assesment2
Ravindu Yasas
2024-05-06
data1=read.csv(file.choose(),header = TRUE)
View(data1)
attach(data1)
library(ggplot2)
# Visualize the relationship between age and diabetes
ggplot(data1, aes(x = age, fill = factor(diabetes))) +
geom_histogram(binwidth = 5, position = "identity", alpha = 0.5) +
labs(title = "Distribution of Diabetes by Age", x = "Age", y = "Frequency", fill = "Diabetes") +
theme_minimal()
linearMod <- lm(platelets ~ diabetes , data = data1)
print(linearMod)##
## Call:
## lm(formula = platelets ~ diabetes, data = data1)
##
## Coefficients:
## (Intercept) diabetes
## 255728 18250summary(linearMod)##
## Call:
## lm(formula = platelets ~ diabetes, data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -248879 -51979 -9728 38772 576021
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 255728 7395 34.580 <2e-16 ***
## diabetes 18250 11438 1.596 0.112
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 97550 on 297 degrees of freedom
## Multiple R-squared: 0.0085, Adjusted R-squared: 0.005161
## F-statistic: 2.546 on 1 and 297 DF, p-value: 0.1116# Check for missing values
any(is.na(data1))## [1] FALSE#Split the data_set
split <- split(data1, sex)
print(split)## $`0`
## age anaemia creatinine_phosphokinase diabetes ejection_fraction
## 5 65.000 1 160 1 20
## 9 65.000 0 157 0 65
## 15 49.000 1 80 0 30
## 19 70.000 1 125 0 25
## 20 48.000 1 582 1 55
## 21 65.000 1 52 0 25
## 22 65.000 1 128 1 30
## 25 75.000 0 582 1 30
## 27 95.000 1 112 0 40
## 33 50.000 1 249 1 35
## 34 50.000 1 159 1 30
## 38 82.000 1 855 1 50
## 40 60.000 0 235 1 38
## 42 50.000 0 124 1 30
## 45 60.000 1 588 1 60
## 50 57.000 1 129 0 30
## 52 53.000 1 91 0 20
## 53 60.000 0 3964 1 62
## 54 70.000 1 69 1 50
## 55 60.000 1 260 1 38
## 62 50.000 0 318 0 40
## 65 45.000 0 582 0 80
## 67 42.000 1 250 1 15
## 69 70.000 0 161 0 25
## 77 70.000 0 92 0 60
## 80 55.000 0 336 0 45
## 81 70.000 0 69 0 40
## 83 60.000 1 76 1 25
## 85 59.000 1 280 1 25
## 93 42.000 0 582 0 60
## 95 58.000 0 144 1 38
## 98 70.000 1 59 0 60
## 99 60.000 1 156 1 25
## 100 63.000 1 61 1 40
## 105 60.000 0 53 0 50
## 106 72.000 1 328 0 30
## 114 70.000 1 143 0 60
## 116 58.000 1 400 0 40
## 117 60.000 1 96 1 60
## 118 85.000 1 102 0 60
## 119 65.000 1 113 1 60
## 120 86.000 0 582 0 38
## 122 66.000 1 68 1 38
## 123 60.000 0 96 1 38
## 124 60.000 1 582 0 30
## 126 43.000 1 358 0 50
## 127 46.000 0 168 1 17
## 128 58.000 1 200 1 60
## 133 46.000 0 719 0 40
