validmind 2.9.1__py3-none-any.whl → 2.9.3__py3-none-any.whl

validmind/__init__.py

@@ -32,15 +32,21 @@ After you have pasted the code snippet into your development source code and exe
 """
 import threading
 import warnings
+from importlib import metadata
 
-import pkg_resources
 from IPython.display import HTML, display
 
 # Ignore Numba warnings. We are not requiring this package directly
-from numba.core.errors import NumbaDeprecationWarning, NumbaPendingDeprecationWarning
+try:
+    from numba.core.errors import (
+        NumbaDeprecationWarning,
+        NumbaPendingDeprecationWarning,
+    )
 
-warnings.simplefilter("ignore", category=NumbaDeprecationWarning)
-warnings.simplefilter("ignore", category=NumbaPendingDeprecationWarning)
+    warnings.simplefilter("ignore", category=NumbaDeprecationWarning)
+    warnings.simplefilter("ignore", category=NumbaPendingDeprecationWarning)
+except ImportError:
+    ...
 
 from .__version__ import __version__  # noqa: E402
 from .api_client import init, log_metric, log_text, reload
@@ -81,7 +87,12 @@ def check_version():
     # get the installed vs running version of validmind
     # to make sure we are using the latest installed version
     # in case user has updated the package but forgot to restart the kernel
-    installed = pkg_resources.get_distribution("validmind").version
+    try:
+        installed = metadata.version("validmind")
+    except metadata.PackageNotFoundError:
+        # Package metadata not found, skip version check
+        return
+
     running = __version__
 
     if parse_version(installed) > parse_version(running):

validmind/__version__.py

@@ -1 +1 @@
-__version__ = "2.9.1"
+__version__ = "2.9.2"

validmind/ai/test_descriptions.py

@@ -14,6 +14,11 @@ from ..logging import get_logger
 from ..utils import NumpyEncoder, md_to_html, test_id_to_name
 from ..vm_models.figure import Figure
 from ..vm_models.result import ResultTable
+from ..vm_models.result.pii_filter import (
+    PIIDetectionMode,
+    get_pii_detection_mode,
+    scan_df,
+)
 from .utils import DescriptionFuture
 
 __executor = ThreadPoolExecutor()
@@ -92,6 +97,13 @@ def generate_description(
         )
 
     if tables:
+        if get_pii_detection_mode() in [
+            PIIDetectionMode.TEST_DESCRIPTIONS,
+            PIIDetectionMode.ALL,
+        ]:
+            for table in tables:
+                scan_df(table.data)
+
         summary = "\n---\n".join(
             [
                 json.dumps(table.serialize(), cls=NumpyEncoder, separators=(",", ":"))
@@ -125,13 +137,16 @@ def background_generate_description(
 ):
     def wrapped():
         try:
-            return generate_description(
-                test_id=test_id,
-                test_description=test_description,
-                tables=tables,
-                figures=figures,
-                metric=metric,
-                title=title,
+            return (
+                generate_description(
+                    test_id=test_id,
+                    test_description=test_description,
+                    tables=tables,
+                    figures=figures,
+                    metric=metric,
+                    title=title,
+                ),
+                True,
             )
         except Exception as e:
             if "maximum context length" in str(e):
@@ -146,7 +161,7 @@ def background_generate_description(
                 logger.warning(f"Failed to generate description for {test_id}: {e}")
             logger.warning(f"Using default description for {test_id}")
 
-            return test_description
+            return test_description, False
 
     return DescriptionFuture(__executor.submit(wrapped))
 
@@ -191,15 +206,7 @@ def get_result_description(
         not in ["0", "false"]
     )
 
-    # TODO: fix circular import
-    from validmind.ai.utils import is_configured
-
-    if (
-        should_generate
-        and (tables or figures)
-        and llm_descriptions_enabled
-        and is_configured()
-    ):
+    if should_generate and (tables or figures) and llm_descriptions_enabled:
         # get description future and set it as the description in the metadata
         # this will lazily retrieved so it can run in the background in parallel
         description = background_generate_description(

validmind/ai/utils.py

@@ -35,13 +35,13 @@ class DescriptionFuture:
         self._future = future
 
     def get_description(self):
-        if isinstance(self._future, str):
+        if isinstance(self._future, tuple):
             description = self._future
         else:
             # This will block until the future is completed
             description = self._future.result()
 
