| """ |
| Regenerate ALL figures with proper spacing, no overlapping legends/labels. |
| Each figure is single-purpose and sized for IEEE column width. |
| """ |
| import os, sys |
| sys.path.insert(0, '/app/fraud_detection') |
| import numpy as np |
| import pandas as pd |
| import matplotlib |
| matplotlib.use('Agg') |
| import matplotlib.pyplot as plt |
| import seaborn as sns |
| import joblib |
| import shap |
| import warnings |
| warnings.filterwarnings('ignore') |
|
|
| from ae_model import AutoencoderWrapper, Autoencoder |
| from sklearn.metrics import ( |
| roc_curve, precision_recall_curve, roc_auc_score, |
| average_precision_score, confusion_matrix, |
| precision_score, recall_score, f1_score, matthews_corrcoef |
| ) |
| from config import DATA_DIR, MODELS_DIR, FIGURES_DIR, FIG_DPI, FIG_BG |
|
|
| |
| plt.rcParams.update({ |
| 'font.size': 10, |
| 'axes.titlesize': 11, |
| 'axes.labelsize': 10, |
| 'xtick.labelsize': 9, |
| 'ytick.labelsize': 9, |
| 'legend.fontsize': 8, |
| 'figure.facecolor': 'white', |
| 'axes.facecolor': 'white', |
| 'savefig.facecolor': 'white', |
| 'savefig.bbox': 'tight', |
| 'savefig.dpi': 300, |
| 'figure.dpi': 100, |
| }) |
| sns.set_style("whitegrid") |
|
|
| def save(fig, name): |
| fig.savefig(os.path.join(FIGURES_DIR, f"{name}.png"), dpi=FIG_DPI, bbox_inches='tight', facecolor='white', pad_inches=0.15) |
| fig.savefig(os.path.join(FIGURES_DIR, f"{name}.pdf"), bbox_inches='tight', facecolor='white', pad_inches=0.15) |
| plt.close(fig) |
| print(f" Saved: {name}.png/pdf") |
|
|
| |
| raw_df = pd.read_csv(os.path.join(DATA_DIR, "creditcard.csv")) |
| data = joblib.load(os.path.join(DATA_DIR, "processed_data.joblib")) |
| models = joblib.load(os.path.join(MODELS_DIR, "all_models_with_ae.joblib")) |
| X_test, y_test = data['X_test'], data['y_test'] |
| feature_names = data['feature_names'] |
|
|
| print("=" * 60) |
| print("REGENERATING ALL FIGURES (fixed spacing)") |
| print("=" * 60) |
|
|
| |
| |
| |
| print("\n[1] Class distribution") |
| cc = raw_df['Class'].value_counts() |
| fig, axes = plt.subplots(1, 2, figsize=(10, 4)) |
| colors = ['#27ae60', '#e74c3c'] |
| bars = axes[0].bar(['Legitimate (0)', 'Fraud (1)'], cc.values, color=colors, edgecolor='black', lw=0.6, width=0.55) |
| axes[0].set_yscale('log') |
| axes[0].set_ylabel('Count (log scale)') |
| axes[0].set_title('(a) Transaction Counts') |
| for b, v in zip(bars, cc.values): |
| axes[0].text(b.get_x()+b.get_width()/2, v*1.15, f'{v:,}', ha='center', va='bottom', fontsize=9, fontweight='bold') |
|
|
| wedges, texts, autotexts = axes[1].pie( |
| cc.values, labels=['Legitimate\n99.827%', 'Fraud\n0.173%'], |
| colors=colors, autopct='', startangle=90, explode=(0, 0.08), |
| textprops={'fontsize': 9}, wedgeprops={'edgecolor': 'white', 'linewidth': 1.5} |
| ) |
