validmind 2.8.27__py3-none-any.whl → 2.8.29__py3-none-any.whl

validmind/tests/ongoing_monitoring/PredictionQuantilesAcrossFeatures.py

@@ -2,15 +2,20 @@
 # 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 plotly.graph_objects as go
 from plotly.subplots import make_subplots
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("visualization")
 @tasks("monitoring")
-def PredictionQuantilesAcrossFeatures(datasets, model):
+def PredictionQuantilesAcrossFeatures(
+    datasets: List[VMDataset], model: VMModel
+) -> Tuple[go.Figure, ...]:
     """
     Assesses differences in model prediction distributions across individual features between reference
     and monitoring datasets through quantile analysis.

validmind/tests/ongoing_monitoring/ROCCurveDrift.py

@@ -2,7 +2,7 @@
 # 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
+from typing import List, Tuple
 
 import numpy as np
 import plotly.graph_objects as go
@@ -20,7 +20,9 @@ from validmind.vm_models import VMDataset, VMModel
     "visualization",
 )
 @tasks("classification", "text_classification")
-def ROCCurveDrift(datasets: List[VMDataset], model: VMModel):
+def ROCCurveDrift(
+    datasets: List[VMDataset], model: VMModel
+) -> Tuple[go.Figure, go.Figure, RawData]:
     """
     Compares ROC curves between reference and monitoring datasets.
 

validmind/tests/ongoing_monitoring/ScoreBandsDrift.py

@@ -2,7 +2,7 @@
 # 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
+from typing import Dict, List, Tuple
 
 import numpy as np
 import pandas as pd
@@ -19,7 +19,7 @@ def ScoreBandsDrift(
     score_column: str = "score",
     score_bands: list = None,
     drift_threshold: float = 20.0,
-):
+) -> Tuple[Dict[str, pd.DataFrame], bool, RawData]:
     """
     Analyzes drift in population distribution and default rates across score bands.
 

validmind/tests/ongoing_monitoring/ScorecardHistogramDrift.py

@@ -2,7 +2,7 @@
 # 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
+from typing import Dict, List, Tuple
 
 import numpy as np
 import pandas as pd
@@ -21,7 +21,7 @@ def ScorecardHistogramDrift(
     score_column: str = "score",
     title: str = "Scorecard Histogram Drift",
     drift_pct_threshold: float = 20.0,
-):
+) -> Tuple[go.Figure, Dict[str, pd.DataFrame], bool]:
     """
     Compares score distributions between reference and monitoring datasets for each class.
 

validmind/tests/ongoing_monitoring/TargetPredictionDistributionPlot.py

@@ -2,17 +2,24 @@
 # See the LICENSE file in the root of this repository for details.
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
+from typing import Dict, List, Tuple
+
 import pandas as pd
 import plotly.figure_factory as ff
 import plotly.graph_objects as go
 from scipy.stats import kurtosis, skew
 
 from validmind import RawData, tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("visualization")
 @tasks("monitoring")
-def TargetPredictionDistributionPlot(datasets, model, drift_pct_threshold=20):
+def TargetPredictionDistributionPlot(
+    datasets: List[VMDataset],
+    model: VMModel,
+    drift_pct_threshold: float = 20,
+) -> Tuple[Dict[str, pd.DataFrame], go.Figure, bool, RawData]:
     """
     Assesses differences in prediction distributions between a reference dataset and a monitoring dataset to identify
     potential data drift.

validmind/tests/prompt_validation/Bias.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -45,7 +47,9 @@ Prompt:
 
 @tags("llm", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Bias(model, min_threshold=7, judge_llm=None):
+def Bias(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Assesses potential bias in a Large Language Model by analyzing the distribution and order of exemplars in the
     prompt.

validmind/tests/prompt_validation/Clarity.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -46,7 +48,9 @@ Prompt:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Clarity(model, min_threshold=7, judge_llm=None):
+def Clarity(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Evaluates and scores the clarity of prompts in a Large Language Model based on specified guidelines.
 