-        return md_to_html(description, mathml=True)
+        return md_to_html(description[0], mathml=True), description[1]
 
 
 def get_client_and_model():

validmind/api_client.py

@@ -40,8 +40,6 @@ __api_session: Optional[aiohttp.ClientSession] = None
 @atexit.register
 def _close_session():
     """Closes the async client session at exit."""
-    global __api_session
-
     if __api_session and not __api_session.closed:
         try:
             loop = asyncio.get_event_loop()

validmind/datasets/credit_risk/lending_club.py

@@ -9,13 +9,25 @@ from typing import Any, Dict, Optional, Tuple
 
 import numpy as np
 import pandas as pd
-import scorecardpy as sc
 import statsmodels.api as sm
 import xgboost as xgb
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
 
 import validmind as vm
+from validmind.errors import MissingDependencyError
+
+try:
+    import scorecardpy as sc
+except ImportError as e:
+    if "scorecardpy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scorecardpy` for credit risk demos. "
+            "Please run `pip install validmind[credit_risk]` or `pip install scorecardpy`.",
+            required_dependencies=["scorecardpy"],
+            extra="credit_risk",
+        ) from e
+    raise e
 
 current_path = os.path.dirname(os.path.abspath(__file__))
 dataset_path = os.path.join(current_path, "datasets")

validmind/datasets/nlp/cnn_dailymail.py

@@ -7,10 +7,11 @@ import textwrap
 from typing import Optional, Tuple
 
 import pandas as pd
-from datasets import load_dataset
 from IPython.display import HTML, display
 from tabulate import tabulate
 
+from validmind.errors import MissingDependencyError
+
 # Define column names
 text_column = "article"
 target_column = "highlights"
@@ -37,6 +38,19 @@ def load_data(
         Tuple containing (train_df, test_df) DataFrames with the loaded data.
     """
     if source == "online":
+        try:
+            from datasets import load_dataset
+        except ImportError as e:
+            if "datasets" in str(e):
+                raise MissingDependencyError(
+                    "Missing required package `datasets` for CNN Daily Mail. "
+                    "Please run `pip install validmind[datasets]` or "
+                    "`pip install datasets` to use CNN Daily Mail dataset",
+                    required_dependencies=["datasets"],
+                    extra="datasets",
+                ) from e
+            raise e
+
         # Load online data without predictions
         cnn_dataset = load_dataset("cnn_dailymail", "3.0.0")
         train_df = cnn_dataset["train"].to_pandas()

validmind/tests/data_validation/ChiSquaredFeaturesTable.py

@@ -4,10 +4,22 @@
 
 
 import pandas as pd
-from scipy.stats import chi2_contingency
 
 from validmind import tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
+
+try:
+    from scipy.stats import chi2_contingency
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for ChiSquaredFeaturesTable. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 
 
 @tags("tabular_data", "categorical_data", "statistical_test")

validmind/tests/data_validation/DickeyFullerGLS.py

@@ -5,14 +5,25 @@
 from typing import Any, Dict, Tuple
 
 import pandas as pd
-from arch.unitroot import DFGLS
 from numpy.linalg import LinAlgError
 
 from validmind import RawData, tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
 from validmind.logging import get_logger
 from validmind.vm_models import VMDataset
 
+try:
+    from arch.unitroot import DFGLS
+except ImportError as e:
+    if "arch" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `arch` for DickeyFullerGLS. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["arch"],
+            extra="stats",
+        ) from e
+    raise e
+
 logger = get_logger(__name__)
 
 

validmind/tests/data_validation/PhillipsPerronArch.py

@@ -6,14 +6,25 @@ from typing import Any, Dict
 
 import numpy as np
 import pandas as pd
-from arch.unitroot import PhillipsPerron
 from numpy.linalg import LinAlgError
 
 from validmind import tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
 from validmind.logging import get_logger
 from validmind.vm_models import VMDataset
 