| axes[1].set_title('(b) Fraud Ratio') |
| fig.suptitle('Class Distribution in Credit Card Fraud Dataset', fontsize=12, fontweight='bold', y=1.02) |
| fig.tight_layout() |
| save(fig, 'class_distribution') |
|
|
| |
| |
| |
| print("[2] Amount analysis") |
| fig, axes = plt.subplots(2, 2, figsize=(10, 8)) |
| legit_amt = raw_df[raw_df['Class']==0]['Amount'] |
| fraud_amt = raw_df[raw_df['Class']==1]['Amount'] |
|
|
| axes[0,0].hist(legit_amt, bins=80, color='#27ae60', alpha=0.8, edgecolor='none') |
| axes[0,0].set_title('(a) Legitimate Amounts') |
| axes[0,0].set_xlabel('Amount ($)') |
| axes[0,0].set_ylabel('Frequency') |
| axes[0,0].set_xlim(0, 1500) |
|
|
| axes[0,1].hist(fraud_amt, bins=40, color='#e74c3c', alpha=0.8, edgecolor='none') |
| axes[0,1].set_title('(b) Fraudulent Amounts') |
| axes[0,1].set_xlabel('Amount ($)') |
| axes[0,1].set_ylabel('Frequency') |
|
|
| axes[1,0].hist(np.log1p(legit_amt), bins=50, color='#27ae60', alpha=0.55, label='Legitimate', edgecolor='none') |
| axes[1,0].hist(np.log1p(fraud_amt), bins=50, color='#e74c3c', alpha=0.55, label='Fraud', edgecolor='none') |
| axes[1,0].set_title('(c) Log-Scaled Comparison') |
| axes[1,0].set_xlabel('log(1 + Amount)') |
| axes[1,0].set_ylabel('Frequency') |
| axes[1,0].legend(loc='upper right', framealpha=0.9) |
|
|
| bp = axes[1,1].boxplot( |
| [legit_amt.clip(upper=500), fraud_amt.clip(upper=500)], |
| labels=['Legitimate', 'Fraud'], patch_artist=True, widths=0.45, |
| medianprops=dict(color='black', lw=1.5) |
| ) |
| bp['boxes'][0].set_facecolor('#27ae60') |
| bp['boxes'][1].set_facecolor('#e74c3c') |
| for b in bp['boxes']: |
| b.set_alpha(0.7) |
| axes[1,1].set_title('(d) Boxplot (capped at $500)') |
| axes[1,1].set_ylabel('Amount ($)') |
|
|
| fig.suptitle('Transaction Amount Analysis by Class', fontsize=12, fontweight='bold', y=1.01) |
| fig.tight_layout() |
| save(fig, 'amount_analysis') |
|
|
| |
| |
| |
| print("[3] Time analysis") |
| raw_df_t = raw_df.copy() |
| raw_df_t['Hour'] = (raw_df_t['Time'] / 3600) % 24 |
| fig, axes = plt.subplots(1, 2, figsize=(10, 4)) |
|
|
| axes[0].hist(raw_df_t[raw_df_t['Class']==0]['Hour'], bins=48, color='#27ae60', alpha=0.55, label='Legitimate', density=True) |
| axes[0].hist(raw_df_t[raw_df_t['Class']==1]['Hour'], bins=48, color='#e74c3c', alpha=0.55, label='Fraud', density=True) |
| axes[0].set_title('(a) Transaction Density by Hour') |
| axes[0].set_xlabel('Hour of Day') |
| axes[0].set_ylabel('Density') |
| axes[0].legend(loc='upper left', framealpha=0.9) |
|
|
| hourly = raw_df_t.groupby(raw_df_t['Hour'].astype(int))['Class'].mean() * 100 |
| axes[1].bar(hourly.index, hourly.values, color='#e74c3c', alpha=0.75, edgecolor='black', lw=0.3) |
| axes[1].set_title('(b) Fraud Rate by Hour') |
| axes[1].set_xlabel('Hour of Day') |
| axes[1].set_ylabel('Fraud Rate (%)') |
|
|
