validmind 2.8.28__py3-none-any.whl → 2.9.1__py3-none-any.whl

validmind/tests/data_validation/LJungBox.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import pandas as pd
 from statsmodels.stats.diagnostic import acorr_ljungbox
 
@@ -10,7 +12,7 @@ from validmind import RawData, tags, tasks
 
 @tasks("regression")
 @tags("time_series_data", "forecasting", "statistical_test", "statsmodels")
-def LJungBox(dataset):
+def LJungBox(dataset) -> Tuple[pd.DataFrame, RawData]:
     """
     Assesses autocorrelations in dataset features by performing a Ljung-Box test on each feature.
 

validmind/tests/data_validation/LaggedCorrelationHeatmap.py

@@ -2,9 +2,12 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import numpy as np
 import pandas as pd
 import plotly.figure_factory as ff
+import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
 from validmind.vm_models import VMDataset
@@ -15,7 +18,9 @@ COOLWARM = [[0, "rgb(95,5,255)"], [0.5, "rgb(255,255,255)"], [1, "rgb(255,5,0)"]
 
 @tags("time_series_data", "visualization")
 @tasks("regression")
-def LaggedCorrelationHeatmap(dataset: VMDataset, num_lags: int = 10):
+def LaggedCorrelationHeatmap(
+    dataset: VMDataset, num_lags: int = 10
+) -> Tuple[go.Figure, RawData]:
     """
     Assesses and visualizes correlation between target variable and lagged independent variables in a time-series
     dataset.

validmind/tests/data_validation/MissingValues.py

@@ -2,13 +2,17 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict, List, Tuple
+
 from validmind import RawData, tags, tasks
 from validmind.vm_models import VMDataset
 
 
 @tags("tabular_data", "data_quality")
 @tasks("classification", "regression")
-def MissingValues(dataset: VMDataset, min_threshold: int = 1):
+def MissingValues(
+    dataset: VMDataset, min_threshold: int = 1
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Evaluates dataset quality by ensuring missing value ratio across all features does not exceed a set threshold.
 

validmind/tests/data_validation/MissingValuesBarPlot.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
@@ -12,7 +14,7 @@ from validmind.vm_models import VMDataset
 @tasks("classification", "regression")
 def MissingValuesBarPlot(
     dataset: VMDataset, threshold: int = 80, fig_height: int = 600
-):
+) -> Tuple[go.Figure, RawData]:
     """
     Assesses the percentage and distribution of missing values in the dataset via a bar plot, with emphasis on
     identifying high-risk columns based on a user-defined threshold.

validmind/tests/data_validation/MutualInformation.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import plotly.graph_objects as go
 from sklearn.feature_selection import mutual_info_classif, mutual_info_regression
 
@@ -14,7 +17,7 @@ from validmind.vm_models.result import RawData
 @tasks("classification", "regression")
 def MutualInformation(
     dataset: VMDataset, min_threshold: float = 0.01, task: str = "classification"
-):
+) -> Tuple[go.Figure, RawData]:
     """
     Calculates mutual information scores between features and target variable to evaluate feature relevance.
 

validmind/tests/data_validation/PearsonCorrelationMatrix.py

@@ -3,6 +3,8 @@
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
 
+from typing import Tuple
+
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
@@ -10,7 +12,7 @@ from validmind import RawData, tags, tasks
 
 @tags("tabular_data", "numerical_data", "correlation")
 @tasks("classification", "regression")
-def PearsonCorrelationMatrix(dataset):
+def PearsonCorrelationMatrix(dataset) -> Tuple[go.Figure, RawData]:
     """
     Evaluates linear dependency between numerical variables in a dataset via a Pearson Correlation coefficient heat map.
 

validmind/tests/data_validation/PhillipsPerronArch.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict
+
 import numpy as np
 import pandas as pd
 from arch.unitroot import PhillipsPerron
@@ -17,7 +19,7 @@ logger = get_logger(__name__)
 
