Pima Indian Diabetes data
mcc
January 14, 2019
setwd("~/Desktop/galaxy500/resources")
library(readr)
pima <- read_csv("Pima.tr2.csv")## Warning: Missing column names filled in: 'X1' [1]## Parsed with column specification:
## cols(
## X1 = col_double(),
## npreg = col_double(),
## glu = col_double(),
## bp = col_double(),
## skin = col_double(),
## bmi = col_double(),
## ped = col_double(),
## age = col_double(),
## type = col_character()
## )Start E.D.A.
dim(pima)## [1] 300 9names(pima)## [1] "X1" "npreg" "glu" "bp" "skin" "bmi" "ped" "age" "type"str(pima)## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 300 obs. of 9 variables:
## $ X1 : num 1 2 3 4 5 6 7 8 9 10 ...
## $ npreg: num 5 7 5 0 0 5 3 1 3 2 ...
## $ glu : num 86 195 77 165 107 97 83 193 142 128 ...
## $ bp : num 68 70 82 76 60 76 58 50 80 78 ...
## $ skin : num 28 33 41 43 25 27 31 16 15 37 ...
## $ bmi : num 30.2 25.1 35.8 47.9 26.4 35.6 34.3 25.9 32.4 43.3 ...
## $ ped : num 0.364 0.163 0.156 0.259 0.133 ...
## $ age : num 24 55 35 26 23 52 25 24 63 31 ...
## $ type : chr "No" "Yes" "No" "No" ...
## - attr(*, "spec")=
## .. cols(
## .. X1 = col_double(),
## .. npreg = col_double(),
## .. glu = col_double(),
## .. bp = col_double(),
## .. skin = col_double(),
## .. bmi = col_double(),
## .. ped = col_double(),
## .. age = col_double(),
## .. type = col_character()
## .. )attributes(pima)## $names
## [1] "X1" "npreg" "glu" "bp" "skin" "bmi" "ped" "age" "type"
##
## $class
## [1] "spec_tbl_df" "tbl_df" "tbl" "data.frame"
##
## $row.names
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
## [18] 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
## [35] 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
## [52] 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
## [69] 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
## [86] 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102
## [103] 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
## [120] 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
## [137] 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
## [154] 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
## [171] 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187
## [188] 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204
## [205] 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221
## [222] 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
## [239] 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
## [256] 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
## [273] 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
## [290] 290 291 292 293 294 295 296 297 298 299 300
##
## $spec
## cols(
## X1 = col_double(),
## npreg = col_double(),
## glu = col_double(),
## bp = col_double(),
## skin = col_double(),
## bmi = col_double(),
## ped = col_double(),
## age = col_double(),
## type = col_character()
## )summary(pima)## X1 npreg glu bp
## Min. : 1.00 Min. : 0.000 Min. : 56.0 Min. : 38.00
## 1st Qu.: 75.75 1st Qu.: 1.000 1st Qu.:101.0 1st Qu.: 64.00
## Median :150.50 Median : 3.000 Median :121.0 Median : 72.00
## Mean :150.50 Mean : 3.787 Mean :123.7 Mean : 72.32
## 3rd Qu.:225.25 3rd Qu.: 6.000 3rd Qu.:142.0 3rd Qu.: 80.00
## Max. :300.00 Max. :14.000 Max. :199.0 Max. :114.00
## NA's :13
## skin bmi ped age
## Min. : 7.00 Min. :18.20 Min. :0.0780 Min. :21.0
## 1st Qu.:21.00 1st Qu.:27.10 1st Qu.:0.2367 1st Qu.:24.0
## Median :29.00 Median :32.00 Median :0.3360 Median :29.0
## Mean :29.15 Mean :32.05 Mean :0.4357 Mean :33.1
## 3rd Qu.:36.00 3rd Qu.:36.50 3rd Qu.:0.5867 3rd Qu.:40.0
## Max. :99.00 Max. :52.90 Max. :2.2880 Max. :72.0
## NA's :98 NA's :3
## type
## Length:300
## Class :character
## Mode :character
##
##
##
## # Number of pregnancies
table(pima$npreg)##
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14
## 44 51 41 26 35 22 19 17 15 9 8 2 6 3 2hist(pima$npreg)
plot(density(pima$npreg))
plot(pima$npreg, pima$age)
pairs(pima[,4:8])