File size: 2,073 Bytes
679bc5b 6b717c4 be16c65 679bc5b be16c65 6b717c4 679bc5b 6b717c4 679bc5b 6b717c4 679bc5b be16c65 6b717c4 be16c65 6b717c4 be16c65 6b717c4 679bc5b 6b717c4 be16c65 679bc5b 6b717c4 679bc5b 6b717c4 679bc5b 6b717c4 be16c65 6b717c4 679bc5b be16c65 679bc5b 6b717c4 679bc5b |
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 |
import pandas as pd
import streamlit as st
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
# Load the pre-trained model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("textattack/roberta-base-imdb")
model = AutoModelForSequenceClassification.from_pretrained("textattack/roberta-base-imdb")
def analyze_text(text):
# Preprocess the text
text = text.lower()
# Encode the text
encoded_text = tokenizer(text, truncation=True, padding=True, return_tensors='pt')
# Classify the text
with torch.no_grad():
output = model(**encoded_text)
predictions = output.logits.argmax(-1).item()
if predictions == 1: # For IMDb sentiment analysis, 1 indicates positive sentiment
return "Job Related"
else:
return "Not Job Related"
def count_job_related_messages(data):
job_related_count = 0
not_job_related_count = 0
for message in data["message"]:
result = analyze_text(message)
if result == "Job Related":
job_related_count += 1
else:
not_job_related_count += 1
return job_related_count, not_job_related_count
# Streamlit application
st.title("Job Related Message Analyzer")
uploaded_file = st.file_uploader("Upload CSV file")
user_input = st.text_input("Enter text")
if uploaded_file:
# Read the CSV file
data = pd.read_csv(uploaded_file)
# Analyze messages
results = []
for message in data["message"]:
result = analyze_text(message)
results.append(result)
data["Job Related"] = results
# Count job-related messages
job_related_count, not_job_related_count = count_job_related_messages(data)
st.dataframe(data)
st.write(f"Job Related Messages: {job_related_count}")
st.write(f"Not Job Related Messages: {not_job_related_count}")
elif user_input:
# Analyze user-input text
result = analyze_text(user_input)
st.write(f"Message Classification: {result}")
else:
st.write("Please upload a CSV file or enter text to analyze.")
|