sinapsis-data-tools 0.2.29__tar.gz → 0.2.31__tar.gz

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-data-tools
-Version: 0.2.29
+Version: 0.2.31
 Summary: Module that contains different packages to perform data-related operations through Sinapsis templates.
 Author-email: SinapsisAI <dev@sinapsis.tech>
 Project-URL: Homepage, https://sinapsis.tech
@@ -22,6 +22,7 @@ Requires-Dist: sinapsis-data-visualization[all]; extra == "all"
 Requires-Dist: sinapsis-generic-data-tools[all]; extra == "all"
 Dynamic: license-file
 
+[![sp](https://img.shields.io/badge/lang-sp-red.svg)](https://github.com/Sinapsis-AI/sinapsis-data-tools/blob/main/README.es.md)
 <h1 align="center">
 <br>
 <a href="https://sinapsis.tech/">

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/README.md

@@ -1,3 +1,4 @@
+[![sp](https://img.shields.io/badge/lang-sp-red.svg)](https://github.com/Sinapsis-AI/sinapsis-data-tools/blob/main/README.es.md)
 <h1 align="center">
 <br>
 <a href="https://sinapsis.tech/">

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/helpers/tags.py

@@ -2,7 +2,7 @@
 from enum import Enum
 
 
-class Tags(Enum):
+class Tags(str, Enum):
     DATA_ANALYSIS = "data_analysis"
     DYNAMIC = "dynamic"
     INFERENCE = "inference"

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/__init__.py

@@ -10,7 +10,6 @@ _ADDITIONAL_TEMPLATE_MODULES = [
     f"{_root_lib_path}.training.sklearn_manifold",
     f"{_root_lib_path}.training.sklearn_train",
     f"{_root_lib_path}.training.xgboost_train",
-
 ]
 _template_lookup: dict = {
     "SKLearnInference": f"{_root_lib_path}.inference.sklearn_inference",
@@ -21,7 +20,7 @@ for t_module in _ADDITIONAL_TEMPLATE_MODULES:
     _template_lookup |= _import_template_package(t_module)
 
 
-def __getattr__(name: str) -> Template:
+def __getattr__(name: str) -> Template | None:
     if name in _template_lookup:
         module = importlib.import_module(_template_lookup[name])
         return getattr(module, name)

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/inference/ml_base_inference.py

@@ -26,14 +26,15 @@ class MLBaseInference(Template):
         """
 
         model_path: str
-        root_dir : str = WORKING_DIR
+        root_dir: str = WORKING_DIR
         generic_field_key: str
-        target_key : str
+        target_key: str
+
+    attributes: AttributesBaseModel
 
     def __init__(self, attributes: TemplateAttributes) -> None:
         super().__init__(attributes)
 
-
     def get_data(self, container: DataContainer) -> Any:
         """Get the data from the data container
 

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/inference/xgboost_inference.py

@@ -5,6 +5,8 @@ from sinapsis_core.template_base.base_models import UIPropertiesMetadata
 from sinapsis_data_analysis.helpers.tags import Tags
 from sinapsis_data_analysis.templates.inference.sklearn_inference import SKLearnInference
 
+tags = SKLearnInference.UIProperties.tags if SKLearnInference.UIProperties.tags is not None else []
+
 
 class XGBoostInference(SKLearnInference):
     """Dynamic templates to perform inference using XGBoost models.
@@ -27,4 +29,4 @@ class XGBoostInference(SKLearnInference):
 
     """
 
-    UIProperties = UIPropertiesMetadata(category="XGBoost", tags=[Tags.XGBOOST, *SKLearnInference.UIProperties.tags])
+    UIProperties = UIPropertiesMetadata(category="XGBoost", tags=[Tags.XGBOOST, *tags])

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/ml_base_training.py

@@ -31,7 +31,7 @@ class MLBaseAttributes(TemplateAttributes):
         model_save_path (str): Path where the trained model will be saved.
     """
 
-    root_dir : str = WORKING_DIR
+    root_dir: str = WORKING_DIR
     model_save_path: str
 
 
@@ -45,6 +45,7 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
     """
 
     AttributesBaseModel = MLBaseAttributes
+    attributes: MLBaseAttributes
 
     def __init__(self, attributes: TemplateAttributes) -> None:
         """Initialize the MLBase template.
@@ -66,7 +67,6 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
             Any: The dataset from the generic field.
         """
 
