File size: 1,870 Bytes
e488f4c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import re
import string
import nltk
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from typing import Optional
from transformers import pipeline
from pyngrok import ngrok
import nest_asyncio
# Download NLTK resources
nltk.download('punkt')
nltk.download('wordnet')
# Initialize FastAPI app
app = FastAPI()
# Text preprocessing functions
def remove_urls(text):
return re.sub(r'http[s]?://\S+', '', text)
def remove_punctuation(text):
regular_punct = string.punctuation
return re.sub(r'['+regular_punct+']', '', text)
def lower_case(text):
return text.lower()
def lemmatize(text):
wordnet_lemmatizer = nltk.WordNetLemmatizer()
tokens = nltk.word_tokenize(text)
return ' '.join([wordnet_lemmatizer.lemmatize(w) for w in tokens])
# Model loading
lyx_pipe = pipeline("text-classification", model="lxyuan/distilbert-base-multilingual-cased-sentiments-student")
# Input data model
class TextInput(BaseModel):
text: str
# Welcome endpoint
@app.get('/')
async def welcome():
return {'message': 'Welcome to the sentiment analysis API!'}
# Sentiment analysis endpoint
@app.post('/analyze/')
async def Predict_Sentiment(text_input: TextInput):
text = text_input.text
# Text preprocessing
text = remove_urls(text)
text = remove_punctuation(text)
text = lower_case(text)
text = lemmatize(text)
# Perform sentiment analysis
try:
return lyx_pipe(text)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
# Run the FastAPI app using Uvicorn
if __name__ == "__main__":
# Create ngrok tunnel
ngrok_tunnel = ngrok.connect(8000)
print('Public URL:', ngrok_tunnel.public_url)
# Allow nested asyncio calls
nest_asyncio.apply()
# Run the FastAPI app with Uvicorn
import uvicorn
uvicorn.run(app, port=8000) |