validmind 2.0.1__py3-none-any.whl → 2.1.0__py3-none-any.whl

validmind/unit_metrics/regression/sklearn/RootMeanSquaredError.py

@@ -0,0 +1,20 @@
+# Copyright © 2023-2024 ValidMind Inc. All rights reserved.
+# See the LICENSE file in the root of this repository for details.
+# SPDX-License-Identifier: AGPL-3.0 AND ValidMind Commercial
+
+import numpy as np
+from sklearn.metrics import mean_squared_error
+
+from validmind import tags, tasks
+
+
+@tags("regression", "sklearn", "unit_metric")
+@tasks("regression")
+def RootMeanSquaredError(model, dataset, **kwargs):
+    return np.sqrt(
+        mean_squared_error(
+            dataset.y,
+            dataset.y_pred(model),
+            **kwargs,
+        )
+    )

validmind/utils.py

@@ -85,6 +85,8 @@ def nan_to_none(obj):
 
 class NumpyEncoder(json.JSONEncoder):
     def default(self, obj):
+        if isinstance(obj, pd.Interval):
+            return f"[{obj.left}, {obj.right}]"
         if isinstance(obj, np.integer):
             return int(obj)
         if isinstance(obj, np.floating):
@@ -236,26 +238,6 @@ def summarize_data_quality_results(results):
     )
 
 
-def clean_docstring(docstring: str) -> str:
-    """
-    Clean up docstrings by removing leading and trailing whitespace and
-    replacing newlines with spaces.
-    """
-    description = (docstring or "").strip()
-    paragraphs = description.split("\n\n")  # Split into paragraphs
-    paragraphs = [
-        " ".join([line.strip() for line in paragraph.split("\n")])
-        for paragraph in paragraphs
-    ]
-    paragraphs = [
-        paragraph.replace(" - ", "\n- ") for paragraph in paragraphs
-    ]  # Add newline before list items
-    # Join paragraphs with double newlines for markdown
-    description = "\n\n".join(paragraphs)
-
-    return description
-
-
 def format_number(number):
     """
     Format a number for display purposes. If the number is a float, round it
@@ -338,20 +320,27 @@ def fuzzy_match(string: str, search_string: str, threshold=0.7):
     return score >= threshold
 
 
-def test_id_to_name(test_id: str):
-    """Convert a test ID to a human-readable name"""
-    # Extract the last part of the ID string
-    last_part = test_id.split(".")[-1]
+def test_id_to_name(test_id: str) -> str:
+    """Convert a test ID to a human-readable name.
 
-    # Use a regular expression to find words and acronyms in the CamelCase string
-    words = re.findall(r"[A-Z]?[a-z]+|[A-Z]+(?=[A-Z]|$)", last_part)
+    Args:
+        test_id (str): The test identifier, typically in CamelCase or snake_case.
 
-    # Join the words with spaces and capitalize the first letter of each word, keeping acronyms unchanged
-    title = " ".join(
-        [word.capitalize() if not word.isupper() else word for word in words]
-    )
+    Returns:
+        str: A human-readable name derived from the test ID.
+    """
+    last_part = test_id.split(".")[-1]
+    words = []
+
+    # Split on underscores and apply regex to each part to handle CamelCase and acronyms
+    for part in last_part.split("_"):
+        # Regex pattern to match uppercase acronyms, mixed-case words, or alphanumeric combinations
+        words.extend(
+            re.findall(r"[A-Z]+(?:_[A-Z]+)*(?=_|$|[A-Z][a-z])|[A-Z]?[a-z0-9]+", part)
+        )
 
-    return title
+    # Join the words with spaces, capitalize non-acronym words
+    return " ".join(word.capitalize() if not word.isupper() else word for word in words)
 
 
 def get_model_info(model):

validmind/vm_models/__init__.py

@@ -15,7 +15,6 @@ from .test.result_summary import ResultSummary, ResultTable, ResultTableMetadata
 from .test.test import Test
 from .test.threshold_test import ThresholdTest
 from .test.threshold_test_result import ThresholdTestResult, ThresholdTestResults
-from .test.unit_metric import UnitMetric
 from .test_context import TestContext, TestInput
 from .test_suite.runner import TestSuiteRunner
 from .test_suite.test_suite import TestSuite
@@ -30,7 +29,6 @@ __all__ = [
     "ResultTable",
     "ResultTableMetadata",
     "Test",
-    "UnitMetric",
     "Metric",
     "MetricResult",
     "ThresholdTest",