## 137 65.000 1 59 1 60
## 139 62.000 0 281 1 35
## 142 46.000 1 291 0 35
## 143 50.000 0 482 1 30
## 144 61.000 1 84 0 40
## 151 72.000 0 233 0 45
## 155 65.000 1 335 0 35
## 157 52.000 1 58 0 35
## 164 50.000 1 2334 1 35
## 166 80.000 0 776 1 38
## 169 65.000 0 582 1 40
## 170 70.000 0 835 0 35
## 178 49.000 1 69 0 50
## 187 50.000 0 582 0 50
## 188 60.000 0 1896 1 25
## 189 60.667 1 151 1 40
## 190 40.000 0 244 0 45
## 192 64.000 1 62 0 60
## 197 45.000 0 582 1 38
## 198 65.000 0 167 0 30
## 199 50.000 1 582 1 20
## 206 50.000 1 167 1 45
## 207 40.000 1 101 0 40
## 209 60.000 1 2281 1 40
## 210 49.000 0 972 1 35
## 214 48.000 1 131 1 30
## 217 70.000 0 1202 0 50
## 218 54.000 1 427 0 70
## 220 55.000 0 582 1 35
## 226 75.000 0 675 1 60
## 229 65.000 0 56 0 25
## 230 72.000 0 211 0 25
## 231 60.000 0 166 0 30
## 239 65.000 1 720 1 40
## 241 70.000 0 81 1 35
## 244 73.000 1 1185 0 40
## 250 53.000 0 207 1 40
## 251 50.000 0 2522 0 30
## 252 55.000 0 572 1 35
## 254 70.000 0 88 1 35
## 257 65.000 0 326 0 38
## 262 62.000 1 655 0 40
## 264 68.000 1 157 1 60
## 269 45.000 0 582 1 38
## 272 51.000 0 582 1 40
## 273 67.000 0 213 0 38
## 276 45.000 0 582 0 38
## 277 70.000 0 618 0 35
## 279 50.000 1 1051 1 30
## 280 55.000 0 84 1 38
## 288 45.000 0 582 1 55
## 289 65.000 0 892 1 35
## 290 90.000 1 337 0 38
## 291 45.000 0 615 1 55
## 296 55.000 0 1820 0 38
## 297 45.000 0 2060 1 60
## high_blood_pressure platelets serum_creatinine serum_sodium sex smoking
## 5 0 327000 2.70 116 0 0
## 9 0 263358 1.50 138 0 0
## 15 1 427000 1.00 138 0 0
## 19 1 237000 1.00 140 0 0
## 20 0 87000 1.90 121 0 0
## 21 1 276000 1.30 137 0 0
## 22 1 297000 1.60 136 0 0
## 25 1 263358 1.83 134 0 0
## 27 1 196000 1.00 138 0 0
## 33 1 319000 1.00 128 0 0
## 34 0 302000 1.20 138 0 0
## 38 1 321000 1.00 145 0 0
## 40 0 329000 3.00 142 0 0
## 42 1 153000 1.20 136 0 1
## 45 0 194000 1.10 142 0 0
## 50 0 395000 1.00 140 0 0
## 52 1 418000 1.40 139 0 0
## 53 0 263358 6.80 146 0 0
## 54 1 351000 1.00 134 0 0
## 55 0 255000 2.20 132 0 1
## 62 1 216000 2.30 131 0 0
## 65 0 263358 1.18 137 0 0
## 67 0 213000 1.30 136 0 0
## 69 0 244000 1.20 142 0 0
## 77 1 317000 0.80 140 0 1
## 80 1 324000 0.90 140 0 0
## 81 0 293000 1.70 136 0 0
## 83 0 196000 2.50 132 0 0
## 85 1 302000 1.00 141 0 0
## 93 0 263358 1.18 137 0 0
## 95 1 327000 0.70 142 0 0
## 98 0 255000 1.10 136 0 0
## 99 1 318000 1.20 137 0 0
## 100 0 221000 1.10 140 0 0
## 105 1 286000 2.30 143 0 