Pushing change for logging

medcat/config_meta_cat.py

@@ -1,10 +1,12 @@
 from typing import Dict, Any
 from medcat.config import MixingConfig, BaseModel, Optional, Extra
+import logging
 
 
 class General(MixingConfig, BaseModel):
     """The General part of the MetaCAT config"""
     device: str = 'cpu'
+    log_level: int = logging.INFO
     disable_component_lock: bool = False
     seed: int = 13
     description: str = "No description"

medcat/meta_cat.py

@@ -57,6 +57,8 @@ def __init__(self,
             config = ConfigMetaCAT()
         self.config = config
         set_all_seeds(config.general['seed'])
+        logging.basicConfig(level=self.config.general.log_level)
+        logger.setLevel(self.config.general.log_level)
 
         if tokenizer is not None:
             # Set it in the config

medcat/utils/meta_cat/data_utils.py

@@ -210,6 +210,7 @@ def encode_category_values(data: Dict, existing_category_value2id: Optional[Dict
     for i in range(len(data)):
         if data[i][2] in category_value2id.values():
             label_data_[data[i][2]] = label_data_[data[i][2]] + 1
+    logger.info(f"Class distribution: {label_data_}")
     # Undersampling data
     if category_undersample is None or category_undersample == '':
         min_label = min(label_data_.values())
@@ -232,7 +233,7 @@ def encode_category_values(data: Dict, existing_category_value2id: Optional[Dict
     for i in range(len(data_undersampled)):
         if data_undersampled[i][2] in category_value2id.values():
             label_data[data_undersampled[i][2]] = label_data[data_undersampled[i][2]] + 1
-    logger.info(f"Updated label_data: {label_data}")
+    # logger.info(f"Updated label_data: {label_data}")
 
     return data_undersampled, data, category_value2id