validmind 2.4.4__py3-none-any.whl → 2.4.6__py3-none-any.whl

validmind/__version__.py

@@ -1 +1 @@
-__version__ = "2.4.4"
+__version__ = "2.4.6"

validmind/tests/data_validation/IQROutliersBarPlot.py

@@ -4,7 +4,6 @@
 
 from dataclasses import dataclass
 
-import numpy as np
 import plotly.graph_objects as go
 
 from validmind.vm_models import Figure, Metric
@@ -62,22 +61,27 @@ class IQROutliersBarPlot(Metric):
 
     name = "iqr_outliers_bar_plot"
     required_inputs = ["dataset"]
-    default_params = {"threshold": 1.5, "num_features": None, "fig_width": 800}
+    default_params = {"threshold": 1.5, "fig_width": 800}
     tasks = ["classification", "regression"]
     tags = ["tabular_data", "visualization", "numerical_data"]
 
     def run(self):
         df = self.inputs.dataset.df
-        num_features = self.params["num_features"]
+
+        # Select numerical features
+        features = self.inputs.dataset.feature_columns_numeric
+
+        # Select non-binary features
+        features = [
+            feature
+            for feature in features
+            if len(self.inputs.dataset.df[feature].unique()) > 2
+        ]
+
         threshold = self.params["threshold"]
         fig_width = self.params["fig_width"]
 
-        # If num_features is None, use all numeric columns.
-        # Otherwise, only use the columns provided in num_features.
-        if num_features is None:
-            df = df.select_dtypes(include=[np.number])
-        else:
-            df = df[num_features]
+        df = df[features]
 
         return self.detect_and_visualize_outliers(df, threshold, fig_width)
 
@@ -98,6 +102,9 @@ class IQROutliersBarPlot(Metric):
             # Compute outliers
             outliers = self.compute_outliers(df[col], threshold)
 
+            if outliers.empty:
+                continue  # Skip plotting if there are no outliers
+
             Q1_count = outliers[
                 (outliers >= 0) & (outliers < outliers.quantile(0.25))
             ].count()

validmind/tests/data_validation/IQROutliersTable.py

@@ -4,7 +4,6 @@
 
 from dataclasses import dataclass
 
-import numpy as np
 import pandas as pd
 
 from validmind.vm_models import Metric, ResultSummary, ResultTable, ResultTableMetadata
@@ -53,12 +52,22 @@ class IQROutliersTable(Metric):
 
     name = "iqr_outliers_table"
     required_inputs = ["dataset"]
-    default_params = {"features": None, "threshold": 1.5}
+    default_params = {"threshold": 1.5}
     tasks = ["classification", "regression"]
     tags = ["tabular_data", "numerical_data"]
 
     def run(self):
-        features = self.params["features"]
+
+        # Select numerical features
+        features = self.inputs.dataset.feature_columns_numeric
+
+        # Select non-binary features
+        features = [
+            feature
+            for feature in features
+            if len(self.inputs.dataset.df[feature].unique()) > 2
+        ]
+
         threshold = self.params["threshold"]
 
         df = self.inputs.dataset.df
@@ -80,9 +89,7 @@ class IQROutliersTable(Metric):
         upper_bound = Q3 + threshold * IQR
         return series[(series < lower_bound) | (series > upper_bound)]
 
-    def detect_and_analyze_outliers(self, df, features=None, threshold=1.5):
-        if features is None:
-            features = df.select_dtypes(include=[np.number]).columns.tolist()
+    def detect_and_analyze_outliers(self, df, features, threshold=1.5):
 
         outliers_summary = []
         for feature in features:

validmind/tests/run.py

@@ -89,22 +89,24 @@ def _update_plotly_titles(figures, input_groups, title_template):
     for i, figure in enumerate(figures):
         figure.figure.layout.title.text = title_template.format(
             current_title=f"{current_title} " if current_title else "",
-            input_description=", ".join(
-                f"{k}={v if isinstance(v, str) else v.input_id}"
+            input_description=" and ".join(
+                f"{k}: {v if isinstance(v, str) else ', '.join(item.input_id for item in v) if isinstance(v, list) and all(hasattr(item, 'input_id') for item in v) else v.input_id}"
                 for k, v in input_groups[i].items()
             ),
         )
 
 
 def _update_matplotlib_titles(figures, input_groups, title_template):
-    current_title = figures[0].figure.get_title()
+    current_title = (
+        figures[0].figure._suptitle.get_text() if figures[0].figure._suptitle else ""
+    )
 
     for i, figure in enumerate(figures):
         figure.figure.suptitle(
             title_template.format(
                 current_title=f"{current_title} " if current_title else "",
                 input_description=" and ".join(
-                    f"{k}: {v if isinstance(v, str) else v.input_id}"
+                    f"{k}: {v if isinstance(v, str) else ', '.join(item.input_id for item in v) if isinstance(v, list) and all(hasattr(item, 'input_id') for item in v) else v.input_id}"
                     for k, v in input_groups[i].items()
                 ),
             )
@@ -139,10 +141,20 @@ def metric_comparison(
     """Build a comparison result for multiple metric results"""
     ref_id = str(uuid4())
 