| fig.suptitle('Temporal Patterns in Transaction Data', fontsize=12, fontweight='bold', y=1.02) |
| fig.tight_layout() |
| save(fig, 'time_analysis') |
|
|
| |
| |
| |
| print("[4] Correlation heatmap") |
| corrs = raw_df.corr()['Class'].drop('Class').sort_values() |
| fig, ax = plt.subplots(figsize=(8, 7)) |
| colors_bar = ['#e74c3c' if v < 0 else '#27ae60' for v in corrs.values] |
| ax.barh(corrs.index, corrs.values, color=colors_bar, edgecolor='none', height=0.7) |
| ax.set_xlabel('Pearson Correlation with Fraud Class') |
| ax.set_title('Feature Correlation with Fraud', fontsize=12, fontweight='bold') |
| ax.axvline(x=0, color='black', lw=0.5) |
| ax.tick_params(axis='y', labelsize=8) |
| fig.tight_layout() |
| save(fig, 'correlation_heatmap') |
|
|
| |
| |
| |
| print("[5] Feature distributions") |
| top6 = corrs.abs().sort_values(ascending=False).head(6).index.tolist() |
| fig, axes = plt.subplots(2, 3, figsize=(12, 7)) |
| axes = axes.ravel() |
| for i, feat in enumerate(top6): |
| axes[i].hist(raw_df[raw_df['Class']==0][feat], bins=50, color='#27ae60', alpha=0.5, label='Legit', density=True) |
| axes[i].hist(raw_df[raw_df['Class']==1][feat], bins=50, color='#e74c3c', alpha=0.5, label='Fraud', density=True) |
| axes[i].set_title(feat, fontweight='bold') |
| axes[i].legend(loc='upper right', fontsize=7, framealpha=0.9) |
| axes[i].set_ylabel('Density') |
| fig.suptitle('Distribution of Top 6 Discriminative Features by Class', fontsize=12, fontweight='bold', y=1.01) |
| fig.tight_layout() |
| save(fig, 'feature_distributions') |
|
|
| |
| |
| |
| print("[6] ROC curves") |
| top_models = ['XGBoost', 'Voting_Ensemble', 'XGBoost_Tuned', 'Random_Forest_Tuned', 'LightGBM_Tuned'] |
| cmap = plt.cm.Set1 |
| fig, ax = plt.subplots(figsize=(7, 6)) |
| for i, name in enumerate(top_models): |
| if name not in models: continue |
| proba = models[name].predict_proba(X_test)[:, 1] |
| fpr, tpr, _ = roc_curve(y_test, proba) |
| auc_val = roc_auc_score(y_test, proba) |
| ax.plot(fpr, tpr, color=cmap(i), lw=2, label=f'{name.replace("_"," ")} ({auc_val:.4f})') |
| ax.plot([0,1],[0,1],'k--', lw=0.8, label='Random Baseline') |
| ax.set_xlabel('False Positive Rate') |
| ax.set_ylabel('True Positive Rate') |
| ax.set_title('ROC Curves — Top 5 Models', fontsize=12, fontweight='bold') |
| ax.legend(loc='lower right', fontsize=8, framealpha=0.95) |
| ax.set_xlim([-0.01, 1.01]) |
| ax.set_ylim([-0.01, 1.03]) |
| fig.tight_layout() |
| save(fig, 'roc_curves') |
|
|
| |
| |
| |
| print("[7] PR curves") |
| fig, ax = plt.subplots(figsize=(7, 6)) |
| for i, name in enumerate(top_models): |
| if name not in models: continue |
| proba = models[name].predict_proba(X_test)[:, 1] |
| prec, rec, _ = precision_recall_curve(y_test, proba) |
| ap = average_precision_score(y_test, proba) |
