Quantile encoder

README.md

@@ -34,6 +34,8 @@ __Supervised:__
  * M-estimator [7]
  * Target Encoding [7]
  * Weight of Evidence [8]
+ * Quantile Encoder [13]
+ * Summary Encoder [13]
 
 Installation
 ------------
@@ -142,4 +144,5 @@ References
  10. Simple Count or Frequency Encoding. From https://www.datacamp.com/community/tutorials/encoding-methodologies
  11. Transforming categorical features to numerical features. From https://tech.yandex.com/catboost/doc/dg/concepts/algorithm-main-stages_cat-to-numberic-docpage/
  12. Andrew Gelman and Jennifer Hill (2006). Data Analysis Using Regression and Multilevel/Hierarchical Models. From https://faculty.psau.edu.sa/filedownload/doc-12-pdf-a1997d0d31f84d13c1cdc44ac39a8f2c-original.pdf
+ 13. Carlos Mougan, David Masip, Jordi Nin and Oriol Pujol (2021). Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems. From https://arxiv.org/abs/2105.13783
 

category_encoders/__init__.py

@@ -23,27 +23,30 @@
 from category_encoders.james_stein import JamesSteinEncoder
 from category_encoders.cat_boost import CatBoostEncoder
 from category_encoders.glmm import GLMMEncoder
+from category_encoders.quantile_encoder import QuantileEncoder, SummaryEncoder
 
-__version__ = '2.2.2'
+__version__ = "2.2.2"
 
-__author__ = 'willmcginnis'
+__author__ = "willmcginnis", "cmougan"
 
 __all__ = [
-    'BackwardDifferenceEncoder',
-    'BinaryEncoder',
-    'CountEncoder',
-    'HashingEncoder',
-    'HelmertEncoder',
-    'OneHotEncoder',
-    'OrdinalEncoder',
-    'SumEncoder',
-    'PolynomialEncoder',
-    'BaseNEncoder',
-    'LeaveOneOutEncoder',
-    'TargetEncoder',
-    'WOEEncoder',
-    'MEstimateEncoder',
-    'JamesSteinEncoder',
-    'CatBoostEncoder',
-    'GLMMEncoder'
+    "BackwardDifferenceEncoder",
+    "BinaryEncoder",
+    "CountEncoder",
+    "HashingEncoder",
+    "HelmertEncoder",
+    "OneHotEncoder",
+    "OrdinalEncoder",
+    "SumEncoder",
+    "PolynomialEncoder",
+    "BaseNEncoder",
+    "LeaveOneOutEncoder",
+    "TargetEncoder",
+    "WOEEncoder",
+    "MEstimateEncoder",
+    "JamesSteinEncoder",
+    "CatBoostEncoder",
+    "GLMMEncoder",
+    "QuantileEncoder",
+    "SummaryEncoder",
 ]