-    input_group_strings = [
-        {k: v if isinstance(v, str) else v.input_id for k, v in group.items()}
-        for group in input_groups
-    ]
+    input_group_strings = []
+
+    for group in input_groups:
+        new_group = {}
+        for k, v in group.items():
+            if isinstance(v, str):
+                new_group[k] = v
+            elif hasattr(v, "input_id"):
+                new_group[k] = v.input_id
+            elif isinstance(v, list) and all(hasattr(item, "input_id") for item in v):
+                new_group[k] = ", ".join([item.input_id for item in v])
+            else:
+                raise ValueError(f"Unsupported type for value: {v}")
+        input_group_strings.append(new_group)
 
     merged_summary = _combine_summaries(
         [
@@ -173,9 +185,11 @@ def metric_comparison(
             ),
         ],
         inputs=[
-            input if isinstance(input, str) else input.input_id
+            item.input_id if hasattr(item, "input_id") else item
             for group in input_groups
             for input in group.values()
+            for item in (input if isinstance(input, list) else [input])
+            if hasattr(item, "input_id") or isinstance(item, str)
         ],
         output_template=output_template,
         metric=MetricResult(
@@ -198,10 +212,20 @@ def threshold_test_comparison(
     """Build a comparison result for multiple threshold test results"""
     ref_id = str(uuid4())
 
-    input_group_strings = [
-        {k: v if isinstance(v, str) else v.input_id for k, v in group.items()}
-        for group in input_groups
-    ]
+    input_group_strings = []
+
+    for group in input_groups:
+        new_group = {}
+        for k, v in group.items():
+            if isinstance(v, str):
+                new_group[k] = v
+            elif hasattr(v, "input_id"):
+                new_group[k] = v.input_id
+            elif isinstance(v, list) and all(hasattr(item, "input_id") for item in v):
+                new_group[k] = ", ".join([item.input_id for item in v])
+            else:
+                raise ValueError(f"Unsupported type for value: {v}")
+        input_group_strings.append(new_group)
 
     merged_summary = _combine_summaries(
         [

{validmind-2.4.4.dist-info → validmind-2.4.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: validmind
-Version: 2.4.4
+Version: 2.4.6
 Summary: ValidMind Developer Framework
 License: Commercial License
 Author: Andres Rodriguez
@@ -32,7 +32,7 @@ Requires-Dist: mistune (>=3.0.2,<4.0.0)
 Requires-Dist: nltk (>=3.8.1,<4.0.0)
 Requires-Dist: numba (<0.59.0)
 Requires-Dist: numpy
-Requires-Dist: openai (>=1) ; extra == "all" or extra == "llm"
+Requires-Dist: openai (>=1) ; extra == "all"
 Requires-Dist: pandas (>=1.1,<2)
 Requires-Dist: plotly
 Requires-Dist: plotly-express

