Data Report — UCI_1150

SemMap JSON-LD: dataset.semmap.json · RDFa HTML

Overview

Metric	Value
Dataset	UCI_1150
Source	UCI dataset 1150
Rows	319
Columns	39
Discrete	8
Continuous	31
SemMap	SemMap JSON-LD SemMap HTML
Missingness	Not modeled

Variables and summary

variable	inferred	dist
Gallstone Status	discrete	Gallstones absent [1]: 158 (49.53%)
Age	continuous	48.0690 ± 12.1146 [20, 38.5, 49, 56, 96]
Gender	discrete	Female [1]: 157 (49.22%)
Comorbidity	discrete	0: 217 (68.03%) 1: 99 (31.03%) 3: 2 (0.63%) 2: 1 (0.31%)
Coronary Artery Disease (CAD)	discrete	1: 12 (3.76%)
Hypothyroidism	discrete	1: 9 (2.82%)
Hyperlipidemia	discrete	1: 8 (2.51%)
Diabetes Mellitus (DM)	discrete	1: 43 (13.48%)
Height	continuous	167.1567 ± 10.0530 [145, 159.5, 168, 175, 191]
Weight	continuous	80.5649 ± 15.7091 [42.9, 69.6, 78.8, 91.25, 143.5]
Body Mass Index (BMI)	continuous	28.8771 ± 5.3137 [17.4, 25.25, 28.3, 31.85, 49.7]
Total Body Water (TBW)	continuous	40.5878 ± 7.9302 [13, 34.2, 39.8, 47, 66.2]
Extracellular Water (ECW)	continuous	17.0712 ± 3.1619 [9, 14.8, 17.1, 19.4, 27.8]
Intracellular Water (ICW)	continuous	23.6345 ± 5.3493 [13.8, 19.3, 23, 27.55, 57.1]
Extracellular Fluid/Total Body Water (ECF/TBW)	continuous	42.2120 ± 3.2445 [29.23, 40.075, 42, 44, 52]
Total Body Fat Ratio (TBFR) (%)	continuous	28.2750 ± 8.4444 [6.3, 22.025, 27.82, 34.81, 50.92]
Lean Mass (LM) (%)	continuous	71.6382 ± 8.4376 [48.99, 65.165, 72.11, 77.85, 93.67]
Body Protein Content (Protein) (%)	continuous	15.9388 ± 2.3347 [5.56, 14.465, 15.87, 17.43, 24.81]
Visceral Fat Rating (VFR)	continuous	9.0784 ± 4.3325 [1, 6, 9, 12, 31]
Bone Mass (BM)	continuous	2.8033 ± 0.5095 [1.4, 2.4, 2.8, 3.2, 4]
Muscle Mass (MM)	continuous	54.2730 ± 10.6038 [4.7, 45.8, 53.9, 62.6, 78.8]
Obesity (%)	continuous	35.8501 ± 109.7997 [0.4, 13.9, 25.6, 41.75, 1954]
Total Fat Content (TFC)	continuous	23.4878 ± 9.6076 [3.1, 17, 22.6, 28.55, 62.5]
Visceral Fat Area (VFA)	continuous	12.1716 ± 5.2622 [0.9, 8.57, 11.59, 15.1, 41]
Visceral Muscle Area (VMA) (Kg)	continuous	30.4034 ± 4.4605 [18.9, 27.25, 30.4081, 33.8, 41.1]
Hepatic Fat Accumulation (HFA)	discrete	0: 129 (40.44%) 2: 122 (38.24%) 1: 41 (12.85%) 3: 26 (8.15%) 4: 1 (0.31%)
Glucose	continuous	108.6887 ± 44.8487 [69, 92, 98, 109, 575]
Total Cholesterol (TC)	continuous	203.4953 ± 45.7585 [60, 172, 198, 233, 360]
Low Density Lipoprotein (LDL)	continuous	126.6524 ± 38.5412 [11, 100.5, 122, 151, 293]
High Density Lipoprotein (HDL)	continuous	49.4755 ± 17.7187 [25, 40, 46.5, 56, 273]
Triglyceride	continuous	144.5022 ± 97.9045 [1.39, 83, 119, 172, 838]
Aspartat Aminotransferaz (AST)	continuous	21.6850 ± 16.6976 [8, 15, 18, 23, 195]
Alanin Aminotransferaz (ALT)	continuous	26.8558 ± 27.8844 [3, 14.25, 19, 30, 372]
Alkaline Phosphatase (ALP)	continuous	73.1125 ± 24.1811 [7, 58, 71, 86, 197]
Creatinine	continuous	0.8006 ± 0.1764 [0.46, 0.65, 0.79, 0.92, 1.46]
Glomerular Filtration Rate (GFR)	continuous	100.8189 ± 16.9714 [10.6, 94.17, 104, 110.745, 132]
C-Reactive Protein (CRP)	continuous	1.8539 ± 4.9896 [0, 0, 0.215, 1.615, 43.4]
Hemoglobin (HGB)	continuous	14.4182 ± 1.7758 [8.5, 13.3, 14.4, 15.7, 18.8]
Vitamin D	continuous	21.4014 ± 9.9817 [3.5, 13.25, 22, 28.06, 53.1]

