final commit

Author: Programmer-RD-AI

.virtual_documents/Dimensionality_Reduction.ipynb

@@ -80,18 +80,18 @@ def sklearn(
             metrics = classification_report(y_test, y_preds, output_dict=True)
             results[model.__class__.__name__] = metrics
             wandb.log(metrics)
-            # wandb.sklearn.plot_classifier(
-            #     model,
-            #     X_train,
-            #     X_test,
-            #     y_train,
-            #     y_test,
-            #     y_preds,
-            #     y_probas,
-            #     range(min(y_probas.shape)),
-            #     model_name=name,
-            #     feature_names=None,
-            # )
+            wandb.sklearn.plot_classifier(
+                model,
+                X_train,
+                X_test,
+                y_train,
+                y_test,
+                y_preds,
+                y_probas,
+                range(min(y_probas.shape)),
+                model_name=name,
+                feature_names=None,
+            )
             if metrics[self.metric] > best_model[0]:
                 best_model[0] = metrics[self.metric]
                 best_model[1] = metrics
@@ -139,7 +139,7 @@ def xgb(
             cp.asarray(X_train),
             cp.asarray(y_train),
             eval_set=[(cp.asarray(X_test), cp.asarray(y_test))],
-            # callbacks=[WandbCallback(log_model=True)],
+            callbacks=[WandbCallback(log_model=True)],
         )
         y_preds = model.predict(X_test)
         metrics = classification_report(y_test, y_preds, output_dict=True)
@@ -189,14 +189,14 @@ def lgb(
             self.lgb_config,
             train_data,
             valid_sets=[test_data],
-            # callbacks=[wandb_callback()],
+            callbacks=[wandb_callback()],
         )
         y_preds = model.predict(X_test)
         metrics = classification_report(
             y_test, np.argmax(y_preds, axis=1), output_dict=True
         )
         results[name] = metrics
-        # log_summary(model, save_model_checkpoint=True)
+        log_summary(model, save_model_checkpoint=True)
         wandb.log(metrics)
         wandb.finish()
         dirs = director_exist(os.path.join(os.getenv("MODEL_PATH"), run))
@@ -225,7 +225,12 @@ def evaluate(self) -> Dict[str, Dict[str, Dict[str, Union[str, int]]]]:
             for pipeline_variation in inner_iterator:
                 name_of_pipeline = pipeline_variation.steps[-1][-1].__class__.__name__
                 pipeline_performance = {}
-                X_train = pipeline_variation.fit_transform(self._data["X_train"])
+                try:
+                    X_train = pipeline_variation.fit_transform(self._data["X_train"])
+                except:
+                    X_train = pipeline_variation.fit_transform(
+                        self._data["X_train"], self._data["y_train"]
+                    )
                 X_test = pipeline_variation.transform(self._data["X_test"])
                 inner_iterator.set_description("Sklearn Model...")
                 pipeline_performance, sklearn_metrics = self.sklearn(
@@ -264,7 +269,7 @@ def evaluate(self) -> Dict[str, Dict[str, Dict[str, Union[str, int]]]]:
                 )
                 if float(avg_var) > float(best_performing_pipeline[0]):
                     best_performing_pipeline[0] = str(avg_var)
-                    best_performing_pipeline[1] = name_of_pipeline
+                    best_performing_pipeline[1] = str(pipeline_variation)
                 inner_iterator.set_description(f"{name_of_pipeline} Done :)")
             best_performances = add_to_dictionary(
                 best_performances, best_performing_pipeline

.virtual_documents/testing.ipynb

@@ -1,2 +1,28 @@
-# DimRed-Unveiling-Data-Insights-with-Dimensionality-Reduction
-Uncover hidden patterns, simplify datasets & accelerate analysis. From PCA to t-SNE, explore advanced techniques with DimRed.
+# DimRed: Unveiling Data Insights with Dimensionality Reduction
+
+DimRed is a Python library designed to uncover hidden patterns, simplify datasets, and accelerate analysis using various dimensionality reduction techniques. From Principal Component Analysis (PCA) to t-Distributed Stochastic Neighbor Embedding (t-SNE), DimRed offers a range of advanced methods for exploring high-dimensional data in a more manageable and interpretable form.
+
+## Features
+
+- **Multiple Techniques**: Explore a variety of dimensionality reduction techniques, including PCA, Incremental PCA, Kernel PCA, t-SNE, and more.
+- **Simplify Analysis**: Reduce the complexity of high-dimensional datasets while preserving important information and patterns.
+- **Visualize Data**: Visualize the transformed data in lower dimensions to gain insights and identify clusters or trends.
+- **Accelerate Processing**: Speed up the analysis process by reducing the number of features while maintaining data integrity.
+
+## Getting Started
+
+### Installation
+
+You can install DimRed using pip:
+
+```
+pip -r install requirements.txt
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to open issues for bug fixes, feature requests, or any suggestions for improvement.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](<[LICENSE](https://github.com/Programmer-RD-AI/Dimensionality-Reduction/blob/main/LICENSE)>) file for details.