sklearn r2 giving wrong score

Author: ahosler

ads/opctl/operator/lowcode/forecast/model/forecast_datasets.py

@@ -7,7 +7,6 @@
 import pandas as pd
 from ..operator_config import ForecastOperatorConfig
 from .. import utils
-from ads.opctl.operator.lowcode.forecast.utils import default_signer
 from .transformations import Transformations
 from ads.opctl import logger
 import pandas as pd
@@ -40,7 +39,6 @@ def _load_data(self, spec):
         raw_data = utils._load_data(
             filename=spec.historical_data.url,
             format=spec.historical_data.format,
-            storage_options=default_signer(),
             columns=spec.historical_data.columns,
         )
         self.original_user_data = raw_data.copy()
@@ -71,7 +69,6 @@ def _load_data(self, spec):
             additional_data = utils._load_data(
                 filename=spec.additional_data.url,
                 format=spec.additional_data.format,
-                storage_options=default_signer(),
                 columns=spec.additional_data.columns,
             )
             additional_data = data_transformer._sort_by_datetime_col(additional_data)

ads/opctl/operator/lowcode/forecast/utils.py

@@ -17,9 +17,13 @@
     explained_variance_score,
     mean_absolute_percentage_error,
     mean_squared_error,
-    r2_score,
 )
 
+try:
+    from scipy.stats import linregress
+except:
+    from sklearn.metrics import r2_score
+
 from ads.common.object_storage_details import ObjectStorageDetails
 from ads.dataset.label_encoder import DataFrameLabelEncoder
 from ads.opctl import logger
@@ -358,7 +362,10 @@ def _build_metrics_df(y_true, y_pred, column_name):
     metrics["sMAPE"] = smape(actual=y_true, predicted=y_pred)
     metrics["MAPE"] = mean_absolute_percentage_error(y_true=y_true, y_pred=y_pred)
     metrics["RMSE"] = np.sqrt(mean_squared_error(y_true=y_true, y_pred=y_pred))
-    metrics["r2"] = r2_score(y_true=y_true, y_pred=y_pred)
+    try:
+        metrics["r2"] = linregress(y_true, y_pred).rvalue ** 2
+    except:
+        metrics["r2"] = r2_score(y_true=y_true, y_pred=y_pred)
     metrics["Explained Variance"] = explained_variance_score(
         y_true=y_true, y_pred=y_pred
     )