validmind/tests/prompt_validation/Conciseness.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -54,7 +56,9 @@ Prompt:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Conciseness(model, min_threshold=7, judge_llm=None):
+def Conciseness(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Analyzes and grades the conciseness of prompts provided to a Large Language Model.
 

validmind/tests/prompt_validation/Delimitation.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -39,7 +41,9 @@ Prompt:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Delimitation(model, min_threshold=7, judge_llm=None):
+def Delimitation(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Evaluates the proper use of delimiters in prompts provided to Large Language Models.
 

validmind/tests/prompt_validation/NegativeInstruction.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -52,7 +54,9 @@ Prompt:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def NegativeInstruction(model, min_threshold=7, judge_llm=None):
+def NegativeInstruction(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Evaluates and grades the use of affirmative, proactive language over negative instructions in LLM prompts.
 

validmind/tests/prompt_validation/Robustness.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
 
 from validmind import RawData, tags, tasks
@@ -56,7 +58,9 @@ Input:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Robustness(model, dataset, num_tests=10, judge_llm=None):
+def Robustness(
+    model, dataset, num_tests=10, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Assesses the robustness of prompts provided to a Large Language Model under varying conditions and contexts. This test
     specifically measures the model's ability to generate correct classifications with the given prompt even when the

validmind/tests/prompt_validation/Specificity.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
+
 from validmind import RawData, tags, tasks
 from validmind.errors import MissingRequiredTestInputError
 
@@ -52,7 +54,9 @@ Prompt:
 
 @tags("llm", "zero_shot", "few_shot")
 @tasks("text_classification", "text_summarization")
-def Specificity(model, min_threshold=7, judge_llm=None):
+def Specificity(
+    model, min_threshold=7, judge_llm=None
+) -> Tuple[List[Dict[str, Any]], bool, RawData]:
     """
     Evaluates and scores the specificity of prompts provided to a Large Language Model (LLM), based on clarity, detail,
     and relevance.

validmind/unit_metrics/classification/Accuracy.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import accuracy_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tasks("classification")
 @tags("classification")
-def Accuracy(dataset, model):
+def Accuracy(dataset: VMDataset, model: VMModel) -> float:
     """Calculates the accuracy of a model"""
     return accuracy_score(dataset.y, dataset.y_pred(model))

validmind/unit_metrics/classification/F1.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import f1_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tasks("classification")
 @tags("classification")
-def F1(model, dataset, **kwargs):
+def F1(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the F1 score for a classification model."""
     return f1_score(dataset.y, dataset.y_pred(model), **kwargs)

validmind/unit_metrics/classification/Precision.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import precision_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tasks("classification")
 @tags("classification")
-def Precision(model, dataset, **kwargs):
+def Precision(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the precision for a classification model."""
     return precision_score(dataset.y, dataset.y_pred(model), **kwargs)

validmind/unit_metrics/classification/ROC_AUC.py

@@ -7,11 +7,12 @@ from sklearn.metrics import roc_auc_score
 from sklearn.preprocessing import LabelBinarizer
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tasks("classification")
 @tags("classification")
-def ROC_AUC(model, dataset, **kwargs):
+def ROC_AUC(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the ROC AUC for a classification model."""
     y_true = dataset.y
 

validmind/unit_metrics/classification/Recall.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import recall_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tasks("classification")
 @tags("classification")
-def Recall(model, dataset, **kwargs):
+def Recall(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the recall for a classification model."""
     return recall_score(dataset.y, dataset.y_pred(model), **kwargs)

validmind/unit_metrics/regression/AdjustedRSquaredScore.py

@@ -5,11 +5,12 @@
 from sklearn.metrics import r2_score as _r2_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def AdjustedRSquaredScore(model, dataset):
+def AdjustedRSquaredScore(model: VMModel, dataset: VMDataset) -> float:
     """Calculates the adjusted R-squared score for a regression model."""
     r2_score = _r2_score(
         dataset.y,

