Create main.py

main.py

@@ -0,0 +1,38 @@
+import re
+import string
+import nltk
+from fastapi import FastAPI, HTTPException, RedirectResponse
+from pydantic import BaseModel
+from transformers import pipeline
+
+# Initialize FastAPI app and download necessary NLTK resources
+app = FastAPI()
+nltk.download('punkt')
+nltk.download('wordnet')
+
+# Text preprocessing and model loading
+def preprocess_text(text):
+    text = re.sub(r'http[s]?://\S+', '', text)  # Remove URLs
+    text = re.sub(r'[' + re.escape(string.punctuation) + ']', '', text)  # Remove punctuation
+    text = text.lower()  # Convert to lowercase
+    lemmatizer = nltk.WordNetLemmatizer()
+    return ' '.join([lemmatizer.lemmatize(w) for w in nltk.word_tokenize(text)])  # Lemmatize
+
+model = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base")
+
+# API endpoints
+@app.get('/')
+async def redirect_to_docs():
+    return RedirectResponse(url='/docs')
+
+@app.post('/analyze/')
+async def predict_sentiment(text: TextInput):
+    try:
+        processed_text = preprocess_text(text.text)
+        return model(processed_text)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# Data model
+class TextInput(BaseModel):
+    text: str