+try:
+    from arch.unitroot import PhillipsPerron
+except ImportError as e:
+    if "arch" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `arch` for PhillipsPerronArch. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["arch"],
+            extra="stats",
+        ) from e
+    raise e
+
 logger = get_logger(__name__)
 
 

validmind/tests/data_validation/ScoreBandDefaultRates.py

@@ -83,7 +83,7 @@ def ScoreBandDefaultRates(
 
     # 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/data_validation/SeasonalDecompose.py

@@ -9,11 +9,23 @@ 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 statsmodels.tsa.seasonal import seasonal_decompose
 
 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 SeasonalDecompose. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 from validmind.logging import get_logger
 from validmind.vm_models import VMDataset
 

validmind/tests/data_validation/ShapiroWilk.py

@@ -6,9 +6,22 @@
 from typing import Tuple
 
 import pandas as pd
-from scipy import stats
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    from scipy import stats
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for ShapiroWilk. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 
 
 @tasks("classification", "regression")

validmind/tests/data_validation/TimeSeriesDescriptiveStatistics.py

@@ -3,9 +3,22 @@
 # SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
 
 import pandas as pd
-from scipy.stats import kurtosis, skew
 
 from validmind import tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    from scipy.stats import kurtosis, skew
+except ImportError as e:
+    if "scipy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scipy` for TimeSeriesDescriptiveStatistics. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["scipy"],
+            extra="stats",
+        ) from e
+
+    raise e
 
 
 @tags("time_series_data", "analysis")

validmind/tests/data_validation/WOEBinPlots.py

@@ -9,7 +9,20 @@ import numpy as np
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
-import scorecardpy as sc
+
+from validmind.errors import MissingDependencyError
+
+try:
+    import scorecardpy as sc
+except ImportError as e:
+    if "scorecardpy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scorecardpy` for WOEBinPlots. "
+            "Please run `pip install validmind[credit_risk]` to use these tests",
+            required_dependencies=["scorecardpy"],
+            extra="credit_risk",
+        ) from e
+    raise e
 from plotly.subplots import make_subplots
 
 from validmind import RawData, tags, tasks

validmind/tests/data_validation/WOEBinTable.py

@@ -5,12 +5,23 @@
 from typing import Dict, Tuple
 
 import pandas as pd
-import scorecardpy as sc
 
 from validmind import RawData, tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
 from validmind.vm_models import VMDataset
 
+try:
+    import scorecardpy as sc
+except ImportError as e:
+    if "scorecardpy" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `scorecardpy` for WOEBinTable. "
+            "Please run `pip install validmind[credit_risk]` to use these tests",
+            required_dependencies=["scorecardpy"],
+            extra="credit_risk",
+        ) from e
+    raise e
+
 
 @tags("tabular_data", "categorical_data")
 @tasks("classification")

validmind/tests/data_validation/ZivotAndrewsArch.py

@@ -5,14 +5,25 @@
 from typing import Any, Dict, Tuple
 
 import pandas as pd
-from arch.unitroot import ZivotAndrews
 from numpy.linalg import LinAlgError
 
 from validmind import RawData, tags, tasks
-from validmind.errors import SkipTestError
+from validmind.errors import MissingDependencyError, SkipTestError
 from validmind.logging import get_logger
 from validmind.vm_models import VMDataset
 
+try:
+    from arch.unitroot import ZivotAndrews
+except ImportError as e:
+    if "arch" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `arch` for ZivotAndrewsArch. "
+            "Please run `pip install validmind[stats]` to use statistical tests",
+            required_dependencies=["arch"],
+            extra="stats",
+        ) from e
+    raise e
+
 logger = get_logger(__name__)
 
 

validmind/tests/data_validation/nlp/CommonWords.py

@@ -5,13 +5,25 @@
 from collections import Counter
 from typing import Tuple
 
-import nltk
 import plotly.graph_objects as go
-from nltk.corpus import stopwords
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset
 
