Update README.md

README.md

@@ -64,7 +64,7 @@ def predict_sentiments(model_name, tokenizer_name, input_file):
     
     df = pd.read_csv(input_file)
 
-    # Tokenize the input text
+    # Tokenize input text
     test_inputs = tokenizer(list(df['text']), padding=True, truncation=True, max_length=128, return_tensors='pt')
 
     # Make predictions
@@ -91,7 +91,7 @@ tokenizer_name = "RinInori/bert-base-uncased_finetune_sentiments"
 #Predict Unlabeled data
 predict_sentiments(model_name, tokenizer_name, '/content/drive/MyDrive/DLBBT01/data/c_unlabeled/dc_America.csv')
 
-# Load the predicted data
+# Load predicted data
 df_Am = pd.read_csv('/content/drive/MyDrive/DLBBT01/data/c_unlabeled/dc_America_predicted.csv')
 df_Am.head()
 
@@ -106,13 +106,13 @@ tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, do_lower_case=True)
 input_file = '/content/drive/MyDrive/DLBBT01/data/c_unlabeled/dc_America_predicted.csv'
 df_Am = pd.read_csv(input_file)
 
-# Examine the distribution of data based on labels
+# Examine distribution of data based on labels
 sentences = df_Am.text.values
 print("Distribution of data based on labels: ", df_Am.label.value_counts())
 
 MAX_LEN = 512
 
-# Plot the label distribution
+# Plot label 
 label_count = df_Am['label'].value_counts()
 plot_users = label_count.plot.pie(autopct='%1.1f%%', figsize=(4, 4))
 plt.rc('axes', unicode_minus=False)