 @tags("time_series_data", "forecasting", "statistical_test", "unit_root_test")
 @tasks("regression")
-def PhillipsPerronArch(dataset: VMDataset):
+def PhillipsPerronArch(dataset: VMDataset) -> Dict[str, Any]:
     """
     Assesses the stationarity of time series data in each feature of the ML model using the Phillips-Perron test.
 

validmind/tests/data_validation/ProtectedClassesCombination.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
 import sys
+from typing import Dict, Tuple
 
 import pandas as pd
 import plotly.graph_objects as go
@@ -11,6 +12,7 @@ import plotly.subplots as sp
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingDependencyError
 from validmind.logging import get_logger
+from validmind.vm_models import VMDataset, VMModel
 
 try:
     from fairlearn.metrics import (
@@ -33,7 +35,9 @@ logger = get_logger(__name__)
 
 @tags("bias_and_fairness")
 @tasks("classification", "regression")
-def ProtectedClassesCombination(dataset, model, protected_classes=None):
+def ProtectedClassesCombination(
+    dataset: VMDataset, model: VMModel, protected_classes=None
+) -> Tuple[Dict[str, pd.DataFrame], Dict[str, pd.DataFrame], go.Figure, RawData]:
     """
     Visualizes combinations of protected classes and their corresponding error metric differences.
 

validmind/tests/data_validation/ProtectedClassesDescription.py

@@ -3,6 +3,8 @@
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
 
+from typing import List, Tuple, Union
+
 import pandas as pd
 import plotly.graph_objects as go
 
@@ -14,7 +16,9 @@ logger = get_logger(__name__)
 
 @tags("bias_and_fairness", "descriptive_statistics")
 @tasks("classification", "regression")
-def ProtectedClassesDescription(dataset, protected_classes=None):
+def ProtectedClassesDescription(
+    dataset, protected_classes=None
+) -> Tuple[pd.DataFrame, Union[go.Figure, List[go.Figure]], RawData]:
     """
     Visualizes the distribution of protected classes in the dataset relative to the target variable
     and provides descriptive statistics.

validmind/tests/data_validation/ProtectedClassesDisparity.py

@@ -4,12 +4,14 @@
 
 import io
 import sys
+from typing import Any, List, Tuple
 
 import pandas as pd
 
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingDependencyError
 from validmind.logging import get_logger
+from validmind.vm_models import VMDataset, VMModel
 
 try:
     import aequitas.plot as ap
@@ -28,12 +30,12 @@ logger = get_logger(__name__)
 @tags("bias_and_fairness")
 @tasks("classification", "regression")
 def ProtectedClassesDisparity(
-    dataset,
-    model,
+    dataset: VMDataset,
+    model: VMModel,
     protected_classes=None,
     disparity_tolerance=1.25,
     metrics=["fnr", "fpr", "tpr"],
-):
+) -> Tuple[pd.DataFrame, List[bytes], Any, RawData]:
     """
     Investigates disparities in model performance across different protected class segments.
 

validmind/tests/data_validation/ProtectedClassesThresholdOptimizer.py

@@ -4,13 +4,16 @@
 
 import json
 import sys
+from typing import Any, Dict, Tuple
 
+import matplotlib.figure
 import matplotlib.pyplot as plt
 import pandas as pd
 
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingDependencyError
 from validmind.logging import get_logger
+from validmind.vm_models import VMDataset
 
 try:
     from fairlearn.metrics import (
@@ -35,8 +38,12 @@ logger = get_logger(__name__)
 @tags("bias_and_fairness")
 @tasks("classification", "regression")
 def ProtectedClassesThresholdOptimizer(
-    dataset, pipeline=None, protected_classes=None, X_train=None, y_train=None
-):
+    dataset: VMDataset,
+    pipeline=None,
+    protected_classes=None,
+    X_train=None,
+    y_train=None,
+) -> Tuple[Dict[str, Any], matplotlib.figure.Figure, RawData]:
     """
     Obtains a classifier by applying group-specific thresholds to the provided estimator.
 

validmind/tests/data_validation/RollingStatsPlot.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import matplotlib.pyplot as plt
 import pandas as pd
 
@@ -42,7 +44,9 @@ def plot_rolling_statistics(df, col, window_size):
 
