validmind 2.9.2__py3-none-any.whl → 2.9.4__py3-none-any.whl

validmind/tests/model_validation/BleuScore.py

@@ -4,14 +4,26 @@
 
 from typing import Tuple
 
-import evaluate
 import pandas as pd
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.tests.utils import validate_prediction
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    import evaluate
+except ImportError as e:
+    if "evaluate" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `evaluate` for BleuScore. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["evaluate"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "visualization")
 @tasks("text_classification", "text_summarization")
@@ -70,7 +82,6 @@ def BleuScore(
     # Ensure equal lengths and get truncated data if necessary
     y_true, y_pred = validate_prediction(y_true, y_pred)
 
-    # Load the BLEU evaluation metric
     bleu = evaluate.load("bleu")
 
     # Calculate BLEU scores

validmind/tests/model_validation/ContextualRecall.py

@@ -4,11 +4,23 @@
 
 from typing import Tuple
 
-import nltk
 import pandas as pd
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    import nltk
+except ImportError as e:
+    if "nltk" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `nltk` for ContextualRecall. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["nltk"],
+            extra="nlp",
+        ) from e
+    raise e
 from validmind.tests.utils import validate_prediction
 from validmind.vm_models import VMDataset, VMModel
 

validmind/tests/model_validation/MeteorScore.py

@@ -4,14 +4,26 @@
 
 from typing import Tuple
 
-import evaluate
 import pandas as pd
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.tests.utils import validate_prediction
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    import evaluate
+except ImportError as e:
+    if "evaluate" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `evaluate` for MeteorScore. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["evaluate"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "visualization")
 @tasks("text_classification", "text_summarization")
@@ -73,7 +85,6 @@ def MeteorScore(
 
     validate_prediction(y_true, y_pred)
 
-    # Load the METEOR evaluation metric
     meteor = evaluate.load("meteor")
 
     # Calculate METEOR scores

validmind/tests/model_validation/ModelPredictionResiduals.py

@@ -6,11 +6,24 @@ from typing import Optional, Tuple
 
 import pandas as pd
 import plotly.graph_objects as go
-from scipy.stats import kstest
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from scipy.stats import kstest
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for ModelPredictionResiduals. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 @tags("regression")
 @tasks("residual_analysis", "visualization")

validmind/tests/model_validation/RegardScore.py

@@ -4,14 +4,26 @@
 
 from typing import Tuple
 
-import evaluate
 import pandas as pd
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.tests.utils import validate_prediction
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    import evaluate
+except ImportError as e:
+    if "evaluate" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `evaluate` for RegardScore. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["evaluate"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "visualization")
 @tasks("text_classification", "text_summarization")
@@ -66,7 +78,6 @@ def RegardScore(
     # Ensure equal lengths and get truncated data if necessary
     y_true, y_pred = validate_prediction(y_true, y_pred)
 
-    # Load the regard evaluation metric
     regard_tool = evaluate.load("regard", module_type="measurement")
 
     # Function to calculate regard scores

validmind/tests/model_validation/RougeScore.py

@@ -6,11 +6,24 @@ from typing import Tuple
 
 import pandas as pd
 import plotly.graph_objects as go
-from rouge import Rouge
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from rouge import Rouge
+except ImportError as e:
+    if "rouge" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `rouge` for RougeScore. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["rouge"],
+            extra="nlp",
+        ) from e
+
+    raise e
+
 
 @tags("nlp", "text_data", "visualization")
 @tasks("text_classification", "text_summarization")

validmind/tests/model_validation/TimeSeriesPredictionWithCI.py

@@ -7,11 +7,24 @@ from typing import Tuple
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from scipy.stats import norm
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from scipy.stats import norm
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for TimeSeriesPredictionWithCI. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 @tags("model_predictions", "visualization")
 @tasks("regression", "time_series_forecasting")

validmind/tests/model_validation/ToxicityScore.py

@@ -4,13 +4,25 @@
 
 from typing import Tuple
 
-import evaluate
 import pandas as pd
 import plotly.graph_objects as go
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    import evaluate
+except ImportError as e:
+    if "evaluate" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `evaluate` for ToxicityScore. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["evaluate"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "visualization")
 @tasks("text_classification", "text_summarization")

validmind/tests/model_validation/embeddings/PCAComponentsPairwisePlots.py

@@ -75,7 +75,7 @@ def PCAComponentsPairwisePlots(
 
     # Prepare DataFrame for Plotly
     pca_df = pd.DataFrame(
-        pca_results, columns=[f"PC{i+1}" for i in range(n_components)]
+        pca_results, columns=[f"PC{i + 1}" for i in range(n_components)]
     )
 
     # List to store each plot

validmind/tests/model_validation/embeddings/TSNEComponentsPairwisePlots.py

@@ -79,7 +79,7 @@ def TSNEComponentsPairwisePlots(
 
     # Prepare DataFrame for Plotly
     tsne_df = pd.DataFrame(
-        tsne_results, columns=[f"Component {i+1}" for i in range(n_components)]
+        tsne_results, columns=[f"Component {i + 1}" for i in range(n_components)]
     )
 
