Spaces:
Runtime error
Runtime error
File size: 2,527 Bytes
06b8918 |
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 75 |
# Now, trying using the youtube video id
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import pandas as pd
import googleapiclient.discovery
app = FastAPI()
api_service_name = "youtube"
api_version = "v3"
DEVELOPER_KEY = "AIzaSyC4Vx8G6nm3Ow9xq7NluTuCCJ1d_5w4YPE" # Replace with your actual YouTube API key
youtube = googleapiclient.discovery.build(api_service_name, api_version, developerKey=DEVELOPER_KEY)
class SingleInput(BaseModel):
video_id: str
# Load the BERT tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
def scrape_comments(video_id):
request = youtube.commentThreads().list(
part="snippet",
videoId=video_id,
maxResults=100 # You can adjust the maximum number of comments to fetch
)
response = request.execute()
comments = []
for item in response['items']:
comment = item['snippet']['topLevelComment']['snippet']
comments.append(comment['textDisplay'])
comments_df = pd.DataFrame(comments, columns=['comment'])
return comments_df
@app.post("/analyze_sentiment/")
def analyze_sentiment_endpoint(data: SingleInput):
video_id = data.video_id
comments_df = scrape_comments(video_id)
if comments_df.empty:
raise HTTPException(status_code=400, detail="No comments found for the provided video ID")
tokenized_comments = tokenizer(list(comments_df['comment']), padding=True, truncation=True, return_tensors="pt")
# Perform sentiment analysis
with torch.no_grad():
outputs = model(**tokenized_comments)
logits = outputs.logits
# Determine sentiment for each comment
sentiment_ids = torch.argmax(logits, dim=1).tolist()
sentiment_labels = []
for sentiment_id in sentiment_ids:
if sentiment_id == 2:
sentiment_labels.append("Positive")
elif sentiment_id == 0:
sentiment_labels.append("Negative")
else:
sentiment_labels.append("Neutral")
sentiment_counts = {
"positive": sentiment_labels.count("Positive"),
"negative": sentiment_labels.count("Negative"),
"neutral": sentiment_labels.count("Neutral")
}
return {"sentiment_counts": sentiment_counts, "comments_count": len(comments_df)}
|