added final rust models - plot logic for ols - and some basic changes to python

Author: Zak Gilliam

.gitignore

@@ -1,10 +1,72 @@
+
+############################
+# Python
+############################
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
 *$py.class
 
+# Distribution / packaging
+build/
+dist/
+*.egg-info/
+.eggs/
+
 # Virtual environments
 .venv/
 venv/
+env/
+ENV/
 .direnv/
 direnv/
+
+# Pytest cache
+.pytest_cache/
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints/
+
+# MyPy cache
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+############################
+# Rust
+############################
+# Cargo build output
+target/
+
+# Rust/Cargo lock files for local dev
+Cargo.lock
+
+# Rust incremental compilation
+**/*.rs.bk
+
+############################
+# Node.js
+############################
+# Dependency directories
+node_modules/
+
+# Build output
+dist/
+build/
+
+# Logs
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+############################
+# OS-generated files
+############################
+.DS_Store
+Thumbs.db

code/main.log

@@ -1,7 +1,26 @@
+import re
 import os
+import logging
 import pandas as pd
 from typing import Dict, List
 
+logger = logging.getLogger(__name__)
+
+_SES_RE = re.compile(r"_ses(\d+)\.csv$", re.IGNORECASE)
+
+def _max_session(dir_path: str) -> int:
+    """
+    Scan a directory and return the largest session number from files
+    named like '*_wkXX_sesNN.CSV'. Returns 0 if none found.
+    """
+    try:
+        return max(
+            (int(m.group(1)) for fn in os.listdir(dir_path)
+             if (m := _SES_RE.search(fn)) is not None),
+            default=0,
+        )
+    except FileNotFoundError:
+        return 0
 
 class Get_Data:
     """
@@ -69,7 +88,9 @@ def get_meta(self) -> Dict:
     def build_master_df(self) -> pd.DataFrame:
         """
         Create one row per subject with:
-          subject, sup_n, sup_prop, unsup_n, unsup_den, unsup_prop, unsup_prop_30
+          subject, sup_n, sup_prop, sup_den, unsup_n, unsup_den, unsup_prop, unsup_prop_30
+        - 'den' for each side is the largest session index seen in filenames.
+        - Skip subjects with fewer than 6 unsupervised sessions.
         """
         sup_subjects = set(self._list_subjects(self.sup_path))
         unsup_subjects = set(self._list_subjects(self.unsup_path))
@@ -83,19 +104,37 @@ def build_master_df(self) -> pd.DataFrame:
             sup_n = self._count_csvs(sup_dir)
             unsup_n = self._count_csvs(unsup_dir)
 
-            sup_prop = sup_n / 30.0
-            unsup_den = max(unsup_n, 0)              # how many unsup observations exist (<=30)
-            unsup_prop = (unsup_n / max(unsup_den, 1)) if unsup_den > 0 else 0.0
-            unsup_prop_30 = unsup_n / 30.0
+            # Denominator = max session index observed in filenames
+            sup_den = _max_session(sup_dir)
+            unsup_den = _max_session(unsup_dir)
+
+            logger.debug(
+                f"Subject {subj}: sup_n={sup_n}, sup_den={sup_den}, "
+                f"unsup_n={unsup_n}, unsup_den={unsup_den}"
+            )
+
+            # Skip if fewer than 6 unsupervised sessions
+            if unsup_n < 6:
+                continue
+
+            # Guard against zero denominators: if no session index found,
+            # fall back to n (prevents div-by-zero but keeps proportion meaningful)
+            sup_den_eff = sup_den if sup_den > 0 else max(sup_n, 1)
+            unsup_den_eff = unsup_den if unsup_den > 0 else max(unsup_n, 1)
+
+            sup_prop = sup_n / float(sup_den_eff)
+            unsup_prop = unsup_n / float(unsup_den_eff)
+            unsup_prop_30 = unsup_n / 30.0  # keep for reference/comparison if you still want it
 
             rows.append({
                 "subject": subj,
                 "sup_n": sup_n,
+                "sup_den": sup_den,          # raw parsed max session
                 "sup_prop": sup_prop,
                 "unsup_n": unsup_n,
-                "unsup_den": unsup_den,
-                "unsup_prop": unsup_prop,       # used by Rust CLI as y
-                "unsup_prop_30": unsup_prop_30  # optional – adherence out of 30 planned
+                "unsup_den": unsup_den,      # raw parsed max session
+                "unsup_prop": unsup_prop,    # used by Rust CLI as y
+                "unsup_prop_30": unsup_prop_30,
             })
 
         self.master = pd.DataFrame(rows)
@@ -106,12 +145,20 @@ def save_for_rust(self, out_csv: str = "data.csv") -> str:
         Save the minimal schema the Rust CLI expects:
           sup_prop (x), unsup_prop (y), unsup_den (m)
         """
-        if self.master.empty:
+        if getattr(self, "master", None) is None or self.master.empty:
             self.build_master_df()
         df = self.master[["sup_prop", "unsup_prop", "unsup_den"]].copy()
-        df.rename(columns={"sup_prop": "sup_prop",
-                           "unsup_prop": "unsup_prop",
-                           "unsup_den": "unsup_den"}, inplace=True)
         df.to_csv(out_csv, index=False)
         return out_csv
+'''
+from main import Main
+from plot.get_data import Get_Data
+import os
+main = Main(system="Home")
+path = os.path.join(main.base_path, "InterventionStudy", "3-Experiment", "data", "polarhrcsv")
+gd = Get_Data(sup_path=os.path.join(path, "Supervised"), unsup_path=os.path.join(path, "Unsupervised"), study="InterventionStudy")
+df_master = gd.build_master_df()
+gd.save_for_rust("../rust-ols-adherence-cli/data.csv")
+
 
+'''