sinapsis-data-analysis 0.1.0__py3-none-any.whl

sinapsis_data_analysis/templates/sklearn_train.py

@@ -0,0 +1,204 @@
+# -*- coding: utf-8 -*-
+import joblib
+from sinapsis_core.template_base import Template
+from sinapsis_core.template_base.dynamic_template import WrapperEntryConfig
+from sinapsis_core.template_base.dynamic_template_factory import make_dynamic_template
+from sinapsis_core.utils.env_var_keys import SINAPSIS_BUILD_DOCS
+from sklearn import linear_model, neighbors, neural_network, tree
+
+from sinapsis_data_analysis.helpers.excluded_models import (
+    excluded_linear_models,
+    excluded_neighbors_models,
+    excluded_tree_models,
+)
+from sinapsis_data_analysis.templates.ml_base_training import MLBaseTraining
+
+
+class SKLearnLinearModelsTrain(MLBaseTraining):
+    """
+    This template dynamically wraps sklearn linear_model module,
+    to train a dataset using linear models.
+
+    Usage example:
+
+        agent:
+          name: my_test_agent
+        templates:
+        - template_name: InputTemplate
+          class_name: InputTemplate
+          attributes: {}
+          template_name: LarsWrapper
+          class_name: LinearRegressionWrapper
+          template_input: load_diabetesWrapper
+          attributes:
+            generic_field_key: InputTemplate
+            model_save_path: "artifacts/linear_regression.joblib"
+            linearregression_init:
+              fit_intercept: true
+              copy_X: true
+              n_jobs: 8
+              positive: false
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=linear_model,
+        signature_from_doc_string=True,
+        exclude_module_atts=excluded_linear_models,
+        force_init_as_method=False,
+    )
+
+    CATEGORY = "SKLearn"
+
+    def _save_model_implementation(self) -> None:
+        """
+        Implements the abstract method from the base class to
+        save the model to the path specified in attributes.
+        """
+        joblib.dump(self.trained_model, self.attributes.model_save_path)
+
+
+class SKLearnNeighborsModelsTrain(SKLearnLinearModelsTrain):
+    """
+    This template dynamically wraps sklearn neighbors module,
+    providing access to models like KNeighborsClassifier,
+    KNeighborsRegressor, etc.
+
+    Usage example:
+
+      agent:
+          name: my_test_agent
+        templates:
+        - template_name: InputTemplate
+          class_name: InputTemplate
+          attributes: {}
+        - template_name: KNeighborsClassifierWrapper
+          class_name: KNeighborsClassifierWrapper
+          template_input: InputTemplate
+          attributes:
+            generic_field_key: 'input_template'
+            model_save_path: 'kneighbors.joblib'
+            kneighborsclassifier_init:
+              n_neighbors: 5
+              weights: uniform
+              algorithm: auto
+              leaf_size: 30
+              p: 2
+              metric: minkowski
+              n_jobs: 2
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=neighbors,
+        signature_from_doc_string=True,
+        exclude_module_atts=excluded_neighbors_models,
+        force_init_as_method=False,
+    )
+
+
+class SKLearnNNModelsTrain(SKLearnLinearModelsTrain):
+    """
+    This template dynamically wraps sklearn's neural_network module,
+    providing access to models like MLPClassifier, MLPRegressor, etc.
+
+    Usage example:
+
+    agent:
+      name: my_test_agent
+    templates:
+    - template_name: InputTemplate
+      class_name: InputTemplate
+      attributes: {}
+    - template_name: BernoulliRBMWrapper
+      class_name: BernoulliRBMWrapper
+      template_input: InputTemplate
+      attributes:
+        generic_field_key: 'input_template'
+        model_save_path: 'artifacts/bernoulli.joblib'
+        bernoullirbm_init:
+          n_components: 256
+          learning_rate: 0.1
+          batch_size: 10
+          n_iter: 10
+          verbose: 0
+          random_state: null
+
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=neural_network, signature_from_doc_string=True, force_init_as_method=False
+    )
+
+
+class SKLearnTreeModelsTrain(SKLearnLinearModelsTrain):
+    """
+    This template dynamically wraps sklearn's tree module,
+    providing access to models like DecisionTreeClassifier,
+    DecisionTreeRegressor, etc.
+
+    Usage example:
+
+    agent:
+      name: my_test_agent
+    templates:
+    - template_name: InputTemplate
+      class_name: InputTemplate
+      attributes: {}
+    - template_name: DecisionTreeClassifierWrapper
+      class_name: DecisionTreeClassifierWrapper
+      template_input: InputTemplate
+      attributes:
+        generic_field_key: 'input_template'
+        model_save_path: 'artifacts/decision_tree.joblib'
+        decisiontreeclassifier_init:
+          criterion: gini
+          splitter: best
+          max_depth: null
+          min_samples_split: 2
+          min_samples_leaf: 1
+          min_weight_fraction_leaf: 0.0
+          max_features: sqrt
+          random_state: 1
+          max_leaf_nodes: 2
+          min_impurity_decrease: 0.0
+          class_weight: balanced
+          ccp_alpha: 0.0
+
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=tree,
+        signature_from_doc_string=True,
+        exclude_module_atts=excluded_tree_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
+    and potential import errors due to not available packages.
+    """
+    if name in SKLearnLinearModelsTrain.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, SKLearnLinearModelsTrain)
+    if name in SKLearnNeighborsModelsTrain.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, SKLearnNeighborsModelsTrain)
+    if name in SKLearnNNModelsTrain.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, SKLearnNNModelsTrain)
+    if name in SKLearnTreeModelsTrain.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, SKLearnTreeModelsTrain)
+    raise AttributeError(f"template `{name}` not found in {__name__}")
+
+
+__all__ = (
+    SKLearnLinearModelsTrain.WrapperEntry.module_att_names
+    + SKLearnNeighborsModelsTrain.WrapperEntry.module_att_names
+    + SKLearnNNModelsTrain.WrapperEntry.module_att_names
+    + SKLearnTreeModelsTrain.WrapperEntry.module_att_names
+)
+
+
+if SINAPSIS_BUILD_DOCS:
+    dynamic_templates = [__getattr__(template_name) for template_name in __all__]
+    for template in dynamic_templates:
+        globals()[template.__name__] = template
+        del template

