validmind 2.8.20__py3-none-any.whl → 2.8.22__py3-none-any.whl

validmind/__version__.py

@@ -1 +1 @@
-__version__ = "2.8.20"
+__version__ = "2.8.22"

validmind/client.py

@@ -61,6 +61,7 @@ def init_dataset(
     class_labels: Optional[Dict[str, Any]] = None,
     type: Optional[str] = None,
     input_id: Optional[str] = None,
+    copy_data: bool = True,
     __log: bool = True,
 ) -> VMDataset:
     """
@@ -92,6 +93,7 @@ def init_dataset(
             this will be set to `dataset` but if you are passing this dataset as a
             test input using some other key than `dataset`, then you should set
             this to the same key.
+        copy_data (bool, optional): Whether to copy the data. Defaults to True.
         __log (bool): Whether to log the input. Defaults to True.
 
     Raises:
@@ -121,6 +123,7 @@ def init_dataset(
             extra_columns=extra_columns,
             target_class_labels=class_labels,
             date_time_index=date_time_index,
+            copy_data=copy_data,
         )
     elif isinstance(dataset, pl.DataFrame):
         vm_dataset = PolarsDataset(

validmind/template.py

@@ -53,8 +53,9 @@ def _convert_sections_to_section_tree(
 
     if start_section_id and not section_tree:
         raise ValueError(f"Section {start_section_id} not found in template")
-
-    return sorted(section_tree, key=lambda x: x.get("order", 0))
+    # sort the section tree by the order of the sections in the template (if provided)
+    # set the order to 9999 for the sections that do not have an order
+    return sorted(section_tree, key=lambda x: x.get("order", 9999))
 
 
 def _create_content_widget(content: Dict[str, Any]) -> Widget:

validmind/vm_models/dataset/dataset.py

@@ -47,6 +47,7 @@ class VMDataset(VMInput):
         target_class_labels (Dict): The class labels for the target columns.
         df (pd.DataFrame): The dataset as a pandas DataFrame.
         extra_columns (Dict): Extra columns to include in the dataset.
+        copy_data (bool): Whether to copy the data. Defaults to True.
     """
 
     def __repr__(self):
@@ -66,6 +67,7 @@ class VMDataset(VMInput):
         text_column: str = None,
         extra_columns: dict = None,
         target_class_labels: dict = None,
+        copy_data: bool = True,
     ):
         """
         Initializes a VMDataset instance.
@@ -82,6 +84,7 @@ class VMDataset(VMInput):
             feature_columns (str, optional): The feature column names of the dataset. Defaults to None.
             text_column (str, optional): The text column name of the dataset for nlp tasks. Defaults to None.
             target_class_labels (Dict, optional): The class labels for the target columns. Defaults to None.
+            copy_data (bool, optional): Whether to copy the data. Defaults to True.
         """
         # initialize input_id
         self.input_id = input_id
@@ -112,6 +115,7 @@ class VMDataset(VMInput):
         self.target_class_labels = target_class_labels
         self.extra_columns = ExtraColumns.from_dict(extra_columns)
         self._set_feature_columns(feature_columns)
+        self._copy_data = copy_data
 
         if model:
             self.assign_predictions(model)
@@ -129,16 +133,19 @@ class VMDataset(VMInput):
             excluded = [self.target_column, *self.extra_columns.flatten()]
             self.feature_columns = [col for col in self.columns if col not in excluded]
 
-        self.feature_columns_numeric = (
-            self._df[self.feature_columns]
-            .select_dtypes(include=[np.number])
-            .columns.tolist()
-        )
-        self.feature_columns_categorical = (
-            self._df[self.feature_columns]
-            .select_dtypes(include=[object, pd.Categorical])
-            .columns.tolist()
-        )
+        # Get dtypes without loading data into memory
+        feature_dtypes = self._df[self.feature_columns].dtypes
+
+        self.feature_columns_numeric = feature_dtypes[
+            feature_dtypes.apply(lambda x: pd.api.types.is_numeric_dtype(x))
+        ].index.tolist()
+
+        self.feature_columns_categorical = feature_dtypes[
+            feature_dtypes.apply(
+                lambda x: pd.api.types.is_categorical_dtype(x)
+                or pd.api.types.is_object_dtype(x)
+            )
+        ].index.tolist()
 
     def _add_column(self, column_name, column_values):
         column_values = np.array(column_values)
@@ -397,8 +404,18 @@ class VMDataset(VMInput):
             assert self.target_column not in columns
             columns.append(self.target_column)
 
-        # return a copy to prevent accidental modification
-        return as_df(self._df[columns]).copy()
+        # Check if all columns in self._df are requested
+        all_columns = set(columns) == set(self._df.columns)
+
+        # For copy_data=False and all columns: return exact same DataFrame object
+        if not self._copy_data and all_columns:
+            return self._df
+        # For copy_data=False and subset of columns: return view with shared data
+        elif not self._copy_data:
+            return as_df(self._df[columns])
+        # For copy_data=True: return independent copy with duplicated data
+        else:
+            return as_df(self._df[columns]).copy()
 
     @property
     def x(self) -> np.ndarray:
@@ -522,9 +539,10 @@ class DataFrameDataset(VMDataset):
         text_column: str = None,
         target_class_labels: dict = None,
         date_time_index: bool = False,
+        copy_data: bool = True,
     ):
         """
-        Initializes a DataFrameDataset instance.
+        Initializes a DataFrameDataset instance, preserving original pandas dtypes.
 