validmind/unit_metrics/regression/GiniCoefficient.py

@@ -5,11 +5,12 @@
 import numpy as np
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def GiniCoefficient(dataset, model):
+def GiniCoefficient(dataset: VMDataset, model: VMModel) -> float:
     """Calculates the Gini coefficient for a regression model."""
     y_true = dataset.y
     y_pred = dataset.y_pred(model)

validmind/unit_metrics/regression/HuberLoss.py

@@ -5,11 +5,12 @@
 import numpy as np
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def HuberLoss(model, dataset):
+def HuberLoss(model: VMModel, dataset: VMDataset) -> float:
     """Calculates the Huber loss for a regression model."""
     y_true = dataset.y
     y_pred = dataset.y_pred(model)

validmind/unit_metrics/regression/KolmogorovSmirnovStatistic.py

@@ -5,11 +5,12 @@
 import numpy as np
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def KolmogorovSmirnovStatistic(dataset, model):
+def KolmogorovSmirnovStatistic(dataset: VMDataset, model: VMModel) -> float:
     """Calculates the Kolmogorov-Smirnov statistic for a regression model."""
     y_true = dataset.y.flatten()
     y_pred = dataset.y_pred(model)

validmind/unit_metrics/regression/MeanAbsoluteError.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import mean_absolute_error as _mean_absolute_error
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def MeanAbsoluteError(model, dataset, **kwargs):
+def MeanAbsoluteError(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the mean absolute error for a regression model."""
     return _mean_absolute_error(dataset.y, dataset.y_pred(model), **kwargs)

validmind/unit_metrics/regression/MeanAbsolutePercentageError.py

@@ -5,11 +5,12 @@
 import numpy as np
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def MeanAbsolutePercentageError(model, dataset):
+def MeanAbsolutePercentageError(model: VMModel, dataset: VMDataset) -> float:
     """Calculates the mean absolute percentage error for a regression model."""
     y_true = dataset.y
     y_pred = dataset.y_pred(model)

validmind/unit_metrics/regression/MeanBiasDeviation.py

@@ -5,10 +5,11 @@
 import numpy as np
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def MeanBiasDeviation(model, dataset):
+def MeanBiasDeviation(model: VMModel, dataset: VMDataset) -> float:
     """Calculates the mean bias deviation for a regression model."""
     return np.mean(dataset.y - dataset.y_pred(model))

validmind/unit_metrics/regression/MeanSquaredError.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import mean_squared_error
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def MeanSquaredError(model, dataset, **kwargs):
+def MeanSquaredError(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the mean squared error for a regression model."""
     return mean_squared_error(dataset.y, dataset.y_pred(model), **kwargs)

validmind/unit_metrics/regression/QuantileLoss.py

@@ -9,7 +9,7 @@ from validmind import tags, tasks
 
 @tags("regression")
 @tasks("regression")
-def QuantileLoss(model, dataset, quantile=0.5):
+def QuantileLoss(model, dataset, quantile=0.5) -> float:
     """Calculates the quantile loss for a regression model."""
     error = dataset.y - dataset.y_pred(model)
 

validmind/unit_metrics/regression/RSquaredScore.py

@@ -5,10 +5,11 @@
 from sklearn.metrics import r2_score
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def RSquaredScore(model, dataset):
+def RSquaredScore(model: VMModel, dataset: VMDataset) -> float:
     """Calculates the R-squared score for a regression model."""
     return r2_score(dataset.y, dataset.y_pred(model))

validmind/unit_metrics/regression/RootMeanSquaredError.py

@@ -6,11 +6,12 @@ import numpy as np
 from sklearn.metrics import mean_squared_error
 
 from validmind import tags, tasks
+from validmind.vm_models import VMDataset, VMModel
 
 
 @tags("regression")
 @tasks("regression")
-def RootMeanSquaredError(model, dataset, **kwargs):
+def RootMeanSquaredError(model: VMModel, dataset: VMDataset, **kwargs) -> float:
     """Calculates the root mean squared error for a regression model."""
     return np.sqrt(
         mean_squared_error(