sinapsis_data_analysis/templates/xgboost_inference.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*-
+
+
+from sinapsis_data_analysis.templates.sklearn_inference import SKLearnInference
+
+
+class XGBoostInference(SKLearnInference):
+    """Dynamic templates to perform inference using XGBoost models.
+    These templates wrap the functionality of the xgb module and use the predict method on execute
+    using a dataset obtained through the container.
+
+    Usage example:
+    agent:
+      name: my_test_agent
+    templates:
+    - template_name: InputTemplate
+      class_name: InputTemplate
+      attributes: {}
+    - template_name: XGBRFClassifierInference
+      class_name: XGBRFClassifierInference
+      template_input: InputTemplate
+      attributes:
+        model_path: 'artifacts/xgb_rf_classifier.model'
+        generic_field_key: 'generic_dataset'
+
+    """

sinapsis_data_analysis/templates/xgboost_train.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+import xgboost as xgb
+from sinapsis_core.template_base import Template
+from sinapsis_core.template_base.dynamic_template import WrapperEntryConfig
+from sinapsis_core.template_base.dynamic_template_factory import make_dynamic_template
+from sinapsis_core.utils.env_var_keys import SINAPSIS_BUILD_DOCS
+
+from sinapsis_data_analysis.templates.sklearn_train import SKLearnLinearModelsTrain
+
+INCLUDED_MODELS = [
+    "XGBClassifier",
+    "XGBRegressor",
+    "XGBRanker",
+    "XGBRFClassifier",
+    "XGBRFRegressor",
+    "Booster",
+]
+
+EXCLUDED_MODELS = [attr for attr in dir(xgb) if attr not in INCLUDED_MODELS]
+
+
+class XGBoostModelsTraining(SKLearnLinearModelsTrain):
+    """Dynamic templates for XGBoost modules for classification, regression and boosting.
+    These templates wrap the functionality provided by the xgb module and use the fit method
+    on a dataset provided by the container.
+
+    Usage example:
+
+    agent:
+      name: my_test_agent
+
+    templates:
+    - template_name: InputTemplate
+      class_name: InputTemplate
+      attributes: {}
+      - template_name: XGBRankerWrapper
+      class_name: XGBClassifierWrapper
+      template_input: load_irisWrapper
+      attributes:
+        generic_field_key: load_irisWrapper
+        model_save_path: "artifacts/xgb_classifier.model"
+        xgbclassifier_init:
+          n_estimators: 100
+          max_depth: 3
+          learning_rate: 0.1
+    """
+
+    WrapperEntry = WrapperEntryConfig(
+        wrapped_object=xgb,
+        parse_entire_mro=True,
+        exclude_module_atts=EXCLUDED_MODELS,
+        force_init_as_method=False,
+        exclude_method_attributes=[
+            "kwargs",
+            "objective",
+        ],
+    )
+
+    CATEGORY = "XGBoost"
+
+
+def __getattr__(name: str) -> Template:
+    if name in XGBoostModelsTraining.WrapperEntry.module_att_names:
+        return make_dynamic_template(name, XGBoostModelsTraining)
+    raise AttributeError(f"template `{name}` not found in {__name__}")
+
+
+__all__ = XGBoostModelsTraining.WrapperEntry.module_att_names
+
+
+if SINAPSIS_BUILD_DOCS:
+    dynamic_templates = [__getattr__(template_name) for template_name in __all__]
+    for template in dynamic_templates:
+        globals()[template.__name__] = template
+        del template

