Add lean percentage to regional data

- Add LeanPercent column to regional.csv matching BodySpec reports
- Calculate lean percentage from lean tissue (excluding BMC) for accuracy
- Update JSON output to include lean_percent for each region
- Document new column in README
- Values now match BodySpec regional reports (e.g., Arms: 73.7%, Legs: 72.7%, Trunk: 64.4%)

README.md

@@ -128,7 +128,14 @@ Time-series data with one row per scan. Includes all primary metrics and derived
 ### 2. `regional.csv`
 Regional body composition breakdown (Arms, Legs, Trunk, Android, Gynoid, Total).
 
-**Columns:** Region, FatPercent, TotalMass_lb, FatTissue_lb, LeanTissue_lb, BMC_lb
+**Columns:**
+- `Region` - Body region name
+- `FatPercent` - Fat percentage in this region
+- `LeanPercent` - Lean tissue percentage in this region
+- `TotalMass_lb` - Total mass of the region
+- `FatTissue_lb` - Fat mass in the region
+- `LeanTissue_lb` - Lean mass in the region
+- `BMC_lb` - Bone mineral content in the region
 
 ### 3. `muscle_balance.csv`
 Left/right limb comparison for tracking muscle symmetry.

dexa_extract.py

@@ -399,22 +399,26 @@ def process_single_pdf(pdf_path, height_in, weight_lb, outdir):
         write_or_append_csv(os.path.join(outdir, "overall.csv"), overall_row, overall_cols)
 
         # Regional table
-        regional_cols = ["Region","FatPercent","TotalMass_lb","FatTissue_lb","LeanTissue_lb","BMC_lb"]
+        regional_cols = ["Region","FatPercent","LeanPercent","TotalMass_lb","FatTissue_lb","LeanTissue_lb","BMC_lb"]
         reg_rows = []
         for name, r in d.get("regional", {}).items():
+            # Calculate lean percentage (lean tissue only, not including BMC - matches BodySpec report)
+            lean_pct = round(100 * r["lean_tissue_lb"] / r["total_mass_lb"], 1) if r["total_mass_lb"] > 0 else None
             reg_rows.append({
                 "Region": name,
                 "FatPercent": r["fat_percent"],
+                "LeanPercent": lean_pct,
                 "TotalMass_lb": r["total_mass_lb"],
                 "FatTissue_lb": r["fat_tissue_lb"],
                 "LeanTissue_lb": r["lean_tissue_lb"],
                 "BMC_lb": r["bmc_lb"],
             })
         regional_path = os.path.join(outdir, "regional.csv")
+        df_regional = pd.DataFrame(reg_rows, columns=regional_cols)
         if os.path.exists(regional_path):
-            pd.DataFrame(reg_rows).to_csv(regional_path, mode="a", header=False, index=False)
+            df_regional.to_csv(regional_path, mode="a", header=False, index=False)
         else:
-            pd.DataFrame(reg_rows).to_csv(regional_path, index=False)
+            df_regional.to_csv(regional_path, index=False)
 
         # Muscle balance
         mb_cols = ["Region","FatPercent","TotalMass_lb","FatMass_lb","LeanMass_lb","BMC_lb"]
@@ -435,10 +439,18 @@ def process_single_pdf(pdf_path, height_in, weight_lb, outdir):
             pd.DataFrame(mb_rows).to_csv(mb_path, index=False)
 
         # JSON
-        regional_array = [
+        regional_array = []
-            {"region": name, **data}
+        for name, data in d.get("regional", {}).items():
-            for name, data in d.get("regional", {}).items()
+            lean_pct = round(100 * (data["lean_tissue_lb"] + data["bmc_lb"]) / data["total_mass_lb"], 1) if data["total_mass_lb"] > 0 else None
-        ]
+            regional_array.append({
+                "region": name,
+                "fat_percent": data["fat_percent"],
+                "lean_percent": lean_pct,
+                "total_mass_lb": data["total_mass_lb"],
+                "fat_tissue_lb": data["fat_tissue_lb"],
+                "lean_tissue_lb": data["lean_tissue_lb"],
+                "bmc_lb": data["bmc_lb"]
+            })
         muscle_balance_array = [
             {"region": name, **data}
             for name, data in d.get("muscle_balance", {}).items()
@@ -724,22 +736,26 @@ def main():
     write_or_append_csv(os.path.join(args.outdir, "overall.csv"), overall_row, overall_cols)
 
     # Regional table
-    regional_cols = ["Region","FatPercent","TotalMass_lb","FatTissue_lb","LeanTissue_lb","BMC_lb"]
+    regional_cols = ["Region","FatPercent","LeanPercent","TotalMass_lb","FatTissue_lb","LeanTissue_lb","BMC_lb"]
     reg_rows = []
     for name, r in d.get("regional", {}).items():
+        # Calculate lean percentage (lean tissue only, not including BMC - matches BodySpec report)
+        lean_pct = round(100 * r["lean_tissue_lb"] / r["total_mass_lb"], 1) if r["total_mass_lb"] > 0 else None
         reg_rows.append({
             "Region": name,
             "FatPercent": r["fat_percent"],
+            "LeanPercent": lean_pct,
             "TotalMass_lb": r["total_mass_lb"],
             "FatTissue_lb": r["fat_tissue_lb"],
             "LeanTissue_lb": r["lean_tissue_lb"],
             "BMC_lb": r["bmc_lb"],
         })
     regional_path = os.path.join(args.outdir, "regional.csv")
+    df_regional = pd.DataFrame(reg_rows, columns=regional_cols)
     if os.path.exists(regional_path):
-        pd.DataFrame(reg_rows).to_csv(regional_path, mode="a", header=False, index=False)
+        df_regional.to_csv(regional_path, mode="a", header=False, index=False)
     else:
-        pd.DataFrame(reg_rows).to_csv(regional_path, index=False)
+        df_regional.to_csv(regional_path, index=False)
 
     # Muscle balance
     mb_cols = ["Region","FatPercent","TotalMass_lb","FatMass_lb","LeanMass_lb","BMC_lb"]
@@ -761,10 +777,18 @@ def main():
 
     # JSON (overall structured object)
     # Convert regional and muscle_balance dicts to arrays
-    regional_array = [
+    regional_array = []
-        {"region": name, **data}
+    for name, data in d.get("regional", {}).items():
-        for name, data in d.get("regional", {}).items()
+        lean_pct = round(100 * data["lean_tissue_lb"] / data["total_mass_lb"], 1) if data["total_mass_lb"] > 0 else None
-    ]
+        regional_array.append({
+            "region": name,
+            "fat_percent": data["fat_percent"],
+            "lean_percent": lean_pct,
+            "total_mass_lb": data["total_mass_lb"],
+            "fat_tissue_lb": data["fat_tissue_lb"],
+            "lean_tissue_lb": data["lean_tissue_lb"],
+            "bmc_lb": data["bmc_lb"]
+        })
     muscle_balance_array = [
         {"region": name, **data}
         for name, data in d.get("muscle_balance", {}).items()