validmind 2.3.3__py3-none-any.whl → 2.4.0__py3-none-any.whl

validmind/tests/data_validation/ADF.py

@@ -47,16 +47,14 @@ class ADF(Metric):
 
     name = "adf"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["regression"],
-        "tags": [
-            "time_series_data",
-            "statsmodels",
-            "forecasting",
-            "statistical_test",
-            "stationarity",
-        ],
-    }
+    tasks = ["regression"]
+    tags = [
+        "time_series_data",
+        "statsmodels",
+        "forecasting",
+        "statistical_test",
+        "stationarity",
+    ]
 
     def summary(self, metric_value: dict):
         table = pd.DataFrame.from_dict(metric_value, orient="index")

validmind/tests/data_validation/ANOVAOneWayTable.py

@@ -57,16 +57,14 @@ class ANOVAOneWayTable(Metric):
     name = "anova_one_way_table"
     required_inputs = ["dataset"]
     default_params = {"features": None, "p_threshold": 0.05}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": [
-            "tabular_data",
-            "statistical_test",
-            "multiclass_classification",
-            "binary_classification",
-            "numerical_data",
-        ],
-    }
+    tasks = ["classification"]
+    tags = [
+        "tabular_data",
+        "statistical_test",
+        "multiclass_classification",
+        "binary_classification",
+        "numerical_data",
+    ]
 
     def run(self):
         features = self.params["features"]

validmind/tests/data_validation/AutoAR.py

@@ -61,10 +61,8 @@ class AutoAR(Metric):
     name = "auto_ar"
     required_inputs = ["dataset"]
     default_params = {"max_ar_order": 3}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "statsmodels", "forecasting", "statistical_test"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "statsmodels", "forecasting", "statistical_test"]
 
     def run(self):
         if "max_ar_order" not in self.params:

validmind/tests/data_validation/AutoMA.py

@@ -57,10 +57,8 @@ class AutoMA(Metric):
     name = "auto_ma"
     required_inputs = ["dataset"]
     default_params = {"max_ma_order": 3}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "statsmodels", "forecasting", "statistical_test"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "statsmodels", "forecasting", "statistical_test"]
 
     def run(self):
         if "max_ma_order" not in self.params:

validmind/tests/data_validation/AutoSeasonality.py

@@ -61,16 +61,14 @@ class AutoSeasonality(Metric):
     name = "auto_seasonality"
     required_inputs = ["dataset"]
     default_params = {"min_period": 1, "max_period": 4}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": [
-            "time_series_data",
-            "forecasting",
-            "statistical_test",
-            "statsmodels",
-            "seasonality",
-        ],
-    }
+    tasks = ["regression"]
+    tags = [
+        "time_series_data",
+        "forecasting",
+        "statistical_test",
+        "statsmodels",
+        "seasonality",
+    ]
 
     def evaluate_seasonal_periods(self, series, min_period, max_period):
         seasonal_periods = []

validmind/tests/data_validation/AutoStationarity.py

@@ -54,16 +54,14 @@ class AutoStationarity(Metric):
     name = "auto_stationarity"
     required_inputs = ["dataset"]
     default_params = {"max_order": 5, "threshold": 0.05}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": [
-            "time_series_data",
-            "statsmodels",
-            "forecasting",
-            "statistical_test",
-            "stationarity",
-        ],
-    }
+    tasks = ["regression"]
+    tags = [
+        "time_series_data",
+        "statsmodels",
+        "forecasting",
+        "statistical_test",
+        "stationarity",
+    ]
 
     def run(self):
         if "max_order" not in self.params:

validmind/tests/data_validation/BivariateFeaturesBarPlots.py

@@ -56,16 +56,14 @@ class BivariateFeaturesBarPlots(Metric):
     name = "bivariate_features_bar_plots"
     required_inputs = ["dataset"]
     default_params = {"features_pairs": None}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": [
-            "tabular_data",
-            "categorical_data",
-            "binary_classification",
-            "multiclass_classification",
-            "visualization",
-        ],
-    }
+    tasks = ["classification"]
+    tags = [
+        "tabular_data",
+        "categorical_data",
+        "binary_classification",
+        "multiclass_classification",
+        "visualization",
+    ]
 
