Adjsuting and cleaning

Data/show_plots.py

@@ -1828,6 +1828,97 @@ plt.tight_layout()
 plt.show()
 ##
 
+
+
+# %% name
+import pandas as pd
+import matplotlib.pyplot as plt
+import os
+import numpy as np
+
+# --- Configuration & Theme ---
+plt.rcParams['font.family'] = 'Arial'
+figure_save_path = 'project/visuals/functional_systems_magnitude_focus.svg'
+
+# --- 1. Process Error Data with Magnitude Breakdown ---
+system_names = [name.split('.')[1] for name, _ in functional_systems_to_plot]
+plot_list = []
+
+for gt_col, res_col in functional_systems_to_plot:
+    sys_name = gt_col.split('.')[1]
+
+    # Robust parsing
+    gt = df[gt_col].apply(safe_parse)
+    res = df[res_col].apply(safe_parse)
+    error = res - gt
+
+    # Granular Counts
+    matches = (error == 0).sum()
+    u_1 = (error == -1).sum()
+    u_2plus = (error <= -2).sum()
+    o_1 = (error == 1).sum()
+    o_2plus = (error >= 2).sum()
+
+    total = error.dropna().count()
+    divisor = max(total, 1)
+
+    plot_list.append({
+        'System': sys_name.replace('_', ' ').title(),
+        'Matches': matches, 'MatchPct': (matches / divisor) * 100,
+        'U1': u_1, 'U2': u_2plus, 'UnderTotal': u_1 + u_2plus,
+        'UnderPct': ((u_1 + u_2plus) / divisor) * 100,
+        'O1': o_1, 'O2': o_2plus, 'OverTotal': o_1 + o_2plus,
+        'OverPct': ((o_1 + o_2plus) / divisor) * 100
+    })
+
+stats_df = pd.DataFrame(plot_list)
+
+# --- 2. Plotting ---
+fig, ax = plt.subplots(figsize=(13, 8))
+
+# Define Magnitude Colors
+c_under_dark, c_under_light = '#C0392B', '#E74C3C' # Dark Red (-2+), Soft Red (-1)
+c_over_dark, c_over_light   = '#2980B9', '#3498DB' # Dark Blue (+2+), Soft Blue (+1)
+bar_height = 0.6
+y_pos = np.arange(len(stats_df))
+
+# Plot Under-scored (Stacked: -2+ then -1)
+ax.barh(y_pos, -stats_df['U2'], bar_height, color=c_under_dark, label='Under -2+', edgecolor='white')
+ax.barh(y_pos, -stats_df['U1'], bar_height, left=-stats_df['U2'], color=c_under_light, label='Under -1', edgecolor='white')
+
+# Plot Over-scored (Stacked: +1 then +2+)
+ax.barh(y_pos, stats_df['O1'], bar_height, color=c_over_light, label='Over +1', edgecolor='white')
+ax.barh(y_pos, stats_df['O2'], bar_height, left=stats_df['O1'], color=c_over_dark, label='Over +2+', edgecolor='white')
+
+# --- 3. Aesthetics & Table Labels ---
+for i, row in stats_df.iterrows():
+    label_text = (
+        f"$\\mathbf{{{row['System']}}}$\n"
+        f"Match: {int(row['Matches'])} ({row['MatchPct']:.1f}%)\n"
+        f"Under: {int(row['UnderTotal'])} ({row['UnderPct']:.1f}%) | Over: {int(row['OverTotal'])} ({row['OverPct']:.1f}%)"
+    )
+    # Position table text to the left
+    ax.text(ax.get_xlim()[0] - 0.5, i, label_text, va='center', ha='right', fontsize=9, color='#333333', linespacing=1.4)
+
+# Formatting
+ax.axvline(0, color='black', linewidth=1.2)
+ax.set_yticks([])
+ax.set_xlabel('Number of Patients with Error', fontsize=11, fontweight='bold')
+#ax.set_title('Directional Error Magnitude (Under vs. Over Scoring)', fontsize=14, pad=35)
+
+# Absolute X-axis labels
+ax.set_xticklabels([int(abs(tick)) for tick in ax.get_xticks()])
+
+# Remove spines and add grid
+for spine in ['top', 'right', 'left']: ax.spines[spine].set_visible(False)
+ax.xaxis.grid(True, linestyle='--', alpha=0.3)
+
+# Legend with magnitude info
+ax.legend(loc='upper right', frameon=False, bbox_to_anchor=(1, 1.1), ncol=2)
+
+plt.tight_layout()
+plt.show()
+##
 # %% test
 # Diagnose: what are the actual differences?
 print("\n🔍 Raw differences (first 5 rows per system):")