     # List to store each plot

validmind/tests/model_validation/sklearn/KMeansClustersOptimization.py

@@ -7,12 +7,24 @@ from typing import List, Optional, Tuple
 import numpy as np
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
-from scipy.spatial.distance import cdist
 from sklearn import clone
 from sklearn.metrics import silhouette_score
 
 from validmind import RawData, tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
+
+try:
+    from scipy.spatial.distance import cdist
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for KMeansClustersOptimization. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 from validmind.vm_models import VMDataset, VMModel
 
 

validmind/tests/model_validation/sklearn/RobustnessDiagnosis.py

@@ -129,7 +129,7 @@ def _plot_robustness(
 
     datasets = results["Dataset"].unique()
     pallete = [
-        f"#{int(r*255):02x}{int(g*255):02x}{int(b*255):02x}"
+        f"#{int(r * 255):02x}{int(g * 255):02x}{int(b * 255):02x}"
         for r, g, b in sns.color_palette("husl", len(datasets))
     ]
 

validmind/tests/model_validation/sklearn/SHAPGlobalImportance.py

@@ -9,14 +9,25 @@ from warnings import filters as _warnings_filters
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-import shap
 
 from validmind import RawData, tags, tasks
-from validmind.errors import UnsupportedModelForSHAPError
+from validmind.errors import MissingDependencyError, UnsupportedModelForSHAPError
 from validmind.logging import get_logger
 from validmind.models import CatBoostModel, SKlearnModel, StatsModelsModel
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    import shap
+except ImportError as e:
+    if "shap" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `shap` for SHAPGlobalImportance. "
+            "Please run `pip install validmind[explainability]` to use SHAP tests",
+            required_dependencies=["shap"],
+            extra="explainability",
+        ) from e
+    raise e
+
 logger = get_logger(__name__)
 
 

validmind/tests/model_validation/statsmodels/CumulativePredictionProbabilities.py

@@ -88,7 +88,7 @@ def _plot_cumulative_prob(df, target_col, title):
     classes = sorted(df[target_col].unique())
     colors = [colormap(i / len(classes))[:3] for i in range(len(classes))]  # RGB
     color_dict = {
-        cls: f"rgb({int(rgb[0]*255)}, {int(rgb[1]*255)}, {int(rgb[2]*255)})"
+        cls: f"rgb({int(rgb[0] * 255)}, {int(rgb[1] * 255)}, {int(rgb[2] * 255)})"
         for cls, rgb in zip(classes, colors)
     }
 

validmind/tests/model_validation/statsmodels/PredictionProbabilitiesHistogram.py

@@ -83,7 +83,7 @@ def _plot_prob_histogram(df, target_col, title):
     classes = sorted(df[target_col].unique())
     colors = [colormap(i / len(classes))[:3] for i in range(len(classes))]  # RGB
     color_dict = {
-        cls: f"rgb({int(rgb[0]*255)}, {int(rgb[1]*255)}, {int(rgb[2]*255)})"
+        cls: f"rgb({int(rgb[0] * 255)}, {int(rgb[1] * 255)}, {int(rgb[2] * 255)})"
         for cls, rgb in zip(classes, colors)
     }
 

validmind/tests/model_validation/statsmodels/RegressionCoeffs.py

@@ -7,10 +7,22 @@ from typing import Tuple
 
 import pandas as pd
 import plotly.graph_objects as go
-from scipy import stats
 
 from validmind import RawData, tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
+
+try:
+    from scipy import stats
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for RegressionCoeffs. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 from validmind.vm_models import VMModel
 
 

validmind/tests/model_validation/statsmodels/ScorecardHistogram.py

@@ -85,7 +85,7 @@ def _plot_score_histogram(df, score_col, target_col, title):
     classes = sorted(df[target_col].unique())
     colors = [colormap(i / len(classes))[:3] for i in range(len(classes))]  # RGB
     color_dict = {
-        cls: f"rgb({int(rgb[0]*255)}, {int(rgb[1]*255)}, {int(rgb[2]*255)})"
+        cls: f"rgb({int(rgb[0] * 255)}, {int(rgb[1] * 255)}, {int(rgb[2] * 255)})"
         for cls, rgb in zip(classes, colors)
     }
 

validmind/tests/ongoing_monitoring/CalibrationCurveDrift.py

@@ -96,7 +96,7 @@ def CalibrationCurveDrift(
 
     # Create bin labels
     bin_edges = np.linspace(0, 1, n_bins + 1)
-    bin_labels = [f"{bin_edges[i]:.1f}-{bin_edges[i+1]:.1f}" for i in range(n_bins)]
+    bin_labels = [f"{bin_edges[i]:.1f}-{bin_edges[i + 1]:.1f}" for i in range(n_bins)]
 
