data-designer 0.3.0__tar.gz → 0.3.2__tar.gz

{data_designer-0.3.0 → data_designer-0.3.2}/.github/workflows/ci.yml

@@ -36,6 +36,30 @@ jobs:
         run: |
           uv run pytest -v --cov=data_designer --cov-report=term-missing --cov-report=xml --cov-fail-under=90
 
+  test-e2e:
+    name: End to end test (Python ${{ matrix.python-version }} on ${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+
+      - name: Run e2e tests
+        run: |
+          make test-e2e
+
   lint:
     name: Lint and Format Check
     runs-on: ubuntu-latest
@@ -70,6 +94,8 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Full history needed for file creation dates
 
       - name: Install uv
         uses: astral-sh/setup-uv@v5

{data_designer-0.3.0 → data_designer-0.3.2}/.gitignore

@@ -91,3 +91,5 @@ docs/notebooks/
 docs/notebook_source/*.ipynb
 docs/notebook_source/*.csv
 docs/**/artifacts/
+
+e2e_tests/uv.lock

{data_designer-0.3.0 → data_designer-0.3.2}/Makefile

@@ -63,28 +63,34 @@ check-all-fix: format lint-fix
 
 format:
 	@echo "📐 Formatting code with ruff..."
-	uv run ruff format src/ tests/ scripts/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff format src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Formatting complete!"
 
 format-check:
 	@echo "📐 Checking code formatting with ruff..."
-	uv run ruff format --check src/ tests/ scripts/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff format --check src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Formatting check complete! Run 'make format' to auto-fix issues."
 
 lint:
 	@echo "🔍 Linting code with ruff..."
-	uv run ruff check --output-format=full src/ tests/ scripts/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff check --output-format=full src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Linting complete! Run 'make lint-fix' to auto-fix issues."
 
 lint-fix:
 	@echo "🔍 Fixing linting issues with ruff..."
-	uv run ruff check --fix src/ tests/ scripts/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff check --fix src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Linting with autofix complete!"
 
 test:
 	@echo "🧪 Running unit tests..."
 	uv run --group dev pytest
 
+test-e2e:
+	@echo "🧹 Cleaning e2e test environment..."
+	rm -rf e2e_tests/uv.lock e2e_tests/.pycache e2e_tests/.venv
+	@echo "🧪 Running e2e tests..."
+	uv run --no-cache --refresh --directory e2e_tests pytest -s
+
 convert-execute-notebooks:
 	@echo "📓 Converting Python tutorials to notebooks and executing..."
 	@mkdir -p docs/notebooks

{data_designer-0.3.0 → data_designer-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.0
+Version: 0.3.2
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -186,7 +186,7 @@ ModelConfig(
         top_p=0.9,
         max_tokens=4096,
     ),
-    )
+)
 ```
 
 The value `openai/gpt-oss-20b` would be collected.

{data_designer-0.3.0 → data_designer-0.3.2}/README.md

@@ -139,7 +139,7 @@ ModelConfig(
         top_p=0.9,
         max_tokens=4096,
     ),
-    )
+)
 ```
 
 The value `openai/gpt-oss-20b` would be collected.