     def run(self):
         features_pairs = self.params["features_pairs"]

validmind/tests/data_validation/BivariateHistograms.py

@@ -55,16 +55,14 @@ class BivariateHistograms(Metric):
     name = "bivariate_histograms"
     required_inputs = ["dataset"]
     default_params = {"features_pairs": None, "target_filter": None}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": [
-            "tabular_data",
-            "categorical_data",
-            "binary_classification",
-            "multiclass_classification",
-            "visualization",
-        ],
-    }
+    tasks = ["classification"]
+    tags = [
+        "tabular_data",
+        "categorical_data",
+        "binary_classification",
+        "multiclass_classification",
+        "visualization",
+    ]
 
     def plot_bivariate_histogram(self, features_pairs, target_filter):
         status_var = self.inputs.dataset.target_column

validmind/tests/data_validation/BivariateScatterPlots.py

@@ -54,16 +54,14 @@ class BivariateScatterPlots(Metric):
     name = "bivariate_scatter_plots"
     required_inputs = ["dataset"]
     default_params = {"selected_columns": None}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": [
-            "tabular_data",
-            "categorical_data",
-            "binary_classification",
-            "multiclass_classification",
-            "visualization",
-        ],
-    }
+    tasks = ["classification"]
+    tags = [
+        "tabular_data",
+        "categorical_data",
+        "binary_classification",
+        "multiclass_classification",
+        "visualization",
+    ]
 
     def plot_bivariate_scatter(self, columns):
         figures = []

validmind/tests/data_validation/ChiSquaredFeaturesTable.py

@@ -54,16 +54,14 @@ class ChiSquaredFeaturesTable(Metric):
     name = "chi_squared_features_table"
     required_inputs = ["dataset"]
     default_params = {"cat_features": None, "p_threshold": 0.05}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": [
-            "tabular_data",
-            "categorical_data",
-            "statistical_test",
-            "binary_classification",
-            "multiclass_classification",
-        ],
-    }
+    tasks = ["classification"]
+    tags = [
+        "tabular_data",
+        "categorical_data",
+        "statistical_test",
+        "binary_classification",
+        "multiclass_classification",
+    ]
 
     def run(self):
         target_column = self.inputs.dataset.target_column

validmind/tests/data_validation/ClassImbalance.py

@@ -73,10 +73,8 @@ class ClassImbalance(ThresholdTest):
     name = "class_imbalance"
     required_inputs = ["dataset"]
     default_params = {"min_percent_threshold": 10}
-    metadata = {
-        "task_types": ["classification"],
-        "tags": ["tabular_data", "binary_classification", "multiclass_classification"],
-    }
+    tasks = ["classification"]
+    tags = ["tabular_data", "binary_classification", "multiclass_classification"]
 
     def summary(self, results: List[ThresholdTestResult], all_passed: bool):
         return ResultSummary(

validmind/tests/data_validation/DFGLSArch.py

@@ -53,10 +53,8 @@ class DFGLSArch(Metric):
 
     name = "dickey_fuller_gls"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "forecasting", "unit_root_test"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "forecasting", "unit_root_test"]
 
     def run(self):
         """

validmind/tests/data_validation/DatasetDescription.py

@@ -69,15 +69,13 @@ class DatasetDescription(Metric):
 
     name = "dataset_description"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": [
-            "classification",
-            "regression",
-            "text_classification",
-            "text_summarization",
-        ],
-        "tags": ["tabular_data", "time_series_data", "text_data"],
-    }
+    tasks = [
+        "classification",
+        "regression",
+        "text_classification",
+        "text_summarization",
+    ]
+    tags = ["tabular_data", "time_series_data", "text_data"]
 
     def summary(self, metric_value):
         """

validmind/tests/data_validation/DatasetSplit.py

@@ -48,15 +48,14 @@ class DatasetSplit(Metric):
 
     name = "dataset_split"
     required_inputs = ["datasets"]
-    metadata = {
-        "task_types": [
-            "classification",
-            "regression",
-            "text_classification",
-            "text_summarization",
-        ],
-        "tags": ["tabular_data", "time_series_data", "text_data"],
-    }
+    tasks = [
+        "classification",
+        "regression",
+        "text_classification",
+        "text_summarization",
+    ]
+
+    tags = ["tabular_data", "time_series_data", "text_data"]
 