 @tags("time_series_data", "visualization", "stationarity")
 @tasks("regression")
-def RollingStatsPlot(dataset: VMDataset, window_size: int = 12):
+def RollingStatsPlot(
+    dataset: VMDataset, window_size: int = 12
+) -> Tuple[plt.Figure, RawData]:
     """
     Evaluates the stationarity of time series data by plotting its rolling mean and standard deviation over a specified
     window.

validmind/tests/data_validation/RunsTest.py

@@ -10,7 +10,7 @@ from validmind import tags, tasks
 
 @tasks("classification", "regression")
 @tags("tabular_data", "statistical_test", "statsmodels")
-def RunsTest(dataset):
+def RunsTest(dataset) -> pd.DataFrame:
     """
     Executes Runs Test on ML model to detect non-random patterns in output data sequence.
 

validmind/tests/data_validation/ScatterPlot.py

@@ -2,6 +2,7 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+import matplotlib.figure
 import matplotlib.pyplot as plt
 import seaborn as sns
 
@@ -10,7 +11,7 @@ from validmind import tags, tasks
 
 @tags("tabular_data", "visualization")
 @tasks("classification", "regression")
-def ScatterPlot(dataset):
+def ScatterPlot(dataset) -> matplotlib.figure.Figure:
     """
     Assesses visual relationships, patterns, and outliers among features in a dataset through scatter plot matrices.
 

validmind/tests/data_validation/ScoreBandDefaultRates.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import numpy as np
 import pandas as pd
 
@@ -16,7 +18,7 @@ def ScoreBandDefaultRates(
     model: VMModel,
     score_column: str = "score",
     score_bands: list = None,
-):
+) -> Tuple[pd.DataFrame, RawData]:
     """
     Analyzes default rates and population distribution across credit score bands.
 

validmind/tests/data_validation/SeasonalDecompose.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
@@ -19,7 +22,9 @@ logger = get_logger(__name__)
 
 @tags("time_series_data", "seasonality", "statsmodels")
 @tasks("regression")
-def SeasonalDecompose(dataset: VMDataset, seasonal_model: str = "additive"):
+def SeasonalDecompose(
+    dataset: VMDataset, seasonal_model: str = "additive"
+) -> Tuple[go.Figure, RawData]:
     """
     Assesses patterns and seasonality in a time series dataset by decomposing its features into foundational components.
 

validmind/tests/data_validation/ShapiroWilk.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import pandas as pd
 from scipy import stats
 
@@ -10,7 +13,7 @@ from validmind import RawData, tags, tasks
 
 @tasks("classification", "regression")
 @tags("tabular_data", "data_distribution", "statistical_test")
-def ShapiroWilk(dataset):
+def ShapiroWilk(dataset) -> Tuple[pd.DataFrame, RawData]:
     """
     Evaluates feature-wise normality of training data using the Shapiro-Wilk test.
 

validmind/tests/data_validation/Skewness.py

@@ -2,13 +2,15 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict, List, Tuple
+
 from validmind import tags, tasks
 from validmind.utils import infer_datatypes
 
 
 @tags("data_quality", "tabular_data")
 @tasks("classification", "regression")
-def Skewness(dataset, max_threshold=1):
+def Skewness(dataset, max_threshold=1) -> Tuple[Dict[str, List[Dict[str, Any]]], bool]:
     """
     Evaluates the skewness of numerical data in a dataset to check against a defined threshold, aiming to ensure data
     quality and optimize model performance.

validmind/tests/data_validation/SpreadPlot.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import matplotlib.pyplot as plt
 import pandas as pd
 import seaborn as sns
@@ -13,7 +15,7 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data", "visualization")
 @tasks("regression")
-def SpreadPlot(dataset: VMDataset):
+def SpreadPlot(dataset: VMDataset) -> Tuple[plt.Figure, RawData]:
     """
     Assesses potential correlations between pairs of time series variables through visualization to enhance
     understanding of their relationships.

