add info while loading data

donglihe-hub · donglihe-hub · commit f00da0aafa31 · 2024-01-22T17:52:26.000+04:00
diff --git a/libmultilabel/nn/data_utils.py b/libmultilabel/nn/data_utils.py
@@ -227,6 +227,7 @@ def load_datasets(
 
     datasets = {}
     if training_data is not None:
+        logging.info(f"Loading training data")
         datasets["train"] = _load_raw_data(
             training_data, tokenize_text=tokenize_text, remove_no_label_data=remove_no_label_data
         )
@@ -239,6 +240,7 @@ def load_datasets(
         datasets["train"], datasets["val"] = train_test_split(datasets["train"], test_size=val_size, random_state=42)
 
     if test_data is not None:
+        logging.info(f"Loading test data")
         datasets["test"] = _load_raw_data(
             test_data, is_test=True, tokenize_text=tokenize_text, remove_no_label_data=remove_no_label_data
         )

Original file line number	Diff line number	Diff line change
`@@ -227,6 +227,7 @@ def load_datasets(`
`227`	`227`
`228`	`228`	`datasets = {}`
`229`	`229`	`if training_data is not None:`
	`230`	`+ logging.info(f"Loading training data")`
`230`	`231`	`datasets["train"] = _load_raw_data(`
`231`	`232`	`training_data, tokenize_text=tokenize_text, remove_no_label_data=remove_no_label_data`
`232`	`233`	`)`
`@@ -239,6 +240,7 @@ def load_datasets(`
`239`	`240`	`datasets["train"], datasets["val"] = train_test_split(datasets["train"], test_size=val_size, random_state=42)`
`240`	`241`
`241`	`242`	`if test_data is not None:`
	`243`	`+ logging.info(f"Loading test data")`
`242`	`244`	`datasets["test"] = _load_raw_data(`
`243`	`245`	`test_data, is_test=True, tokenize_text=tokenize_text, remove_no_label_data=remove_no_label_data`
`244`	`246`	`)`