-
         return container.data_frames
 
     @staticmethod
@@ -105,7 +105,7 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
                     y_test = data_set.content
                 else:
                     if "x_dataset" in data_set.source:
-                        x_train =  data_set.content
+                        x_train = data_set.content
                     elif "y_dataset" in data_set.source:
                         y_train = data_set.content
 
@@ -119,7 +119,7 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
             y_train (Any): The training targets
         """
 
-        self.trained_model = self.model.fit(x_train, y_train)
+        self.trained_model = self.model.fit(x_train, y_train)  # ty: ignore[unresolved-attribute]
 
     @staticmethod
     def calculate_classification_metrics(y_true: np.ndarray, y_pred: np.ndarray) -> ModelMetrics:
@@ -192,8 +192,8 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
             predictions = self.trained_model.predict(x_test)
 
             metrics = self.calculate_metrics(y_test, predictions)
-
-            return ModelPredictionResults(predictions=predictions, metrics=metrics)
+            if metrics is not None:
+                return ModelPredictionResults(predictions=predictions, metrics=metrics)
         return None
 
     def handle_model_training(self, processed_data: tuple) -> ModelPredictionResults | None:

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/sklearn_manifold.py

@@ -4,7 +4,6 @@ import numpy as np
 import pandas as pd
 from pydantic import BaseModel, ConfigDict
 from sinapsis_core.data_containers.data_packet import DataContainer
-from sinapsis_core.template_base import Template
 from sinapsis_core.template_base.base_models import TemplateAttributes, UIPropertiesMetadata
 from sinapsis_core.template_base.dynamic_template import (
     BaseDynamicWrapperTemplate,
@@ -44,7 +43,8 @@ class SKLearnManifold(BaseDynamicWrapperTemplate):
             target_key (str): Key of the generic field where data is stored.
         """
 
-        target_key : str =  'target'
+        target_key: str = "target"
+
     WrapperEntry = WrapperEntryConfig(
         wrapped_object=manifold,
         signature_from_doc_string=True,
@@ -56,7 +56,7 @@ class SKLearnManifold(BaseDynamicWrapperTemplate):
         category="SKLearn",
         tags=[Tags.DATA_ANALYSIS, Tags.DYNAMIC, Tags.MANIFOLD, Tags.SKLEARN, Tags.MODELS],
     )
-
+    attributes: AttributesBaseModel
 
     def __init__(self, attributes: TemplateAttributes) -> None:
         super().__init__(attributes)
@@ -89,7 +89,6 @@ class SKLearnManifold(BaseDynamicWrapperTemplate):
         """
         return container.data_frames
 
-
     def process_dataset(self, dataset: list) -> ManifoldResults | None:
         """
         Extracts the training data, reshapes it, and applies the
@@ -113,11 +112,12 @@ class SKLearnManifold(BaseDynamicWrapperTemplate):
                 y_train = set.content[self.attributes.target_key]
                 x_train = set.content.pop(self.attributes.target_key)
 
+        if x_train is not None and y_train is not None:
+            x_train_reshaped = self.reshape_arrays(x_train)
+            x_transformed = self.manifold_model.fit_transform(x_train_reshaped)  # ty: ignore[unresolved-attribute]
 
-        x_train_reshaped = self.reshape_arrays(x_train)
-        x_transformed = self.manifold_model.fit_transform(x_train_reshaped)
-
-        return ManifoldResults(labels=y_train, x_transformed=x_transformed)
+            return ManifoldResults(labels=y_train, x_transformed=x_transformed)
+        return None
 
     def execute(self, container: DataContainer) -> DataContainer:
         """
@@ -143,7 +143,7 @@ class SKLearnManifold(BaseDynamicWrapperTemplate):
         return container
 
 
-def __getattr__(name: str) -> Template:
+def __getattr__(name: str) -> type[BaseDynamicWrapperTemplate]:
     """
     Only create a template if it's imported, this avoids creating all the base models for all templates
     and potential import errors due to not available packages.

