sinapsis-data-tools 0.2.28__tar.gz → 0.2.29__tar.gz

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-data-tools
-Version: 0.2.28
+Version: 0.2.29
 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

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/helpers/excluded_models.py

@@ -25,3 +25,16 @@ excluded_neighbors_models = [
 ]
 excluded_tree_models = ["plot_tree", "export_text", "export_graphviz", "BaseDecisionTree"]
 excluded_svm_models = ["l1_min_c"]
+excluded_cluster_models = ["affinity_propagation",
+    "cluster_optics_dbscan",
+    "cluster_optics_xi",
+    "compute_optics_graph",
+    "dbscan",
+    "estimate_bandwidth",
+    "get_bin_seeds",
+    "k_means",
+    "kmeans_plusplus",
+    "linkage_tree",
+    "mean_shift",
+    "spectral_clustering",
+    "ward_tree"]

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/ml_base_training.py

@@ -93,20 +93,21 @@ class MLBaseTraining(BaseDynamicWrapperTemplate):
                 or None if the dataset doesn't have the expected attributes
         """
         x_train, y_train, x_test, y_test = None, None, None, None
-        for set in dataset:
-            if "x_train" in set.source:
-                x_train = set.content
-            elif "x_test" in set.source:
-                x_test = set.content
-            elif "y_train" in set.source:
-                y_train = set.content
-            elif "y_test" in set.source:
-                y_test = set.content
-            else:
-                if "x_dataset" in set.source:
-                    x_train =  set.content
-                elif "y_dataset" in set.source:
-                    y_train = set.content
+        for data_set in dataset:
+            if data_set.source:
+                if "x_train" in data_set.source:
+                    x_train = data_set.content
+                elif "x_test" in data_set.source:
+                    x_test = data_set.content
+                elif "y_train" in data_set.source:
+                    y_train = data_set.content
+                elif "y_test" in data_set.source:
+                    y_test = data_set.content
+                else:
+                    if "x_dataset" in data_set.source:
+                        x_train =  data_set.content
+                    elif "y_dataset" in data_set.source:
+                        y_train = data_set.content
 
         return x_train, y_train, x_test, y_test
 

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_analysis/src/sinapsis_data_analysis/templates/training/sklearn_train.py

@@ -10,10 +10,11 @@ from sinapsis_data_analysis.helpers.excluded_models import (
     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
+from sklearn import linear_model, neighbors, neural_network, svm, tree, cluster
 
 
 class SKLearnLinearModelsTrain(MLBaseTraining):
@@ -212,6 +213,44 @@ class SKLearnSVMModelsTrain(SKLearnLinearModelsTrain):
     )
 
 
+
+class SKLearnClusterModelsTrain(SKLearnLinearModelsTrain):
+    """
+    This template dynamically wraps sklearn's svm module,
+    providing access to models like SVC, SVR, LinearSVC,
+    LinearSVR, NuSVC, NuSVR, and OneClassSVM.
+
+    Usage example:
+
+    agent:
+      name: my_test_agent
+    templates:
+    - template_name: InputTemplate
+      class_name: InputTemplate
+      attributes: {}
+    - template_name: SVCWrapper
+      class_name: SVCWrapper
+      template_input: DataLoaderTemplate
+      attributes:
+        generic_field_key: 'data_loader_key'
+        model_save_path: 'artifacts/svc_model.joblib'
+        svc_init:
+          C: 1.0
+          kernel: rbf
+          random_state: 42
+
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=cluster,
+        signature_from_doc_string=True,
+        exclude_module_atts=excluded_cluster_models,
+        force_init_as_method=False,
+    )
+
+
+
+
 def __getattr__(name: str) -> Template:
     """
     Only create a template if it's imported, this avoids creating all the base models for all templates
@@ -227,6 +266,8 @@ def __getattr__(name: str) -> Template:
         return make_dynamic_template(name, SKLearnTreeModelsTrain)
     if name in SKLearnSVMModelsTrain.WrapperEntry.module_att_names:
         return make_dynamic_template(name, SKLearnSVMModelsTrain)
+    if name in SKLearnClusterModelsTrain.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, SKLearnClusterModelsTrain)
     raise AttributeError(f"template `{name}` not found in {__name__}")
 
 
@@ -236,6 +277,7 @@ __all__ = (
     + SKLearnNNModelsTrain.WrapperEntry.module_att_names
     + SKLearnTreeModelsTrain.WrapperEntry.module_att_names
     + SKLearnSVMModelsTrain.WrapperEntry.module_att_names
++ SKLearnClusterModelsTrain.WrapperEntry.module_att_names
 )
 
 

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/__init__.py

@@ -20,7 +20,6 @@ _template_lookup = {
     "ExecuteNTimesLazyAudioReaderPydub": f"{_root_lib_path}.audio_readers.audio_reader_pydub",
     "ExecuteNTimesLazyAudioReaderSoundfile": f"{_root_lib_path}.audio_readers.audio_reader_soundfile",
     "FolderImageDatasetCV2": f"{_root_lib_path}.image_readers.image_folder_reader_cv2",
-    "ImageDatasetSplitter": f"{_root_lib_path}.datasets_readers.dataset_splitter",
     "LazyAudioReaderPydub": f"{_root_lib_path}.audio_readers.audio_reader_pydub",
     "LazyAudioReaderSoundfile": f"{_root_lib_path}.audio_readers.audio_reader_soundfile",
     "LiveVideoReaderCV2": f"{_root_lib_path}.video_readers.video_reader_cv2",
@@ -29,7 +28,7 @@ _template_lookup = {
     "MultiVideoReaderPytorch": f"{_root_lib_path}.video_readers.video_reader_dali",
     "MultiVideoReaderFFMPEG": f"{_root_lib_path}.video_readers.video_reader_ffmpeg",
     "MultiVideoReaderTorchCodec": f"{_root_lib_path}.video_readers.video_reader_torchcodec",
-    "TabularDatasetSplitter": f"{_root_lib_path}.datasets_readers.dataset_splitter",
+    "CSVDatasetSplitter": f"{_root_lib_path}.datasets_readers.dataset_splitter",
     "TextInput": f"{_root_lib_path}.text_readers.text_input",
     "VideoReaderCV2": f"{_root_lib_path}.video_readers.video_reader_cv2",
     "VideoReaderDali": f"{_root_lib_path}.video_readers.video_reader_dali",

