From ad43e62e0866f7d6028e40b7ced4771de97e0999 Mon Sep 17 00:00:00 2001
From: Anirban Ray <39331844+yarnabrina@users.noreply.github.com>
Date: Wed, 25 Oct 2023 22:41:49 +0530
Subject: [PATCH] added workflow to validate datasets

---
 .github/workflows/validate_datasets.yml | 81 +++++++++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 .github/workflows/validate_datasets.yml

diff --git a/.github/workflows/validate_datasets.yml b/.github/workflows/validate_datasets.yml
new file mode 100644
index 00000000000..ece65570874
--- /dev/null
+++ b/.github/workflows/validate_datasets.yml
@@ -0,0 +1,81 @@
+name: datasets validation
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - sktime/datasets/**
+  schedule:
+    - cron: 0 0 1 * *
+  workflow_dispatch:
+jobs:
+  test_internal_data:
+    name: test data shipped with sktime
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+        operating-system:
+          - macos-latest
+          - ubuntu-latest
+          - windows-latest
+    runs-on: ${{ matrix.operating-system }}
+    steps:
+      - name: repository checkout step
+        uses: actions/checkout@v4
+      - name: update tracking reference step
+        run: git remote set-branches origin main
+        shell: bash
+      - name: shallow clone update step
+        run: git fetch --depth 1
+        shell: bash
+      - name: python environment step
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: dependencies installation step
+        run: python3 -m pip install .[tests]
+        shell: bash
+      - name: unit test step
+        run: python3 -m pytest -m "not datadownload" sktime/datasets
+        shell: bash
+  test_external_data:
+    name: test data downloaded from external sources
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+        operating-system:
+          - macos-latest
+          - ubuntu-latest
+          - windows-latest
+    runs-on: ${{ matrix.operating-system }}
+    steps:
+      - name: repository checkout step
+        uses: actions/checkout@v4
+      - name: update tracking reference step
+        run: git remote set-branches origin main
+        shell: bash
+      - name: shallow clone update step
+        run: git fetch --depth 1
+        shell: bash
+      - name: python environment step
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: dependencies installation step
+        run: python3 -m pip install .[tests]
+        shell: bash
+      - name: unit test step
+        run: python3 -m pytest -m "datadownload" sktime/datasets
+        shell: bash