0
## 106 1 621000 1.70 138 0 1
## 114 0 351000 1.30 137 0 0
## 116 0 164000 1.00 139 0 0
## 117 1 271000 0.70 136 0 0
## 118 0 507000 3.20 138 0 0
## 119 1 203000 0.90 140 0 0
## 120 0 263358 1.83 134 0 0
## 122 1 162000 1.00 136 0 0
## 123 0 228000 0.75 140 0 0
## 124 1 127000 0.90 145 0 0
## 126 0 237000 1.30 135 0 0
## 127 1 271000 2.10 124 0 0
## 128 0 300000 0.80 137 0 0
## 133 1 263358 1.18 137 0 0
## 137 0 172000 0.90 137 0 0
## 139 0 221000 1.00 136 0 0
## 142 0 348000 0.90 140 0 0
## 143 0 329000 0.90 132 0 0
## 144 1 229000 0.90 141 0 0
## 151 1 235000 2.50 135 0 0
## 155 1 235000 0.80 136 0 0
## 157 0 277000 1.40 136 0 0
## 164 0 75000 0.90 142 0 0
## 166 1 192000 1.30 135 0 0
## 169 0 270000 1.00 138 0 0
## 170 1 305000 0.80 133 0 0
## 178 0 132000 1.00 140 0 0
## 187 0 153000 0.60 134 0 0
## 188 0 365000 2.10 144 0 0
## 189 1 201000 1.00 136 0 0
## 190 1 275000 0.90 140 0 0
## 192 0 309000 1.50 135 0 0
## 197 1 263358 1.18 137 0 0
## 198 0 259000 0.80 138 0 0
## 199 1 279000 1.00 134 0 0
## 206 0 362000 1.00 136 0 0
## 207 0 226000 0.80 141 0 0
## 209 0 283000 1.00 141 0 0
## 210 1 268000 0.80 130 0 0
## 214 1 244000 1.60 130 0 0
## 217 1 358000 0.90 141 0 0
## 218 1 151000 9.00 137 0 0
## 220 1 371000 0.70 140 0 0
## 226 0 265000 1.40 125 0 0
## 229 0 237000 5.00 130 0 0
## 230 0 274000 1.20 134 0 0
## 231 0 62000 1.70 127 0 0
## 239 0 257000 1.00 136 0 0
## 241 1 533000 1.30 139 0 0
## 244 1 220000 0.90 141 0 0
## 250 0 223000 1.20 130 0 0
## 251 1 404000 0.50 139 0 0
## 252 0 231000 0.80 143 0 0
## 254 1 236000 1.20 132 0 0
## 257 0 294000 1.70 139 0 0
## 262 0 283000 0.70 133 0 0
## 264 0 208000 1.00 140 0 0
## 269 0 302000 0.90 140 0 0
## 272 0 221000 0.90 134 0 0
## 273 0 215000 1.20 133 0 0
## 276 1 422000 0.80 137 0 0
## 277 0 327000 1.10 142 0 0
## 279 0 232000 0.70 136 0 0
## 280 0 451000 1.30 136 0 0
## 288 0 543000 1.00 132 0 0
## 289 0 263358 1.10 142 0 0
## 290 0 390000 0.90 144 0 0
## 291 0 222000 0.80 141 0 0
## 296 0 270000 1.20 139 0 0
## 297 0 742000 0.80 138 0 0
##
## $`1`
## age anaemia creatinine_phosphokinase diabetes ejection_fraction
## 1 75.000 0 582 0 20
## 2 55.000 0 7861 0 38
## 3 65.000 0 146 0 20
## 4 50.000 1 111 0 20
## 6 90.000 1 47 0 40
## 7 75.000 1 246 0 15
## 8 60.000 1 315 1 60
## 10 80.000 1 123 0 35
## 11 75.000 1 81 0 38
## 12 62.000 0 231 0 25
## 13 45.000 1 981 0 30
## 14 50.000 1 168 0 38
## 16 82.000 1 379 0 50
## 17 87.000 1 149 0 38
## 18 45.000 0 