Fidelity summary

model	backend	disc jsd mean	disc jsd median	cont ks mean	cont w1 mean	downstream sign match
metasyn	metasyn	0.0243	0.0107	0.0934	2.3584	1
clg_mi2	pybnesian	0.0238	0.0192	0.1047	4.2669
semi_mi5	pybnesian	0.0218	0.0189	0.0985	3.4149
ctgan_fast	synthcity	0.1235	0.0649	0.8082	34.5586
tvae_quick	synthcity	0.0792	0.0944	0.2344	5.3212

Privacy summary

model	backend	n real	n synth	near duplicate rate eps	nn distance mean	k min	k pct lt5	k map	delta presence
metasyn	metasyn	319	319	0.9906	0.0128	1	1	1	3
clg_mi2	pybnesian	319	319	0.9969	0.0139	1	1	1	3.6154
semi_mi5	pybnesian	319	319	0.9969	0.0129	1	1	1	3
ctgan_fast	synthcity	319	319	0.9749	0.1023	1	1	1	137
tvae_quick	synthcity	319	319	0.9906	0.0241	1	1	2	14.3333

Models

UMAP Details Structure

Real data

Model: metasyn (metasyn)

Seed: 42, rows: 319
Missingness: wrapped (random state 42) via pipeline
Synthetic CSV
Per-variable metrics
Metrics JSON
Privacy metrics
Downstream metrics

Per-variable fidelity

variable	type	KS	W1	JSD
Gallstone Status	discrete			0.0053
Age	continuous	0.069	0.9299
Gender	discrete			0.0186
Comorbidity	discrete			0.1044
Coronary Artery Disease (CAD)	discrete			0
Hypothyroidism	discrete			0
Hyperlipidemia	discrete			0.0161
Diabetes Mellitus (DM)	discrete			0.0039
Height	continuous	0.1223	1.3322
Weight	continuous	0.0721	1.5836

Downstream metrics

metric	value
sign_match_rate	1
formula	Gallstone_Status ~ Q('Age') + Q('Gender') + Q('Glucose') + Q('Age'):Q('Gender') + Q('Gender'):Q('Glucose')
skipped_reason

Privacy metrics

metric	value
n_real	319
n_synth	319
exact_overlap_rate	0
near_duplicate_rate_eps	0.9906
nn_distance_mean	0.0128
k_min	1
k_pct_lt5	1
k_map	1
rare_qi_reproduction_rate	0
delta_presence	3

variable	distribution
Gallstone Status	core.multinoulli
Age	core.normal
Gender	core.multinoulli
Comorbidity	core.multinoulli
Coronary Artery Disease (CAD)	core.multinoulli
Hypothyroidism	core.multinoulli
Hyperlipidemia	core.multinoulli
Diabetes Mellitus (DM)	core.multinoulli
Height	core.truncated_normal
Weight	core.lognormal
Body Mass Index (BMI)	core.lognormal
Total Body Water (TBW)	core.normal
Extracellular Water (ECW)	core.normal
Intracellular Water (ICW)	core.lognormal
Extracellular Fluid/Total Body Water (ECF/TBW)	core.normal
Total Body Fat Ratio (TBFR) (%)	core.normal
Lean Mass (LM) (%)	core.normal
Body Protein Content (Protein) (%)	core.normal
Visceral Fat Rating (VFR)	core.truncated_normal
Bone Mass (BM)	core.lognormal
Muscle Mass (MM)	core.normal
Obesity (%)	core.lognormal
Total Fat Content (TFC)	core.lognormal
Visceral Fat Area (VFA)	core.lognormal
Visceral Muscle Area (VMA) (Kg)	core.normal
Hepatic Fat Accumulation (HFA)	core.multinoulli
Glucose	core.truncated_normal
Total Cholesterol (TC)	core.normal
Low Density Lipoprotein (LDL)	core.normal
High Density Lipoprotein (HDL)	core.lognormal
Triglyceride	core.lognormal
Aspartat Aminotransferaz (AST)	core.lognormal
Alanin Aminotransferaz (ALT)	core.lognormal
Alkaline Phosphatase (ALP)	core.normal
Creatinine	core.lognormal
Glomerular Filtration Rate (GFR)	core.truncated_normal
C-Reactive Protein (CRP)	core.truncated_normal
Hemoglobin (HGB)	core.normal
Vitamin D	core.truncated_normal