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/datasets_readers/csv_datasets.py

@@ -25,7 +25,7 @@ class CSVDatasetReader(Template):
             packet = TimeSeriesPacket(content=self.csv_file)
             container.time_series.append(packet)
         else:
-            packet = DataFramePacket(content=self.csv_file)
+            packet = DataFramePacket(content=self.csv_file, source=f"{self.instance_name}_x_dataset")
             container.data_frames.append(packet)
 
         return container

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/datasets_readers/dataset_splitter.py

@@ -30,7 +30,7 @@ class CSVDatasetSplitter(Template):
         target = data_frame.content.get(self.attributes.target_key)
         feature = data_frame.content.get(self.attributes.feature_key) \
             if self.attributes.feature_key \
-            else data_frame.drop(columns=[self.attributes.target_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:
@@ -55,11 +55,14 @@ class CSVDatasetSplitter(Template):
         return container
 
     def execute(self, container: DataContainer) -> DataContainer:
+        new_samples = []
         for df in container.data_frames:
             feature, target = self.extract_x_y_from_packet(df)
-            sample = feature, target, None, None
+
             if self.attributes.train_size:
                 sample = self.split_dataset(feature, target)
+                new_samples.append(sample)
+        for sample in new_samples:
             for name, data_frame in sample.items():
                 container = self.assign_to_dataframe_packets(container, name, data_frame)
         return container

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_readers/src/sinapsis_data_readers/templates/datasets_readers/sktime_datasets.py

@@ -83,7 +83,7 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
 
         split_dataset: bool = True
         train_size: float = 0.7
-        store_as_time_series: bool = False
+        store_as_data_frame: bool = False
 
     def __init__(self, attributes: TemplateAttributeType) -> None:
         super().__init__(attributes)
@@ -101,9 +101,7 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
             TabularDatasetSplit: Object containing the split time series data
         """
         y_train, y_test = temporal_train_test_split(dataset, train_size=self.attributes.train_size)
-        x_train = pd.DataFrame(index=y_train.index)
-        x_test = pd.DataFrame(index=y_test.index)
-        data_map = {"x_train": x_train, "y_train": y_train, "x_test": x_test, "y_test": y_test}
+        data_map = {"x_train": None, "y_train": y_train, "x_test": None, "y_test": y_test}
         return data_map
 
     def split_classification_dataset(self, X: Any, y: Any) -> dict:
@@ -137,6 +135,7 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
         return self.wrapped_callable.__func__(**self.dataset_attributes.model_dump())
 
 
+
     def execute(self, container: DataContainer) -> DataContainer:
         """Execute the SKTimeDatasets template to load and process a dataset.
 
@@ -149,34 +148,30 @@ class SKTimeDatasets(BaseDynamicWrapperTemplate):
         Returns:
             DataContainer: The container with the dataset added to it.
         """
+
         dataset = self.create_dataset()
-        if isinstance(dataset, tuple):
-            if self.attributes.split_dataset:
+
+        if self.attributes.split_dataset:
+            if isinstance(dataset, tuple):
                 data_map = self.split_classification_dataset(dataset[0], dataset[1])
             else:
-                container.time_series.append(TimeSeriesPacket(content=dataset))
-                return container
-
-        else:
-            if self.attributes.split_dataset:
                 data_map = self.split_time_series_dataset(dataset)
-            else:
-                container.data_frames.append(DataFramePacket(content=dataset))
-                return container
-        for name,data in data_map.items():
-            if data is not None:
-                if self.attributes.store_as_time_series:
-                    new_packet = TimeSeriesPacket(content=data, source=f"{self.instance_name}_{name}")
-                    container.time_series.append(new_packet)
-                else:
-                    new_packet = DataFramePacket(content=data, source=f"{self.instance_name}_{name}")
-                    container.data_frames.append(new_packet)
-
-
+        else:
+            # no split → single entry
+            data_map = {"full": dataset}
+        # ---- Step 2: choose packet class ----
+        PacketCls = DataFramePacket if self.attributes.store_as_data_frame else TimeSeriesPacket
+        target_list = container.data_frames if self.attributes.store_as_data_frame else container.time_series
+
+        # ---- Step 3: store ----
+        for name, data in data_map.items():
+            if data is None:
+                continue
+            packet = PacketCls(content=data, source=f"{self.instance_name}_{name}")
+            target_list.append(packet)
 
         return container
 
-
 @execute_template_n_times_wrapper
 class ExecuteNTimesSKTimeDatasets(SKTimeDatasets):
     """This template extends the functionality of the SKTimeDatasets template

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/packages/sinapsis_data_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sinapsis-data-tools
-Version: 0.2.28
+Version: 0.2.29
 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

{sinapsis_data_tools-0.2.28 → sinapsis_data_tools-0.2.29}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sinapsis-data-tools"
-version = "0.2.28"
+version = "0.2.29"
 description = "Module that contains different packages to perform data-related operations through Sinapsis templates."
 authors = [{ name = "SinapsisAI", email = "dev@sinapsis.tech" }]
 dependencies = [