feat(pointcloud): Add HDBSCAN to point cloud (#57)

* Restore umap_demo deleted * Add HDBSCAN clustering * Fix style * Fix json int bug * Update src/phoenix/pcloud/pcloud.py Co-authored-by: Mikyo King <[email protected]> * Update src/phoenix/pcloud/projectors.py Co-authored-by: Mikyo King <[email protected]> * Delete _fit_transform method * Restore umap_demo deleted * Add HDBSCAN clustering * Fix style * Fix json int bug * Delete _fit_transform method * Update src/phoenix/pcloud/pcloud.py Co-authored-by: Mikyo King <[email protected]> * Update src/phoenix/pcloud/projectors.py Co-authored-by: Mikyo King <[email protected]> * fix types: * more fixes * black * Add .coverage to gitignore * Add tables dependency toml file * wip * Use pull_request_target, better for forked repos * Add PR lint action * Not use pull_request_target * Add edited trigger * Ignore type hints from umap and hdbscan * Rename module pcloud -> pointcloud * Ignore E203 flake8 * HDBSCAN finished * wip * Define and use Coordinates classes * Parametrize HDBSCAN hyperparams * Rename to DriftPointCloud * Update .github/workflows/pull-requests.yaml Co-authored-by: Mikyo King <[email protected]> Co-authored-by: Mikyo King <[email protected]>
Arize-ai · Nov 28, 2022 · 9aa2a3f · 9aa2a3f
1 parent 7629de0
commit 9aa2a3f
Show file tree

Hide file tree

Showing 9 changed files with 443 additions and 253 deletions.
diff --git a/.github/workflows/pull-requests.yaml b/.github/workflows/pull-requests.yaml
@@ -0,0 +1,17 @@
+name: Semantic PR
+
+on:
+  pull_request:
+    types:
+      - opened
+      - edited
+      - synchronize
+
+jobs:
+  main:
+    name: Validate PR title
+    runs-on: ubuntu-latest
+    steps:
+      - uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
diff --git a/.github/workflows/python-CI.yml b/.github/workflows/python-CI.yml
@@ -1,113 +1,113 @@
 name: Python CI
 
 on:
-    push:
-        branches: [main]
-    pull_request:
-        paths:
-            - "**.py"
-    # Allows you to run this workflow manually from the Actions tab
-    workflow_dispatch:
+  push:
+    branches: [ main ]
+  pull_request:
+    paths:
+      - "**.py"
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
 
 concurrency:
-    group: test-python-${{ github.head_ref }}
-    cancel-in-progress: true
+  group: test-python-${{ github.head_ref }}
+  cancel-in-progress: true
 
 env:
-    pip-version: 22.3.1
+  pip-version: 22.3.1
 
 jobs:
-    types:
-        name: Type Check
-        runs-on: ubuntu-latest
-        steps:
-            - name: Checkout Repository
-              uses: actions/checkout@v3
-            - name: Set up python 3.10
-              uses: actions/setup-python@v4
-              with:
-                  python-version: "3.10"
-            - name: Install dependencies
-              run: |
-                  python -m pip install --upgrade pip==${{ env.pip-version }}
-                  pip install hatch
-            - name: Check types
-              run: |
-                  hatch run types:check
+  types:
+    name: Type Check
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+      - name: Set up python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip==${{ env.pip-version }}
+          pip install hatch
+      - name: Check types
+        run: |
+          hatch run type:check
 
-    code-format:
-        name: Code Format
-        runs-on: ubuntu-latest
-        steps:
-            - name: Checkout Repository
-              uses: actions/checkout@v3
-            - name: Set up python 3.10
-              uses: actions/setup-python@v4
-              with:
-                  python-version: "3.10"
-            - name: Install dependencies
-              run: |
-                  python -m pip install --upgrade pip==${{ env.pip-version }}
-                  pip install hatch
-            - name: Check format
-              run: |
-                  hatch run style:check
+  code-format:
+    name: Code Format
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+      - name: Set up python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip==${{ env.pip-version }}
+          pip install hatch
+      - name: Check format
+        run: |
+          hatch run style:check
 