         Args:
             raw_dataset (pd.DataFrame): The raw dataset as a pandas DataFrame.
@@ -536,25 +554,44 @@ class DataFrameDataset(VMDataset):
             text_column (str, optional): The text column name of the dataset for NLP tasks. Defaults to None.
             target_class_labels (dict, optional): The class labels for the target columns. Defaults to None.
             date_time_index (bool, optional): Whether to use date-time index. Defaults to False.
+            copy_data (bool, optional): Whether to create a copy of the input data. Defaults to True.
         """
+
+        VMInput.__init__(self)
+
+        self.input_id = input_id
+
         index = None
         if isinstance(raw_dataset.index, pd.Index):
             index = raw_dataset.index.values
+        self.index = index
 
-        super().__init__(
-            raw_dataset=raw_dataset.values,
-            input_id=input_id,
-            model=model,
-            index_name=raw_dataset.index.name,
-            index=index,
-            columns=raw_dataset.columns.to_list(),
-            target_column=target_column,
-            extra_columns=extra_columns,
-            feature_columns=feature_columns,
-            text_column=text_column,
-            target_class_labels=target_class_labels,
-            date_time_index=date_time_index,
-        )
+        # Store the DataFrame directly
+        self._df = raw_dataset
+
+        if date_time_index:
+            self._df = convert_index_to_datetime(self._df)
+
+        self.columns = raw_dataset.columns.tolist()
+        self.column_aliases = {}
+        self.target_column = target_column
+        self.text_column = text_column
+        self.target_class_labels = target_class_labels
+        self.extra_columns = ExtraColumns.from_dict(extra_columns)
+        self._copy_data = copy_data
+
+        # Add warning when copy_data is False
+        if not copy_data:
+            logger.warning(
+                "Dataset initialized with copy_data=False. Changes to the original DataFrame "
+                "may affect this dataset. Use this option only when memory efficiency is critical "
+                "and you won't modify the source data."
+            )
+
+        self._set_feature_columns(feature_columns)
+
+        if model:
+            self.assign_predictions(model)
 
 
 class PolarsDataset(VMDataset):

{validmind-2.8.20.dist-info → validmind-2.8.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: validmind
-Version: 2.8.20
+Version: 2.8.22
 Summary: ValidMind Library
 License: Commercial License
 Author: Andres Rodriguez