582 0 14
## 23 68.000 1 220 0 35
## 24 53.000 0 63 1 60
## 26 80.000 0 148 1 38
## 28 70.000 0 122 1 45
## 29 58.000 1 60 0 38
## 30 82.000 0 70 1 30
## 31 94.000 0 582 1 38
## 32 85.000 0 23 0 45
## 35 65.000 0 94 1 50
## 36 69.000 0 582 1 35
## 37 90.000 1 60 1 50
## 39 60.000 0 2656 1 30
## 41 70.000 0 582 0 20
## 43 70.000 0 571 1 45
## 44 72.000 0 127 1 50
## 46 50.000 0 582 1 38
## 47 51.000 0 1380 0 25
## 48 60.000 0 582 1 38
## 49 80.000 1 553 0 20
## 51 68.000 1 577 0 25
## 56 95.000 1 371 0 30
## 57 70.000 1 75 0 35
## 58 60.000 1 607 0 40
## 59 49.000 0 789 0 20
## 60 72.000 0 364 1 20
## 61 45.000 0 7702 1 25
## 63 55.000 0 109 0 35
## 64 45.000 0 582 0 35
## 66 60.000 0 68 0 20
## 68 72.000 1 110 0 25
## 70 65.000 0 113 1 25
## 71 41.000 0 148 0 40
## 72 58.000 0 582 1 35
## 73 85.000 0 5882 0 35
## 74 65.000 0 224 1 50
## 75 69.000 0 582 0 20
## 76 60.000 1 47 0 20
## 78 42.000 0 102 1 40
## 79 75.000 1 203 1 38
## 82 67.000 0 582 0 50
## 84 79.000 1 55 0 50
## 86 51.000 0 78 0 50
## 87 55.000 0 47 0 35
## 88 65.000 1 68 1 60
## 89 44.000 0 84 1 40
## 90 57.000 1 115 0 25
## 91 70.000 0 66 1 45
## 92 60.000 0 897 1 45
## 94 60.000 1 154 0 25
## 96 58.000 1 133 0 60
## 97 63.000 1 514 1 25
## 101 65.000 1 305 0 25
## 102 75.000 0 582 0 45
## 103 80.000 0 898 0 25
## 104 42.000 0 5209 0 30
## 107 55.000 0 748 0 45
## 108 45.000 1 1876 1 35
## 109 63.000 0 936 0 38
## 110 45.000 0 292 1 35
## 111 85.000 0 129 0 60
## 112 55.000 0 60 0 35
## 113 50.000 0 369 1 25
## 115 60.000 1 754 1 40
## 121 60.000 1 737 0 60
## 125 60.000 0 582 0 40
## 129 61.000 0 248 0 30
## 130 53.000 1 270 1 35
## 131 53.000 1 1808 0 60
## 132 60.000 1 1082 1 45
## 134 63.000 0 193 0 60
## 135 81.000 0 4540 0 35
## 136 75.000 0 582 0 40
## 138 68.000 1 646 0 25
## 140 50.000 0 1548 0 30
## 141 80.000 0 805 0 38
## 145 72.000 1 943 0 25
## 146 50.000 0 185 0 30
## 147 52.000 0 132 0 30
## 148 64.000 0 1610 0 60
## 149 75.000 1 582 0 30
## 150 60.000 0 2261 0 35
## 152 62.000 0 30 1 60
## 153 50.000 0 115 0 45
## 154 50.000 0 1846 1 35
## 156 60.000 1 231 1 25
## 158 50.000 0 250 0 25
## 159 85.000 1 910 0 50
## 160 59.000 1 129 0 45
## 161 66.000 1 72 0 40
## 162 45.000 1 130 0 35
## 163 63.000 1 582 0 40
## 165 45.000 0 2442 1 30
## 167 53.000 0 196 0 60
## 168 59.000 0 66 1 20
## 171 51.000 1 582 1 35
## 172 52.000 0 3966 0 40
## 173 70.000 1 171 0 60
## 174 50.000 1 115 0 20
## 175 65.000 0 198 1 35
## 176 60.000 1 95 0 60