-    test-coverage:
-        name: Test Coverage
-        runs-on: ubuntu-latest
-        steps:
-            - name: Checkout Repository
-              uses: actions/checkout@v3
-            - name: Set up python 3.10
-              uses: actions/setup-python@v4
-              with:
-                  python-version: "3.10"
-            - name: Install dependencies
-              run: |
-                  python -m pip install --upgrade pip==${{ env.pip-version }}
-                  pip install hatch
-            - name: Test coverage
-              run: |
-                  hatch run coverage
+  test-coverage:
+    name: Test Coverage
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+      - name: Set up python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip==${{ env.pip-version }}
+          pip install hatch
+      - name: Test coverage
+        run: |
+          hatch run coverage
 
-    docs-coverage:
-        name: Documentation Coverage
-        runs-on: ubuntu-latest
-        steps:
-            - name: Checkout Repository
-              uses: actions/checkout@v3
-            - name: Set up python 3.11
-              uses: actions/setup-python@v4
-              with:
-                  python-version: 3.11
-            - name: Install dependencies
-              run: |
-                  python -m pip install --upgrade pip==${{ env.pip-version }}
-                  pip install hatch
-            - name: Check documentation coverage
-              run: |
-                  hatch run docs:check
+  docs-coverage:
+    name: Documentation Coverage
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+      - name: Set up python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip==${{ env.pip-version }}
+          pip install hatch
+      - name: Check documentation coverage
+        run: |
+          hatch run docs:check
 
-    test:
-        name: Test Python
-        runs-on: ${{ matrix.os }}
-        needs: [code-format, test-coverage, docs-coverage]
-        strategy:
-            matrix:
-                os: [ubuntu-latest, macos-latest, windows-latest]
-                python-version: ["3.10"]
-        steps:
-            - name: Checkout Repository
-              uses: actions/checkout@v3
-            - name: Set up python ${{ matrix.python-version }}
-              uses: actions/setup-python@v4
-              with:
-                  python-version: ${{ matrix.python-version }}
-            - name: Install dependencies
-              run: |
-                  python -m pip install --upgrade pip==${{ env.pip-version }}
-                  pip install hatch
-            - name: Run tests
-              run: |
-                  hatch run tests
+  test:
+    name: Test Python
+    runs-on: ${{ matrix.os }}
+    needs: [ code-format, test-coverage, docs-coverage ]
+    strategy:
+      matrix:
+        os: [ ubuntu-latest, macos-latest, windows-latest ]
+        python-version: [ "3.10" ]
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+      - name: Set up python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip==${{ env.pip-version }}
+          pip install hatch
+      - name: Run tests
+        run: |
+          hatch run tests
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,7 @@
 # Generated dirs
 .vscode
 .idea
+.coverage
 node_modules
 dist
 *__pycache__*

