 @@
     "                line=dict(color=\"black\", width=0.5),\n",
     "                label=formatted_labels,\n",
     "                color=colors,\n",
+    "                customdata=all_nodes,\n",
+    "                hovertemplate=\"<b>%{customdata}</b><extra></extra>\",\n",
+    "\n",
     "            ),\n",
     "            link=dict(\n",
     "                source=source,\n",
     "                target=target,\n",
     "                value=value,\n",
+    "                customdata=link_customdata,\n",
+    "                hovertemplate=\"<b>Source:</b> %{customdata[0]}<br><b>Target:</b> %{customdata[1]}<br><b>Count:</b> %{value}<extra></extra>\",\n",
     "            ),\n",
     "        )\n",
     "    ]\n",
@@ -172,16 +162,16 @@
     "fig.update_layout(\n",
     "    title_text=\"Recipes that made changes\",\n",
     "    font_size=10,\n",
-    "    height=max(len(all_nodes) * 15, 400),\n",
+    "    height=max(len(all_nodes) * 10, 500),\n",
     ")\n",
     "\n",
-    "fig.show()"
+    "fig.show()\n"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "moderne-visualizations-misc",
    "language": "python",
    "name": "python3"
   },

moderne_visualizations_misc-0.72.0/moderne_visualizations_misc/dependency_vulnerabilities.ipynb

@@ -0,0 +1,45 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": [
+     "parameters"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "repository_filter: list[str] = []"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": "import pandas as pd\nimport warnings\nimport plotly.graph_objects as go\nimport code_data_science.data_table as dt\n\nwarnings.simplefilter(\"ignore\")\n\ndf = dt.read_csv(\"../samples/dependency_vulnerabilities.csv\")\n\ndf[\"repositoryWithBranch\"] = df[\"repositoryPath\"] + \"/\" + df[\"repositoryBranch\"]\n\n# Filter the data frame to only include rows where repositoryWithBranch contain\n# a term in the repository_filter (case insensitive)\nif len(repository_filter) > 0:\n    df = df[\n        df[\"repositoryWithBranch\"].str.contains(\"|\".join(repository_filter), case=False)\n    ]\n\n\ndef create_bar_plot(df_direct, df_transitive):\n    if df_direct is None or df_transitive is None:\n        # Create empty dataframes with the correct structure\n        fix_types = [\"Patch\", \"Minor\", \"Major\", \"No fixed version\"]\n        df_direct = pd.DataFrame({\n            \"Type\": fix_types,\n            \"Low\": [0] * 4,\n            \"Moderate\": [0] * 4,\n            \"High\": [0] * 4,\n            \"Critical\": [0] * 4,\n        })\n        df_transitive = pd.DataFrame({\n            \"Type\": fix_types,\n            \"Low\": [0] * 4,\n            \"Moderate\": [0] * 4,\n            \"High\": [0] * 4,\n            \"Critical\": [0] * 4,\n        })\n\n    fig = go.Figure()\n    \n    # Define colors for severity levels\n    colors = {\n        \"Critical\": \"#FF5B5B\",\n        \"High\": \"#FABA49\",\n        \"Moderate\": \"#FEE968\",\n        \"Low\": \"#52BBA0\"\n    }\n    \n    # Calculate totals for percentage calculations\n    df_direct[\"Total\"] = df_direct[[\"Critical\", \"High\", \"Moderate\", \"Low\"]].sum(axis=1)\n    df_transitive[\"Total\"] = df_transitive[[\"Critical\", \"High\", \"Moderate\", \"Low\"]].sum(axis=1)\n    grand_total = df_direct[\"Total\"].sum() + df_transitive[\"Total\"].sum()\n    \n    # Add traces for direct dependencies\n    for i, severity in enumerate([\"Critical\", \"High\", \"Moderate\", \"Low\"]):\n        # Calculate percentages for hover\n        percentages_direct = []\n        for idx in range(len(df_direct)):\n            count = df_direct.iloc[idx][severity]\n            total_in_category = df_direct.iloc[idx][\"Total\"] + df_transitive.iloc[idx][\"Total\"]\n            pct_of_category = (count / total_in_category * 100) if total_in_category > 0 else 0\n            pct_of_all = (count / grand_total * 100) if grand_total > 0 else 0\n            percentages_direct.append({\n                \"category_pct\": round(pct_of_category, 1),\n                \"total_pct\": round(pct_of_all, 1)\n            })\n        \n        fig.add_trace(go.Bar(\n            name=severity,\n            x=df_direct[\"Type\"],\n            y=df_direct[severity],\n            marker_color=colors[severity],\n            legendgroup=severity,\n            offsetgroup=\"direct\",\n            showlegend=True,\n            customdata=percentages_direct,\n            hovertemplate=(\n                '<b>%{x}</b><br>' +\n                f'{severity} (Direct): %{{y}}<br>' +\n                'Percent of %{x}: %{customdata.category_pct}%<br>' +\n                'Percent of all: %{customdata.total_pct}%' +\n                '<extra></extra>'\n            )\n        ))\n    \n    # Add traces for transitive dependencies\n    for i, severity in enumerate([\"Critical\", \"High\", \"Moderate\", \"Low\"]):\n        # Calculate percentages for hover\n        percentages_transitive = []\n        for idx in range(len(df_transitive)):\n            count = df_transitive.iloc[idx][severity]\n            total_in_category = df_direct.iloc[idx][\"Total\"] + df_transitive.iloc[idx][\"Total\"]\n            pct_of_category = (count / total_in_category * 100) if total_in_category > 0 else 0\n            pct_of_all = (count / grand_total * 100) if grand_total > 0 else 0\n            percentages_transitive.append({\n                \"category_pct\": round(pct_of_category, 1),\n                \"total_pct\": round(pct_of_all, 1)\n            })\n        \n        fig.add_trace(go.Bar(\n            name=f'{severity} ',  # Add space to make it different from direct\n            x=df_transitive[\"Type\"],\n            y=df_transitive[severity],\n            marker_color=colors[severity],\n            marker_pattern_shape=\"/\",\n            legendgroup=severity,\n            offsetgroup=\"transitive\",\n            showlegend=False,  # Hide from legend since we'll use annotations\n            customdata=percentages_transitive,\n            hovertemplate=(\n                '<b>%{x}</b><br>' +\n                f'{severity} (Transitive): %{{y}}<br>' +\n                'Percent of %{x}: %{customdata.category_pct}%<br>' +\n                'Percent of all: %{customdata.total_pct}%' +\n                '<extra></extra>'\n            )\n        ))\n    \n    # Update layout with improved legend\n    fig.update_layout(\n        xaxis={\"title\": \"Type of version required to fix vulnerability\"},\n        yaxis={\"title\": \"Vulnerability count\"},\n        barmode='group',\n        bargap=0.15,\n        bargroupgap=0.05,\n        margin=dict(l=0, r=0, t=60, b=60),\n        legend=dict(\n            orientation=\"v\",\n            yanchor=\"top\",\n            y=0.95,\n            xanchor=\"left\",\n            x=1.02,\n            title=dict(\n                text=\"Severity Level<br><sub>Solid: Direct | Striped: Transitive</sub>\",\n                font=dict(size=12)\n            )\n        ),\n        annotations=[\n            dict(\n                text=\"<b>Dependency Vulnerabilities by Fix Type</b>\",\n                xref=\"paper\",\n                yref=\"paper\",\n                x=0.5,\n                y=1.05,\n                showarrow=False,\n                font=dict(size=14)\n            )\n        ]\n    )\n    \n    return fig\n\n\n# Exit early if there are no stack traces and render a plot with a message\nif len(df) == 0:\n    fig = create_bar_plot(None, None)\n    fig.update_yaxes(range=[0, 10])\n    fig.show(render=\"plotly_mimetype\")\nelse:\n\n    def get_semver_fix(version, fixed_version):\n        \"\"\"\n        looks at current version and fixed version and determines if the fix is a major, minor, patch version, or no fix\n        \"\"\"\n        version_components = version.split(\".\")\n        fixed_components = fixed_version.split(\".