[skip actions] minor update readme and logging

Author: manujosephv

README.md

@@ -58,13 +58,7 @@ git clone git://github.com/manujosephv/pytorch_tabular
 Once you have a copy of the source, you can install it with:
 
 ```bash
-pip install .
-```
-
-or
-
-```bash
-python setup.py install
+pip install .[extra]
 ```
 
 ## Documentation
@@ -142,11 +136,11 @@ loaded_model = TabularModel.load_from_checkpoint("examples/basic")
 
 ## Future Roadmap(Contributions are Welcome)
 
-1. Add GaussRank as Feature Transformation
 1. Integrate Optuna Hyperparameter Tuning
 1. Integrate SHAP for interpretability
 1. Add Variable Importance
 1. Add ability to use custom activations in CategoryEmbeddingModel
+1. Add GaussRank as Feature Transformation
 1. ~~Add differential dropouts(layer-wise) in CategoryEmbeddingModel~~
 1. ~~Add Fourier Encoding for cyclic time variables~~
 1. ~~Add Text and Image Modalities for mixed modal problems~~

examples/covertype_classification.py

@@ -98,7 +98,7 @@
 model_config = CategoryEmbeddingModelConfig(
     task="classification", metrics=["f1_score", "accuracy"], metrics_params=[{"num_classes": num_classes}, {}]
 )
-trainer_config = TrainerConfig(auto_select_gpus=True, fast_dev_run=False, max_epochs=5, batch_size=512)
+trainer_config = TrainerConfig(auto_lr_find=True, fast_dev_run=False, max_epochs=5, batch_size=512)
 optimizer_config = OptimizerConfig()
 tabular_model = TabularModel(
     data_config=data_config,

src/pytorch_tabular/tabular_model.py

@@ -556,7 +556,8 @@ def train(
         self.model.train()
         if self.config.auto_lr_find and (not self.config.fast_dev_run):
             logger.info("Auto LR Find Started")
-            self.trainer.tune(self.model, train_loader, val_loader)
+            result = self.trainer.tune(self.model, train_loader, val_loader)
+            logger.info(f"Suggested LR: {result['lr_find'].suggestion()}. For plot and detailed analysis, use `find_learning_rate` method.")
             # Parameters in models needs to be initialized again after LR find
             self.model.data_aware_initialization(self.datamodule)
         self.model.train()