sinapsis_data_analysis-0.1.0.dist-info/METADATA

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: sinapsis-data-analysis
+Version: 0.1.0
+Summary: Templates to work with models for classification, regression and clustering with xgboost and sklearn.
+Author-email: SinapsisAI <dev@sinapsis.tech>
+Project-URL: Homepage, https://sinapsis.tech
+Project-URL: Documentation, https://docs.sinapsis.tech/docs
+Project-URL: Tutorials, https://docs.sinapsis.tech/tutorials
+Project-URL: Repository, https://github.com/Sinapsis-AI/sinapsis-data-tools.git
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: scikit-learn>=1.6.1
+Requires-Dist: sinapsis>=0.1.1
+Requires-Dist: sinapsis-data-readers
+Requires-Dist: xgboost>=3.0.0
+Provides-Extra: all
+Dynamic: license-file
+
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis Data Analysis
+<br>
+</h1>
+
+<h4 align="center">Module for machine learning model training, analysis, and inference, using the Scikit-learn and XGBoost libraries.</h4>
+
+<p align="center">
+<a href="#installation">🐍  Installation</a> •
+<a href="#features"> 🚀 Features</a> •
+<a href="#example"> 📚 Usage Example</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license"> 🔍 License </a>
+</p>
+
+**Sinapsis Data Analysis** provides a comprehensive set of tools for machine learning model training, evaluation, and inference using industry-standard libraries like scikit-learn and XGBoost.
+
+<h2 id="installation"> 🐍  Installation </h2>
+
+Install using your package manager of choice. We encourage the use of <code>uv</code>
+
+Example with <code>uv</code>:
+
+```bash
+  uv pip install sinapsis-data-analysis --extra-index-url https://pypi.sinapsis.tech
+```
+ or with raw <code>pip</code>:
+```bash
+  pip install sinapsis-data-analysis --extra-index-url https://pypi.sinapsis.tech
+```
+
+
+<h2 id="features">🚀 Features</h2>
+
+<h3> Templates Supported</h3>
+
+**Sinapsis Data Analysis** provides a variety of templates for machine learning workflows:
+
+<details>
+<summary><strong><span style="font-size: 1.25em;">Scikit-Learn Models</span></strong></summary>
+
+The following model types are supported:
+
+- **Linear Models**: LinearRegression, Ridge, Lasso, ElasticNet, LogisticRegression, etc.
+- **Neighbors Models**: KNeighborsClassifier, KNeighborsRegressor, RadiusNeighborsClassifier, etc.
+- **Neural Network Models**: MLPClassifier, MLPRegressor, BernoulliRBM
+- **Tree Models**: DecisionTreeClassifier, DecisionTreeRegressor, ExtraTreeClassifier, etc.
+
+Each template uses the same base attributes:
+- **`generic_field_key` (str, required)**: Key of the generic field where datasets are stored
+- **`model_save_path` (str, required)**: Path where the trained model will be saved
+</details>
+
+<details>
+<summary><strong><span style="font-size: 1.25em;">XGBoost Models</span></strong></summary>
+
+XGBoost model templates include:
+- XGBClassifier
+- XGBRegressor
+- XGBRanker
+- XGBRFClassifier
+- XGBRFRegressor
+- Booster
+
+Attributes are the same as those for Scikit-learn templates.
+</details>
+
+<details>
+<summary><strong><span style="font-size: 1.25em;">Manifold Learning</span></strong></summary>
+
+Templates for dimensionality reduction using scikit-learn's manifold learning techniques:
+
+- **SKLearnManifold**: Base class for all manifold learning algorithms
+  - **`generic_field_key` (str, required)**: Key of the generic field where the input data is stored
+
+Specific algorithms include t-SNE, MDS, Isomap, LocallyLinearEmbedding, and more.
+</details>
+
+<details>
+<summary><strong><span style="font-size: 1.25em;">Inference Templates</span></strong></summary>
+
+Templates for using trained models to make predictions on new data:
+
+- **SKLearnInference**: For inference with scikit-learn models
+- **XGBoostInference**: For inference with XGBoost models
+
+To use these templates, you should replace the **`model_path`** to point to the path of the trained model.
+</details>
+
+> [!TIP]
+> Use CLI command ``` sinapsis info --all-template-names``` to show a list with all the available Template names installed with Sinapsis Data Analysis.
+
+> [!TIP]
+> Use CLI command ```sinapsis info --example-template-config TEMPLATE_NAME``` to produce an example Agent config for the Template specified in ***TEMPLATE_NAME***.
+
+For example, for ***LinearRegression*** use ```sinapsis info --example-template-config LinearRegression``` to produce an example config.
+
+<h2 id="example"> 📚 Usage Example </h2>
+Below is an example configuration for **Sinapsis Data Analysis** using LinearRegressionWrapper for regression.
+
+<details>
+<summary><strong><span style="font-size: 1.25em;">Example config</span></strong></summary>
+
+```yaml
+agent:
+  name: sklearn_linear_models_agent
+  description: agent to train a LinearRegression model from scikit-learn using the load_diabetes dataset
+
+templates:
+- template_name: InputTemplate
+  class_name: InputTemplate
+  attributes: {}
+
+- template_name: load_diabetesWrapper
+  class_name: load_diabetesWrapper
+  template_input: InputTemplate
+  attributes:
+    split_dataset: true
+    train_size: 0.8
+    load_diabetes:
+      return_X_y: false
+      as_frame: true
+
+- template_name: LinearRegressionWrapper
+  class_name: LinearRegressionWrapper
+  template_input: load_diabetesWrapper
+  attributes:
+    generic_field_for_data: load_diabetesWrapper
+    model_save_path: "artifacts/linear_regression.joblib"
+    linearregression_init:
+      fit_intercept: true
+      copy_X: true
+      n_jobs: null
+      positive: false
+```
+</details>
+
+To run the config, use the CLI:
+```bash
+sinapsis run name_of_config.yml
+```
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation for this and other sinapsis packages is available on the [sinapsis website](https://docs.sinapsis.tech/docs)
+
+Tutorials for different projects within sinapsis are available at [sinapsis tutorials page](https://docs.sinapsis.tech/tutorials)
+
+<h2 id="license">🔍 License</h2>
+
+This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the [LICENSE](LICENSE) file.
+
+For commercial use, please refer to our [official Sinapsis website](https://sinapsis.tech) for information on obtaining a commercial license.

