metadata_dict = metadata.to_dict() diagnostic = DiagnosticReport() diagnostic.generate(real_data=real, synthetic_data=synthetic_sdv, metadata=metadata_dict, verbose=True) print("Diagnostic score:", diagnostic.get_score()) quality = QualityReport() quality.generate(real_data=real, synthetic_data=synthetic_sdv, metadata=metadata_dict, verbose=True) print("Quality score:", quality.get_score()) def show_report_details(report, title): print(f"\n===== {title} details =====") props = report.get_properties() for p in props: print(f"\n--- {p} ---") details = report.get_details(property_name=p) try: display(details.head(10)) except Exception: display(details) show_report_details(diagnostic, "DiagnosticReport") show_report_details(quality, "QualityReport") train_real, test_real = train_test_split( real, test_size=0.25, random_state=42, stratify=real ) def make_pipeline(cat_cols, num_cols): pre = ColumnTransformer( transformers=[ ("cat", OneHotEncoder(handle_unknown="ignore"), cat_cols), ("num", "passthrough", num_cols), ], remainder="drop" ) clf = LogisticRegression(max_iter=200) return Pipeline([("pre", pre), ("clf", clf)]) pipe_syn = make_pipeline(categorical_cols, numerical_cols) pipe_syn.fit(synthetic_sdv.drop(columns=), synthetic_sdv) proba_syn = pipe_syn.predict_proba(test_real.drop(columns=))[:, 1] y_true = (test_real.astype(str).str.contains(">")).astype(int) auc_syn = roc_auc_score(y_true, proba_syn) print("Synthetic-train -> Real-test AUC:", auc_syn) pipe_real = make_pipeline(categorical_cols, numerical_cols) pipe_real.fit(train_real.drop(columns=), train_real) proba_real = pipe_real.predict_proba(test_real.drop(columns=))[:, 1] auc_real = roc_auc_score(y_true, proba_real) print("Real-train -> Real-test AUC:", auc_real) model_path = "ctgan_sdv_synth.pkl" synth.save(model_path) print("Saved synthesizer to:", model_path) from sdv.utils import load_synthesizer synth_loaded = load_synthesizer(model_path) synthetic_loaded = synth_loaded.sample(1000) print("Loaded synthesizer sample:") display(synthetic_loaded.head())

metadata_dict = metadata.to_dict() diagnostic = DiagnosticReport() diagnostic.generate(real_data=real, synthetic_data=synthetic_sdv, metadata=metadata_dict, verbose=True) print("Diagnostic score:", diagnostic.get_score()) quality = QualityReport() quality.generate(real_data=real, synthetic_data=synthetic_sdv, metadata=metadata_dict, verbose=True) print("Quality score:", quality.get_score()) def show_report_details(report, title): print(f"\n===== {title} details =====") props = report.get_properties() for p in props: print(f"\n--- {p} ---") details = report.get_details(property_name=p) try: display(details.head(10)) except Exception: display(details) show_report_details(diagnostic, "DiagnosticReport") show_report_details(quality, "QualityReport") train_real, test_real = train_test_split( real, test_size=0.25, random_state=42, stratify=real ) def make_pipeline(cat_cols, num_cols): pre = ColumnTransformer( transformers=[ ("cat", OneHotEncoder(handle_unknown="ignore"), cat_cols), ("num", "passthrough", num_cols), ], remainder="drop" ) clf = LogisticRegression(max_iter=200) return Pipeline([("pre", pre), ("clf", clf)]) pipe_syn = make_pipeline(categorical_cols, numerical_cols) pipe_syn.fit(synthetic_sdv.drop(columns=), synthetic_sdv) proba_syn = pipe_syn.predict_proba(test_real.drop(columns=))[:, 1] y_true = (test_real.astype(str).str.contains(">")).astype(int) auc_syn = roc_auc_score(y_true, proba_syn) print("Synthetic-train -> Real-test AUC:", auc_syn) pipe_real = make_pipeline(categorical_cols, numerical_cols) pipe_real.fit(train_real.drop(columns=), train_real) proba_real = pipe_real.predict_proba(test_real.drop(columns=))[:, 1] auc_real = roc_auc_score(y_true, proba_real) print("Real-train -> Real-test AUC:", auc_real) model_path = "ctgan_sdv_synth.pkl" synth.save(model_path) print("Saved synthesizer to:", model_path) from sdv.utils import load_synthesizer synth_loaded = load_synthesizer(model_path) synthetic_loaded = synth_loaded.sample(1000) print("Loaded synthesizer sample:") display(synthetic_loaded.head())