## 177 69.000 0 1419 0 40
## 179 63.000 1 122 1 60
## 180 55.000 0 835 0 40
## 181 40.000 0 478 1 30
## 182 59.000 1 176 1 25
## 183 65.000 0 395 1 25
## 184 75.000 0 99 0 38
## 185 58.000 1 145 0 25
## 186 60.667 1 104 1 30
## 191 80.000 0 582 1 35
## 193 50.000 1 121 1 40
## 194 73.000 1 231 1 30
## 195 45.000 0 582 0 20
## 196 77.000 1 418 0 45
## 200 60.000 0 1211 1 35
## 201 63.000 1 1767 0 45
## 202 45.000 0 308 1 60
## 203 70.000 0 97 0 60
## 204 60.000 0 59 0 25
## 205 78.000 1 64 0 40
## 208 85.000 0 212 0 38
## 211 70.000 0 212 1 17
## 212 50.000 0 582 0 62
## 213 78.000 0 224 0 50
## 215 65.000 1 135 0 35
## 216 73.000 0 582 0 35
## 219 68.000 1 1021 1 35
## 221 73.000 0 582 0 20
## 222 65.000 0 118 0 50
## 223 42.000 1 86 0 35
## 224 47.000 0 582 0 25
## 225 58.000 0 582 1 25
## 227 58.000 1 57 0 25
## 228 55.000 1 2794 0 35
## 232 70.000 0 93 0 35
## 233 40.000 1 129 0 35
## 234 53.000 1 707 0 38
## 235 53.000 1 582 0 45
## 236 77.000 1 109 0 50
## 237 75.000 0 119 0 50
## 238 70.000 0 232 0 30
## 240 55.000 1 180 0 45
## 242 65.000 0 582 1 30
## 243 40.000 0 90 0 35
## 245 54.000 0 582 1 38
## 246 61.000 1 80 1 38
## 247 55.000 0 2017 0 25
## 248 64.000 0 143 0 25
## 249 40.000 0 624 0 35
## 253 50.000 0 245 0 45
## 255 53.000 1 446 0 60
## 256 52.000 1 191 1 30
## 258 58.000 0 132 1 38
## 259 45.000 1 66 1 25
## 260 53.000 0 56 0 50
## 261 55.000 0 66 0 40
## 263 65.000 1 258 1 25
## 265 61.000 0 582 1 38
## 266 50.000 1 298 0 35
## 267 55.000 0 1199 0 20
## 268 56.000 1 135 1 38
## 270 40.000 0 582 1 35
## 271 44.000 0 582 1 30
## 274 42.000 0 64 0 40
## 275 60.000 1 257 1 30
## 278 70.000 0 582 1 38
## 281 70.000 0 2695 1 40
## 282 70.000 0 582 0 40
## 283 42.000 0 64 0 30
## 284 65.000 0 1688 0 38
## 285 50.000 1 54 0 40
## 286 55.000 1 170 1 40
## 287 60.000 0 253 0 35
## 292 60.000 0 320 0 35
## 293 52.000 0 190 1 38
## 294 63.000 1 103 1 35
## 295 62.000 0 61 1 38
## 298 45.000 0 2413 0 38
## 299 50.000 0 196 0 45
## high_blood_pressure platelets serum_creatinine serum_sodium sex smoking
## 1 1 265000 1.90 130 1 0
## 2 0 263358 1.10 136 1 0
## 3 0 162000 1.30 129 1 1
## 4 0 210000 1.90 137 1 0
## 6 1 204000 2.10 132 1 1
## 7 0 127000 1.20 137 1 0
## 8 0 454000 1.10 131 1 1
## 10 1 388000 9.40 133 1 1
## 11 1 368000 4.00 131 1 1
## 12 1 253000 0.90 140 1 1
## 13 0 136000 1.10 137 1 0
## 14 1 276000 1.10 137 1 0
## 16 0 47000 1.30 136 1 0
## 17 0 262000 0.90 140 1 0
## 18 0 166000 0.80 127 