+try:
+    import nltk
+    from nltk.corpus import stopwords
+except ImportError as e:
+    if "nltk" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `nltk` for CommonWords. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["nltk"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "visualization", "frequency_analysis")
 @tasks("text_classification", "text_summarization")

validmind/tests/data_validation/nlp/LanguageDetection.py

@@ -6,9 +6,22 @@ from typing import Tuple
 
 import plotly.express as px
 import plotly.graph_objects as go
-from langdetect import LangDetectException, detect
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    from langdetect import LangDetectException, detect
+except ImportError as e:
+    if "langdetect" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `langdetect` for LanguageDetection. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["langdetect"],
+            extra="nlp",
+        ) from e
+
+    raise e
 
 
 @tags("nlp", "text_data", "visualization")

validmind/tests/data_validation/nlp/PolarityAndSubjectivity.py

@@ -8,9 +8,21 @@ from typing import Dict, Tuple
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
-from textblob import TextBlob
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    from textblob import TextBlob
+except ImportError as e:
+    if "textblob" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `textblob` for PolarityAndSubjectivity. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["textblob"],
+            extra="nlp",
+        ) from e
+    raise e
 
 
 @tags("nlp", "text_data", "data_validation")

validmind/tests/data_validation/nlp/Sentiment.py

@@ -8,9 +8,21 @@ from typing import Tuple
 import matplotlib.pyplot as plt
 import nltk
 import seaborn as sns
-from nltk.sentiment import SentimentIntensityAnalyzer
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    from nltk.sentiment import SentimentIntensityAnalyzer
+except ImportError as e:
+    if "nltk" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `nltk` for Sentiment. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["nltk"],
+            extra="nlp",
+        ) from e
+    raise e
 
 
 @tags("nlp", "text_data", "data_validation")

validmind/tests/data_validation/nlp/StopWords.py

@@ -9,14 +9,26 @@ Threshold based tests
 from collections import defaultdict
 from typing import Dict, Tuple
 
-import nltk
 import pandas as pd
 import plotly.graph_objects as go
-from nltk.corpus import stopwords
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset
 
+try:
+    import nltk
+    from nltk.corpus import stopwords
+except ImportError as e:
+    if "nltk" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `nltk` for StopWords. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["nltk"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 @tags("nlp", "text_data", "frequency_analysis", "visualization")
 @tasks("text_classification", "text_summarization")

validmind/tests/data_validation/nlp/TextDescription.py

@@ -5,15 +5,27 @@
 import string
 from typing import Tuple
 
-import nltk
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
-from nltk.corpus import stopwords
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
 from validmind.vm_models import VMDataset
 
+try:
+    import nltk
+    from nltk.corpus import stopwords
+except ImportError as e:
+    if "nltk" in str(e).lower():
+        raise MissingDependencyError(
+            "Missing required package `nltk` for TextDescription. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["nltk"],
+            extra="nlp",
+        ) from e
+    raise e
+
 
 def create_metrics_df(df, text_column, unwanted_tokens, lang):
     stop_words = set(word.lower() for word in stopwords.words(lang))

validmind/tests/data_validation/nlp/Toxicity.py

@@ -4,11 +4,23 @@
 
 from typing import Tuple
 
-import evaluate
 import matplotlib.pyplot as plt
 import seaborn as sns
 
 from validmind import RawData, tags, tasks
+from validmind.errors import MissingDependencyError
+
+try:
+    import evaluate
+except ImportError as e:
+    if "evaluate" in str(e):
+        raise MissingDependencyError(
+            "Missing required package `evaluate` for Toxicity. "
+            "Please run `pip install validmind[nlp]` to use NLP tests",
+            required_dependencies=["evaluate"],
+            extra="nlp",
+        ) from e
+    raise e
 
 
 @tags("nlp", "text_data", "data_validation")

validmind/tests/model_validation/BertScore.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 BertScore. "
+            "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")
@@ -75,7 +87,6 @@ def BertScore(
     # Ensure equal lengths and get truncated data if necessary
     y_true, y_pred = validate_prediction(y_true, y_pred)
 
-    # Load the BERT evaluation metric
     bert = evaluate.load("bertscore")
 
     # Compute the BERT score