| ax.plot(rec, prec, color=cmap(i), lw=2, label=f'{name.replace("_"," ")} ({ap:.4f})') |
| baseline = y_test.mean() |
| ax.axhline(y=baseline, color='k', ls='--', lw=0.8, label=f'Baseline ({baseline:.4f})') |
| ax.set_xlabel('Recall') |
| ax.set_ylabel('Precision') |
| ax.set_title('Precision-Recall Curves — Top 5 Models', fontsize=12, fontweight='bold') |
| ax.legend(loc='upper right', fontsize=8, framealpha=0.95) |
| ax.set_xlim([-0.01, 1.01]) |
| ax.set_ylim([-0.01, 1.03]) |
| fig.tight_layout() |
| save(fig, 'pr_curves') |
|
|
| |
| |
| |
| print("[8] Confusion matrices") |
| cm_models = ['XGBoost', 'Voting_Ensemble', 'Random_Forest_Tuned', 'LightGBM_Tuned', 'MLP', 'Logistic_Regression'] |
| fig, axes = plt.subplots(2, 3, figsize=(13, 8)) |
| axes = axes.ravel() |
| for i, name in enumerate(cm_models): |
| if name not in models: continue |
| proba = models[name].predict_proba(X_test)[:, 1] |
| preds = (proba >= 0.5).astype(int) |
| cm = confusion_matrix(y_test, preds) |
| sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', ax=axes[i], |
| xticklabels=['Legit', 'Fraud'], yticklabels=['Legit', 'Fraud'], |
| cbar=False, annot_kws={'size': 10}) |
| axes[i].set_title(name.replace('_', ' '), fontsize=10, fontweight='bold') |
| axes[i].set_ylabel('Actual') |
| axes[i].set_xlabel('Predicted') |
| fig.suptitle('Confusion Matrices on Test Set (threshold = 0.5)', fontsize=12, fontweight='bold', y=1.01) |
| fig.tight_layout() |
| save(fig, 'confusion_matrices') |
|
|
| |
| |
| |
| print("[9] Threshold analysis") |
| proba_xgb = models['XGBoost'].predict_proba(X_test)[:, 1] |
| thresholds = np.arange(0.05, 0.96, 0.025) |
| rows = [] |
| for t in thresholds: |
| p = (proba_xgb >= t).astype(int) |
| rows.append({'t': t, 'Prec': precision_score(y_test, p, zero_division=0), |
| 'Rec': recall_score(y_test, p, zero_division=0), |
| 'F1': f1_score(y_test, p, zero_division=0), |
| 'MCC': matthews_corrcoef(y_test, p)}) |
| dt = pd.DataFrame(rows) |
| best_t = dt.loc[dt['F1'].idxmax(), 't'] |
|
|
| fig, axes = plt.subplots(1, 2, figsize=(10, 4.5)) |
| axes[0].plot(dt['t'], dt['Prec'], 'b-', lw=2, label='Precision') |
| axes[0].plot(dt['t'], dt['Rec'], 'r-', lw=2, label='Recall') |
| axes[0].plot(dt['t'], dt['F1'], 'g-', lw=2.5, label='F1 Score') |
| axes[0].axvline(x=best_t, color='gray', ls='--', lw=1.2, label=f'Optimal ({best_t:.2f})') |
| axes[0].set_xlabel('Decision Threshold') |
| axes[0].set_ylabel('Score') |
| axes[0].set_title('(a) Precision / Recall / F1', fontweight='bold') |
| axes[0].legend(loc='center left', framealpha=0.95, fontsize=8) |
|
|
| axes[1].plot(dt['t'], dt['MCC'], 'm-', lw=2, label='MCC') |
| axes[1].axvline(x=best_t, color='gray', ls='--', lw=1.2) |
| axes[1].set_xlabel('Decision Threshold') |
| axes[1].set_ylabel('MCC') |
| axes[1].set_title('(b) Matthews Correlation Coefficient', fontweight='bold') |