{data_designer-0.3.0 → data_designer-0.3.2}/docs/colab_notebooks/1-the-basics.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "32827bda",
+   "id": "adb0c3cd",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: The Basics\n",
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cbe6b81e",
+   "id": "73d42bda",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -25,7 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5b007eed",
+   "id": "c6675487",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,7 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "58dfdb07",
+   "id": "b98ebeee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "03d07dff",
+   "id": "6e2355bb",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -64,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "749a1536",
+   "id": "95bf5ae3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5c31d723",
+   "id": "ee906a92",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -98,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "826f2421",
+   "id": "15b35cb8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,7 +107,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b6bfc01a",
+   "id": "999ce38a",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -124,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "11aa0146",
+   "id": "f5ab65d5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -154,7 +154,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c10b93a6",
+   "id": "912d7954",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -169,7 +169,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "02ae97ca",
+   "id": "0ba83688",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -178,7 +178,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c4c780c8",
+   "id": "ee2de21d",
    "metadata": {},
    "source": [
     "## 🎲 Getting started with sampler columns\n",
@@ -195,7 +195,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "685417ab",
+   "id": "3009cfa5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6bae388c",
+   "id": "c42c890f",
    "metadata": {},
    "source": [
     "Let's start designing our product review dataset by adding product category and subcategory columns.\n"
@@ -213,7 +213,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6122711b",
+   "id": "16251687",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -294,7 +294,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "12d8c063",
+   "id": "ff41c919",
    "metadata": {},
    "source": [
     "Next, let's add samplers to generate data related to the customer and their review.\n"
@@ -303,7 +303,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c4c21fa0",
+   "id": "78ec15fc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -335,12 +335,12 @@
     "    )\n",
     ")\n",
     "\n",
-    "config_builder.validate()"
+    "data_designer.validate(config_builder)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "be6bd3c8",
+   "id": "8ac2131e",
    "metadata": {},
    "source": [
     "## 🦜 LLM-generated columns\n",
@@ -355,7 +355,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "99e953d8",
+   "id": "d8232495",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -386,12 +386,12 @@
     "    )\n",
     ")\n",
     "\n",
-    "config_builder.validate()"
+    "data_designer.validate(config_builder)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "ec30007b",
+   "id": "9105ddf2",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -408,7 +408,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7ac1f25b",
+   "id": "a6b02b74",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -418,7 +418,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "67d8dff4",
+   "id": "74a4a386",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +429,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f78e4d9f",
+   "id": "b1be4d95",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -439,7 +439,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ee838ed6",
+   "id": "c2871df4",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -452,7 +452,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4bea0fca",
+   "id": "b2beb476",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -462,7 +462,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "da9875d4",
+   "id": "765fb038",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -475,7 +475,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8c7f20b4",
+   "id": "f4fc625e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -485,7 +485,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2f5fdaa8",
+   "id": "58989731",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -498,7 +498,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5c2d935f",
+   "id": "80351a24",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a80515b7",
+   "id": "cc79ae74",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",

{data_designer-0.3.0 → data_designer-0.3.2}/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "ba3eb53c",
+   "id": "166f4a41",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Structured Outputs and Jinja Expressions\n",
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "71e3de28",
+   "id": "00a139eb",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -27,7 +27,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f12bda54",
+   "id": "a60a4a4e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c8e1f477",
+   "id": "14fc001f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "efc5ac26",
+   "id": "22c4fe6b",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -66,7 +66,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3ffd67ca",
+   "id": "b2f8e13d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "782aaacd",
+   "id": "e644b2a8",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -100,7 +100,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1b092ccc",
+   "id": "74b146e7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +109,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cf4e19e2",
+   "id": "7471f914",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -126,7 +126,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ff05156e",
+   "id": "ea1fcee5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -156,7 +156,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bfbac905",
+   "id": "53855c58",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -171,7 +171,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d2c7a5d7",
+   "id": "74064875",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,7 +180,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6fb54697",
+   "id": "808534e9",
    "metadata": {},
    "source": [
     "### 🧑‍🎨 Designing our data\n",
@@ -207,7 +207,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0ea9bb0f",
+   "id": "26d84a29",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -235,7 +235,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "987fbf33",
+   "id": "624111a6",
    "metadata": {},
    "source": [
     "Next, let's design our product review dataset using a few more tricks compared to the previous notebook.\n"
@@ -244,7 +244,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9960d332",
+   "id": "c63fbc58",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -353,7 +353,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "81f8d04a",
+   "id": "60832414",
    "metadata": {},
    "source": [
     "Next, we will use more advanced Jinja expressions to create new columns.\n",
@@ -370,7 +370,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e9583bf7",
+   "id": "0964aff9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -418,12 +418,12 @@
     "    )\n",
     ")\n",
     "\n",
-    "config_builder.validate()"
+    "data_designer.validate(config_builder)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "c79829f3",
+   "id": "a818e85f",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -440,7 +440,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "cceb2346",
+   "id": "4af25c1e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -450,7 +450,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4c35a66e",
+   "id": "2594a896",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -461,7 +461,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c5cd23a7",
+   "id": "bfffec10",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -471,7 +471,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2486fc8b",
+   "id": "54ce7f5d",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -484,7 +484,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ef90239f",
+   "id": "841f74c7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -494,7 +494,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d9cbd2f6",
+   "id": "14573ebb",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -507,7 +507,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f0dcf922",
+   "id": "49b43121",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -517,7 +517,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "aac62046",
+   "id": "d74648e8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -530,7 +530,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "33875a50",
+   "id": "c811b234",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -542,7 +542,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4d532955",
+   "id": "56509580",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",