EDA Dashboard • Train

Train Dimensions

668,665 × 15

Secondary Datasets

Golden Features

Strong Predictors

Collinear Warnings

Detailed Feature Statistics & Health Profiling

Feature	Dtype	Missing	Zeros	Distinct	Min	Q25	Median	Mean	Q75	Max	IQR	Outliers	Skewness	Kurtosis
id	int64	0.0%	0.0%	668665	0.0	167166.0	334332.0	334332.0	501498.0	668664.0	334332.00	0 (0.0%)	+0.00	-1.20
Age	int64	0.0%	0.0%	45	25.0	36.0	47.0	47.0392	58.0	69.0	22.00	0 (0.0%)	-0.00	-1.17
Annual_Income_USD	float64	0.0%	0.0%	13214	30000.0	67376.0	84880.0	84769.267	102753.0	188549.0	35377.00	3678 (0.6%)	-0.01	-0.15
Daily_Commute_km	float64	0.0%	0.0%	805	5.0	17.2	33.6	32.1583	47.4	98.7	30.20	41 (0.0%)	-0.08	-1.06
Number_of_Cars_Owned	int64	0.0%	0.0%	4	1.0	1.0	2.0	1.7126	2.0	4.0	1.00	13489 (2.0%)	+0.81	+0.36
Charging_Stations_Near_Home	int64	0.0%	10.4%	15	0.0	2.0	4.0	4.9604	7.0	14.0	5.00	0 (0.0%)	+0.70	-0.48
Charging_Stations_Near_Work	int64	0.0%	3.8%	20	0.0	3.0	6.0	7.1763	10.0	19.0	7.00	0 (0.0%)	+0.70	-0.49
Environmental_Concern_Level	float64	0.0%	0.0%	5	1.0	2.0	3.0	2.9355	4.0	5.0	2.00	0 (0.0%)	+0.05	-1.33
Gender	str	0.0%	0.0%	3	-	-	-	-	-	-	-	-	-	-
City_Type	str	0.0%	0.0%	3	-	-	-	-	-	-	-	-	-	-
Current_Car_Type	str	0.0%	0.0%	4	-	-	-	-	-	-	-	-	-	-
Home_Charging_Possible	str	0.0%	0.0%	2	-	-	-	-	-	-	-	-	-	-
Subsidy_Available	str	0.0%	0.0%	2	-	-	-	-	-	-	-	-	-	-
Range_Anxiety_Level	str	0.0%	0.0%	3	-	-	-	-	-	-	-	-	-	-

Feature distribution and empirical target association cards

Will_Buy_EV

str 🎯 Target Variable

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	2 (0.0%)
Dominant Mode	`No`
Top Categories	`No` (82.535%), `Yes` (17.465%)

Environmental_Concern_Level

float64 🌟 Prominent Predictor Rank #1

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	5 (0.0%)
Zeros	0 (0.0%)
Mean ± Std	2.9355 ± 1.4291
Median (IQR)	3.0 (2.0)
Min – Max	[1.0, 5.0]
Outliers	0 (0.0%)
Skewness	0.0543
Test Missing	0.0% (+0.0%)
Mutual Information	`0.1301`
Pearson Correlation	`+0.4641`
Permutation Drop	`0.2033`

Distribution for Environmental_Concern_Level

Subsidy_Available

str 🌟 Prominent Predictor Rank #2

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	2 (0.0%)
Dominant Mode	`Yes`
Top Categories	`Yes` (62.798%), `No` (37.202%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0800`
Permutation Drop	`0.1866`

Annual_Income_USD

float64 🌟 Prominent Predictor Rank #3

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	13,214 (2.0%)
Zeros	0 (0.0%)
Mean ± Std	84769.267 ± 28648.029
Median (IQR)	84880.0 (35377.0)
Min – Max	[30000.0, 188549.0]
Outliers	3678 (0.6%)
Skewness	-0.0131
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0475`
Pearson Correlation	`+0.2257`
Permutation Drop	`0.0141`

