Merge branch 'dev' of https://github.com/Quantmetry/qolmat into dev_test_rpca

Author: Gsaes

examples/benchmark.md

@@ -144,7 +144,7 @@ imputer_mice = imputers.ImputerMICE(groups=["station"], estimator=LinearRegressi
 imputer_regressor = imputers.ImputerRegressor(groups=["station"], estimator=LinearRegression())
 
 dict_imputers = {
-    # "mean": imputer_mean,
+    "mean": imputer_mean,
     # "median": imputer_median,
     # "mode": imputer_mode,
     "interpolation": imputer_interpol,
@@ -160,7 +160,7 @@ dict_imputers = {
     # "nocb": imputer_nocb,
     # "knn": imputer_knn,
     "ols": imputer_regressor,
-    "mice_ols": imputer_mice,
+    # "mice_ols": imputer_mice,
 }
 n_imputers = len(dict_imputers)
 
@@ -193,14 +193,24 @@ comparison = comparator.Comparator(
     dict_imputers,
     cols_to_impute,
     generator_holes = generator_holes,
-    metrics=["mae", "wmape", "KL"],
+    metrics=["mae", "wmape", "KL", "ks_test", "energy"],
     n_calls_opt=10,
     search_params=search_params,
 )
 results = comparison.compare(df_data)
 results
 ```
 
+```python
+df_plot
+```
+
+```python
+df_plot = results.loc["energy", "All"]
+plt.bar(df_plot.index, df_plot, color=tab10(0))
+plt.show()
+```
+
 ```python
 fig = plt.figure(figsize=(24, 8))
 fig.add_subplot(2, 1, 1)

examples/metrics_usage.md

@@ -28,7 +28,7 @@ from sklearn.linear_model import LinearRegression
 from qolmat.utils import data, plot, utils
 from qolmat.imputations import imputers
 from qolmat.benchmark import comparator, missing_patterns
-from qolmat.benchmark.utils import wasser_distance, kl_divergence, frechet_distance
+from qolmat.benchmark.utils import wasser_distance_columnwise, kl_divergence, frechet_distance
 ```
 
 ```python
@@ -106,7 +106,7 @@ ratio_masked = 0.1
 ```python
 # Métriques
 metrics = {
-    "wasser": wasser_distance,
+    "wasserstein_columnwise": wasserstein_distance_columnwise,
     "KL": kl_divergence
     #"frechet": frechet_distance
 }

qolmat/benchmark/comparator.py

@@ -1,4 +1,5 @@
 import logging
+from functools import partial
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -33,10 +34,14 @@ class Comparator:
         "rmse": metrics.root_mean_squared_error,
         "mae": metrics.mean_absolute_error,
         "wmape": metrics.weighted_mean_absolute_percentage_error,
-        "wasser": metrics.wasser_distance,
-        "KL": metrics.kl_divergence,
+        "wasserstein_columnwise": partial(metrics.wasserstein_distance, method="columnwise"),
+        "KL_columnwise": partial(metrics.kl_divergence, method="columnwise"),
+        "KL_gaussian": partial(metrics.kl_divergence, method="gaussian"),
+        "ks_test": metrics.kolmogorov_smirnov_test,
+        "correlation_diff": metrics.mean_difference_correlation_matrix_numerical_features,
+        "pairwise_dist": metrics.sum_pairwise_distances,
+        "energy": metrics.sum_energy_distances,
         "frechet": metrics.frechet_distance,
-        "energy": metrics.energy_dist,
     }
 
     def __init__(