Create app.py

app.py

@@ -0,0 +1,65 @@
+import gradio as gr
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+import re
+import nltk
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+
+# NLTK setup
+nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+stop_words = set(stopwords.words('english'))
+lemmatizer = WordNetLemmatizer()
+
+# Load model & tokenizer
+model_dir = "./model"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = BertTokenizer.from_pretrained(model_dir)
+model = BertForSequenceClassification.from_pretrained(model_dir).to(device)
+model.eval()
+
+MBTI_CLASSES = [
+    "ISTJ", "ISFJ", "INFJ", "INTJ",
+    "ISTP", "ISFP", "INFP", "INTP",
+    "ESTP", "ESFP", "ENFP", "ENTP",
+    "ESTJ", "ESFJ", "ENFJ", "ENTJ"
+]
+
+def preprocess(text):
+    text = text.lower()
+    text = re.sub(r"http\S+|www.\S+", "", text)
+    text = re.sub(r"[^a-zA-Z\s]", "", text)
+    text = text.replace("|||", " ")
+    tokens = word_tokenize(text)
+    tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
+    return " ".join(tokens)
+
+def predict_mbti(passage):
+    if not passage.strip():
+        return "Please enter your text."
+    
+    cleaned = preprocess(passage)
+    inputs = tokenizer(cleaned, return_tensors="pt", padding="max_length", truncation=True, max_length=512).to(device)
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        pred = torch.argmax(outputs.logits, dim=1).item()
+
+    return MBTI_CLASSES[pred]
+
+# Gradio Interface
+demo = gr.Interface(
+    fn=predict_mbti,
+    inputs=gr.Textbox(lines=10, label="Combined Response Passage", placeholder="Paste all question-answer text here..."),
+    outputs=gr.Textbox(label="Predicted MBTI Type"),
+    title="🔮 MBTI Personality Classifier API",
+    description="Pass a single combined text input (like 'Q1 A1 Q2 A2...') to get back the MBTI type."
+)
+
+if __name__ == "__main__":
+    demo.launch()