Range_Anxiety_Level

str 🌟 Prominent Predictor Rank #4

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	3 (0.0%)
Dominant Mode	`Low`
Top Categories	`Low` (90.325%), `Medium` (9.347%), `High` (0.328%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0088`
Permutation Drop	`0.0053`

Home_Charging_Possible

str 🌟 Prominent Predictor Rank #5

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	2 (0.0%)
Dominant Mode	`Yes`
Top Categories	`Yes` (69.194%), `No` (30.806%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0033`
Permutation Drop	`0.0025`

Daily_Commute_km

float64 🌟 Prominent Predictor Rank #6

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	805 (0.1%)
Zeros	0 (0.0%)
Mean ± Std	32.1583 ± 18.7305
Median (IQR)	33.6 (30.2)
Min – Max	[5.0, 98.7]
Outliers	41 (0.0%)
Skewness	-0.0846
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0006`
Pearson Correlation	`-0.0459`
Permutation Drop	`0.0002`

Charging_Stations_Near_Home

int64 Rank #7

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	15 (0.0%)
Zeros	69,865 (10.4%)
Mean ± Std	4.9604 ± 3.9268
Median (IQR)	4.0 (5.0)
Min – Max	[0.0, 14.0]
Outliers	0 (0.0%)
Skewness	0.6987
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0007`
Pearson Correlation	`-0.0164`
Permutation Drop	`0.0000`

Distribution for Charging_Stations_Near_Home

Current_Car_Type

str Rank #8

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	4 (0.0%)
Dominant Mode	`Sedan`
Top Categories	`Sedan` (45.383%), `SUV` (36.871%), `Hatchback` (11.88%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0003`
Permutation Drop	`0.0003`

City_Type

str Rank #9

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	3 (0.0%)
Dominant Mode	`Urban`
Top Categories	`Urban` (43.266%), `Suburban` (38.192%), `Rural` (18.542%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0005`
Permutation Drop	`0.0004`

Age

int64 Rank #10

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	45 (0.0%)
Zeros	0 (0.0%)
Mean ± Std	47.0392 ± 12.8754
Median (IQR)	47.0 (22.0)
Min – Max	[25.0, 69.0]
Outliers	0 (0.0%)
Skewness	-0.0038
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0031`
Pearson Correlation	`-0.0074`
Permutation Drop	`0.0000`

int64 Rank #11

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	668,665 (100.0%)
Zeros	1 (0.0%)
Mean ± Std	334332.0 ± 193027.1032
Median (IQR)	334332.0 (334332.0)
Min – Max	[0.0, 668664.0]
Outliers	0 (0.0%)
Skewness	0.0
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0000`
Pearson Correlation	`-0.0000`
Permutation Drop	`0.0000`

Number_of_Cars_Owned

int64 Rank #12

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	4 (0.0%)
Zeros	0 (0.0%)
Mean ± Std	1.7126 ± 0.7293
Median (IQR)	2.0 (1.0)
Min – Max	[1.0, 4.0]
Outliers	13489 (2.0%)
Skewness	0.8145
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0001`
Pearson Correlation	`+0.0039`
Permutation Drop	`0.0001`

Charging_Stations_Near_Work

int64 Rank #13

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	20 (0.0%)
Zeros	25,673 (3.8%)
Mean ± Std	7.1763 ± 5.1866
Median (IQR)	6.0 (7.0)
Min – Max	[0.0, 19.0]
Outliers	0 (0.0%)
Skewness	0.7002
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0003`
Pearson Correlation	`-0.0122`
Permutation Drop	`0.0000`

Distribution for Charging_Stations_Near_Work

Gender

str Rank #14

Total Count	668,665
Train Missing	0 (0.0%)
Distinct Count	3 (0.0%)
Dominant Mode	`Male`
Top Categories	`Male` (55.028%), `Female` (44.182%), `Other` (0.79%)
Test Missing	0.0% (+0.0%)
Mutual Information	`0.0000`
Permutation Drop	`0.0000`

Comparison: Train vs. Test

Train Shape

668,665 × 15

Test Shape

286,571 × 14

Max Missing Shift (Δ)