| axes[1].legend(loc='upper right', framealpha=0.95, fontsize=8) |
|
|
| fig.suptitle(f'Threshold Sensitivity Analysis — XGBoost (Optimal = {best_t:.2f})', fontsize=12, fontweight='bold', y=1.02) |
| fig.tight_layout() |
| save(fig, 'threshold_analysis') |
|
|
| |
| |
| |
| print("[10] Feature importance") |
| fig, axes = plt.subplots(2, 2, figsize=(12, 10)) |
| tree_map = {'(a) Random Forest': 'Random_Forest_Tuned', '(b) XGBoost': 'XGBoost_Tuned', '(c) LightGBM': 'LightGBM_Tuned'} |
| for idx, (title, key) in enumerate(tree_map.items()): |
| r, c = idx // 2, idx % 2 |
| m = models[key] |
| imp = m.feature_importances_ |
| top_idx = np.argsort(imp)[-12:] |
| axes[r,c].barh(range(len(top_idx)), imp[top_idx], color='steelblue', edgecolor='none', height=0.7) |
| axes[r,c].set_yticks(range(len(top_idx))) |
| axes[r,c].set_yticklabels([feature_names[j] for j in top_idx], fontsize=8) |
| axes[r,c].set_xlabel('Importance') |
| axes[r,c].set_title(title, fontweight='bold') |
|
|
| lr = models['Logistic_Regression'] |
| coefs = np.abs(lr.coef_[0]) |
| top_idx = np.argsort(coefs)[-12:] |
| axes[1,1].barh(range(len(top_idx)), coefs[top_idx], color='coral', edgecolor='none', height=0.7) |
| axes[1,1].set_yticks(range(len(top_idx))) |
| axes[1,1].set_yticklabels([feature_names[j] for j in top_idx], fontsize=8) |
| axes[1,1].set_xlabel('|Coefficient|') |
| axes[1,1].set_title('(d) Logistic Regression', fontweight='bold') |
| fig.suptitle('Feature Importance Across Models (Top 12)', fontsize=12, fontweight='bold', y=1.0) |
| fig.tight_layout() |
| save(fig, 'feature_importance') |
|
|
| |
| |
| |
| print("[11] SHAP summary") |
| explainer = shap.TreeExplainer(models['XGBoost']) |
| X_sample = X_test.iloc[:2000] |
| shap_vals = explainer.shap_values(X_sample) |
| if isinstance(shap_vals, list): |
| shap_vals = shap_vals[1] |
|
|
| plt.figure(figsize=(9, 7)) |
| shap.summary_plot(shap_vals, X_sample, feature_names=feature_names, show=False, max_display=15, plot_size=None) |
| plt.title('SHAP Feature Impact on Fraud Prediction (XGBoost)', fontsize=11, fontweight='bold', pad=12) |
| plt.tight_layout() |
| plt.savefig(os.path.join(FIGURES_DIR, "shap_summary.png"), dpi=FIG_DPI, bbox_inches='tight', facecolor='white', pad_inches=0.15) |
| plt.savefig(os.path.join(FIGURES_DIR, "shap_summary.pdf"), bbox_inches='tight', facecolor='white', pad_inches=0.15) |
| plt.close('all') |
| print(" Saved: shap_summary.png/pdf") |
|
|
| |
| |
| |
| print("[12] SHAP top 10") |
| mean_shap = np.abs(shap_vals).mean(axis=0) |
| fi = pd.DataFrame({'Feature': feature_names, 'SHAP': mean_shap}).sort_values('SHAP', ascending=False) |
| top10 = fi.head(10) |
| fig, ax = plt.subplots(figsize=(7, 5)) |
| ax.barh(range(10), top10['SHAP'].values[::-1], color='steelblue', edgecolor='none', height=0.6) |
