VerticaPy Documentation Update : Fixed link + RFClassifier description (

#1241) * corrected features engineering page link for docs * updated doc/description for RandomForestClassifier * correcting unit tests * Update test_tree_model.py * version --------- Co-authored-by: Badr <[email protected]>
vertica · Jun 22, 2024 · 6e1432a · 6e1432a
1 parent 490e6ef
commit 6e1432a
Show file tree

Hide file tree

Showing 7 changed files with 48 additions and 19 deletions.
diff --git a/docs/source/user_guide_data_preparation.rst b/docs/source/user_guide_data_preparation.rst
@@ -104,7 +104,7 @@ Data Preparation
     .. grid-item::
 
         .. card:: Feature engineering
-          :link: notebooks/data_prep/featrues_engineering/index.html
+          :link: notebooks/data_prep/features_engineering/index.html
           :text-align: center
           :class-card: custom-card-13
 
@@ -121,7 +121,7 @@ Data Preparation
   notebooks/data_prep/decomposition/index.ipynb
   notebooks/data_prep/duplicates/index.ipynb
   notebooks/data_prep/encoding/index.ipynb
-  notebooks/data_prep/featrues_engineering/index.ipynb
+  notebooks/data_prep/features_engineering/index.ipynb
   notebooks/data_prep/joins/index.ipynb
   notebooks/data_prep/missing_values/index.ipynb
   notebooks/data_prep/normalization/index.ipynb

diff --git a/setup.py b/setup.py
@@ -23,7 +23,7 @@
 
 setuptools.setup(
     name="verticapy",
-    version="1.0.3",
+    version="1.0.4",
     author="Badr Ouali",
     author_email="[email protected]",
     url="https://github.com/vertica/VerticaPy",

diff --git a/verticapy/__init__.py b/verticapy/__init__.py
@@ -36,10 +36,10 @@
 )
 __url__: str = "https://github.com/vertica/verticapy/"
 __license__: str = "Apache License, Version 2.0"
-__version__: str = "1.0.3"
+__version__: str = "1.0.4"
 __iteration__: int = 1
-__date__: str = "05172024"
-__last_commit__: str = "916be8bc734a83d5e7f71ee6737cac7ec4b1a686"
+__date__: str = "06222024"
+__last_commit__: str = "b37e103cd5fbfea64eb167d42dcf2cdaad99fd75"
 __long_version__: str = f"{__version__}-{__iteration__}—{__date__}-{__last_commit__}"
 __codecov__: float = 0.8316
 

diff --git a/verticapy/machine_learning/vertica/ensemble.py b/verticapy/machine_learning/vertica/ensemble.py
@@ -1846,13 +1846,21 @@ def to_memmodel(self) -> mm.XGBRegressor:
 
 class RandomForestClassifier(MulticlassClassifier, RandomForest):
     """
-    Creates a ``RandomForestClassifier``
-    object using the Vertica RF_CLASSIFIER
-    function. It is an ensemble learning
-    method for classification that operates
-    by constructing a multitude of decision
-    trees at training-time and outputting a
-    class with the mode.
+    Creates a RandomForestClassifier object
+    using the Vertica RF_CLASSIFIER function.
+    It is an ensemble learning method for
+    classification that operates by constructing
+    a multitude of decision trees during
+    training and predicting the class by using
+    a majority voting strategy among the
+    individual trees.
+
+    The classifier aggregates the predictions
+    of multiple decision trees to determine
+    the final output class, thus improving
+    the overall prediction accuracy and
+    robustness compared to a single decision
+    tree.
 
     Parameters
     ----------

diff --git a/verticapy/tests/vModel/test_xgb_classifier.py b/verticapy/tests/vModel/test_xgb_classifier.py
@@ -19,6 +19,7 @@
 import pytest
 
 # Standard Python Modules
+import sys
 import os
 
 # Other Modules
@@ -561,6 +562,9 @@ def test_plot_tree(self, model):
         result = model.plot_tree()
         assert model.to_graphviz() == result.source.strip()
 
+    @pytest.mark.skipif(
+        sys.version_info > (3, 11), reason="Requires Python 3.11 or lower"
+    )
     def test_to_json_binary(self, titanic_vd):
         import xgboost as xgb
 
@@ -593,6 +597,9 @@ def test_to_json_binary(self, titanic_vd):
         model.drop()
         os.remove(path)
 
+    @pytest.mark.skipif(
+        sys.version_info > (3, 11), reason="Requires Python 3.11 or lower"
+    )
     def test_to_json_multiclass(self, titanic_vd):
         titanic = titanic_vd.copy()
         titanic.fillna()

diff --git a/verticapy/tests_new/machine_learning/vertica/test_linear_model.py b/verticapy/tests_new/machine_learning/vertica/test_linear_model.py
@@ -288,9 +288,14 @@ def test_regression_report_anova(
 
                 if metric_type != "":
                     _rel_tol, _abs_tol = calculate_tolerance(vpy_res, py_res)
-                    print(
-                        f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % Decimal(_rel_tol)}, abs_tol(e): {'%.e' % Decimal(_abs_tol)}"
-                    )
+                    try:
+                        print(
+                            f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % Decimal(_rel_tol)}, abs_tol(e): {'%.e' % Decimal(_abs_tol)}"
+                        )
+                    except:
+                        print(
+                            f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % float(_rel_tol)}, abs_tol(e): {'%.e' % float(_abs_tol)}"
+                        )
 
                     if py_res == 0:
                         assert vpy_res == pytest.approx(py_res, abs=1e-9)

diff --git a/verticapy/tests_new/machine_learning/vertica/test_tree_model.py b/verticapy/tests_new/machine_learning/vertica/test_tree_model.py
@@ -15,6 +15,7 @@
 permissions and limitations under the License.
 """
 from decimal import Decimal
+import sys
 import os
 import pandas as pd
 import pytest
@@ -289,9 +290,14 @@ def test_regression_report_anova(
 
             if metric_type != "":
                 _rel_tol, _abs_tol = calculate_tolerance(vpy_res, py_res)
-                print(
-                    f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % Decimal(_rel_tol)}, abs_tol(e): {'%.e' % Decimal(_abs_tol)}"
-                )
+                try:
+                    print(
+                        f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % Decimal(_rel_tol)}, abs_tol(e): {'%.e' % Decimal(_abs_tol)}"
+                    )
+                except:
+                    print(
+                        f"Model_class: {model_class}, Metric_name: {metric}, Metric_type: {metric_type}, rel_tol(e): {'%.e' % float(_rel_tol)}, abs_tol(e): {'%.e' % float(_abs_tol)}"
+                    )
 
                 if py_res == 0:
                     assert vpy_res == pytest.approx(py_res, abs=1e-9)
@@ -645,6 +651,9 @@ class TestXGBModel:
     test class - test class for xgb model
     """
 
+    @pytest.mark.skipif(
+        sys.version_info > (3, 11), reason="Requires Python 3.11 or lower"
+    )
     def test_to_json(self, model_class, get_vpy_model, get_py_model):
         """
         test function - test_to_json