\")\n\n        # if fixed version is empty, return \"No fixed version\"\n        if fixed_version == \"\":\n            return \"No fixed version\"\n\n        if len(version_components) < 3:\n            # fill in the missing version components with 0\n            for i in range(3 - len(version_components)):\n                version_components.append(\"0\")\n        if len(fixed_components) < 3:\n            # fill in the missing version components with 0\n            for i in range(3 - len(fixed_components)):\n                fixed_components.append(\"0\")\n\n        elif version_components[0] != fixed_components[0]:\n            return \"Major\"\n        elif version_components[1] != fixed_components[1]:\n            return \"Minor\"\n        elif version_components[2] != fixed_components[2]:\n            return \"Patch\"\n        else:\n            return \"Unknown\"\n\n    # drop unnecessary columns except depth which we need\n    df = df.drop(\n        columns=[\n            \"repositoryOrigin\",\n            \"repositoryPath\",\n            \"repositoryBranch\",\n            \"repositoryWithBranch\",\n            \"cve\",\n            \"groupId\",\n            \"artifactId\",\n            \"summary\",\n        ]\n    )\n\n    # fill NaN values with empty string\n    df[\"fixedVersion\"] = df[\"fixedVersion\"].fillna(\"\")\n    df[\"version\"] = df[\"version\"].fillna(\"\")\n    # make sure version and fixedVersion is a string\n    df[\"fixedVersion\"] = df[\"fixedVersion\"].astype(str)\n    df[\"version\"] = df[\"version\"].astype(str)\n\n    # add column 'semverFix' to dataframe\n    df[\"semverFix\"] = df.apply(\n        lambda x: get_semver_fix(x[\"version\"], x[\"fixedVersion\"]), axis=1\n    )\n    \n    # Split into direct and transitive\n    df_direct = df[df[\"depth\"] == 0]\n    df_transitive = df[df[\"depth\"] != 0]\n    \n    # Define the order for fix types\n    fix_order = [\"Patch\", \"Minor\", \"Major\", \"No fixed version\"]\n    \n    # Create aggregated data for direct dependencies\n    direct_data = []\n    for fix_type in fix_order:\n        fix_df = df_direct[df_direct[\"semverFix\"] == fix_type]\n        severity_counts = fix_df[\"severity\"].value_counts()\n        direct_data.append({\n            \"Type\": fix_type,\n            \"Critical\": severity_counts.get(\"CRITICAL\", 0),\n            \"High\": severity_counts.get(\"HIGH\", 0),\n            \"Moderate\": severity_counts.get(\"MODERATE\", 0),\n            \"Low\": severity_counts.get(\"LOW\", 0)\n        })\n    df_direct_plot = pd.DataFrame(direct_data)\n    \n    # Create aggregated data for transitive dependencies\n    transitive_data = []\n    for fix_type in fix_order:\n        fix_df = df_transitive[df_transitive[\"semverFix\"] == fix_type]\n        severity_counts = fix_df[\"severity\"].value_counts()\n        transitive_data.append({\n            \"Type\": fix_type,\n            \"Critical\": severity_counts.get(\"CRITICAL\", 0),\n            \"High\": severity_counts.get(\"HIGH\", 0),\n            \"Moderate\": severity_counts.get(\"MODERATE\", 0),\n            \"Low\": severity_counts.get(\"LOW\", 0)\n        })\n    df_transitive_plot = pd.DataFrame(transitive_data)\n\n    fig = create_bar_plot(df_direct_plot, df_transitive_plot)\n\n    # Show the figure\n    fig.show(render=\"plotly_mimetype\")"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

{moderne_visualizations_misc-0.71.1 → moderne_visualizations_misc-0.72.0}/moderne_visualizations_misc.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: moderne_visualizations_misc
-Version: 0.71.1
+Version: 0.72.0
 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-0.71.1 → moderne_visualizations_misc-0.72.0}/pyproject.toml

@@ -1,7 +1,7 @@
 # @see https://packaging.python.org/en/latest/specifications/declaring-project-metadata/
 [project]
 name = "moderne_visualizations_misc"
-version = "0.71.1"
+version = "0.72.0"
 description = "Miscellaneous visualizations for the Moderne platform"
 authors = [
     { name = "Jonathan Schneider", email = "jonathan@moderne.io" },