Create app.py

app.py

@@ -0,0 +1,89 @@
+import os
+import pandas as pd
+import streamlit as st
+import re
+import logging
+import nltk
+from docx import Document
+from collections import Counter
+import io
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Initialize logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+
+# Download required NLTK resources
+nltk.download("punkt")
+
+st.title("AI-Powered Coding Sheet Generator")
+st.write("Enter text or upload a DOCX/Excel file for analysis:")
+
+# Option to enable separate tab feature
+separate_tab = st.checkbox("Enable Separate Tab for Summary")
+
+input_text = st.text_area("Input Text", height=200)
+uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"])
+uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])
+
+output_data = {}
+
+# Function to extract text from DOCX
+def extract_text_from_docx(docx_file):
+    doc = Document(docx_file)
+    return "\n".join([para.text for para in doc.paragraphs if para.text.strip()])
+
+# Function to analyze summary data
+def generate_summary(data):
+    total_posts = len(data)
+    tones = Counter()
+    languages = Counter()
+    frames = Counter()
+    frame_focus = {"Major Focus": Counter(), "Significant Focus": Counter(), "Minor Mention": Counter(), "Not Applicable": Counter()}
+    
+    for post in data.values():
+        tones.update(post.get("Tone", []))
+        languages[post.get("Language", "Unknown")] += 1
+        frame_mapping = post.get("FramesMapping", {})
+        for frame, focus in frame_mapping.items():
+            frames[frame] += 1
+            frame_focus[focus][frame] += 1
+    
+    abstract = f"This document contains {total_posts} posts. The most commonly used tone is '{tones.most_common(1)}'. "
+    abstract += f"The most frequently mentioned frame is '{frames.most_common(1)}'. Languages used include {list(languages.keys())}."
+    
+    return total_posts, tones, languages, frames, frame_focus, abstract
+
+# Function to create an Excel summary
+def create_summary_excel(summary_data):
+    total_posts, tones, languages, frames, frame_focus, abstract = summary_data
+    with io.BytesIO() as buffer:
+        writer = pd.ExcelWriter(buffer, engine='xlsxwriter')
+        
+        pd.DataFrame(tones.items(), columns=["Tone", "Count"]).to_excel(writer, sheet_name="Tones", index=False)
+        pd.DataFrame(languages.items(), columns=["Language", "Count"]).to_excel(writer, sheet_name="Languages", index=False)
+        pd.DataFrame(frames.items(), columns=["Frame", "Count"]).to_excel(writer, sheet_name="Frames", index=False)
+        
+        for focus, counts in frame_focus.items():
+            pd.DataFrame(counts.items(), columns=["Frame", "Count"]).to_excel(writer, sheet_name=focus, index=False)
+        
+        pd.DataFrame({"Abstract": [abstract]}).to_excel(writer, sheet_name="Abstract", index=False)
+        
+        writer.close()
+        buffer.seek(0)
+        return buffer.getvalue()
+
+if uploaded_docx:
+    docx_text = extract_text_from_docx(uploaded_docx)
+    summary_data = generate_summary({"Uploaded DOCX": {"Full Caption": docx_text}})
+    if separate_tab:
+        with st.expander("Summary Tab"):
+            st.write(f"Total Posts: {summary_data[0]}")
+            st.write(f"Tones: {dict(summary_data[1])}")
+            st.write(f"Languages: {dict(summary_data[2])}")
+            st.write(f"Frames: {dict(summary_data[3])}")
+            st.write(f"Abstract: {summary_data[5]}")
+        excel_data = create_summary_excel(summary_data)
+        st.download_button("Download Summary as Excel", data=excel_data, file_name="summary.xlsx", mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet")