Merge branch 'master' into gaugup/AddValidationsToGenerateCounterfactuals

Author: gaugup

.github/workflows/code-scan.yml

@@ -0,0 +1,57 @@
+name: code scan
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ["python"]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
+        # Learn more:
+        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v1
+        with:
+          languages: ${{ matrix.language }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
+          # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+      # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+      # If this step fails, then you should remove it and run the build manually (see below)
+      - name: Autobuild
+        uses: github/codeql-action/autobuild@v1
+
+      # ℹ️ Command-line programs to run using the OS shell.
+      # 📚 https://git.io/JvXDl
+
+      # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+      #    and modify them (or add more) to build your code if your project
+      #    uses a compiled language
+
+      #- run: |
+      #   make bootstrap
+      #   make release
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v1

.github/workflows/python-linting.yml

@@ -22,7 +22,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8==3.9.2 flake8-nb==0.3.0 isort
+        pip install -r requirements-linting.txt
     - name: Check sorted python imports using isort
       run: |
         isort . -c

.github/workflows/python-package-conda.yml

@@ -0,0 +1,31 @@
+name: Python Package using Conda
+
+on: [push]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.8
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install core dependencies
+      run: |
+        conda env update --file environment.yml --name base
+    - name: Install deep learning dependencies
+      run: |
+        conda env update --file environment-deeplearning.yml --name base
+    - name: Test with pytest
+      run: |
+        conda install pytest ipython jupyter nbformat pytest-mock
+
+        pytest

dice_ml/data_interfaces/public_data_interface.py

@@ -260,7 +260,7 @@ def get_valid_feature_range(self, feature_range_input, normalized=True):
         """
         feature_range = {}
 
-        for idx, feature_name in enumerate(self.feature_names):
+        for _, feature_name in enumerate(self.feature_names):
             feature_range[feature_name] = []
             if feature_name in self.continuous_feature_names:
                 max_value = self.data_df[feature_name].max()

dice_ml/explainer_interfaces/dice_KD.py

@@ -260,7 +260,7 @@ def find_counterfactuals(self, data_df_copy, query_instance, query_instance_orig
             if total_cfs_found < total_CFs:
                 self.elapsed = timeit.default_timer() - start_time
                 m, s = divmod(self.elapsed, 60)
-                print('Only %d (required %d) ' % (total_cfs_found, self.total_CFs),
+                print('Only %d (required %d) ' % (total_cfs_found, total_CFs),
                       'Diverse Counterfactuals found for the given configuation, perhaps ',
                       'change the query instance or the features to vary...'  '; total time taken: %02d' % m,
                       'min %02d' % s, 'sec')

dice_ml/explainer_interfaces/dice_tensorflow2.py

@@ -177,7 +177,7 @@ def do_cf_initializations(self, total_CFs, algorithm, features_to_vary):
         # CF initialization
         if len(self.cfs) != self.total_CFs:
             self.cfs = []
-            for ix in range(self.total_CFs):
+            for _ in range(self.total_CFs):
                 one_init = [[]]
                 for jx in range(self.minx.shape[1]):
                     one_init[0].append(np.random.uniform(self.minx[0][jx], self.maxx[0][jx]))

dice_ml/explainer_interfaces/explainer_base.py

@@ -380,7 +380,7 @@ def feature_importance(self, query_instances, cf_examples_list=None,
                 continue
 
             per_query_point_cfs = 0
-            for index, row in df.iterrows():
+            for _, row in df.iterrows():
                 per_query_point_cfs += 1
                 for col in self.data_interface.continuous_feature_names:
                     if not np.isclose(org_instance[col].iat[0], row[col]):
@@ -561,7 +561,7 @@ def misc_init(self, stopping_threshold, desired_class, desired_range, test_pred)
             self.target_cf_class = np.array(
                 [[self.infer_target_cfs_class(desired_class, test_pred, self.num_output_nodes)]],
                 dtype=np.float32)
-            desired_class = self.target_cf_class[0][0]
+            desired_class = int(self.target_cf_class[0][0])
             if self.target_cf_class == 0 and self.stopping_threshold > 0.5:
                 self.stopping_threshold = 0.25
             elif self.target_cf_class == 1 and self.stopping_threshold < 0.5:

dice_ml/explainer_interfaces/feasible_base_vae.py

@@ -186,7 +186,7 @@ def generate_counterfactuals(self, query_instance, total_CFs, desired_class="opp
             curr_cf_pred = []
             curr_test_pred = train_y.numpy()
 
-            for cf_count in range(total_CFs):
+            for _ in range(total_CFs):
                 recon_err, kl_err, x_true, x_pred, cf_label = \
                     self.cf_vae.compute_elbo(train_x, 1.0-train_y, self.pred_model)
                 while(cf_label == train_y):

dice_ml/model_interfaces/base_model.py

@@ -64,7 +64,7 @@ def get_num_output_nodes(self, inp_size):
         temp_input = np.transpose(np.array([np.random.uniform(0, 1) for i in range(inp_size)]).reshape(-1, 1))
         return self.get_output(temp_input).shape[1]
 
-    def get_num_output_nodes2(self, input):
+    def get_num_output_nodes2(self, input_instance):
         if self.model_type == ModelTypes.Regressor:
             raise SystemException('Number of output nodes not supported for regression')
-        return self.get_output(input).shape[1]
+        return self.get_output(input_instance).shape[1]

dice_ml/model_interfaces/keras_tensorflow_model.py

@@ -40,7 +40,7 @@ def get_output(self, input_tensor, training=False, transform_data=False):
         else:
             return self.model(input_tensor)
 
-    def get_gradient(self, input):
+    def get_gradient(self, input_instance):
         # Future Support
         raise NotImplementedError("Future Support")