+0.0%

Unseen Category Alerts

Detailed Feature Comparison & Drift Table

Feature	Coverage	Type	Train Missing	Test Missing	Δ Missing %	Mean (Train / Test)	Distinct (Train / Test)	Novel Unseen Levels
id	Both	numeric	0.0%	0.0%	+0.0%	334332.00 / 811950.00 (+477618.00)	668665 / 286571	None
Age	Both	numeric	0.0%	0.0%	+0.0%	47.04 / 47.07 (+0.03)	45 / 45	None
Annual_Income_USD	Both	numeric	0.0%	0.0%	+0.0%	84769.27 / 84799.51 (+30.24)	13214 / 10526	None
Daily_Commute_km	Both	numeric	0.0%	0.0%	+0.0%	32.16 / 32.16 (+0.00)	805 / 781	None
Number_of_Cars_Owned	Both	numeric	0.0%	0.0%	+0.0%	1.71 / 1.72 (+0.00)	4 / 4	None
Charging_Stations_Near_Home	Both	numeric	0.0%	0.0%	+0.0%	4.96 / 4.95 (-0.01)	15 / 15	None
Charging_Stations_Near_Work	Both	numeric	0.0%	0.0%	+0.0%	7.18 / 7.16 (-0.02)	20 / 20	None
Environmental_Concern_Level	Both	numeric	0.0%	0.0%	+0.0%	2.94 / 2.93 (-0.00)	5 / 5	None
Gender	Both	categorical	0.0%	0.0%	+0.0%	-	3 / 3	None
City_Type	Both	categorical	0.0%	0.0%	+0.0%	-	3 / 3	None
Current_Car_Type	Both	categorical	0.0%	0.0%	+0.0%	-	4 / 4	None
Home_Charging_Possible	Both	categorical	0.0%	0.0%	+0.0%	-	2 / 2	None
Subsidy_Available	Both	categorical	0.0%	0.0%	+0.0%	-	2 / 2	None
Range_Anxiety_Level	Both	categorical	0.0%	0.0%	+0.0%	-	3 / 3	None

Golden Features Ranking Leaderboard

Rank	Feature	Quality Tier	Golden Score	Permutation Drop	Attribution Score	Mutual Info	Recommendation
#1	Environmental_Concern_Level	🥇 Tier 1	1.0000	`0.2033` (±0.0021)	`0.0998`	`0.1294`	Primary Predictor
#2	Subsidy_Available	🥇 Tier 1	0.8406	`0.1866` (±0.0040)	`0.0930`	`0.0824`	Primary Predictor
#3	Annual_Income_USD	🥉 Tier 3	0.1567	`0.0141` (±0.0014)	`0.0184`	`0.0446`	Auxiliary Predictor
#4	Range_Anxiety_Level	⚠️ Low	0.0607	`0.0053` (±0.0006)	`0.0091`	`0.0136`	Candidate for pruning
#5	Home_Charging_Possible	⚠️ Low	0.0485	`0.0025` (±0.0004)	`0.0108`	`0.0048`	Candidate for pruning
#6	Daily_Commute_km	⚠️ Low	0.0091	`0.0002` (±0.0001)	`0.0021`	`0.0026`	Candidate for pruning
#7	Charging_Stations_Near_Home	⚠️ Low	0.0071	`0.0000` (±0.0001)	`0.0011`	`0.0043`	Candidate for pruning
#8	Current_Car_Type	⚠️ Low	0.0045	`0.0003` (±0.0001)	`0.0012`	`0.0016`	Candidate for pruning
#9	City_Type	⚠️ Low	0.0039	`0.0004` (±0.0001)	`0.0014`	`0.0001`	Candidate for pruning
#10	Age	⚠️ Low	0.0017	`0.0000` (±0.0001)	`0.0010`	`0.0000`	Candidate for pruning
#11	id	⚠️ Low	0.0012	`0.0000` (±0.0001)	`0.0009`	`0.0000`	Candidate for pruning
#12	Number_of_Cars_Owned	⚠️ Low	0.0011	`0.0001` (±0.0001)	`0.0008`	`0.0000`	Candidate for pruning
#13	Charging_Stations_Near_Work	⚠️ Low	0.0007	`0.0000` (±0.0000)	`0.0007`	`0.0000`	Candidate for pruning
#14	Gender	⚠️ Low	0.0001	`0.0000` (±0.0001)	`0.0006`	`0.0000`	Candidate for pruning

Multicollinear Feature Pairs (|r| ≥ 0.80)

✅ No collinear feature pairs detected above threshold (|r| ≥ 0.80).