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/sklearn_train.py

@@ -1,20 +1,19 @@
 # -*- coding: utf-8 -*-
 import joblib
-from sinapsis_core.template_base import Template
 from sinapsis_core.template_base.base_models import UIPropertiesMetadata
 from sinapsis_core.template_base.dynamic_template import WrapperEntryConfig
-from sinapsis_core.template_base.dynamic_template_factory import make_dynamic_template
+from sinapsis_core.template_base.dynamic_template_factory import BaseDynamicWrapperTemplate, make_dynamic_template
 from sinapsis_core.utils.env_var_keys import SINAPSIS_BUILD_DOCS
 from sinapsis_data_analysis.helpers.excluded_models import (
+    excluded_cluster_models,
     excluded_linear_models,
     excluded_neighbors_models,
     excluded_svm_models,
     excluded_tree_models,
-excluded_cluster_models
 )
 from sinapsis_data_analysis.helpers.tags import Tags
 from sinapsis_data_analysis.templates.training.ml_base_training import MLBaseTraining
-from sklearn import linear_model, neighbors, neural_network, svm, tree, cluster
+from sklearn import cluster, linear_model, neighbors, neural_network, svm, tree
 
 
 class SKLearnLinearModelsTrain(MLBaseTraining):
@@ -54,7 +53,7 @@ class SKLearnLinearModelsTrain(MLBaseTraining):
         category="SKLearn", tags=[Tags.DATA_ANALYSIS, Tags.LINEAR_REGRESSION, Tags.MODELS, Tags.SKLEARN, Tags.TRAINING]
     )
 
-    def _save_model_implementation(self, full_path:str) -> None:
+    def _save_model_implementation(self, full_path: str) -> None:
         """
         Implements the abstract method from the base class to
         save the model to the path specified in attributes.
@@ -213,7 +212,6 @@ class SKLearnSVMModelsTrain(SKLearnLinearModelsTrain):
     )
 
 
-
 class SKLearnClusterModelsTrain(SKLearnLinearModelsTrain):
     """
     This template dynamically wraps sklearn's svm module,
@@ -249,9 +247,7 @@ class SKLearnClusterModelsTrain(SKLearnLinearModelsTrain):
     )
 
 
-
-
-def __getattr__(name: str) -> Template:
+def __getattr__(name: str) -> type[BaseDynamicWrapperTemplate]:
     """
     Only create a template if it's imported, this avoids creating all the base models for all templates
     and potential import errors due to not available packages.
@@ -277,7 +273,7 @@ __all__ = (
     + SKLearnNNModelsTrain.WrapperEntry.module_att_names
     + SKLearnTreeModelsTrain.WrapperEntry.module_att_names
     + SKLearnSVMModelsTrain.WrapperEntry.module_att_names
-+ SKLearnClusterModelsTrain.WrapperEntry.module_att_names
+    + SKLearnClusterModelsTrain.WrapperEntry.module_att_names
 )
 
 

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/xgboost_train.py

@@ -1,9 +1,8 @@
 # -*- coding: utf-8 -*-
 import xgboost as xgb
-from sinapsis_core.template_base import Template
 from sinapsis_core.template_base.base_models import UIPropertiesMetadata
 from sinapsis_core.template_base.dynamic_template import WrapperEntryConfig
-from sinapsis_core.template_base.dynamic_template_factory import make_dynamic_template
+from sinapsis_core.template_base.dynamic_template_factory import BaseDynamicWrapperTemplate, make_dynamic_template
 from sinapsis_core.utils.env_var_keys import SINAPSIS_BUILD_DOCS
 from sinapsis_data_analysis.helpers.tags import Tags
 from sinapsis_data_analysis.templates.training.sklearn_train import SKLearnLinearModelsTrain
@@ -61,7 +60,7 @@ class XGBoostModelsTraining(SKLearnLinearModelsTrain):
     )
 
 
-def __getattr__(name: str) -> Template:
+def __getattr__(name: str) -> type[BaseDynamicWrapperTemplate]:
     if name in XGBoostModelsTraining.WrapperEntry.module_att_names:
         return make_dynamic_template(name, XGBoostModelsTraining)
     raise AttributeError(f"template `{name}` not found in {__name__}")

sinapsis_data_tools-0.2.31/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/transformation/categorical_to_numerical.py