     dataset_labels = {
         "train_ds": "Training",

validmind/tests/data_validation/DescriptiveStatistics.py

@@ -53,10 +53,8 @@ class DescriptiveStatistics(Metric):
 
     name = "descriptive_statistics"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "time_series_data"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "time_series_data"]
 
     def get_summary_statistics_numerical(self, df, numerical_fields):
         percentiles = [0.25, 0.5, 0.75, 0.90, 0.95]

validmind/tests/data_validation/Duplicates.py

@@ -55,10 +55,8 @@ class Duplicates(ThresholdTest):
     name = "duplicates"
     required_inputs = ["dataset"]
     default_params = {"min_threshold": 1}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality", "text_data"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality", "text_data"]
 
     def summary(self, results: List[ThresholdTestResult], all_passed: bool):
         """

validmind/tests/data_validation/EngleGrangerCoint.py

@@ -51,10 +51,8 @@ class EngleGrangerCoint(Metric):
     name = "engle_granger_coint"
     required_inputs = ["dataset"]
     default_params = {"threshold": 0.05}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "statistical_test", "forecasting"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "statistical_test", "forecasting"]
 
     def run(self):
         threshold = self.params["threshold"]

validmind/tests/data_validation/FeatureTargetCorrelationPlot.py

@@ -48,10 +48,8 @@ class FeatureTargetCorrelationPlot(Metric):
     name = "feature_target_correlation_plot"
     required_inputs = ["dataset"]
     default_params = {"features": None, "fig_height": 600}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "visualization", "feature_importance", "correlation"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "visualization", "feature_importance", "correlation"]
 
     def run(self):
         fig_height = self.params["fig_height"]

validmind/tests/data_validation/HeatmapFeatureCorrelations.py

@@ -56,10 +56,8 @@ class HeatmapFeatureCorrelations(Metric):
     name = "heatmap_feature_correlations"
     required_inputs = ["dataset"]
     default_params = {"declutter": None, "fontsize": None, "num_features": None}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "visualization", "correlation"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "visualization", "correlation"]
 
     def run(self):
         features = self.params.get("features")

validmind/tests/data_validation/HighCardinality.py

@@ -57,10 +57,8 @@ class HighCardinality(ThresholdTest):
         "percent_threshold": 0.1,
         "threshold_type": "percent",  # or "num"
     }
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality", "categorical_data"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality", "categorical_data"]
 
     def summary(self, results: List[ThresholdTestResult], all_passed: bool):
         """

validmind/tests/data_validation/HighPearsonCorrelation.py

@@ -59,10 +59,8 @@ class HighPearsonCorrelation(ThresholdTest):
     name = "pearson_correlation"
     required_inputs = ["dataset"]
     default_params = {"max_threshold": 0.3}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality", "correlation"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality", "correlation"]
 
     def summary(self, results: List[ThresholdTestResult], all_passed: bool):
         """The high pearson correlation test returns results like these:

validmind/tests/data_validation/IQROutliersBarPlot.py

@@ -63,10 +63,8 @@ class IQROutliersBarPlot(Metric):
     name = "iqr_outliers_bar_plot"
     required_inputs = ["dataset"]
     default_params = {"threshold": 1.5, "num_features": None, "fig_width": 800}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "visualization", "numerical_data"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "visualization", "numerical_data"]
 
     def run(self):
         df = self.inputs.dataset.df

validmind/tests/data_validation/IQROutliersTable.py

@@ -54,10 +54,8 @@ class IQROutliersTable(Metric):
     name = "iqr_outliers_table"
     required_inputs = ["dataset"]
     default_params = {"features": None, "threshold": 1.5}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "numerical_data"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "numerical_data"]
 
     def run(self):
         features = self.params["features"]

validmind/tests/data_validation/IsolationForestOutliers.py

@@ -55,10 +55,8 @@ class IsolationForestOutliers(Metric):
         "contamination": 0.1,
         "features_columns": None,
     }
-    metadata = {
-        "task_types": ["classification"],
-        "tags": ["tabular_data", "anomaly_detection"],
-    }
+    tasks = ["classification"]
+    tags = ["tabular_data", "anomaly_detection"]
 