Pairwise Interaction Spaces (Bivariate Distribution with Target Coloring)

Visualizes joint feature geometries. Diagonal separation lines suggest addition/subtraction ($A \pm B$), hyperbolic contours suggest ratios ($A / B$), and quadrant clustering signals multiplicative interactions ($A imes B$).

Arithmetic Feature Engineering Synergy Leaderboard

Ranks candidate operations where the combined feature exceeds the individual predictive performance of either component ($\Delta > 0$).

Rank	Candidate Formula	Operation	Best Single Baseline	Combined Score	Synergy Gain (Δ)	Evaluated Metric
#1	`Environmental_Concern_Level * Annual_Income_USD`	Multiplication	`8.8745`	9.2178	+0.3433 Synergy	log(1 + F-statistic)
#2	`Annual_Income_USD - Daily_Commute_km`	Difference	`7.3033`	7.3036	+0.0003 Gain	log(1 + F-statistic)
#3	`Annual_Income_USD + Daily_Commute_km`	Sum	`7.3033`	7.3030	-0.0003	log(1 + F-statistic)
#4	`Daily_Commute_km / (Annual_Income_USD + eps)`	Ratio (B/A)	`7.3033`	6.2427	-1.0606	log(1 + F-statistic)
#5	`Daily_Commute_km / (Environmental_Concern_Level + eps)`	Ratio (B/A)	`8.8745`	7.4943	-1.3802	log(1 + F-statistic)
#6	`Annual_Income_USD / (Environmental_Concern_Level + eps)`	Ratio (B/A)	`8.8745`	7.4028	-1.4717	log(1 + F-statistic)
#7	`Environmental_Concern_Level * Daily_Commute_km`	Multiplication	`8.8745`	7.3680	-1.5065	log(1 + F-statistic)
#8	`Environmental_Concern_Level + Annual_Income_USD`	Sum	`8.8745`	7.3035	-1.5710	log(1 + F-statistic)
#9	`Environmental_Concern_Level - Annual_Income_USD`	Difference	`8.8745`	7.3031	-1.5714	log(1 + F-statistic)
#10	`Environmental_Concern_Level / (Daily_Commute_km + eps)`	Ratio (A/B)	`8.8745`	6.9714	-1.9031	log(1 + F-statistic)
#11	`Annual_Income_USD / (Daily_Commute_km + eps)`	Ratio (A/B)	`7.3033`	5.3406	-1.9627	log(1 + F-statistic)
#12	`Annual_Income_USD * Daily_Commute_km`	Multiplication	`7.3033`	4.8889	-2.4144	log(1 + F-statistic)
#13	`Environmental_Concern_Level / (Annual_Income_USD + eps)`	Ratio (A/B)	`8.8745`	6.1287	-2.7458	log(1 + F-statistic)
#14	`Environmental_Concern_Level - Daily_Commute_km`	Difference	`8.8745`	5.1021	-3.7724	log(1 + F-statistic)
#15	`Environmental_Concern_Level + Daily_Commute_km`	Sum	`8.8745`	1.1378	-7.7367	log(1 + F-statistic)

Synergy Case Study: Environmental_Concern_Level & Annual_Income_USD → Environmental_Concern_Level * Annual_Income_USD (Multiplication) [Synergy: +0.3433]

Synergy Case Study: Annual_Income_USD & Daily_Commute_km → Annual_Income_USD - Daily_Commute_km (Difference) [Synergy: +0.0003]

