Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import pipeline | |
| import pdfplumber | |
| from PIL import Image | |
| import easyocr | |
| from langdetect import detect | |
| # Initialize Models | |
| def initialize_models(): | |
| return { | |
| "report_check_model": pipeline("text-classification", model="facebook/bart-large-mnli"), | |
| "sentiment_model": pipeline("sentiment-analysis"), | |
| "summarize_model": pipeline("summarization", model="facebook/bart-large-cnn"), | |
| "translation_model": { | |
| "en": pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en"), | |
| "hi": pipeline("translation", model="Helsinki-NLP/opus-mt-en-hi"), | |
| "ur": pipeline("translation", model="Helsinki-NLP/opus-mt-en-ur") | |
| } | |
| } | |
| # Extract text from PDF | |
| def extract_text_from_pdf(pdf_file): | |
| text = "" | |
| with pdfplumber.open(pdf_file) as pdf: | |
| for page in pdf.pages: | |
| text += page.extract_text() | |
| return text.strip() | |
| # Extract text from Image using EasyOCR | |
| def extract_text_from_image(image_file): | |
| reader = easyocr.Reader(['en']) # Add more languages if needed | |
| image = Image.open(image_file) | |
| result = reader.readtext(image, detail=0) # `detail=0` returns only the text | |
| return " ".join(result).strip() | |
| # Check if content is a lab report | |
| def is_lab_report(text, model): | |
| result = model(text, candidate_labels=["lab report", "not lab report"]) | |
| return result["labels"][0] == "lab report" | |
| # Analyze sentiment | |
| def analyze_sentiment(text, sentiment_model): | |
| result = sentiment_model(text)[0] | |
| sentiment = "Positive" if result["label"] == "POSITIVE" else "Negative" | |
| return sentiment, result["score"] | |
| # Summarize content | |
| def summarize_content(text, summarize_model): | |
| summary = summarize_model(text, max_length=130, min_length=30, do_sample=False) | |
| return summary[0]['summary_text'] | |
| # Translate content | |
| def translate_content(text, translation_models): | |
| return { | |
| "English": text, | |
| "Hindi": translation_models["hi"](text)[0]["translation_text"], | |
| "Urdu": translation_models["ur"](text)[0]["translation_text"] | |
| } | |
| # Streamlit App | |
| def main(): | |
| st.title("Lab Test Analyzer") | |
| models = initialize_models() | |
| uploaded_file = st.file_uploader("Upload a Lab Report (PDF, Image, or Text)", type=["pdf", "png", "jpg", "jpeg", "txt"]) | |
| if uploaded_file: | |
| file_type = uploaded_file.name.split(".")[-1].lower() | |
| extracted_text = "" | |
| if file_type == "pdf": | |
| st.write("Processing PDF file...") | |
| extracted_text = extract_text_from_pdf(uploaded_file) | |
| elif file_type in ["png", "jpg", "jpeg"]: | |
| st.write("Processing Image file...") | |
| extracted_text = extract_text_from_image(uploaded_file) | |
| elif file_type == "txt": | |
| st.write("Processing Text file...") | |
| extracted_text = uploaded_file.read().decode("utf-8") | |
| else: | |
| st.error("Unsupported file type.") | |
| if extracted_text: | |
| st.subheader("Extracted Content") | |
| st.text_area("Extracted Text", extracted_text, height=200) | |
| # Check if it's a lab report | |
| if not is_lab_report(extracted_text, models["report_check_model"]): | |
| st.error("The uploaded file does not appear to be a lab report.") | |
| return | |
| st.success("The uploaded file is a valid lab report.") | |
| # Sentiment Analysis | |
| sentiment, confidence = analyze_sentiment(extracted_text, models["sentiment_model"]) | |
| st.subheader("Sentiment Analysis") | |
| st.write(f"**Sentiment**: {sentiment} (Confidence: {confidence:.2f})") | |
| # Summarization | |
| summary = summarize_content(extracted_text, models["summarize_model"]) | |
| st.subheader("Summary") | |
| st.text_area("Summary", summary, height=150) | |
| # Translation | |
| translations = translate_content(summary, models["translation_model"]) | |
| st.subheader("Translations") | |
| st.write("**English**: ", translations["English"]) | |
| st.write("**Hindi**: ", translations["Hindi"]) | |
| st.write("**Urdu**: ", translations["Urdu"]) | |
| else: | |
| st.error("Could not extract text from the uploaded file.") | |
| if __name__ == "__main__": | |
| main() | |