## Loading required package: Hmisc
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## Loading required package: ggplot2
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:base':
##
## format.pval, units
## funModeling v.1.9.3 :)
## Examples and tutorials at livebook.datascienceheroes.com
## / Now in Spanish: librovivodecienciadedatos.ai
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:Hmisc':
##
## src, summarize
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
## [1] 303 16
## age gender chest_pain resting_blood_pressure serum_cholestoral
## 1 63 male 1 145 233
## 2 67 male 4 160 286
## 3 67 male 4 120 229
## 4 37 male 3 130 250
## 5 41 female 2 130 204
## 6 56 male 2 120 236
## fasting_blood_sugar resting_electro max_heart_rate exer_angina oldpeak
## 1 1 2 150 0 2.3
## 2 0 2 108 1 1.5
## 3 0 2 129 1 2.6
## 4 0 0 187 0 3.5
## 5 0 2 172 0 1.4
## 6 0 0 178 0 0.8
## slope num_vessels_flour thal heart_disease_severity exter_angina
## 1 3 0 6 0 0
## 2 2 3 3 2 1
## 3 2 2 7 1 1
## 4 3 0 3 0 0
## 5 1 0 3 0 0
## 6 1 0 3 0 0
## has_heart_disease
## 1 no
## 2 yes
## 3 yes
## 4 no
## 5 no
## 6 no
## variable q_zeros p_zeros q_na p_na q_inf p_inf type
## 1 age 0 0.00 0 0.00 0 0 integer
## 2 gender 0 0.00 0 0.00 0 0 factor
## 3 chest_pain 0 0.00 0 0.00 0 0 factor
## 4 resting_blood_pressure 0 0.00 0 0.00 0 0 integer
## 5 serum_cholestoral 0 0.00 0 0.00 0 0 integer
## 6 fasting_blood_sugar 258 85.15 0 0.00 0 0 factor
## 7 resting_electro 151 49.83 0 0.00 0 0 factor
## 8 max_heart_rate 0 0.00 0 0.00 0 0 integer
## 9 exer_angina 204 67.33 0 0.00 0 0 integer
## 10 oldpeak 99 32.67 0 0.00 0 0 numeric
## 11 slope 0 0.00 0 0.00 0 0 integer
## 12 num_vessels_flour 176 58.09 4 1.32 0 0 integer
## 13 thal 0 0.00 2 0.66 0 0 factor
## 14 heart_disease_severity 164 54.13 0 0.00 0 0 integer
## 15 exter_angina 204 67.33 0 0.00 0 0 factor
## 16 has_heart_disease 0 0.00 0 0.00 0 0 factor
## unique
## 1 41
## 2 2
## 3 4
## 4 50
## 5 152
## 6 2
## 7 3
## 8 91
## 9 2
## 10 40
## 11 3
## 12 4
## 13 3
## 14 5
## 15 2
## 16 2
## variable q_zeros p_zeros q_na p_na q_inf p_inf
## 1 age 0 0.0000000 0 0.00000000 0 0
## 2 gender 0 0.0000000 0 0.00000000 0 0
## 3 chest_pain 0 0.0000000 0 0.00000000 0 0
## 4 resting_blood_pressure 0 0.0000000 0 0.00000000 0 0
## 5 serum_cholestoral 0 0.0000000 0 0.00000000 0 0
## 6 fasting_blood_sugar 258 0.8514851 0 0.00000000 0 0
## 7 resting_electro 151 0.4983498 0 0.00000000 0 0
## 8 max_heart_rate 0 0.0000000 0 0.00000000 0 0
## 9 exer_angina 204 0.6732673 0 0.00000000 0 0
## 10 oldpeak 99 0.3267327 0 0.00000000 0 0
## 11 slope 0 0.0000000 0 0.00000000 0 0
## 12 num_vessels_flour 176 0.5808581 4 0.01320132 0 0
## 13 thal 0 0.0000000 2 0.00660066 0 0
## 14 heart_disease_severity 164 0.5412541 0 0.00000000 0 0
## 15 exter_angina 204 0.6732673 0 0.00000000 0 0
