Update app.py

app.py

@@ -8,7 +8,7 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 from logic.care_gap_engine import evaluate_care_gaps
 from logic.financial_model import estimate_financial_recovery
-from logic.nlp_report import generate_patient_summary
+from logic.nlp_report import generate_patient_summary, summarize_data_quality
 from logic.exporter import export_to_docx_and_zip
 
 CONFIG = {
@@ -27,7 +27,9 @@ CONFIG = {
 
 def run_analysis(file, tone, gap_filter, custom_prompt):
     df = pd.read_csv(file.name)
-    df = df.fillna({col: "" for col in df.select_dtypes(include='object').columns})
+    df.fillna("", inplace=True)
+
+    quality_issues_df = summarize_data_quality(df)
 
     care_gaps = evaluate_care_gaps(df, CONFIG)
     financials = estimate_financial_recovery(care_gaps, df, CONFIG['base_rate'], CONFIG['sdoh_modifiers'])
@@ -74,7 +76,7 @@ def run_analysis(file, tone, gap_filter, custom_prompt):
     plt.tight_layout()
     plt.savefig(top10_chart_path)
 
-    return merged, zip_bytes, "risk_score_plot.png", "care_gap_freq.png", top10_chart_path
+    return quality_issues_df, merged, zip_bytes, "risk_score_plot.png", "care_gap_freq.png", top10_chart_path
 
 iface = gr.Interface(
     fn=run_analysis,
@@ -85,6 +87,7 @@ iface = gr.Interface(
         gr.Textbox(label="Custom Prompt Override (optional)", value="")
     ],
     outputs=[
+        gr.Dataframe(label="⚠️ Data Quality Issues"),
         gr.Dataframe(label="Care Gap & Financial Report"),
         gr.File(label="Download All Reports as ZIP"),
         gr.Image(label="Risk Score Distribution"),
@@ -92,7 +95,7 @@ iface = gr.Interface(
         gr.Image(label="Top 10 Revenue Opportunities")
     ],
     title="AI Medicare Advantage Analyzer",
-    description="Upload a patient dataset, evaluate CMS care gaps and SDOH risk, forecast financial recovery, and generate NLP summaries with LLMs."
+    description="Upload a patient dataset, evaluate CMS care gaps and SDOH risk, forecast financial recovery, generate NLP summaries, and validate data quality."
 )
 
 if __name__ == "__main__":