correction of the shap explainer and refactoring

eXascaleInfolab · Sep 25, 2024 · ee6b97b · ee6b97b
1 parent eb5543a
commit ee6b97b
Show file tree

Hide file tree

Showing 70 changed files with 426 additions and 204 deletions.
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
diff --git a/assets/test_contamination.png b/assets/test_contamination.png
diff --git a/assets/test_ground_truth.png b/assets/test_ground_truth.png
diff --git a/imputegap/algorithms/__pycache__/cdrec.cpython-312.pyc b/imputegap/algorithms/__pycache__/cdrec.cpython-312.pyc
diff --git a/imputegap/algorithms/cdrec.py b/imputegap/algorithms/cdrec.py
@@ -18,7 +18,7 @@ def __marshal_as_native_column(__py_matrix):
     return __ctype_marshal;
 
 
-def load_share_lib(name="lib_algo"):
+def load_share_lib(name="lib_cdrec"):
     """
     Determine the OS and load the correct shared library
     :param name: name of the library
@@ -36,7 +36,6 @@ def load_share_lib(name="lib_algo"):
         lib_path = os.path.join(local_path_win)
     else:
         lib_path = os.path.join(local_path_lin)
-    print("\n", lib_path, " has been loaded...")
 
     return ctypes.CDLL(lib_path)
 
@@ -71,11 +70,6 @@ def native_cdrec(__py_matrix, __py_rank, __py_eps, __py_iters):
     # Native code uses linear matrix layout, and also it's easier to pass it in like this
     __ctype_input_matrix = __marshal_as_native_column(__py_matrix);
 
-    # extern "C" void
-    # cdrec_imputation_parametrized(
-    #         double *matrixNative, size_t dimN, size_t dimM,
-    #         size_t truncation, double epsilon, size_t iters
-    # )
     shared_lib.cdrec_imputation_parametrized(
         __ctype_input_matrix, __ctype_sizen, __ctype_sizem,
         __ctype_rank, __ctype_eps, __ctype_iters

