Update app.py
Browse files
app.py
CHANGED
|
@@ -341,32 +341,32 @@ else:
|
|
| 341 |
if st.button("Analyze"):
|
| 342 |
# Ensure full extracted text is used for analysis
|
| 343 |
text_for_analysis = st.session_state["pdf_text"].strip() if st.session_state["pdf_text"] else example_text.strip()
|
| 344 |
-
|
| 345 |
if text_for_analysis:
|
| 346 |
with st.spinner("Analyzing text..."):
|
| 347 |
# Extract structured financial data using regex (Now using full text)
|
| 348 |
extracted_data = {
|
| 349 |
key: (match.group(1) if match else "N/A")
|
| 350 |
for key, pattern in patterns.items()
|
| 351 |
-
|
| 352 |
-
|
| 353 |
|
| 354 |
-
|
| 355 |
-
|
| 356 |
-
|
| 357 |
|
| 358 |
-
|
| 359 |
-
|
| 360 |
|
| 361 |
-
|
| 362 |
-
|
| 363 |
-
|
| 364 |
|
| 365 |
-
|
| 366 |
-
|
| 367 |
|
| 368 |
-
|
| 369 |
-
|
| 370 |
|
| 371 |
# Step 4: Summarization
|
| 372 |
st.subheader("Summarization")
|
|
|
|
| 341 |
if st.button("Analyze"):
|
| 342 |
# Ensure full extracted text is used for analysis
|
| 343 |
text_for_analysis = st.session_state["pdf_text"].strip() if st.session_state["pdf_text"] else example_text.strip()
|
| 344 |
+
|
| 345 |
if text_for_analysis:
|
| 346 |
with st.spinner("Analyzing text..."):
|
| 347 |
# Extract structured financial data using regex (Now using full text)
|
| 348 |
extracted_data = {
|
| 349 |
key: (match.group(1) if match else "N/A")
|
| 350 |
for key, pattern in patterns.items()
|
| 351 |
+
if (match := re.search(pattern, text_for_analysis, re.IGNORECASE))
|
| 352 |
+
}
|
| 353 |
|
| 354 |
+
# ✅ Correct indentation
|
| 355 |
+
doc = nlp(text_for_analysis)
|
| 356 |
+
financial_entities = [(ent.text, ent.label_) for ent in doc.ents if ent.label_ in ["MONEY", "PERCENT", "ORG", "DATE"]]
|
| 357 |
|
| 358 |
+
# Store extracted data in a structured dictionary
|
| 359 |
+
structured_data = {**extracted_data, "Named Entities Extracted": financial_entities}
|
| 360 |
|
| 361 |
+
# Display results
|
| 362 |
+
st.write("Entities Found:")
|
| 363 |
+
st.write(pd.DataFrame(financial_entities, columns=["Entity", "Label"]))
|
| 364 |
|
| 365 |
+
st.write("Structured Data Extracted:")
|
| 366 |
+
st.write(pd.DataFrame([structured_data]))
|
| 367 |
|
| 368 |
+
else:
|
| 369 |
+
st.error("Please provide some text for analysis.")
|
| 370 |
|
| 371 |
# Step 4: Summarization
|
| 372 |
st.subheader("Summarization")
|