@@ -0,0 +1,43 @@
+# -*- coding: utf-8 -*-
+import pandas as pd
+from sinapsis_core.data_containers.data_packet import DataContainer, DataFramePacket
+from sinapsis_core.template_base.base_models import TemplateAttributes
+from sinapsis_core.template_base.template import Template
+
+
+class CategoricalToNumerical(Template):
+    class AttributesBaseModel(TemplateAttributes):
+        generic_key: str
+
+    attributes: AttributesBaseModel
+
+    @staticmethod
+    def map_categorical_to_numerical(df: pd.DataFrame | pd.Series) -> tuple:
+        if isinstance(df, pd.Series):
+            categorical_cols = [df.name] if df.dtype in ["object", "string", "category"] else []
+        else:
+            categorical_cols = df.select_dtypes(include=["object", "string", "category"]).columns.tolist()
+
+        category_maps = {}
+
+        for col in categorical_cols:
+            categories = df[col].astype("string").unique()
+            category_maps[col] = {cat: idx for idx, cat in enumerate(categories)}
+        for col, mapping in category_maps.items():
+            df[col] = df[col].map(mapping)
+        return df, category_maps
+
+    @staticmethod
+    def unmap_numerical_to_categorical(df: pd.DataFrame | pd.Series, categories: dict) -> pd.DataFrame | pd.Series:
+        inverse_maps = {col: {v: k for k, v in mapping.items()} for col, mapping in categories.items()}
+
+        for col in inverse_maps:
+            df[col] = df[col].map(inverse_maps[col])
+        return df
+
+    def execute(self, container: DataContainer) -> DataContainer:
+        for data_frame in container.data_frames:
+            transformed_dataset, labels = self.map_categorical_to_numerical(data_frame.content)
+            container.data_frames.append(DataFramePacket(content=transformed_dataset, generic_data=labels))
+
+        return container

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/helpers/tags.py

@@ -2,7 +2,7 @@
 from enum import Enum
 
 
-class Tags(Enum):
+class Tags(str, Enum):
     AUDIO = "audio"
     COCO = "coco"
     CSV = "csv"

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/audio_readers/audio_reader_pydub.py

@@ -17,7 +17,8 @@ from sinapsis_data_readers.templates.audio_readers.base_audio_reader import (
 )
 
 AudioReaderPydubUIProperties = _AudioBaseReader.UIProperties
-AudioReaderPydubUIProperties.tags.extend([Tags.PYDUB])
+if AudioReaderPydubUIProperties.tags is not None:
+    AudioReaderPydubUIProperties.tags.extend([Tags.PYDUB])
 
 
 class AudioReaderPydub(_AudioBaseReader):
@@ -66,6 +67,7 @@ class AudioReaderPydub(_AudioBaseReader):
         audio_reader_format: Literal["wav", "raw", "pcm"] | None = None
 
     UIProperties = AudioReaderPydubUIProperties
+    attributes: AttributesBaseModel
 
     def read_file(self) -> AudioPacket | None:
         """Reads audio data from a file path or bytes and returns an AudioPacket.
@@ -84,9 +86,7 @@ class AudioReaderPydub(_AudioBaseReader):
             audio_segment = AudioSegment.from_file(io.BytesIO(audio_bytes))
 
         else:
-
             audio_file_path = self.get_full_path()
-            #audio_file_path = os.path.join(self.attributes.root_dir, audio_file_path)
             if os.path.exists(audio_file_path):
                 audio_segment = AudioSegment.from_file(audio_file_path, format=self.attributes.audio_reader_format)
 
@@ -138,7 +138,9 @@ class LazyAudioReaderPydub(AudioReaderPydub):
 
     class AttributesBaseModel(AudioReaderPydub.AttributesBaseModel):
         generic_key: str
-        audio_file_path: str | None = None  # type:ignore[assignment]
+        audio_file_path: str | None = None
+
+    attributes: AttributesBaseModel
 
     def get_file_path_from_generic_data(self, container: DataContainer) -> None:
         """Method to retrieve the file path from the genetic data field of DataContainer.
@@ -148,7 +150,8 @@ class LazyAudioReaderPydub(AudioReaderPydub):
             container (DataContainer): The DataContainer to extract the file path from
         """
         if self.attributes.generic_key:
-            file_path = self._get_generic_data(container, self.attributes.generic_key)
+            generic_data = self._get_generic_data(container)
+            file_path = getattr(generic_data, self.attributes.generic_key, None)
             if file_path:
                 self.attributes.audio_file_path = file_path
             else:

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/audio_readers/audio_reader_soundfile.py

@@ -14,7 +14,8 @@ from sinapsis_data_readers.templates.audio_readers.base_audio_reader import (
 )
 
 AudioReaderSoundfileUIProperties = _AudioBaseReader.UIProperties
-AudioReaderSoundfileUIProperties.tags.extend([Tags.SOUNDFILE])
+if AudioReaderSoundfileUIProperties.tags is not None:
+    AudioReaderSoundfileUIProperties.tags.extend([Tags.SOUNDFILE])
 
 
 class AudioReaderSoundfile(_AudioBaseReader):
@@ -111,7 +112,9 @@ class LazyAudioReaderSoundfile(AudioReaderSoundfile):
 
     class AttributesBaseModel(_AudioBaseReader.AttributesBaseModel):
         generic_key: str
-        audio_file_path: str | None = None  # type:ignore[assignment]
+        audio_file_path: str | None = None
+
+    attributes: AttributesBaseModel
 
     def get_file_path_from_generic_data(self, container: DataContainer) -> None:
         """Method to retrieve the file path from the genetic data field of DataContainer.
@@ -121,8 +124,9 @@ class LazyAudioReaderSoundfile(AudioReaderSoundfile):
             container (DataContainer): The DataContainer to extract the file path from
         """
         if self.attributes.generic_key:
-            file_path = self._get_generic_data(container, self.attributes.generic_key)
-            if file_path:
+            generic_data = self._get_generic_data(container)
+            file_path = getattr(generic_data, self.attributes.generic_key, None)
+            if file_path is not None:
                 self.attributes.audio_file_path = file_path
             else:
                 self.logger.warning("No audio path in the existing container")

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/audio_readers/base_audio_reader.py

@@ -2,7 +2,6 @@
 
 import abc
 import os
-from typing import cast
 from uuid import uuid4
 
 from sinapsis_core.data_containers.data_packet import AudioPacket, DataContainer
@@ -30,11 +29,12 @@ class _AudioBaseReader(_BaseDataReader):
             The source identifier, defaults to "streamlit".
         """
 
-
         root_dir: str | None = None
         audio_file_path: str
         source: str = str(uuid4())
 
+    attributes: AttributesBaseModel
+
     @abc.abstractmethod
     def read_file(self) -> AudioPacket | None:
         """Abstract method to read the audio data.
@@ -46,9 +46,10 @@ class _AudioBaseReader(_BaseDataReader):
         Returns:
             AudioPacket: The audio data wrapped in an AudioPacket.
         """
-    def get_full_path(self):
-        audio_file_path = cast(str, self.attributes.audio_file_path)
-        full_path = os.path.join(self.attributes.root_dir, audio_file_path)
+
+    def get_full_path(self) -> str:
+        audio_file_path = self.attributes.audio_file_path
+        full_path = os.path.join(self.root_dir, audio_file_path)
         return full_path
 
     def has_elements(self) -> bool:

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/base_file_data_loader.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 import abc
-from typing import Generator
+from typing import Any, Generator
 
 from sinapsis_core.data_containers.data_packet import DataContainer, Packet
 from sinapsis_core.template_base import Template
@@ -81,7 +81,7 @@ class _BaseDataReader(Template, abc.ABC):
         __doc__ = f"""
         {base_attributes_documentation()}
         """
-        root_dir : str | None = None
+        root_dir: str | None = None
         data_dir: str
         pattern: str = "**/*"
         batch_size: int = 1
@@ -89,17 +89,18 @@ class _BaseDataReader(Template, abc.ABC):
         samples_to_load: int = -1
         load_on_init: bool = False
 
+    attributes: AttributesBaseModel
+
     PACKET_ATT_NAME: str
 
     def __init__(self, attributes: TemplateAttributeType) -> None:
         super().__init__(attributes)
         self.counter = 0
-        self.attributes.root_dir = self.attributes.root_dir or SINAPSIS_CACHE_DIR
+        self.root_dir = self.attributes.root_dir or SINAPSIS_CACHE_DIR
         self.data_collection = self.make_data_entries()
 
-
     @abc.abstractmethod
-    def make_data_entries(self) -> list[Packet]:
+    def make_data_entries(self) -> list[Any]:
         """
         This method creates the data entries for this template. Each data entry
         consists of a `Packet` type.
@@ -109,7 +110,7 @@ class _BaseDataReader(Template, abc.ABC):
             list[Packet]: list of ImagePacket
         """
 
-    def read_packet_content(self, data_packet: Packet) -> None:
+    def read_packet_content(self, data_packet: Any) -> None:
         """
         Sets the value for data_packet.content where data packets can be ImagePacket|TextPacket...
 