{validmind-2.8.20.dist-info → validmind-2.8.22.dist-info}/RECORD

@@ -1,9 +1,9 @@
 validmind/__init__.py,sha256=qmC6WY6ifIQpCU38V91EN91UlIEcOG7a9jWK3smZJoY,4220
-validmind/__version__.py,sha256=iRm89S5RopcoKz6axcNfUiasj1Y2r4BwSP5aughGqlE,23
+validmind/__version__.py,sha256=KYh5XihUKlbKxUpWkhRlJg_POPRyBFW9RUgXYfdQc0s,23
 validmind/ai/test_descriptions.py,sha256=eBF09MAyqAAD-Ah7vxXVRbHxOmGx5_10ZkoJmMvEaEA,7123
 validmind/ai/utils.py,sha256=O5gTkvGsPCCdKCdBGvpDaJM1oL_msdm2xKkf9fFpIy8,4172
 validmind/api_client.py,sha256=slvf0FJ8olYsK1-EPetMVYV7UvhjMAIFBxwBWSVT9BI,16807
-validmind/client.py,sha256=mVctTYyoDFDKnCA_eT99ZmOmOznOStx_C1vBJhET9sM,18908
+validmind/client.py,sha256=XKb4uc7yXVV_3NH9-zTrS9jCbLPX2zZZU12vKKlSpIc,19049
 validmind/client_config.py,sha256=O1gopTaNADM4ZVPj383AJTjcpjdxyEvUQY5cFt7nbIs,1366
 validmind/datasets/__init__.py,sha256=c0hQZN_6GrUEJxdFHdQaEsQrSYNABG84ZCY0H-PzOZk,260
 validmind/datasets/classification/__init__.py,sha256=p2p9r3SE4FIm4WNNJb4-axnkD5EexVW9VxIRYTbA6dI,1941
@@ -73,7 +73,7 @@ validmind/models/pipeline.py,sha256=nSskKWxaS4SGmx_B0IAvS5ogDZyh6tdx_aUkyxSXt88,
 validmind/models/pytorch.py,sha256=aAEUWtISwLh-PMvHkcLwBEbBStAByt4J-NpK-Ndv38E,1826
 validmind/models/r_model.py,sha256=TPUwPmxz3cNzJ1bAA5vz6P9xS6deVcLTuIO1e7rD1vY,7306
 validmind/models/sklearn.py,sha256=lOCJlP2wvd5IJHtBS1XG9FXrtIvO_f8xm2Qp1UdsiBw,2406
-validmind/template.py,sha256=e_5PvX-CotA7gz45gQ5zoHgIUECMyVYxlJK56Oc1cnA,7742
+validmind/template.py,sha256=ezmHLee5QkccBf4n8iBFcXw7EMljSceGgGJb3O0c4cE,7902
 validmind/test_suites/__init__.py,sha256=ofNaXD2SdkHko_Fy_RTr29YBHPGWiXVzHd1nENwi2ms,6973
 validmind/test_suites/classifier.py,sha256=0ZE3z5X_ZewTvmwQ3cVGJQh7dPgg0IlqcQshJJxCFWQ,4003
 validmind/test_suites/cluster.py,sha256=Wc2NViwivjiuiJMwrnGbOJYeZ3ApN8usWlOPYZYWAgE,2276
@@ -309,7 +309,7 @@ validmind/unit_metrics/regression/RootMeanSquaredError.py,sha256=uIDsSpy75Z7W3zu
 validmind/utils.py,sha256=59WWVV_JhvxzPr8Y625qw_wsyu_ZVRoLJyi0Pw3MTMU,28613
 validmind/vm_models/__init__.py,sha256=lcqf9q2aRzrVrNN6R--81IkrnSa6BXPbhJ8SnkT_hcI,702
 validmind/vm_models/dataset/__init__.py,sha256=U4CxZjdoc0dd9u2AqBl5PJh1UVbzXWNrmundmjLF-qE,346
-validmind/vm_models/dataset/dataset.py,sha256=4RCKyWIHd-RCIpleMIlfURGEQlmCRQkFZ5CRsJRC-g4,26479
+validmind/vm_models/dataset/dataset.py,sha256=lP0XLncHV6V5P-DG-Zs__wgirlUrEHokST-dQpb81Ro,28038
 validmind/vm_models/dataset/utils.py,sha256=g6mBPrBmVYf8wJAlTxeg9DTiNvts4ZaaT5mbnQAPWaU,5638
 validmind/vm_models/figure.py,sha256=ZMO_nIIleNhkBV1vJeF_UUsVDCzrXNOYwV1Lbg9E0XY,6303
 validmind/vm_models/input.py,sha256=nTBQB6aqirhF-0Gmg5mYc4_vNyypvbYUfahMovcK02M,1095
@@ -323,8 +323,8 @@ validmind/vm_models/test_suite/runner.py,sha256=JqW8LW4X1Ri2C6wSsAGSki-JxGUGV8zm
 validmind/vm_models/test_suite/summary.py,sha256=7P4zhfeU7a3I1MMBn8f7s-2lzdAz7U4y6LblpR89_vE,5401
 validmind/vm_models/test_suite/test.py,sha256=C8xPGKSyYF9oMJ3VegwFJDF7cwYlIgtQoQ7nzXIS1uc,3914
 validmind/vm_models/test_suite/test_suite.py,sha256=CciC6IhrLEeWwcpY3Np8EmQCB8XEF2ljwEXcvmNYgZc,5090
-validmind-2.8.20.dist-info/LICENSE,sha256=XonPUfwjvrC5Ombl3y-ko0Wubb1xdG_7nzvIbkZRKHw,35772
-validmind-2.8.20.dist-info/METADATA,sha256=iy0RjnDMshRPOKnzwT4N4fEh8cR1YKakh5IrYn2-jyM,6032
-validmind-2.8.20.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-validmind-2.8.20.dist-info/entry_points.txt,sha256=HuW7YyOv9u_OEWpViQXtv0nfoI67uieJHawKWA4Hv9A,76
-validmind-2.8.20.dist-info/RECORD,,
+validmind-2.8.22.dist-info/LICENSE,sha256=XonPUfwjvrC5Ombl3y-ko0Wubb1xdG_7nzvIbkZRKHw,35772
+validmind-2.8.22.dist-info/METADATA,sha256=cLg53_Ec1ZxQQ1eiIsBugTOh8e2_wjgCnPfWBWAEuZc,6032
+validmind-2.8.22.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+validmind-2.8.22.dist-info/entry_points.txt,sha256=HuW7YyOv9u_OEWpViQXtv0nfoI67uieJHawKWA4Hv9A,76
+validmind-2.8.22.dist-info/RECORD,,