{validmind-2.4.4.dist-info → validmind-2.4.6.dist-info}/RECORD

@@ -1,5 +1,5 @@
 validmind/__init__.py,sha256=UfmzPwUCdUWbWq3zPqqmq4jw0_kfl3hX4U72p_seE4I,3700
-validmind/__version__.py,sha256=zUyWRJ2idk3EkNSUQlyMfzQtAlpD5CCHF2ifejOcf-w,22
+validmind/__version__.py,sha256=jbv3GfuSUTWNtlhuY3Dgm_vD4Uuj9i1AVwV8tthwnik,22
 validmind/ai/test_descriptions.py,sha256=Q1Ftus4x5eiVLKWJu7hqPLukBQZzhy-dARqq_6_JWtk,9464
 validmind/ai/utils.py,sha256=TEXII_S5CpkpczzSyHwTlqLcPMLnPBJWEBR6QFMKh1U,3421
 validmind/api_client.py,sha256=xr9VNqCmA_WFf8rVm-0M0pmzVyLAPFOnfEe4dAog1LA,17144
@@ -110,8 +110,8 @@ validmind/tests/data_validation/FeatureTargetCorrelationPlot.py,sha256=zSrHZ1kuZ
 validmind/tests/data_validation/HeatmapFeatureCorrelations.py,sha256=yGA7douxs7jga6RaS8wIBs9JEee_67w0uN8mQP-7_to,5671
 validmind/tests/data_validation/HighCardinality.py,sha256=HE3lH5cL2Gc9HNR3F0kx4Jhk4WJiXtWfdoCG1mlWS1A,5071
 validmind/tests/data_validation/HighPearsonCorrelation.py,sha256=n4zPGj-ydV1pZIyDidFybC3kItDJrxZgOPHessJcwU0,5702
-validmind/tests/data_validation/IQROutliersBarPlot.py,sha256=0mrLeaoN9NryMa1BM7SnV0KXCOPlt6Nb-9EKyT9GDJY,6310
-validmind/tests/data_validation/IQROutliersTable.py,sha256=k4JO_u5_zOpYmqs_qMPgPCr2kbpJkGiok_HOZE51ZXQ,5848
+validmind/tests/data_validation/IQROutliersBarPlot.py,sha256=BAFGtEA5ySKMuxQcjDZl1uV1bIZek5J10jF5fTVYqhw,6370
+validmind/tests/data_validation/IQROutliersTable.py,sha256=URpkGCP_OWkumDMiRbrKGs5ePcmAAQtTEna2OjvDbUA,5947
 validmind/tests/data_validation/IsolationForestOutliers.py,sha256=fYTM4H8JWgpJH-G8Sxxj5cKmJ8_EVxKn4lm64frGp4A,4841
 validmind/tests/data_validation/KPSS.py,sha256=Ob9UVSlwbxGND0B0qJKmaBskJmGCKxpctpnqosLFK-8,5114
 validmind/tests/data_validation/LaggedCorrelationHeatmap.py,sha256=iAXQU4KJKX1Rum3vJiJmIQsOZ2a-bFqSy4xfTKlfFBs,6008
@@ -266,7 +266,7 @@ validmind/tests/prompt_validation/Robustness.py,sha256=fBdkYnO9yoBazz4wD-l62tT8D
 validmind/tests/prompt_validation/Specificity.py,sha256=h3gKRTTi2rfnGWmGC1YnSt2s_VbZU4KX0iY7LciZ3PU,6068
 validmind/tests/prompt_validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 validmind/tests/prompt_validation/ai_powered_test.py,sha256=7TTeIR5GotQosm7oVT8Y3KnwPB3XkVT1Fzhckpr-SgE,1963
-validmind/tests/run.py,sha256=OI0SxHvJGH0L2o7LyiK-723Cui1UFAu30YxG52ooU7M,14305
+validmind/tests/run.py,sha256=24E5pRg6p0dUHoK6shB9KeKHWTOEJa5HymT6tD8Ozl4,15574
 validmind/tests/test_providers.py,sha256=47xe5eb5ufvj1jmhdRsbSvDQTXSDpFDFNeXg3xtXwhw,5320
 validmind/tests/utils.py,sha256=kNrxfUYbj4DwmkZtpp_1rG4GMUGxYEhvqnYR_A7qAKM,471
 validmind/unit_metrics/__init__.py,sha256=AlFnWA9pmzVf8xysPxYpQ3kBTQ81-YVxRTJpgC0Q41w,7344
@@ -307,8 +307,8 @@ validmind/vm_models/test_suite/runner.py,sha256=aewxadRfoOPH48jes2Gtb3Ju_FWFfVM_
 validmind/vm_models/test_suite/summary.py,sha256=GQRNe2ZvvqjQN0yKmaN7ohAUjRFQIN4YYUYxfOuWN6M,4682
 validmind/vm_models/test_suite/test.py,sha256=_GfbK36l98SjzgVcucmp0OKBJKqMW3neO7SqJ3EWeps,5049
 validmind/vm_models/test_suite/test_suite.py,sha256=Cns2wL54v0T5Mv5_HJb3kMeaa4rtycdqT8KxK9_rWEU,6279
-validmind-2.4.4.dist-info/LICENSE,sha256=XonPUfwjvrC5Ombl3y-ko0Wubb1xdG_7nzvIbkZRKHw,35772
-validmind-2.4.4.dist-info/METADATA,sha256=keXWOaqBlRbo2FO8FDtwgd37iscJMcloL1A3qmY6NGk,4240
-validmind-2.4.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-validmind-2.4.4.dist-info/entry_points.txt,sha256=HuW7YyOv9u_OEWpViQXtv0nfoI67uieJHawKWA4Hv9A,76
-validmind-2.4.4.dist-info/RECORD,,
+validmind-2.4.6.dist-info/LICENSE,sha256=XonPUfwjvrC5Ombl3y-ko0Wubb1xdG_7nzvIbkZRKHw,35772
+validmind-2.4.6.dist-info/METADATA,sha256=fcDV-5tH1o8RdJpJD07ablIH3yDsar6sWfWeEuXo0Fg,4222
+validmind-2.4.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+validmind-2.4.6.dist-info/entry_points.txt,sha256=HuW7YyOv9u_OEWpViQXtv0nfoI67uieJHawKWA4Hv9A,76
+validmind-2.4.6.dist-info/RECORD,,