## 16 has_heart_disease 0 0.0000000 0 0.00000000 0 0
## type unique
## 1 integer 41
## 2 factor 2
## 3 factor 4
## 4 integer 50
## 5 integer 152
## 6 factor 2
## 7 factor 3
## 8 integer 91
## 9 integer 2
## 10 numeric 40
## 11 integer 3
## 12 integer 4
## 13 factor 3
## 14 integer 5
## 15 factor 2
## 16 factor 2
##
## ( ) {Numerical with NA} num_vessels_flour
## ( ) {Categorical with NA} thal
## $vars_num_with_NA
## variable q_na p_na
## 1 num_vessels_flour 4 0.01320132
##
## $vars_cat_with_NA
## variable q_na p_na
## 1 thal 2 0.00660066
##
## $vars_cat_high_card
## [1] variable unique
## <0 rows> (or 0-length row.names)
##
## $MAX_UNIQUE
## [1] 35
##
## $vars_one_value
## character(0)
##
## $vars_cat
## [1] "gender" "chest_pain" "fasting_blood_sugar"
## [4] "resting_electro" "thal" "exter_angina"
## [7] "has_heart_disease"
##
## $vars_num
## [1] "age" "resting_blood_pressure"
## [3] "serum_cholestoral" "max_heart_rate"
## [5] "exer_angina" "oldpeak"
## [7] "slope" "num_vessels_flour"
## [9] "heart_disease_severity"
##
## $vars_char
## character(0)
##
## $vars_factor
## [1] "gender" "chest_pain" "fasting_blood_sugar"
## [4] "resting_electro" "thal" "exter_angina"
## [7] "has_heart_disease"
##
## $vars_other
## character(0)
## variable mean std_dev variation_coef p_01
## 1 age 54.4389439 9.0386624 0.1660330 35.00
## 2 resting_blood_pressure 131.6897690 17.5997477 0.1336455 100.00
## 3 serum_cholestoral 246.6930693 51.7769175 0.2098840 149.00
## 4 max_heart_rate 149.6072607 22.8750033 0.1529004 95.02
## 5 exer_angina 0.3267327 0.4697945 1.4378558 0.00
## 6 oldpeak 1.0396040 1.1610750 1.1168436 0.00
## 7 slope 1.6006601 0.6162261 0.3849825 1.00
## 8 num_vessels_flour 0.6722408 0.9374383 1.3944978 0.00
## 9 heart_disease_severity 0.9372937 1.2285357 1.3107265 0.00
## p_05 p_25 p_50 p_75 p_95 p_99 skewness kurtosis iqr
## 1 40.0 48.0 56.0 61.0 68.0 71.00 -0.2080241 2.465477 13.0
## 2 108.0 120.0 130.0 140.0 160.0 180.00 0.7025346 3.845881 20.0
## 3 175.1 211.0 241.0 275.0 326.9 406.74 1.1298741 7.398208 64.0
## 4 108.1 133.5 153.0 166.0 181.9 191.96 -0.5347844 2.927602 32.5
## 5 0.0 0.0 0.0 1.0 1.0 1.00 0.7388506 1.545900 1.0
## 6 0.0 0.0 0.8 1.6 3.4 4.20 1.2634255 4.530193 1.6
## 7 1.0 1.0 2.0 2.0 3.0 3.00 0.5057957 2.363050 1.0
## 8 0.0 0.0 0.0 1.0 3.0 3.00 1.1833771 3.234941 1.0
## 9 0.0 0.0 0.0 2.0 3.0 4.00 1.0532483 2.843788 2.0
## range_98 range_80
## 1 [35, 71] [42, 66]
## 2 [100, 180] [110, 152]
## 3 [149, 406.74] [188.8, 308.8]
## 4 [95.02, 191.96] [116, 176.6]
## 5 [0, 1] [0, 1]
## 6 [0, 4.2] [0, 2.8]
## 7 [1, 3] [1, 2]
## 8 [0, 3] [0, 2]
## 9 [0, 4] [0, 3]
## chest_pain frequency percentage cumulative_perc
## 1 4 144 47.52 47.52
## 2 3 86 28.38 75.90
## 3 2 50 16.50 92.40
## 4 1 23 7.59 100.00
## thal frequency percentage cumulative_perc
## 1 3 166 54.79 54.79
## 