diff --git a/imputegap/algorithms/lib/lib_cdrec.so b/imputegap/algorithms/lib/lib_cdrec.so
diff --git a/imputegap/assets/contamination/.gitkeep b/imputegap/assets/contamination/.gitkeep
diff --git a/imputegap/assets/test_contamination.png → ...sets/contamination/test_contamination.png b/imputegap/assets/test_contamination.png → ...sets/contamination/test_contamination.png
diff --git a/imputegap/assets/ground_truth/.gitkeep b/imputegap/assets/ground_truth/.gitkeep
@@ -0,0 +1 @@
+
diff --git a/imputegap/assets/test_ground_truth.png → ...assets/ground_truth/test_ground_truth.png b/imputegap/assets/test_ground_truth.png → ...assets/ground_truth/test_ground_truth.png
diff --git a/imputegap/assets/ground_truth_normalized/.gitkeep b/imputegap/assets/ground_truth_normalized/.gitkeep
diff --git a/imputegap/assets/iim_imputation.png b/imputegap/assets/iim_imputation.png
diff --git a/imputegap/assets/imputation/.gitkeep b/imputegap/assets/imputation/.gitkeep
diff --git a/imputegap/assets/test_imputation.png → ...gap/assets/imputation/test_imputation.png b/imputegap/assets/test_imputation.png → ...gap/assets/imputation/test_imputation.png
diff --git a/imputegap/assets/min_max_ground_truth_normalized.png b/imputegap/assets/min_max_ground_truth_normalized.png
diff --git a/imputegap/assets/shap/.gitkeep b/imputegap/assets/shap/.gitkeep
diff --git a/imputegap/assets/shap/chlorine_cdrec_DTL_Beeswarm.png b/imputegap/assets/shap/chlorine_cdrec_DTL_Beeswarm.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_DTL_Waterfall.png b/imputegap/assets/shap/chlorine_cdrec_DTL_Waterfall.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_results.txt b/imputegap/assets/shap/chlorine_cdrec_results.txt
@@ -0,0 +1,22 @@
+Feature : 1     cdrec      with a score of 87.98      Geometry           10-bin histogram mode                                             DN_HistogramMode_10
+Feature : 12    cdrec      with a score of 5.06       Correlation        Change in autocorrelation timescale after incremental differencing FC_LocalSimple_mean1_tauresrat
+Feature : 5     cdrec      with a score of 4.74       Correlation        Time reversibility                                                CO_trev_1_num
+Feature : 3     cdrec      with a score of 1.21       Correlation        First minimum of the ACF                                          CO_FirstMin_ac
+Feature : 18    cdrec      with a score of 0.53       Geometry           Rescaled range fluctuation analysis (low-scale scaling)           SC_FluctAnal_2_rsrangefit_50_1_logi_prop_r1
+Feature : 14    cdrec      with a score of 0.28       Geometry           Negative outlier timing                                           DN_OutlierInclude_n_001_mdrmd
+Feature : 13    cdrec      with a score of 0.11       Geometry           Positive outlier timing                                           DN_OutlierInclude_p_001_mdrmd
+Feature : 6     cdrec      with a score of 0.08       Geometry           Proportion of high incremental changes in the series              MD_hrv_classic_pnn40
+Feature : 0     cdrec      with a score of 0.0        Geometry           5-bin histogram mode                                              DN_HistogramMode_5
+Feature : 2     cdrec      with a score of 0.0        Correlation        First 1/e crossing of the ACF                                     CO_f1ecac
+Feature : 4     cdrec      with a score of 0.0        Correlation        Histogram-based automutual information (lag 2, 5 bins)            CO_HistogramAMI_even_2_5
+Feature : 7     cdrec      with a score of 0.0        Geometry           Longest stretch of above-mean values                              SB_BinaryStats_mean_longstretch1
+Feature : 8     cdrec      with a score of 0.0        Geometry           Transition matrix column variance                                 SB_TransitionMatrix_3ac_sumdiagcov
+Feature : 9     cdrec      with a score of 0.0        Trend              Wangs periodicity metric                                          PD_PeriodicityWang_th0_01
+Feature : 10    cdrec      with a score of 0.0        Geometry           Goodness of exponential fit to embedding distance distribution    CO_Embed2_Dist_tau_d_expfit_meandiff
+Feature : 11    cdrec      with a score of 0.0        Correlation        First minimum of the AMI function                                 IN_AutoMutualInfoStats_40_gaussian_fmmi
+Feature : 15    cdrec      with a score of 0.0        Transformation     Power in the lowest 20% of frequencies                            SP_Summaries_welch_rect_area_5_1
+Feature : 16    cdrec      with a score of 0.0        Geometry           Longest stretch of decreasing values                              SB_BinaryStats_diff_longstretch0
+Feature : 17    cdrec      with a score of 0.0        Trend              Entropy of successive pairs in symbolized series                  SB_MotifThree_quantile_hh
+Feature : 19    cdrec      with a score of 0.0        Geometry           Detrended fluctuation analysis (low-scale scaling)                SC_FluctAnal_2_dfa_50_1_2_logi_prop_r1
+Feature : 20    cdrec      with a score of 0.0        Transformation     Centroid frequency                                                SP_Summaries_welch_rect_centroid
+Feature : 21    cdrec      with a score of 0.0        Trend              Error of 3-point rolling mean forecast                            FC_LocalSimple_mean3_stderr
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_aggregate_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_aggregate_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_aggregate_reverse_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_aggregate_reverse_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_correlation_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_correlation_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_geometry_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_geometry_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_reverse_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_reverse_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_transformation_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_transformation_plot.png
diff --git a/imputegap/assets/shap/chlorine_cdrec_shap_trend_plot.png b/imputegap/assets/shap/chlorine_cdrec_shap_trend_plot.png
diff --git a/imputegap/assets/z_score_ground_truth_normalized.png b/imputegap/assets/z_score_ground_truth_normalized.png
diff --git a/imputegap/contamination/__pycache__/contamination.cpython-312.pyc b/imputegap/contamination/__pycache__/contamination.cpython-312.pyc
diff --git a/imputegap/contamination/contamination.py b/imputegap/contamination/contamination.py
@@ -69,14 +69,15 @@ def scenario_mcar(ts, series_impacted=0.2, missing_rate=0.2, block_size=10, prot
 
         series_selected = Contamination.format_selection(ts_contaminated, series_indices)
 
-        print("\n\nMCAR contamination has been called with :"
-              "\n\ta number of series impacted ", series_impacted * 100, "%",
-              "\n\ta missing rate of ", missing_rate * 100, "%",
-              "\n\ta starting position at ", protection,
-              "\n\ta block size of ", block_size,
-              "\n\twith a seed option set to ", use_seed,
-              "\n\tshape of the set ", ts_contaminated.shape,
-              "\n\tthis selection of series", *series_selected, "\n\n")
+        if not explainer:
+            print("\n\nMCAR contamination has been called with :"
+                  "\n\ta number of series impacted ", series_impacted * 100, "%",
+                  "\n\ta missing rate of ", missing_rate * 100, "%",
+                  "\n\ta starting position at ", protection,
+                  "\n\ta block size of ", block_size,
+                  "\n\twith a seed option set to ", use_seed,
+                  "\n\tshape of the set ", ts_contaminated.shape,
+                  "\n\tthis selection of series", *series_selected, "\n\n")
 
         for series in series_selected:
             S = int(series)

diff --git a/imputegap/explainer/__pycache__/explainer.cpython-312.pyc b/imputegap/explainer/__pycache__/explainer.cpython-312.pyc