validmind/tests/data_validation/TabularCategoricalBarPlots.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import plotly.graph_objs as go
 
 from validmind import RawData, tags, tasks
@@ -11,7 +14,7 @@ from validmind.vm_models import VMDataset
 
 @tags("tabular_data", "visualization")
 @tasks("classification", "regression")
-def TabularCategoricalBarPlots(dataset: VMDataset):
+def TabularCategoricalBarPlots(dataset: VMDataset) -> Tuple[go.Figure, RawData]:
     """
     Generates and visualizes bar plots for each category in categorical features to evaluate the dataset's composition.
 

validmind/tests/data_validation/TabularDateTimeHistograms.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import pandas as pd
 import plotly.graph_objects as go
 
@@ -12,7 +14,7 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data", "visualization")
 @tasks("classification", "regression")
-def TabularDateTimeHistograms(dataset: VMDataset):
+def TabularDateTimeHistograms(dataset: VMDataset) -> Tuple[go.Figure, RawData]:
     """
     Generates histograms to provide graphical insight into the distribution of time intervals in a model's datetime
     data.

validmind/tests/data_validation/TabularDescriptionTables.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import pandas as pd
 
 from validmind import tags, tasks
@@ -9,7 +12,7 @@ from validmind import tags, tasks
 
 @tags("tabular_data")
 @tasks("classification", "regression")
-def TabularDescriptionTables(dataset):
+def TabularDescriptionTables(dataset) -> Tuple[pd.DataFrame]:
     """
     Summarizes key descriptive statistics for numerical, categorical, and datetime variables in a dataset.
 

validmind/tests/data_validation/TabularNumericalHistograms.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import plotly.graph_objs as go
 
 from validmind import tags, tasks
@@ -10,7 +12,7 @@ from validmind.vm_models import VMDataset
 
 @tags("tabular_data", "visualization")
 @tasks("classification", "regression")
-def TabularNumericalHistograms(dataset: VMDataset):
+def TabularNumericalHistograms(dataset: VMDataset) -> Tuple[go.Figure]:
     """
     Generates histograms for each numerical feature in a dataset to provide visual insights into data distribution and
     detect potential issues.

validmind/tests/data_validation/TargetRateBarPlots.py

@@ -2,6 +2,9 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Tuple
+
 import numpy as np
 import plotly.graph_objs as go
 from plotly.subplots import make_subplots
@@ -13,7 +16,7 @@ from validmind.vm_models import VMDataset
 
 @tags("tabular_data", "visualization", "categorical_data")
 @tasks("classification")
-def TargetRateBarPlots(dataset: VMDataset):
+def TargetRateBarPlots(dataset: VMDataset) -> Tuple[go.Figure, RawData]:
     """
     Generates bar plots visualizing the default rates of categorical features for a classification machine learning
     model.

validmind/tests/data_validation/TimeSeriesDescription.py

@@ -9,7 +9,7 @@ from validmind import tags, tasks
 
 @tags("time_series_data", "analysis")
 @tasks("regression")
-def TimeSeriesDescription(dataset):
+def TimeSeriesDescription(dataset) -> pd.DataFrame:
     """
     Generates a detailed analysis for the provided time series dataset, summarizing key statistics to identify trends,
     patterns, and data quality issues.

validmind/tests/data_validation/TimeSeriesDescriptiveStatistics.py

@@ -10,7 +10,7 @@ from validmind import tags, tasks
 
 @tags("time_series_data", "analysis")
 @tasks("regression")
-def TimeSeriesDescriptiveStatistics(dataset):
+def TimeSeriesDescriptiveStatistics(dataset) -> pd.DataFrame:
     """
     Evaluates the descriptive statistics of a time series dataset to identify trends, patterns, and data quality issues.
 

validmind/tests/data_validation/TimeSeriesFrequency.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict, List, Tuple
+
 import pandas as pd
 import plotly.graph_objects as go
 
@@ -12,7 +14,9 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data")
 @tasks("regression")
-def TimeSeriesFrequency(dataset: VMDataset):
+def TimeSeriesFrequency(
+    dataset: VMDataset,
+) -> Tuple[List[Dict[str, Any]], go.Figure, bool, RawData]:
     """
     Evaluates consistency of time series data frequency and generates a frequency plot.
 