Synergy Case Study: Environmental_Concern_Level & Daily_Commute_km → Daily_Commute_km / (Environmental_Concern_Level + eps) (Ratio (B/A)) [Synergy: -1.3802]

Partition: 2 Clusters

Clusters Count

K-Means Partitions

Silhouette Score

0.2169

Separation Quality (-1 to 1)

Target Dependency

0.0047

Mutual Information I(Cluster; Y)

Inertia

199,017.3

Sum of Squared Distances

Cluster ID	Sample Size	Target Summary	Defining Attributes (σ from global mean)
Cluster 0	20,829 (69.4%)	No: 80.6%, Yes: 19.4%	Home_Charging_Possible (+0.66σ) Range_Anxiety_Level (-0.31σ) Charging_Stations_Near_Home (-0.27σ) Environmental_Concern_Level (+0.03σ)
Cluster 1	9,171 (30.6%)	No: 86.9%, Yes: 13.1%	Home_Charging_Possible (-1.50σ) Range_Anxiety_Level (+0.70σ) Charging_Stations_Near_Home (+0.60σ) Environmental_Concern_Level (-0.08σ)

Partition: 4 Clusters

Clusters Count

K-Means Partitions

Silhouette Score

0.1954

Separation Quality (-1 to 1)

Target Dependency

0.0718

Mutual Information I(Cluster; Y)

Inertia

153,695.5

Sum of Squared Distances

Cluster ID	Sample Size	Target Summary	Defining Attributes (σ from global mean)
Cluster 0	6,533 (21.8%)	No: 83.4%, Yes: 16.6%	Home_Charging_Possible (-1.50σ) Charging_Stations_Near_Home (+0.79σ) Range_Anxiety_Level (-0.35σ) Daily_Commute_km (-0.15σ)
Cluster 1	2,762 (9.2%)	No: 95.7%, Yes: 4.3%	Range_Anxiety_Level (+3.08σ) Home_Charging_Possible (-1.45σ) Daily_Commute_km (+0.57σ) Environmental_Concern_Level (-0.16σ)
Cluster 2	7,577 (25.3%)	No: 99.3%, Yes: 0.7%	Subsidy_Available (-1.30σ) Home_Charging_Possible (+0.66σ) Range_Anxiety_Level (-0.30σ) Charging_Stations_Near_Home (-0.26σ)
Cluster 3	13,128 (43.8%)	No: 69.7%, Yes: 30.3%	Subsidy_Available (+0.77σ) Home_Charging_Possible (+0.67σ) Range_Anxiety_Level (-0.30σ) Charging_Stations_Near_Home (-0.27σ)

Top Selected Prominent Features (De-duplicated & Screened)

Selected by synthesizing Golden Feature scores, Permutation Importance, Mutual Information, and Pearson correlation while eliminating collinear redundancy.

Selection Rank	Feature	Type	Golden Score	Permutation Drop	Mutual Info	Pearson r	Status
#1	Environmental_Concern_Level	float64	`1.0000`	`0.2033`	`0.1301`	`+0.4641`	Prominent Predictor
#2	Subsidy_Available	str	`0.8406`	`0.1866`	`0.0800`	`[Non-linear / Cat]`	Prominent Predictor
#3	Annual_Income_USD	float64	`0.1567`	`0.0141`	`0.0475`	`+0.2257`	Prominent Predictor
#4	Range_Anxiety_Level	str	`0.0607`	`0.0053`	`0.0088`	`[Non-linear / Cat]`	Prominent Predictor
#5	Home_Charging_Possible	str	`0.0485`	`0.0025`	`0.0033`	`[Non-linear / Cat]`	Prominent Predictor
#6	Daily_Commute_km	float64	`0.0091`	`0.0002`	`0.0006`	`-0.0459`	Prominent Predictor

Partial Dependence (PDP) & Individual Conditional Expectation (ICE)

The blue line represents the average marginal response (PDP). The light blue lines display ICE samples; parallel lines indicate additive behavior, while divergent slopes signal feature interactions.

yaEDA Dashboard