| ax.set_yticks(range(10)) |
| ax.set_yticklabels(top10['Feature'].values[::-1]) |
| ax.set_xlabel('Mean |SHAP Value|') |
| ax.set_title('Top 10 Features Driving Fraud Predictions', fontsize=11, fontweight='bold') |
| fig.tight_layout() |
| save(fig, 'shap_top10') |
|
|
| |
| |
| |
| print("[13] LIME explanation") |
| from lime.lime_tabular import LimeTabularExplainer |
| proba_all = models['XGBoost'].predict_proba(X_test)[:, 1] |
| fraud_idx = np.where(y_test == 1)[0] |
| sample_idx = None |
| for idx in fraud_idx: |
| if proba_all[idx] > 0.5: |
| sample_idx = idx |
| break |
| if sample_idx is None: |
| sample_idx = fraud_idx[0] |
|
|
| X_np = X_test.values |
| lime_exp = LimeTabularExplainer(X_np, feature_names=feature_names, class_names=['Legit', 'Fraud'], discretize_continuous=True, random_state=42) |
| explanation = lime_exp.explain_instance(X_np[sample_idx], models['XGBoost'].predict_proba, num_features=12, top_labels=1) |
| exp_list = explanation.as_list(label=1) |
| feats = [f for f, w in exp_list] |
| weights = [w for f, w in exp_list] |
| cols = ['#e74c3c' if w > 0 else '#27ae60' for w in weights] |
|
|
| fig, ax = plt.subplots(figsize=(9, 6)) |
| ax.barh(range(len(feats)), weights, color=cols, edgecolor='none', height=0.6) |
| ax.set_yticks(range(len(feats))) |
| ax.set_yticklabels(feats, fontsize=8) |
| ax.set_xlabel('Feature Contribution') |
| ax.set_title(f'LIME Explanation — Fraud Sample (P = {proba_all[sample_idx]:.4f})', fontsize=11, fontweight='bold') |
| ax.axvline(x=0, color='black', lw=0.5) |
| from matplotlib.patches import Patch |
| ax.legend(handles=[Patch(fc='#e74c3c', label='Increases fraud risk'), Patch(fc='#27ae60', label='Decreases fraud risk')], |
| loc='lower right', fontsize=8, framealpha=0.95) |
| fig.tight_layout() |
| save(fig, 'lime_explanation') |
|
|
| |
| |
| |
| print("[14] Error analysis") |
| proba_xgb = models['XGBoost'].predict_proba(X_test)[:, 1] |
| preds = (proba_xgb >= 0.5).astype(int) |
| fn_mask = (preds == 0) & (y_test.values == 1) |
| fp_mask = (preds == 1) & (y_test.values == 0) |
| fn_proba = proba_xgb[fn_mask] |
| fp_proba = proba_xgb[fp_mask] |
|
|
| fig, axes = plt.subplots(1, 3, figsize=(14, 4.5)) |
| if fn_mask.sum() > 0: |
| axes[0].hist(fn_proba, bins=15, color='#e74c3c', alpha=0.75, edgecolor='black', lw=0.3) |
| axes[0].axvline(x=0.5, color='black', ls='--', lw=1, label='Threshold') |
| axes[0].set_title('(a) Missed Fraud (FN)', fontweight='bold') |
| axes[0].set_xlabel('Predicted P(Fraud)') |
| axes[0].set_ylabel('Count') |
| axes[0].legend(fontsize=8) |
|
|
| if fp_mask.sum() > 0: |
| axes[1].hist(fp_proba, bins=15, color='#f39c12', alpha=0.75, edgecolor='black', lw=0.3) |
| axes[1].axvline(x=0.5, color='black', ls='--', lw=1, label='Threshold') |
| axes[1].set_title('(b) False Alarms (FP)', fontweight='bold') |