     required_inputs = ["dataset"]
 

validmind/tests/data_validation/KPSS.py

@@ -51,16 +51,14 @@ class KPSS(Metric):
 
     name = "kpss"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["regression"],
-        "tags": [
-            "time_series_data",
-            "forecasting",
-            "stationarity",
-            "unit_root_test",
-            "statsmodels",
-        ],
-    }
+    tasks = ["regression"]
+    tags = [
+        "time_series_data",
+        "forecasting",
+        "stationarity",
+        "unit_root_test",
+        "statsmodels",
+    ]
 
     def run(self):
         """

validmind/tests/data_validation/LaggedCorrelationHeatmap.py

@@ -51,10 +51,8 @@ class LaggedCorrelationHeatmap(Metric):
 
     name = "lagged_correlation_heatmap"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "visualization"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "visualization"]
 
     def _compute_correlations(self, df, target_col, independent_vars, num_lags):
         correlations = np.zeros((len(independent_vars), num_lags + 1))

validmind/tests/data_validation/MissingValues.py

@@ -52,10 +52,8 @@ class MissingValues(ThresholdTest):
     name = "missing"
     required_inputs = ["dataset"]
     default_params = {"min_threshold": 1}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality"]
 
     def summary(self, results: List[ThresholdTestResult], all_passed: bool):
         """

validmind/tests/data_validation/MissingValuesBarPlot.py

@@ -55,10 +55,8 @@ class MissingValuesBarPlot(Metric):
     name = "missing_values_bar_plot"
     required_inputs = ["dataset"]
     default_params = {"threshold": 80, "fig_height": 600}
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality", "visualization"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality", "visualization"]
 
     def run(self):
         threshold = self.params["threshold"]

validmind/tests/data_validation/MissingValuesRisk.py

@@ -52,10 +52,8 @@ class MissingValuesRisk(Metric):
 
     name = "missing_values_risk"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "data_quality", "risk_analysis"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "data_quality", "risk_analysis"]
 
     def run(self):
         total_cells = self.inputs.dataset.df.size

validmind/tests/data_validation/PearsonCorrelationMatrix.py

@@ -50,10 +50,8 @@ class PearsonCorrelationMatrix(Metric):
 
     name = "pearson_correlation_matrix"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "numerical_data", "correlation"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "numerical_data", "correlation"]
 
     def run(self):
         columns = self.params.get("columns", list(self.inputs.dataset.df.columns))

validmind/tests/data_validation/PhillipsPerronArch.py

@@ -51,15 +51,13 @@ class PhillipsPerronArch(Metric):
 
     name = "phillips_perron"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["regression"],
-        "tags": [
-            "time_series_data",
-            "forecasting",
-            "statistical_test",
-            "unit_root_test",
-        ],
-    }
+    tasks = ["regression"]
+    tags = [
+        "time_series_data",
+        "forecasting",
+        "statistical_test",
+        "unit_root_test",
+    ]
 
     def run(self):
         """

validmind/tests/data_validation/RollingStatsPlot.py

@@ -54,10 +54,8 @@ class RollingStatsPlot(Metric):
     name = "rolling_stats_plot"
     required_inputs = ["dataset"]
     default_params = {"window_size": 12}
-    metadata = {
-        "task_types": ["regression"],
-        "tags": ["time_series_data", "visualization", "stationarity"],
-    }
+    tasks = ["regression"]
+    tags = ["time_series_data", "visualization", "stationarity"]
 
     def plot_rolling_statistics(self, col, window_size=12):
         """

validmind/tests/data_validation/ScatterPlot.py

@@ -52,10 +52,8 @@ class ScatterPlot(Metric):
 
     name = "scatter_plot"
     required_inputs = ["dataset"]
-    metadata = {
-        "task_types": ["classification", "regression"],
-        "tags": ["tabular_data", "visualization"],
-    }
+    tasks = ["classification", "regression"]
+    tags = ["tabular_data", "visualization"]
 
     def run(self):
         columns = list(self.inputs.dataset.df.columns)