Merge branch 'MAIF:master' into feature/scikit_learn_fix

fcas · Mar 28, 2024 · 4902b1e · 4902b1e
2 parents 424793d + 9be4d36
commit 4902b1e
Show file tree

Hide file tree

Showing 12 changed files with 27 additions and 42 deletions.
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -8,7 +8,7 @@ jobs:
     strategy:
       max-parallel: 1
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}

diff --git a/README.md b/README.md
@@ -143,7 +143,7 @@ Shapash can use category-encoders object, sklearn ColumnTransformer or simply fe
 
 ## 🛠 Installation
 
-Shapash is intended to work with Python versions 3.8 to 3.11. Installation can be done with pip:
+Shapash is intended to work with Python versions 3.9 to 3.12. Installation can be done with pip:
 
 ```bash
 pip install shapash

diff --git a/docs/installation-instructions/index.rst b/docs/installation-instructions/index.rst
@@ -4,7 +4,7 @@ Installation instructions
 Installing
 ----------
 
-**Shapash** is intended to work with Python versions 3.8 to 3.11. Installation can be done with pip:
+**Shapash** is intended to work with Python versions 3.9 to 3.12. Installation can be done with pip:
 
 .. code:: bash
 

diff --git a/requirements.dev.txt b/requirements.dev.txt
@@ -13,7 +13,7 @@ dash-table==5.0.0
 lightgbm==2.3.1
 pandas>1.0.2
 plotly==5.6.0
-shap>=0.38.1
+shap>=0.38.1,<0.45.0
 Sphinx==4.5.0
 sphinxcontrib-applehelp==1.0.2
 sphinxcontrib-devhelp==1.0.2

diff --git a/setup.py b/setup.py
@@ -21,7 +21,7 @@
     "matplotlib>=3.2.0",
     "numpy>1.18.0",
     "pandas>1.0.2",
-    "shap>=0.38.1",
+    "shap>=0.38.1,<0.45.0",
     "Flask<2.3.0",
     "dash>=2.3.1",
     "dash-bootstrap-components>=1.1.0",
@@ -66,7 +66,7 @@
 setup(
     name="shapash",
     version=version_d["__version__"],
-    python_requires=">3.7, <3.12",
+    python_requires=">3.8, <3.13",
     url="https://github.com/MAIF/shapash",
     author="Yann Golhen, Sebastien Bidault, Yann Lagre, Maxime Gendre",
     author_email="yann.golhen@maif.fr",
@@ -75,10 +75,10 @@
     long_description_content_type="text/markdown",
     classifiers=[
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
         "License :: OSI Approved :: Apache Software License",
         "Operating System :: OS Independent",
     ],

diff --git a/shapash/__version__.py b/shapash/__version__.py
@@ -1,3 +1,3 @@
-VERSION = (2, 4, 2)
+VERSION = (2, 4, 3)
 
 __version__ = ".".join(map(str, VERSION))
diff --git a/shapash/utils/category_encoder_backend.py b/shapash/utils/category_encoder_backend.py
@@ -2,7 +2,6 @@
 Category_encoder
 """
 
-import category_encoders as ce
 import numpy as np
 import pandas as pd
 
@@ -54,12 +53,8 @@ def inv_transform_ce(x_in, encoding):
         rst = inv_transform_ordinal(x, encoding.ordinal_encoder.mapping)
 
     elif str(type(encoding)) == category_encoder_binary:
-        if ce.__version__ <= "2.2.2":
-            x = reverse_basen(x_in, encoding.base_n_encoder)
-            rst = inv_transform_ordinal(x, encoding.base_n_encoder.ordinal_encoder.mapping)
-        else:
-            x = reverse_basen(x_in, encoding)
-            rst = inv_transform_ordinal(x, encoding.ordinal_encoder.mapping)
+        x = reverse_basen(x_in, encoding)
+        rst = inv_transform_ordinal(x, encoding.ordinal_encoder.mapping)
 
     elif str(type(encoding)) == category_encoder_targetencoder:
         rst = inv_transform_target(x_in, encoding)
@@ -206,8 +201,6 @@ def calc_inv_contrib_ce(x_contrib, encoding, agg_columns):
         The aggregate contributions depending on which processing is apply.
     """
     if str(type(encoding)) in dummies_category_encoder:
-        if str(type(encoding)) in category_encoder_binary and ce.__version__ <= "2.2.2":
-            encoding = encoding.base_n_encoder
         drop_col = []
         for switch in encoding.mapping:
             col_in = switch.get("col")
@@ -312,10 +305,7 @@ def get_col_mapping_ce(encoder):
     ]:
         encoder_mapping = encoder.mapping
     elif str(type(encoder)) == category_encoder_binary:
-        if ce.__version__ <= "2.2.2":
-            encoder_mapping = encoder.base_n_encoder.mapping
-        else:
-            encoder_mapping = encoder.mapping
+        encoder_mapping = encoder.mapping
     else:
         raise NotImplementedError(f"{encoder} not supported.")
 

diff --git a/tests/unit_tests/explainer/test_smart_explainer.py b/tests/unit_tests/explainer/test_smart_explainer.py
@@ -1,6 +1,7 @@
 """
 Unit test for smart explainer
 """
+
 import os
 import sys
 import types
@@ -633,14 +634,14 @@ def test_load_1(self):
         temp, xpl = init_sme_to_pickle_test()
 
         current = Path(path.abspath(__file__)).parent.parent.parent
-        if str(sys.version)[0:3] == "3.8":
-            pkl_file = path.join(current, "data/xpl_to_load_38.pkl")
-        elif str(sys.version)[0:3] == "3.9":
+        if str(sys.version)[0:3] == "3.9":
             pkl_file = path.join(current, "data/xpl_to_load_39.pkl")
         elif str(sys.version)[0:4] == "3.10":
             pkl_file = path.join(current, "data/xpl_to_load_310.pkl")
         elif str(sys.version)[0:4] == "3.11":
             pkl_file = path.join(current, "data/xpl_to_load_311.pkl")
+        elif str(sys.version)[0:4] == "3.12":
+            pkl_file = path.join(current, "data/xpl_to_load_312.pkl")
         else:
             raise NotImplementedError
 

diff --git a/tests/unit_tests/utils/test_category_encoders_backend.py b/tests/unit_tests/utils/test_category_encoders_backend.py
@@ -739,18 +739,11 @@ def test_get_col_mapping_ce_4(self):
         enc.fit(test, y)
 
         mapping = get_col_mapping_ce(enc)
-        if ce.__version__ <= "2.2.2":
-            expected_mapping = {
-                "city": ["city_0", "city_1", "city_2"],
-                "state": ["state_0", "state_1"],
-                "other": ["other_0", "other_1"],
-            }
-        else:
-            expected_mapping = {
-                "city": ["city_0", "city_1"],
-                "state": ["state_0", "state_1"],
-                "other": ["other_0", "other_1"],
-            }
+        expected_mapping = {
+            "city": ["city_0", "city_1"],
+            "state": ["state_0", "state_1"],
+            "other": ["other_0", "other_1"],
+        }
 
         self.assertDictEqual(mapping, expected_mapping)
 

diff --git a/tests/unit_tests/utils/test_columntransformer_backend.py b/tests/unit_tests/utils/test_columntransformer_backend.py
@@ -1178,10 +1178,7 @@ def test_get_col_mapping_ct_6(self):
 
         test_encoded = pd.DataFrame(enc.fit_transform(test, y))
         mapping = get_col_mapping_ct(enc, test_encoded)
-        if ce.__version__ <= "2.2.2":
-            expected_mapping = {"basen_city": [0, 1, 2], "basen_state": [3, 4]}
-        else:
-            expected_mapping = {"basen_city": [0, 1], "basen_state": [2, 3]}
+        expected_mapping = {"basen_city": [0, 1], "basen_state": [2, 3]}
 
         self.assertDictEqual(mapping, expected_mapping)
 

diff --git a/tests/unit_tests/utils/test_load_smartpredictor.py b/tests/unit_tests/utils/test_load_smartpredictor.py
@@ -1,6 +1,7 @@
 """
 Unit test smart predictor
 """
+
 import sys
 import unittest
 from os import path
@@ -29,12 +30,12 @@ def test_load_smartpredictor_1(self):
         current = Path(path.abspath(__file__)).parent.parent.parent
         if str(sys.version)[0:4] == "3.10":
             pkl_file = path.join(current, "data/predictor_to_load_310.pkl")
-        elif str(sys.version)[0:3] == "3.8":
-            pkl_file = path.join(current, "data/predictor_to_load_38.pkl")
         elif str(sys.version)[0:3] == "3.9":
             pkl_file = path.join(current, "data/predictor_to_load_39.pkl")
         elif str(sys.version)[0:4] == "3.11":
             pkl_file = path.join(current, "data/predictor_to_load_311.pkl")
+        elif str(sys.version)[0:4] == "3.12":
+            pkl_file = path.join(current, "data/predictor_to_load_312.pkl")
         else:
             raise NotImplementedError
 

diff --git a/tutorial/generate_report/shapash_report_example.py b/tutorial/generate_report/shapash_report_example.py
@@ -4,12 +4,15 @@
 that generates the same report.
 """
 import os
+import sys
 
 import pandas as pd
 from category_encoders import OrdinalEncoder
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.model_selection import train_test_split
 
+sys.path.insert(0, "..")
+
 from shapash import SmartExplainer
 from shapash.data.data_loader import data_loading