settingupthird

app.py

@@ -6,13 +6,6 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import torch.nn.functional as F
 
-model_name = "distilbert-base-uncased-finetuned-sst-2-english"
-
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-classifier = pipeline(task="sentiment-analysis", model=model, tokenizer=tokenizer)
-
 textIn = st.text_input("Input Text Here:", "I really like the color of your car!")
 
 option = st.selectbox('Which pre-trained model would you like for your sentiment analysis?',('Pipeline', 'TextBlob', 'MILESTONE 3: FINE-TUNED'))
@@ -48,6 +41,12 @@ st.write('You selected:', option)
 #------------------------------------------------------------------------
 
 if option == 'Pipeline':
+
+    model_name = "distilbert-base-uncased-finetuned-sst-2-english"
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    classifier = pipeline(task="sentiment-analysis", model=model, tokenizer=tokenizer)
+
     # pipeline
     preds = classifier(textIn)
     preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
@@ -69,4 +68,11 @@ if option == 'TextBlob':
 
 
 if option == 'MILESTONE 3: FINE-TUNED':
-    ...
+    model_name = "distilbert-base-uncased-finetuned-sst-2-english"
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    classifier = pipeline(task="sentiment-analysis", model=model, tokenizer=tokenizer)
+    # pipeline
+    preds = classifier(textIn)
+    preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
+    st.write('According to Pipeline, input text is ', preds[0]['label'], ' with a confidence of ', preds[0]['score'])