1 0
## 23 1 289000 0.90 140 1 1
## 24 0 368000 0.80 135 1 0
## 26 0 149000 1.90 144 1 1
## 28 1 284000 1.30 136 1 1
## 29 0 153000 5.80 134 1 0
## 30 0 200000 1.20 132 1 1
## 31 1 263358 1.83 134 1 0
## 32 0 360000 3.00 132 1 0
## 35 1 188000 1.00 140 1 0
## 36 0 228000 3.50 134 1 0
## 37 0 226000 1.00 134 1 0
## 39 0 305000 2.30 137 1 0
## 41 1 263358 1.83 134 1 1
## 43 1 185000 1.20 139 1 1
## 44 1 218000 1.00 134 1 0
## 46 0 310000 1.90 135 1 1
## 47 1 271000 0.90 130 1 0
## 48 1 451000 0.60 138 1 1
## 49 1 140000 4.40 133 1 0
## 51 1 166000 1.00 138 1 0
## 56 0 461000 2.00 132 1 0
## 57 0 223000 2.70 138 1 1
## 58 0 216000 0.60 138 1 1
## 59 1 319000 1.10 136 1 1
## 60 1 254000 1.30 136 1 1
## 61 1 390000 1.00 139 1 0
## 63 0 254000 1.10 139 1 1
## 64 0 385000 1.00 145 1 0
## 66 0 119000 2.90 127 1 1
## 68 0 274000 1.00 140 1 1
## 70 0 497000 1.83 135 1 0
## 71 0 374000 0.80 140 1 1
## 72 0 122000 0.90 139 1 1
## 73 0 243000 1.00 132 1 1
## 74 0 149000 1.30 137 1 1
## 75 0 266000 1.20 134 1 1
## 76 0 204000 0.70 139 1 1
## 78 0 237000 1.20 140 1 0
## 79 1 283000 0.60 131 1 1
## 82 0 263358 1.18 137 1 1
## 84 1 172000 1.80 133 1 0
## 86 0 406000 0.70 140 1 0
## 87 1 173000 1.10 137 1 0
## 88 1 304000 0.80 140 1 0
## 89 1 235000 0.70 139 1 0
## 90 1 181000 1.10 144 1 0
## 91 0 249000 0.80 136 1 1
## 92 0 297000 1.00 133 1 0
## 94 0 210000 1.70 135 1 0
## 96 1 219000 1.00 141 1 0
## 97 1 254000 1.30 134 1 0
## 101 0 298000 1.10 141 1 0
## 102 1 263358 1.18 137 1 0
## 103 0 149000 1.10 144 1 1
## 104 0 226000 1.00 140 1 1
## 107 0 263000 1.30 137 1 0
## 108 0 226000 0.90 138 1 0
## 109 0 304000 1.10 133 1 1
## 110 0 850000 1.30 142 1 1
## 111 0 306000 1.20 132 1 1
## 112 0 228000 1.20 135 1 1
## 113 0 252000 1.60 136 1 0
## 115 1 328000 1.20 126 1 0
## 121 1 210000 1.50 135 1 1
## 125 0 217000 3.70 134 1 0
## 129 1 267000 0.70 136 1 1
## 130 0 227000 3.40 145 1 0
## 131 1 249000 0.70 138 1 1
## 132 0 250000 6.10 131 1 0
## 134 1 295000 1.30 145 1 1
## 135 0 231000 1.18 137 1 1
## 136 0 263358 1.18 137 1 0
## 138 0 305000 2.10 130 1 0
## 140 1 211000 0.80 138 1 0
## 141 0 263358 1.10 134 1 0
## 145 1 338000 1.70 139 1 1
## 146 0 266000 0.70 141 1 1
## 147 0 218000 0.70 136 1 1
## 148 0 242000 1.00 137 1 0
## 149 0 225000 1.83 134 1 0
## 150 1 228000 0.90 136 1 0
## 152 1 244000 0.90 139 1 0
## 153 1 184000 0.90 134 1 1
## 154 0 263358 1.18 137 1 1
## 156 0 194000 1.70 140 1 0
## 158 0 262000 1.00 136 1 1
## 159 