Merge pull request #12 from IBM/encode_features

Add support for exogenous, encoding of categorical
ibm-granite · Mar 21, 2024 · 1bb542b · 1bb542b
2 parents 98bfa05 + a643d5f
commit 1bb542b
Show file tree

Hide file tree

Showing 26 changed files with 1,867 additions and 985 deletions.
diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
@@ -0,0 +1,39 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python package
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        # python -m pip install flake8 pytest
+        # if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        pip install ".[dev]"
+    - name: Ruff quality checks
+      run: |
+        # use hf-style check
+        make quality
+    - name: Test with pytest
+      run: |
+        pytest
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -3,7 +3,7 @@
     "editor.defaultFormatter": "ms-python.black-formatter",
     "editor.formatOnSave": true,
     "editor.codeActionsOnSave": {
-      "source.organizeImports": true
+      "source.organizeImports": "explicit"
     }
   },
   "isort.args": [

diff --git a/Makefile b/Makefile
@@ -1,18 +1,18 @@
 # Adapted from HF Transformers: https://github.com/huggingface/transformers/tree/main
 .PHONY: quality style
 
-check_dirs := tests src tsfm notebooks
+check_dirs := tests tsfm_public tsfmhfdemos notebooks
 
 
 # this target runs checks on all files
 
 quality:
-	ruff check $(check_dirs) setup.py
-	ruff format --check $(check_dirs) setup.py
+	ruff check $(check_dirs)
+	ruff format --check $(check_dirs)
 
 # this target runs checks on all files and potentially modifies some of them
 
 style:
-	ruff check $(check_dirs) setup.py --fix 
-	ruff format $(check_dirs) setup.py
+	ruff check $(check_dirs) --fix 
+	ruff format $(check_dirs)
 
diff --git a/notebooks/hfdemo/patch_tsmixer_blog.ipynb b/notebooks/hfdemo/patch_tsmixer_blog.ipynb
@@ -240,8 +240,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp = tsp.train(train_data)"
@@ -257,26 +256,23 @@
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
     "    timestamp_column=\"date\",\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
     "    timestamp_column=\"date\",\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
     "    timestamp_column=\"date\",\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"
@@ -862,8 +858,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp = tsp.train(train_data)"
@@ -878,24 +873,21 @@
     "train_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"

diff --git a/notebooks/hfdemo/patch_tsmixer_getting_started.ipynb b/notebooks/hfdemo/patch_tsmixer_getting_started.ipynb
@@ -258,8 +258,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp.train(train_data)"
@@ -275,24 +274,21 @@
     "train_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"

diff --git a/notebooks/hfdemo/patch_tsmixer_transfer.ipynb b/notebooks/hfdemo/patch_tsmixer_transfer.ipynb
@@ -189,8 +189,7 @@
     "    tsp = TimeSeriesPreprocessor(\n",
     "        timestamp_column=timestamp_column,\n",
     "        id_columns=id_columns,\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        scaling=True,\n",
     "    )\n",
     "    tsp.train(train_data)"
@@ -207,26 +206,23 @@
     "        tsp.preprocess(train_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )\n",
     "    valid_dataset = ForecastDFDataset(\n",
     "        tsp.preprocess(valid_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )\n",
     "    test_dataset = ForecastDFDataset(\n",
     "        tsp.preprocess(test_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )"
@@ -869,8 +865,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp.train(train_data)"
@@ -885,24 +880,21 @@
     "train_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"

diff --git a/notebooks/hfdemo/patch_tst_getting_started.ipynb b/notebooks/hfdemo/patch_tst_getting_started.ipynb
@@ -246,8 +246,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp.train(train_data)"
@@ -263,24 +262,21 @@
     "train_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"

diff --git a/notebooks/hfdemo/patch_tst_transfer.ipynb b/notebooks/hfdemo/patch_tst_transfer.ipynb
@@ -175,8 +175,7 @@
     "    tsp = TimeSeriesPreprocessor(\n",
     "        timestamp_column=timestamp_column,\n",
     "        id_columns=id_columns,\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        scaling=True,\n",
     "    )\n",
     "    tsp.train(train_data)"
@@ -193,26 +192,23 @@
     "        tsp.preprocess(train_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )\n",
     "    valid_dataset = ForecastDFDataset(\n",
     "        tsp.preprocess(valid_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )\n",
     "    test_dataset = ForecastDFDataset(\n",
     "        tsp.preprocess(test_data),\n",
     "        id_columns=id_columns,\n",
     "        timestamp_column=\"date\",\n",
-    "        input_columns=forecast_columns,\n",
-    "        output_columns=forecast_columns,\n",
+    "        target_columns=forecast_columns,\n",
     "        context_length=context_length,\n",
     "        prediction_length=forecast_horizon,\n",
     "    )"
@@ -584,8 +580,7 @@
     "tsp = TimeSeriesPreprocessor(\n",
     "    timestamp_column=timestamp_column,\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    scaling=True,\n",
     ")\n",
     "tsp.train(train_data)"
@@ -600,24 +595,21 @@
     "train_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(train_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "valid_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(valid_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")\n",
     "test_dataset = ForecastDFDataset(\n",
     "    tsp.preprocess(test_data),\n",
     "    id_columns=id_columns,\n",
-    "    input_columns=forecast_columns,\n",
-    "    output_columns=forecast_columns,\n",
+    "    target_columns=forecast_columns,\n",
     "    context_length=context_length,\n",
     "    prediction_length=forecast_horizon,\n",
     ")"