1b PM - alpha correction

.github/workflows/pytest_pipeline_10.yml → .github/workflows/pytest_pipeline_3_10.yml

@@ -1,4 +1,4 @@
-name: Pytest - ImputeGAP - Pipeline - 10
+name: VERSIONING 3.10 - Pipeline
 
 on:
   push:

.github/workflows/pytest_pipeline_3_11.yml

@@ -0,0 +1,35 @@
+name: VERSIONING 3.11 - Pipeline
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        lfs: true
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+
+    - name: Install dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install libmlpack-dev
+        sudo apt-get install libopenblas-dev
+        sudo apt-get install python3-dev build-essential
+        pip install --upgrade google protobuf
+        pip install -r requirements.txt
+        pip install mypy
+        pip install pytest
+
+
+    - name: Run pytest
+      run: |
+        python -m pytest ./tests/test_pipeline.py

.github/workflows/pytest_pipeline.yml → .github/workflows/pytest_pipeline_3_12.yml

@@ -1,4 +1,4 @@
-name: Pytest - ImputeGAP - Pipeline - 12
+name: VERSIONING 3.12 - Pipeline
 
 on:
   push:

.github/workflows/pytest_pipeline_12_6.yml → .github/workflows/pytest_pipeline_3_12_6.yml

@@ -1,4 +1,4 @@
-name: Pytest - ImputeGAP - Pipeline - 12.6
+name: VERSIONING 3.12.6 - Pipeline
 
 on:
   push:

.github/workflows/pytest_pipeline_12_8.yml → .github/workflows/pytest_pipeline_3_12_8.yml

@@ -1,4 +1,4 @@
-name: Pytest - ImputeGAP - Pipeline - 12.8
+name: VERSIONING 3.12.8 - Pipeline
 
 on:
   push:

.github/workflows/pytest_pipeline_13.yml → .github/workflows/pytest_pipeline_3_13.yml

@@ -1,4 +1,4 @@
-name: Pytest - ImputeGAP - Pipeline - 13
+name: VERSIONING 3.13 - Pipeline
 
 on:
   push:

.github/workflows/pytest_pipeline_3_8.yml

@@ -0,0 +1,35 @@
+name: VERSIONING 3.8 - Pipeline
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        lfs: true
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.8'
+
+    - name: Install dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install libmlpack-dev
+        sudo apt-get install libopenblas-dev
+        sudo apt-get install python3-dev build-essential
+        pip install --upgrade google protobuf
+        pip install -r requirements.txt
+        pip install mypy
+        pip install pytest
+
+
+    - name: Run pytest
+      run: |
+        python -m pytest ./tests/test_pipeline.py

.github/workflows/pytest_pipeline_3_9.yml

@@ -0,0 +1,35 @@
+name: VERSIONING 3.9 - Pipeline
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        lfs: true
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install libmlpack-dev
+        sudo apt-get install libopenblas-dev
+        sudo apt-get install python3-dev build-essential
+        pip install --upgrade google protobuf
+        pip install -r requirements.txt
+        pip install mypy
+        pip install pytest
+
+
+    - name: Run pytest
+      run: |
+        python -m pytest ./tests/test_pipeline.py

imputegap/recovery/explainer.py

@@ -533,6 +533,9 @@ def shap_explainer(input_data, algorithm="cdrec", params=None, pattern="mcar", m
 
         training_ratio = int(limit * split_ratio)
 
+        if limit > M:
+            limit = M
+
         print("\nFrom", limit, "/", M, "elements, the training dataset has been set with", training_ratio,"elements and the testing dataset with", (limit-training_ratio), "elements")
 
         if verbose:

tests/assets/shap/chlorine_cdrec_results.txt

@@ -1,20 +1,20 @@
-Feature : 1     cdrec      with a score of 68.3       Geometry           10-bin histogram mode                                             DN_HistogramMode_10
-Feature : 12    cdrec      with a score of 9.34       Correlation        Change in autocorrelation timescale after incremental differencing FC_LocalSimple_mean1_tauresrat
-Feature : 5     cdrec      with a score of 4.68       Correlation        Time reversibility                                                CO_trev_1_num
-Feature : 6     cdrec      with a score of 4.63       Geometry           Proportion of high incremental changes in the series              MD_hrv_classic_pnn40
-Feature : 13    cdrec      with a score of 3.38       Geometry           Positive outlier timing                                           DN_OutlierInclude_p_001_mdrmd
-Feature : 4     cdrec      with a score of 2.68       Correlation        Histogram-based automutual information (lag 2, 5 bins)            CO_HistogramAMI_even_2_5
-Feature : 2     cdrec      with a score of 2.28       Correlation        First 1/e crossing of the ACF                                     CO_f1ecac
-Feature : 14    cdrec      with a score of 1.37       Geometry           Negative outlier timing                                           DN_OutlierInclude_n_001_mdrmd
-Feature : 17    cdrec      with a score of 0.66       Trend              Entropy of successive pairs in symbolized series                  SB_MotifThree_quantile_hh
-Feature : 0     cdrec      with a score of 0.65       Geometry           5-bin histogram mode                                              DN_HistogramMode_5
-Feature : 21    cdrec      with a score of 0.62       Trend              Error of 3-point rolling mean forecast                            FC_LocalSimple_mean3_stderr
-Feature : 8     cdrec      with a score of 0.5        Geometry           Transition matrix column variance                                 SB_TransitionMatrix_3ac_sumdiagcov
-Feature : 10    cdrec      with a score of 0.5        Geometry           Goodness of exponential fit to embedding distance distribution    CO_Embed2_Dist_tau_d_expfit_meandiff
-Feature : 15    cdrec      with a score of 0.42       Transformation     Power in the lowest 20% of frequencies                            SP_Summaries_welch_rect_area_5_1
-Feature : 3     cdrec      with a score of 0.0        Correlation        First minimum of the ACF                                          CO_FirstMin_ac
+Feature : 6     cdrec      with a score of 22.22      Geometry           Proportion of high incremental changes in the series              MD_hrv_classic_pnn40
+Feature : 15    cdrec      with a score of 10.24      Transformation     Power in the lowest 20% of frequencies                            SP_Summaries_welch_rect_area_5_1
+Feature : 10    cdrec      with a score of 9.27       Geometry           Goodness of exponential fit to embedding distance distribution    CO_Embed2_Dist_tau_d_expfit_meandiff
+Feature : 0     cdrec      with a score of 9.07       Geometry           5-bin histogram mode                                              DN_HistogramMode_5
+Feature : 5     cdrec      with a score of 8.31       Correlation        Time reversibility                                                CO_trev_1_num
+Feature : 21    cdrec      with a score of 7.84       Trend              Error of 3-point rolling mean forecast                            FC_LocalSimple_mean3_stderr
+Feature : 2     cdrec      with a score of 7.65       Correlation        First 1/e crossing of the ACF                                     CO_f1ecac
+Feature : 14    cdrec      with a score of 6.67       Geometry           Negative outlier timing                                           DN_OutlierInclude_n_001_mdrmd
+Feature : 1     cdrec      with a score of 5.0        Geometry           10-bin histogram mode                                             DN_HistogramMode_10
+Feature : 8     cdrec      with a score of 3.75       Geometry           Transition matrix column variance                                 SB_TransitionMatrix_3ac_sumdiagcov
+Feature : 4     cdrec      with a score of 3.11       Correlation        Histogram-based automutual information (lag 2, 5 bins)            CO_HistogramAMI_even_2_5
+Feature : 17    cdrec      with a score of 2.06       Trend              Entropy of successive pairs in symbolized series                  SB_MotifThree_quantile_hh
+Feature : 3     cdrec      with a score of 1.63       Correlation        First minimum of the ACF                                          CO_FirstMin_ac
+Feature : 12    cdrec      with a score of 1.58       Correlation        Change in autocorrelation timescale after incremental differencing FC_LocalSimple_mean1_tauresrat
+Feature : 13    cdrec      with a score of 1.55       Geometry           Positive outlier timing                                           DN_OutlierInclude_p_001_mdrmd
+Feature : 9     cdrec      with a score of 0.04       Trend              Wangs periodicity metric                                          PD_PeriodicityWang_th0_01
 Feature : 7     cdrec      with a score of 0.0        Geometry           Longest stretch of above-mean values                              SB_BinaryStats_mean_longstretch1
-Feature : 9     cdrec      with a score of 0.0        Trend              Wangs periodicity metric                                          PD_PeriodicityWang_th0_01
 Feature : 11    cdrec      with a score of 0.0        Correlation        First minimum of the AMI function                                 IN_AutoMutualInfoStats_40_gaussian_fmmi
 Feature : 16    cdrec      with a score of 0.0        Geometry           Longest stretch of decreasing values                              SB_BinaryStats_diff_longstretch0
 Feature : 18    cdrec      with a score of 0.0        Geometry           Rescaled range fluctuation analysis (low-scale scaling)           SC_FluctAnal_2_rsrangefit_50_1_logi_prop_r1

tests/test_contamination_mcar.py

@@ -200,6 +200,6 @@ def test_mcar_size_of_block(self):
 
                         for block in nan_blocks:
                             assert block >= block_size, (
-                                f"Dataset: {dataset}, Series: {i}, Seed: {seed_value}, "
+                                f"Dataset: {dataset}, Series: {i}, "
                                 f"Block size {block} found, expected at least {block_size}."
                             )

tests/test_explainer.py

@@ -29,6 +29,9 @@ def test_explainer_shap(self):
         self.assertTrue(shap_values is not None)
         self.assertTrue(shap_details is not None)
 
+        print("shap_details", np.array(shap_details).shape)
+        print("RMSE", np.array(RMSE).shape)
+
         for i, (_, output) in enumerate(shap_details):
             assert np.isclose(RMSE[i], output, atol=0.01)
 
@@ -41,8 +44,7 @@ def test_explainer_shap(self):
             self.assertTrue(description is not None)
             self.assertTrue(feature is not None)
             self.assertTrue(category is not None)
-            self.assertTrue(
-                mean_features is not None and not (isinstance(mean_features, (int, float)) and np.isnan(mean_features)))
+            self.assertTrue(mean_features is not None and not (isinstance(mean_features, (int, float)) and np.isnan(mean_features)))
 
             # Check relation feature/category
             feature_found_in_category = False