Model: clg_mi2 (pybnesian)

Seed: 42, rows: 319
Params: {"max_indegree": 2, "operators": ["arcs"], "score": "bic", "type": "clg"}
Missingness: wrapped (random state 42) via pipeline
Synthetic CSV
Per-variable metrics
Metrics JSON
Privacy metrics

Per-variable fidelity

variable	type	KS	W1	JSD
Gallstone Status	discrete			0.016
Age	continuous	0.0752	1.0865
Gender	discrete			0.0027
Comorbidity	discrete			0.049
Coronary Artery Disease (CAD)	discrete			0.0224
Hypothyroidism	discrete			0.0264
Hyperlipidemia	discrete			0.0083
Diabetes Mellitus (DM)	discrete			0.0115
Height	continuous	0.0784	1.4113
Weight	continuous	0.069	1.729

Privacy metrics

metric	value
n_real	319
n_synth	319
exact_overlap_rate	0
near_duplicate_rate_eps	0.9969
nn_distance_mean	0.0139
k_min	1
k_pct_lt5	1
k_map	1
rare_qi_reproduction_rate	0
delta_presence	3.6154

Model: semi_mi5 (pybnesian)

Seed: 42, rows: 319
Params: {"max_indegree": 5, "operators": ["arcs"], "score": "bic", "type": "semiparametric"}
Missingness: wrapped (random state 42) via pipeline
Synthetic CSV
Per-variable metrics
Metrics JSON
Privacy metrics

Per-variable fidelity

variable	type	KS	W1	JSD
Gallstone Status	discrete			0.0053
Age	continuous	0.0721	0.9809
Gender	discrete			0.0133
Comorbidity	discrete			0.0335
Coronary Artery Disease (CAD)	discrete			0.0224
Hypothyroidism	discrete			0.0153
Hyperlipidemia	discrete			0.0088
Diabetes Mellitus (DM)	discrete			0.0227
Height	continuous	0.0721	1.2361
Weight	continuous	0.069	1.232

Privacy metrics

metric	value
n_real	319
n_synth	319
exact_overlap_rate	0
near_duplicate_rate_eps	0.9969
nn_distance_mean	0.0129
k_min	1
k_pct_lt5	1
k_map	1
rare_qi_reproduction_rate	0
delta_presence	3

Model: ctgan_fast (synthcity)

Seed: 42, rows: 256
Params: {"batch_size": 256, "n_iter": 5}
Missingness: wrapped (random state 42) via pipeline
Synthetic CSV
Per-variable metrics
Metrics JSON
Privacy metrics

Per-variable fidelity

variable	type	KS	W1	JSD
Gallstone Status	discrete			0.0777
Age	continuous	0.9875	28.069
Gender	discrete			0.2665
Comorbidity	discrete			0.4142
Coronary Artery Disease (CAD)	discrete			0.0069
Hypothyroidism	discrete			0.0293
Hyperlipidemia	discrete			0.0521
Diabetes Mellitus (DM)	discrete			0.019
Height	continuous	0.9373	21.4306
Weight	continuous	0.9875	53.784

Privacy metrics

metric	value
n_real	319
n_synth	319
exact_overlap_rate	0
near_duplicate_rate_eps	0.9749
nn_distance_mean	0.1023
k_min	1
k_pct_lt5	1
k_map	1
rare_qi_reproduction_rate	0
delta_presence	137

Model: tvae_quick (synthcity)

Seed: 42, rows: 256
Params: {"batch_size": 256}
Missingness: wrapped (random state 42) via pipeline
Synthetic CSV
Per-variable metrics
Metrics JSON
Privacy metrics

Per-variable fidelity

variable	type	KS	W1	JSD
Gallstone Status	discrete			0.0694
Age	continuous	0.2696	5.7794
Gender	discrete			0.0107
Comorbidity	discrete			0.1266
Coronary Artery Disease (CAD)	discrete			0.0071
Hypothyroidism	discrete			0.1194
Hyperlipidemia	discrete			0.0284
Diabetes Mellitus (DM)	discrete			0.1383
Height	continuous	0.1693	2.4626
Weight	continuous	0.2696	8.1252

Privacy metrics

metric	value
n_real	319
n_synth	319
exact_overlap_rate	0
near_duplicate_rate_eps	0.9906
nn_distance_mean	0.0241
k_min	1
k_pct_lt5	1
k_map	2
rare_qi_reproduction_rate	0
delta_presence	14.3333