validmind/tests/data_validation/TimeSeriesHistogram.py

@@ -2,8 +2,11 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import pandas as pd
 import plotly.express as px
+import plotly.graph_objects as go
 
 from validmind import tags, tasks
 from validmind.logging import get_logger
@@ -13,7 +16,7 @@ logger = get_logger(__name__)
 
 @tags("data_validation", "visualization", "time_series_data")
 @tasks("regression", "time_series_forecasting")
-def TimeSeriesHistogram(dataset, nbins=30):
+def TimeSeriesHistogram(dataset, nbins=30) -> Tuple[go.Figure]:
     """
     Visualizes distribution of time-series data using histograms and Kernel Density Estimation (KDE) lines.
 

validmind/tests/data_validation/TimeSeriesLinePlot.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Tuple
+
 import pandas as pd
 import plotly.graph_objects as go
 
@@ -12,7 +14,7 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data", "visualization")
 @tasks("regression")
-def TimeSeriesLinePlot(dataset: VMDataset):
+def TimeSeriesLinePlot(dataset: VMDataset) -> Tuple[go.Figure]:
     """
     Generates and analyses time-series data through line plots revealing trends, patterns, anomalies over time.
 

validmind/tests/data_validation/TimeSeriesMissingValues.py

@@ -2,9 +2,12 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict, List, Tuple
+
 import pandas as pd
 import plotly.express as px
 import plotly.figure_factory as ff
+import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
 from validmind.errors import SkipTestError
@@ -13,7 +16,9 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data")
 @tasks("regression")
-def TimeSeriesMissingValues(dataset: VMDataset, min_threshold: int = 1):
+def TimeSeriesMissingValues(
+    dataset: VMDataset, min_threshold: int = 1
+) -> Tuple[List[Dict[str, Any]], go.Figure, go.Figure, bool, RawData]:
     """
     Validates time-series data quality by confirming the count of missing values is below a certain threshold.
 

validmind/tests/data_validation/TimeSeriesOutliers.py

@@ -2,6 +2,8 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import List, Tuple
+
 import pandas as pd
 import plotly.graph_objects as go
 
@@ -12,7 +14,9 @@ from validmind.vm_models import VMDataset
 
 @tags("time_series_data")
 @tasks("regression")
-def TimeSeriesOutliers(dataset: VMDataset, zscore_threshold: int = 3):
+def TimeSeriesOutliers(
+    dataset: VMDataset, zscore_threshold: int = 3
+) -> Tuple[pd.DataFrame, List[go.Figure], bool, RawData]:
     """
     Identifies and visualizes outliers in time-series data using the z-score method.
 

validmind/tests/data_validation/TooManyZeroValues.py

@@ -2,13 +2,18 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+
+from typing import Any, Dict, List, Tuple
+
 from validmind.tests import tags, tasks
 from validmind.vm_models import VMDataset
 
 
 @tags("tabular_data")
 @tasks("regression", "classification")
-def TooManyZeroValues(dataset: VMDataset, max_percent_threshold: float = 0.03):
+def TooManyZeroValues(
+    dataset: VMDataset, max_percent_threshold: float = 0.03
+) -> Tuple[List[Dict[str, Any]], bool]:
     """
     Identifies numerical columns in a dataset that contain an excessive number of zero values, defined by a threshold
     percentage.

validmind/tests/data_validation/UniqueRows.py

@@ -2,13 +2,17 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Any, Dict, List, Tuple
+
 from validmind import tags, tasks
 from validmind.vm_models import VMDataset
 
 
 @tags("tabular_data")
 @tasks("regression", "classification")
-def UniqueRows(dataset: VMDataset, min_percent_threshold: float = 1):
+def UniqueRows(
+    dataset: VMDataset, min_percent_threshold: float = 1
+) -> Tuple[List[Dict[str, Any]], bool]:
     """
     Verifies the diversity of the dataset by ensuring that the count of unique rows exceeds a prescribed threshold.