2 7 117 38.61 93.40
## 3 6 18 5.94 99.34
## 4 <NA> 2 0.66 100.00
## [1] "Variables processed: chest_pain, thal"
## Variable has_heart_disease
## 1 has_heart_disease 1.00
## 2 heart_disease_severity 0.83
## 3 num_vessels_flour 0.46
## 4 oldpeak 0.42
## 5 slope 0.34
## 6 age 0.23
## 7 resting_blood_pressure 0.15
## 8 serum_cholestoral 0.08
## 9 max_heart_rate -0.42
## var en mi ig gr
## 1 heart_disease_severity 1.846 0.995 0.9950837595 0.5390655068
## 2 thal 2.032 0.209 0.2094550580 0.1680456709
## 3 exer_angina 1.767 0.139 0.1391389302 0.1526393841
## 4 exter_angina 1.767 0.139 0.1391389302 0.1526393841
## 5 chest_pain 2.527 0.205 0.2050188327 0.1180286190
## 6 num_vessels_flour 2.381 0.182 0.1815217813 0.1157736478
## 7 slope 2.177 0.112 0.1124219069 0.0868799615
## 8 serum_cholestoral 7.481 0.561 0.5605556771 0.0795557228
## 9 gender 1.842 0.057 0.0572537665 0.0632970555
## 10 oldpeak 4.874 0.249 0.2491668741 0.0603576874
## 11 max_heart_rate 6.832 0.334 0.3336174096 0.0540697329
## 12 resting_blood_pressure 5.567 0.143 0.1425548155 0.0302394591
## 13 age 5.928 0.137 0.1371752885 0.0270548944
## 14 resting_electro 2.059 0.024 0.0241482908 0.0221938072
## 15 fasting_blood_sugar 1.601 0.000 0.0004593775 0.0007579095
## Plotting transformed variable 'age' with 'equal_freq', (too many values). Disable with 'auto_binning=FALSE'
## Plotting transformed variable 'oldpeak' with 'equal_freq', (too many values). Disable with 'auto_binning=FALSE'
## country mean_target sum_target perc_target q_rows perc_rows
## 1 Malaysia 1.000 1 0.012 1 0.001
## 2 Mexico 0.667 2 0.024 3 0.003
## 3 Portugal 0.200 1 0.012 5 0.005
## 4 United Kingdom 0.178 8 0.096 45 0.049
## 5 Uruguay 0.175 11 0.133 63 0.069
## 6 Israel 0.167 1 0.012 6 0.007
## Variables processed: max_heart_rate, oldpeak
## Variables processed: max_heart_rate, oldpeak
## Variables processed: Sepal.Length, Sepal.Width, Petal.Length, Petal.Width
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 [ 5.1, 5.7) [ 3.5, Inf] [-Inf, 1.6) [-Inf, 0.3) setosa
## 2 [-Inf, 5.1) [ 2.8, 3.1) [-Inf, 1.6) [-Inf, 0.3) setosa
## 3 [-Inf, 5.1) [ 3.2, 3.5) [-Inf, 1.6) [-Inf, 0.3) setosa
## 4 [-Inf, 5.1) [ 3.1, 3.2) [-Inf, 1.6) [-Inf, 0.3) setosa
## 5 [-Inf, 5.1) [ 3.5, Inf] [-Inf, 1.6) [-Inf, 0.3) setosa
## 6 [ 5.1, 5.7) [ 3.5, Inf] [ 1.6, 4.0) [ 0.3, 1.2) setosa
## new_age
## n missing distinct
## 303 0 5
##
## Value [29,46) [46,54) [54,59) [59,63) [63,77]
## Frequency 63 64 71 45 60
## Proportion 0.208 0.211 0.234 0.149 0.198
## Population Gain Lift Score.Point
## 1 10 20.86 2.09 0.8185793
## 2 20 35.97 1.80 0.6967124
## 3 30 48.92 1.63 0.5657817
## 4 40 61.15 1.53 0.4901940
## 5 50 69.06 1.38 0.4033640
## 6 60 78.42 1.31 0.3344170
## 7 70 87.77 1.25 0.2939878
## 8 80 92.09 1.15 0.2473671
## 9 90 96.40 1.07 0.1980453
## 10 100 100.00 1.00 0.1195511