| axes[1].set_xlabel('Predicted P(Fraud)') |
| axes[1].set_ylabel('Count') |
| axes[1].legend(fontsize=8) |
|
|
| axes[2].hist(proba_xgb[y_test.values==0], bins=50, color='#27ae60', alpha=0.5, label='Legit', density=True) |
| axes[2].hist(proba_xgb[y_test.values==1], bins=50, color='#e74c3c', alpha=0.5, label='Fraud', density=True) |
| axes[2].axvline(x=0.5, color='black', ls='--', lw=1, label='Threshold') |
| axes[2].set_title('(c) Score Distribution by Class', fontweight='bold') |
| axes[2].set_xlabel('Predicted P(Fraud)') |
| axes[2].set_ylabel('Density') |
| axes[2].legend(fontsize=8, loc='upper center') |
|
|
| fig.suptitle('Error Analysis — XGBoost Predictions', fontsize=12, fontweight='bold', y=1.02) |
| fig.tight_layout() |
| save(fig, 'error_analysis') |
|
|
| |
| |
| |
| print("[15] Architecture diagram") |
| from matplotlib.patches import FancyBboxPatch |
| fig, ax = plt.subplots(figsize=(14, 9), facecolor='white') |
| ax.set_xlim(0, 14) |
| ax.set_ylim(0, 10) |
| ax.axis('off') |
|
|
| c_in, c_proc, c_mod, c_out, c_stor = '#3498db', '#27ae60', '#c0392b', '#f39c12', '#8e44ad' |
|
|
| def bx(x, y, w, h, txt, col, fs=9): |
| r = FancyBboxPatch((x,y), w, h, boxstyle="round,pad=0.12", fc=col, ec='#2c3e50', lw=1.5, alpha=0.88) |
| ax.add_patch(r) |
| ax.text(x+w/2, y+h/2, txt, ha='center', va='center', fontsize=fs, fontweight='bold', color='white', multialignment='center') |
|
|
| def ar(x1,y1,x2,y2): |
| ax.annotate('', xy=(x2,y2), xytext=(x1,y1), arrowprops=dict(arrowstyle='->', color='#2c3e50', lw=1.8)) |
|
|
| ax.text(7, 9.4, 'Fraud Detection System — End-to-End Architecture', ha='center', fontsize=14, fontweight='bold', color='#2c3e50') |
|
|
| |
| bx(0.3, 7.8, 2.8, 0.9, 'Transaction\nInput', c_in, 10) |
| bx(3.8, 7.8, 2.8, 0.9, 'Feature\nEngineering\n(12 new features)', c_proc, 8) |
| bx(7.3, 7.8, 2.8, 0.9, 'RobustScaler\n(train-only fit)', c_proc, 8) |
| bx(10.8, 7.8, 2.8, 0.9, 'Drift\nMonitoring', c_stor, 9) |
| ar(3.1, 8.25, 3.8, 8.25) |
| ar(6.6, 8.25, 7.3, 8.25) |
| ar(10.1, 8.25, 10.8, 8.25) |
|
|
| |
| model_names = ['LR', 'RF', 'XGBoost\n(BEST)', 'LightGBM', 'MLP', 'Auto-\nencoder'] |
| for i, mn in enumerate(model_names): |
| bx(0.3 + i*2.3, 5.5, 2.0, 1.0, mn, c_mod, 8) |
| ar(8.7, 7.8, 0.3+i*2.3+1.0, 6.5) |
|
|
| |
| bx(2.5, 3.2, 3.5, 1.0, 'Optuna\nHyperparameter\nTuning (TPE)', c_stor, 9) |
| bx(7.5, 3.2, 3.5, 1.0, 'Voting Ensemble\n(XGB + LGBM + RF)', c_out, 9) |
| ar(6.0, 3.7, 7.5, 3.7) |
|
|
| |
| bx(2.5, 1.0, 3.5, 1.0, 'FastAPI\nPOST /predict\n< 10 ms', c_in, 9) |
| bx(7.5, 1.0, 3.5, 1.0, 'Explainability\nSHAP + LIME', c_proc, 9) |
| ar(9.25, 3.2, 9.25, 2.0) |
| ar(4.25, 3.2, 4.25, 2.0) |
|
|
| fig.tight_layout() |
| save(fig, 'architecture_diagram') |
|
|
| print("\n" + "=" * 60) |
| print("ALL 15 FIGURES REGENERATED SUCCESSFULLY") |
| print("=" * 60) |
|
|