sinapsis_data_analysis-0.1.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+sinapsis_data_analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sinapsis_data_analysis/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sinapsis_data_analysis/helpers/excluded_models.py,sha256=qrxx3ct44nZYYOIF5QJKYMdSlyCPI0ch3t_AqVaSGTs,537
+sinapsis_data_analysis/helpers/model_metrics.py,sha256=mR-ZLD8PrGgOh1PrYG8TOjFhJz6l2EDRtn6jtMMyI7A,729
+sinapsis_data_analysis/templates/__init__.py,sha256=Q898W-pTXGVjsMZn7wgmMYjrIstoo2bVzAXAgP75qaA,883
+sinapsis_data_analysis/templates/ml_base_inference.py,sha256=gtieXQ955QxlXQLaWJqTppwhjGHU6dcJfj46IoESyHE,3455
+sinapsis_data_analysis/templates/ml_base_training.py,sha256=sW4isOU8B8_s32-IKzLLzz_0xvvpB4M8LhcBmtYxN_s,9043
+sinapsis_data_analysis/templates/sklearn_inference.py,sha256=r_7eGi1Z1F24HojTK1b5YYJLw7uOjNn2Mvf8-JIcJB0,689
+sinapsis_data_analysis/templates/sklearn_manifold.py,sha256=BXLACGI2M5_zvlPxsKlFtTj3QNKXtawNP3_W8uBU-Ug,5200
+sinapsis_data_analysis/templates/sklearn_train.py,sha256=ZDBMAabDKuopyvkLd9poaRKJFY2tUbx9h6MTkvEmpvs,6489
+sinapsis_data_analysis/templates/xgboost_inference.py,sha256=fjHzjFeIxtRv1oSm5P-TgYUBvwB49JUVdNaPlszl1fI,782
+sinapsis_data_analysis/templates/xgboost_train.py,sha256=9oI570dMn32D6pVxLas_XhtcUO0a53PIHkf9UwNe_l8,2260
+sinapsis_data_analysis-0.1.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+sinapsis_data_analysis-0.1.0.dist-info/METADATA,sha256=VEinA85NDwJQzrpDA-swhD0q5TQAUbL28LvNU_y4G94,6316
+sinapsis_data_analysis-0.1.0.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+sinapsis_data_analysis-0.1.0.dist-info/top_level.txt,sha256=Mc5OyqBINgXFLrAyVBmjg25MQd6Lbg7z-rwotzEeygQ,23
+sinapsis_data_analysis-0.1.0.dist-info/RECORD,,

sinapsis_data_analysis-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (79.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+