@@ -142,7 +143,7 @@ class _BaseDataReader(Template, abc.ABC):
                 )
                 yield image_packets
 
-    def __next__(self) -> StopIteration | Generator:  # type:ignore #the yield method returns the Generator object
+    def __next__(self) -> StopIteration | Generator:
         if not self.has_elements():
             raise StopIteration("No more data to load")
         if self.attributes.batch_size == -1:

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/datasets_readers/csv_datasets.py

@@ -11,14 +11,16 @@ from sinapsis_data_readers.helpers.csv_reader import read_file
 
 class CSVDatasetReader(Template):
     class AttributesBaseModel(TemplateAttributes):
-        root_dir : str | None = None
+        root_dir: str | None = None
         path_to_csv: str
         store_as_time_series: bool = False
 
+    attributes: AttributesBaseModel
+
     def __init__(self, attributes: TemplateAttributeType) -> None:
         super().__init__(attributes)
-        self.attributes.root_dir = self.attributes.root_dir or SINAPSIS_CACHE_DIR
-        self.csv_file = read_file(os.path.join(self.attributes.root_dir, self.attributes.path_to_csv))
+        self.root_dir = self.attributes.root_dir or SINAPSIS_CACHE_DIR
+        self.csv_file = read_file(os.path.join(self.root_dir, self.attributes.path_to_csv))
 
     def execute(self, container: DataContainer) -> DataContainer:
         if self.attributes.store_as_time_series:

{sinapsis_data_tools-0.2.29 → sinapsis_data_tools-0.2.31}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/datasets_readers/dataset_splitter.py

@@ -17,24 +17,22 @@ class CSVDatasetSplitter(Template):
 
     class AttributesBaseModel(TemplateAttributes):
         target_key: str = "target"  # labels
-        feature_key: str | None  = None  # arrays
+        feature_key: str | None = None  # arrays
         random_state: int = 42
         train_size: float = 0.2
 
-
-
+    attributes: AttributesBaseModel
 
     def extract_x_y_from_packet(self, data_frame: DataFramePacket) -> tuple[pd.DataFrame, pd.DataFrame]:
-
-
         target = data_frame.content.get(self.attributes.target_key)
-        feature = data_frame.content.get(self.attributes.feature_key) \
-            if self.attributes.feature_key \
+        feature = (
+            data_frame.content.get(self.attributes.feature_key)
+            if self.attributes.feature_key
             else data_frame.content.drop(columns=[self.attributes.target_key])
+        )
         return feature, target
 
-    def split_dataset(self, x_data:pd.DataFrame, y_data:pd.DataFrame) -> dict:
-
+    def split_dataset(self, x_data: pd.DataFrame, y_data: pd.DataFrame) -> dict:
         x_train, x_test, y_train, y_test = train_test_split(
             x_data,
             y_data,
@@ -42,14 +40,10 @@ class CSVDatasetSplitter(Template):
             test_size=1 - self.attributes.train_size,
             random_state=self.attributes.random_state,
         )
-        data_map = {
-            "x_train": x_train,
-            "y_train": y_train,
-            "x_test": x_test,
-            "y_test": y_test
-        }
+        data_map = {"x_train": x_train, "y_train": y_train, "x_test": x_test, "y_test": y_test}
         return data_map
-    def assign_to_dataframe_packets(self,container: DataContainer, source: str, data: pd.DataFrame) -> DataContainer:
+
+    def assign_to_dataframe_packets(self, container: DataContainer, source: str, data: pd.DataFrame) -> DataContainer:
         df_packet = DataFramePacket(content=data, source=f"{self.instance_name}_{source}")
         container.data_frames.append(df_packet)
         return container
@@ -66,4 +60,3 @@ class CSVDatasetSplitter(Template):
             for name, data_frame in sample.items():
                 container = self.assign_to_dataframe_packets(container, name, data_frame)
         return container
-