Added the workflow file for sample data

It is the bt_clustering and simulation runner running on the sample data with most of the default params.

.github/workflows/test.yml

@@ -1,35 +1,34 @@
-name: Test active learning in drug discovery
-
-on:
-- push
-- pull_request
-jobs:
-  Test:
-    name: Test active learning in drug discovery
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ubuntu-latest, windows-latest, macos-latest]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v2
-      - name: Install conda environment
-        uses: conda-incubator/setup-miniconda@v2
-        with:
-          activate-environment: active_learning_dd
-          environment-file: conda_cpu_env.yml
-          auto-activate-base: false
-          miniconda-version: 'latest'
-      - name: Install active_learning_dd package
-        shell: bash --login {0}
-        run: pip install -e .
-      - name: Test sample data runner
-        shell: bash --login {0}
-        run: |
-          cd chtc_runners
-          python sample_data_runner.py \
-            --pipeline_params_json_file=../param_configs/sample_data_config.json \
-            --hyperparams_json_file=../param_configs/experiment_PstP_hyperparams/sampled_hyparams/ClusterBasedWCSelector_609.json \
-            --iter_max=5 \
-            --no-precompute_dissimilarity_matrix \
-            --initial_dataset_file=../datasets/sample_data/training_data/iter_0.csv.gz
+name: Test
+on:
+- push
+- pull_request
+jobs:
+  Test:
+    name: Test nn4dms
+    runs-on: ${{ matrix.os }}
+    continue-on-error: true
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+      - name: Install conda environment
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: active_learning_dd
+          environment-file: conda_cpu_env.yml
+          auto-activate-base: false
+          miniconda-version: 'latest'
+     # Log conda environment contents
+      - name: Log conda environment
+        shell: bash --login {0}
+        run: conda list
+      # Tests that the regression training code runs in the conda environment
+      - name: Test BT_Clustering
+        shell: bash --login {0}
+        run: python utils/generate_bt_clustering.py --csv_file_or_dir=datasets/sample_data/training_data/iter_{}.csv --output_dir=datasets/sample_data/training_data --feature_name="Morgan FP_2_1024" --cutoff=0.4 --dist_function=tanimoto_dissimilarity --process_count=2 --index_name="Index ID"
+      # Tests that inference notebook can execute in the conda environment
+      - name: Test Simulation Runner
+        shell: bash --login {0}
+        run: python chtc_runners/simulation_runner.py --pipeline_params_json_file=param_configs/sample_data_config.json --nbs_params_json_file=param_configs/ClusterBasedWCSelector_params_reduced.json --exploration_strategy=weighted --iter_max=5 --process_num=0 --batch_size_index=0 --rnd_seed=0 --no-random_param_sampling --precompute_dissimilarity_matrix