diff --git a/examples/umap_demo.ipynb b/examples/umap_demo.ipynb
@@ -6,7 +6,7 @@
    "source": [
     "# Phoenix Embeddings\n",
     "\n",
-    "A simple demo of the `UMAPWidget`"
+    "This small tutorial goes over creating Phoenix's `Dataset` objects and using them to obtain a UMAP pointcloud using the `UMAPWidget`"
    ]
   },
   {
@@ -15,7 +15,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from phoenix.widgets import UMAPWidget, demo_json"
+    "from phoenix.datasets import Dataset, EmbeddingColumnNames, Schema\n",
+    "from phoenix.pointcloud import DriftPointCloud, UMAPProjector\n",
+    "from phoenix.widgets import UMAPWidget"
    ]
   },
   {
@@ -24,7 +26,59 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "widget = UMAPWidget(demo_json())\n",
+    "test_filename = \"NLP_sentiment_classification_language_drift\"\n",
+    "\n",
+    "features = [\n",
+    "    \"reviewer_age\",\n",
+    "    \"reviewer_gender\",\n",
+    "    \"product_category\",\n",
+    "    \"language\",\n",
+    "]\n",
+    "\n",
+    "embedding_features = {\n",
+    "    \"embedding_feature\": EmbeddingColumnNames(\n",
+    "        vector_column_name=\"text_vector\",  # Will be name of embedding feature in the app\n",
+    "        data_column_name=\"text\",\n",
+    "    ),\n",
+    "}\n",
+    "\n",
+    "# Define a Schema() object for Arize to pick up data from the correct columns for logging\n",
+    "schema = Schema(\n",
+    "    prediction_id_column_name=\"prediction_id\",\n",
+    "    timestamp_column_name=\"prediction_ts\",\n",
+    "    prediction_label_column_name=\"pred_label\",\n",
+    "    actual_label_column_name=\"label\",\n",
+    "    feature_column_names=features,\n",
+    "    embedding_feature_column_names=embedding_features,\n",
+    ")\n",
+    "\n",
+    "train_ds = Dataset.from_hdf(f\"./fixtures/{test_filename}.hdf5\", schema=schema, key=\"training\")\n",
+    "prod_ds = Dataset.from_hdf(f\"./fixtures/{test_filename}.hdf5\", schema=schema, key=\"production\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Obtain the point cloud\n",
+    "UMAP_hyperparameters = {\n",
+    "    \"n_components\": 3,\n",
+    "    \"min_dist\": 0,\n",
+    "}\n",
+    "projector = UMAPProjector(hyperparameters=UMAP_hyperparameters)\n",
+    "primary_pts, reference_pts, clusters = projector.project(prod_ds, train_ds, \"embedding_feature\")\n",
+    "pc = DriftPointCloud(primary_pts, reference_pts, clusters)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "widget = UMAPWidget(pc.to_json())\n",
     "widget.show()"
    ]
   }
@@ -45,7 +99,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.3"
+   "version": "3.10.0"
   },
   "vscode": {
    "interpreter": {

diff --git a/pyproject.toml b/pyproject.toml
@@ -23,6 +23,8 @@ dependencies = [
     "numpy",
     "pandas",
     "umap-learn",
+    "hdbscan",
+    "tables",
 ]
 dynamic = ["version"]
 
@@ -57,7 +59,7 @@ dependencies = [
   "pytest-cov",
 ]
 
-[tool.hatch.envs.types]
+[tool.hatch.envs.type]
 dependencies = [
   "mypy",
   "pytest",
@@ -110,7 +112,7 @@ exclude_lines = [
   "if TYPE_CHECKING:",
 ]
 
-[tool.hatch.envs.types.scripts]
+[tool.hatch.envs.type.scripts]
 check = [
   "mypy .",
 ]
@@ -119,12 +121,12 @@ check = [
 check = [
   "isort --check-only --diff .",
   "black --check --diff --color .",
-  "flake8 --max-line-length=100 --exclude=__init__.py .",
+  "flake8 --extend-ignore E203 --max-line-length=100 --exclude=__init__.py .",
 ]
 fix = [
   "isort .",
   "black .",
-  "flake8 --max-line-length=100 --exclude=__init__.py .",
+  "flake8 --extend-ignore E203 --max-line-length=100 --exclude=__init__.py .",
 ]
 
 [tool.isort]
@@ -152,4 +154,11 @@ ignore-property-decorators = false
 ignore-module = false
 ignore-nested-functions = false
 ignore-nested-classes = false
-ignore-setters = false
+ignore-setters = false
+
+[[tool.mypy.overrides]]
+module = [
+    "hdbscan",
+    "umap",
+]
+ignore_missing_imports = true
diff --git a/src/phoenix/__init__.py b/src/phoenix/__init__.py
@@ -1 +1 @@
-__version__ = "0.0.1"
+
diff --git a/src/phoenix/pointcloud/__init__.py b/src/phoenix/pointcloud/__init__.py
@@ -1 +1,2 @@
-from .pointcloud import CalculateUMAP
+from .pointcloud import DriftPointCloud
+from .projectors import UMAPProjector