     # Create predicted probabilities table
     pred_metrics = []

validmind/tests/ongoing_monitoring/ClassDiscriminationDrift.py

@@ -6,13 +6,26 @@ from typing import Dict, List, Tuple
 
 import numpy as np
 import pandas as pd
-from scipy import stats
 from sklearn.metrics import roc_auc_score
 from sklearn.preprocessing import LabelBinarizer
 
 from validmind import tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from scipy import stats
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for ClassDiscriminationDrift. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 def multiclass_roc_auc_score(y_test, y_pred, average="macro"):
     lb = LabelBinarizer()

validmind/tests/ongoing_monitoring/PredictionProbabilitiesHistogramDrift.py

@@ -8,11 +8,24 @@ import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
-from scipy import stats
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from scipy import stats
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for PredictionProbabilitiesHistogramDrift. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 @tags("visualization", "credit_risk")
 @tasks("classification")
@@ -191,7 +204,7 @@ def PredictionProbabilitiesHistogramDrift(
         # Add separate legend for each subplot
         fig.update_layout(
             **{
-                f'legend{i+1 if i > 0 else ""}': dict(
+                f'legend{i + 1 if i > 0 else ""}': dict(
                     yanchor="middle",
                     y=1 - (i / len(classes)) - (0.5 / len(classes)),
                     xanchor="left",

validmind/tests/ongoing_monitoring/ScoreBandsDrift.py

@@ -84,7 +84,7 @@ def ScoreBandsDrift(
 
     # Create band labels
     band_labels = [
-        f"{score_bands[i]}-{score_bands[i+1]}" for i in range(len(score_bands) - 1)
+        f"{score_bands[i]}-{score_bands[i + 1]}" for i in range(len(score_bands) - 1)
     ]
     band_labels.insert(0, f"<{score_bands[0]}")
     band_labels.append(f">{score_bands[-1]}")

validmind/tests/ongoing_monitoring/ScorecardHistogramDrift.py

@@ -8,11 +8,24 @@ import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
-from scipy import stats
 
 from validmind import tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset
 
+try:
+    from scipy import stats
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for ScorecardHistogramDrift. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 @tags("visualization", "credit_risk", "logistic_regression")
 @tasks("classification")
@@ -196,7 +209,7 @@ def ScorecardHistogramDrift(
         # Add separate legend for each subplot
         fig.update_layout(
             **{
-                f'legend{i+1 if i > 0 else ""}': dict(
+                f'legend{i + 1 if i > 0 else ""}': dict(
                     yanchor="middle",
                     y=1 - (i / len(classes)) - (0.5 / len(classes)),
                     xanchor="left",

validmind/tests/ongoing_monitoring/TargetPredictionDistributionPlot.py

@@ -7,11 +7,24 @@ 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.errors import MissingDependencyError
 from validmind.vm_models import VMDataset, VMModel
 
+try:
+    from scipy.stats import kurtosis, skew
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for TargetPredictionDistributionPlot. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
+
 
 @tags("visualization")
 @tasks("monitoring")

validmind/tests/plots/BoxPlot.py

@@ -149,8 +149,8 @@ def _create_multiple_boxplots(
                 text=f"No data available<br>for {column}",
                 x=0.5,
                 y=0.5,
-                xref=f"x{idx+1} domain" if idx > 0 else "x domain",
-                yref=f"y{idx+1} domain" if idx > 0 else "y domain",
+                xref=f"x{idx + 1} domain" if idx > 0 else "x domain",
+                yref=f"y{idx + 1} domain" if idx > 0 else "y domain",
                 showarrow=False,
                 row=row,
                 col=col,

validmind/tests/plots/HistogramPlot.py

@@ -95,8 +95,8 @@ def _add_stats_annotation(fig, data, idx, row, col):
         text=stats_text,
         x=0.02,
         y=0.98,
-        xref=f"x{idx+1} domain" if idx > 0 else "x domain",
-        yref=f"y{idx+1} domain" if idx > 0 else "y domain",
+        xref=f"x{idx + 1} domain" if idx > 0 else "x domain",
+        yref=f"y{idx + 1} domain" if idx > 0 else "y domain",
         showarrow=False,
         align="left",
         bgcolor="rgba(255,255,255,0.8)",
@@ -195,8 +195,8 @@ def HistogramPlot(
                 text=f"No data available<br>for {column}",
                 x=0.5,
                 y=0.5,
-                xref=f"x{idx+1}" if idx > 0 else "x",
-                yref=f"y{idx+1}" if idx > 0 else "y",
+                xref=f"x{idx + 1}" if idx > 0 else "x",
+                yref=f"y{idx + 1}" if idx > 0 else "y",
                 showarrow=False,
                 row=row,
                 col=col,

validmind/tests/stats/DescriptiveStats.py

@@ -96,8 +96,8 @@ def _compute_advanced_stats(column: str, data, confidence_level: float):
             "Skewness": skewness,
             "Kurtosis": kurtosis_val,
             "CV %": cv,
-            f"CI Lower ({confidence_level*100:.0f}%)": ci_lower,
-            f"CI Upper ({confidence_level*100:.0f}%)": ci_upper,
+            f"CI Lower ({confidence_level * 100:.0f}%)": ci_lower,
+            f"CI Upper ({confidence_level * 100:.0f}%)": ci_upper,
             "Normality Test": normality_test,
             "Normality Stat": normality_stat,
             "Normality p-value": normality_p,