Norm the API (#873)

* Norm of return_report * removing name generation from functions * Update kmeans.py * format * Removing endogtest - the test is wrong and there is no equivalent in other Python module = useless
vertica · Nov 16, 2023 · c07b6d5 · c07b6d5
1 parent 374099c
commit c07b6d5
Show file tree

Hide file tree

Showing 20 changed files with 205 additions and 388 deletions.
diff --git a/docs/source/stats.rst b/docs/source/stats.rst
@@ -21,18 +21,6 @@ Heteroscedascity
    ols.het_goldfeldquandt
    ols.het_white
 
-____
-
-Endogeneity
--------------
-
-.. currentmodule:: verticapy.machine_learning.model_selection.statistical_tests
-
-.. autosummary:: 
-   :toctree: api/
-
-   ols.endogtest
-
 
 ____
 

diff --git a/verticapy/core/vdataframe/_corr.py b/verticapy/core/vdataframe/_corr.py
@@ -1993,6 +1993,7 @@ def pacf(
                     input_relation=tmp_view_name,
                     X=[f"lag_{i}_{gen_name([column])}" for i in range(1, p)],
                     y=column,
+                    return_report=True,
                 )
                 model.predict(vdf, name="prediction_0")
                 drop(tmp_lr1_name, method="model")
@@ -2001,6 +2002,7 @@ def pacf(
                     input_relation=tmp_view_name,
                     X=[f"lag_{i}_{gen_name([column])}" for i in range(1, p)],
                     y=f"lag_{p}_{gen_name([column])}",
+                    return_report=True,
                 )
                 model.predict(vdf, name="prediction_p")
                 vdf.eval(expr=f"{column} - prediction_0", name="eps_0")

diff --git a/verticapy/core/vdataframe/_encoding.py b/verticapy/core/vdataframe/_encoding.py
@@ -301,7 +301,12 @@ def discretize(
             model.set_params(RFmodel_params)
             parameters = model.get_params()
             try:
-                model.fit(tmp_view_name, [self._alias], response)
+                model.fit(
+                    tmp_view_name,
+                    [self._alias],
+                    response,
+                    return_report=True,
+                )
                 query = [
                     f"""
                     (SELECT 

diff --git a/verticapy/machine_learning/model_selection/hp_tuning/cv.py b/verticapy/machine_learning/model_selection/hp_tuning/cv.py
@@ -719,7 +719,12 @@ def bayesian_search_cv(
         hyper_param_estimator = vml.RandomForestRegressor(
             name=estimator.model_name, **RFmodel_params
         )
-        hyper_param_estimator.fit(relation, all_params, "score")
+        hyper_param_estimator.fit(
+            relation,
+            all_params,
+            "score",
+            return_report=True,
+        )
         if random_grid:
             vdf = gen_dataset(model_grid, nrows=nrows)
         else:

diff --git a/verticapy/machine_learning/model_selection/kmeans.py b/verticapy/machine_learning/model_selection/kmeans.py
@@ -139,7 +139,11 @@ def best_k(
                 max_iter=max_iter,
                 tol=tol,
             )
-        model.fit(input_relation, X)
+        model.fit(
+            input_relation,
+            X,
+            return_report=True,
+        )
         score = model.elbow_score_
         if score > elbow_score_stop:
             return i
@@ -266,7 +270,11 @@ def elbow(
                 max_iter=max_iter,
                 tol=tol,
             )
-        model.fit(input_relation, X)
+        model.fit(
+            input_relation,
+            X,
+            return_report=True,
+        )
         elbow_score += [float(model.elbow_score_)]
         between_cluster_ss += [float(model.between_cluster_ss_)]
         total_ss += [float(model.total_ss_)]

diff --git a/verticapy/machine_learning/model_selection/model_validation.py b/verticapy/machine_learning/model_selection/model_validation.py
@@ -229,7 +229,13 @@ def cross_validate(
             test_size=float(1 / cv), order_by=[X[0]], random_state=random_state
         )
         start_time = time.time()
-        estimator.fit(train, X, y, test)
+        estimator.fit(
+            train,
+            X,
+            y,
+            test,
+            return_report=True,
+        )
         total_time += [time.time() - start_time]
         fun = estimator.report
         kwargs = {"metrics": final_metrics}

diff --git a/verticapy/machine_learning/model_selection/statistical_tests/__init__.py b/verticapy/machine_learning/model_selection/statistical_tests/__init__.py
@@ -24,7 +24,6 @@
     seasonal_decompose,
 )
 from verticapy.machine_learning.model_selection.statistical_tests.ols import (
-    endogtest,
     het_breuschpagan,
     het_goldfeldquandt,
     het_white,