0 235000 1.30 134 1 0
## 160 1 362000 1.10 139 1 1
## 161 1 242000 1.20 134 1 0
## 162 0 174000 0.80 139 1 1
## 163 0 448000 0.90 137 1 1
## 165 0 334000 1.10 139 1 0
## 167 0 220000 0.70 133 1 1
## 168 0 70000 2.40 134 1 0
## 171 0 263358 1.50 136 1 1
## 172 0 325000 0.90 140 1 1
## 173 1 176000 1.10 145 1 1
## 174 0 189000 0.80 139 1 0
## 175 1 281000 0.90 137 1 1
## 176 0 337000 1.00 138 1 1
## 177 0 105000 1.00 135 1 1
## 179 0 267000 1.20 145 1 0
## 180 0 279000 0.70 140 1 1
## 181 0 303000 0.90 136 1 0
## 182 0 221000 1.00 136 1 1
## 183 0 265000 1.20 136 1 1
## 184 1 224000 2.50 134 1 0
## 185 0 219000 1.20 137 1 1
## 186 0 389000 1.50 136 1 0
## 191 0 350000 2.10 134 1 0
## 193 0 260000 0.70 130 1 0
## 194 0 160000 1.18 142 1 1
## 195 1 126000 1.60 135 1 0
## 196 0 223000 1.80 145 1 0
## 200 0 263358 1.80 113 1 1
## 201 0 73000 0.70 137 1 0
## 202 1 377000 1.00 136 1 0
## 203 1 220000 0.90 138 1 0
## 204 1 212000 3.50 136 1 1
## 205 0 277000 0.70 137 1 1
## 208 0 186000 0.90 136 1 0
## 211 1 389000 1.00 136 1 1
## 212 1 147000 0.80 140 1 1
## 213 0 481000 1.40 138 1 1
## 215 1 290000 0.80 134 1 0
## 216 1 203000 1.30 134 1 0
## 219 0 271000 1.10 134 1 0
## 221 0 263358 1.83 134 1 0
## 222 0 194000 1.10 145 1 1
## 223 0 365000 1.10 139 1 1
## 224 0 130000 0.80 134 1 0
## 225 0 504000 1.00 138 1 0
## 227 0 189000 1.30 132 1 1
## 228 1 141000 1.00 140 1 0
## 232 0 185000 1.10 134 1 1
## 233 0 255000 0.90 137 1 0
## 234 0 330000 1.40 137 1 1
## 235 0 305000 1.10 137 1 1
## 236 1 406000 1.10 137 1 0
## 237 1 248000 1.10 148 1 0
## 238 0 173000 1.20 132 1 0
## 240 0 263358 1.18 137 1 1
## 242 0 249000 1.30 136 1 1
## 243 0 255000 1.10 136 1 1
## 245 0 264000 1.80 134 1 0
## 246 0 282000 1.40 137 1 0
## 247 0 314000 1.10 138 1 0
## 248 0 246000 2.40 135 1 0
## 249 0 301000 1.00 142 1 1
## 253 1 274000 1.00 133 1 0
## 255 1 263358 1.00 139 1 0
## 256 1 334000 1.00 142 1 1
## 258 1 253000 1.00 139 1 0
## 259 0 233000 0.80 135 1 0
## 260 0 308000 0.70 135 1 1
## 261 0 203000 1.00 138 1 0
## 263 0 198000 1.40 129 1 0
## 265 0 147000 1.20 141 1 0
## 266 0 362000 0.90 140 1 1
## 267 0 263358 1.83 134 1 1
## 268 0 133000 1.70 140 1 0
## 270 0 222000 1.00 132 1 0
## 271 1 263358 1.60 130 1 1
## 274 0 189000 0.70 140 1 0
## 275 0 150000 1.00 137 1 1
## 278 0 25100 1.10 140 1 0
## 281 0 241000 1.00 137 1 0
## 282 0 51000 2.70 136 1 1
## 283 0 215000 3.80 128 1 1
## 284 0 263358 1.10 138 1 1
## 285 0 279000 0.80 141 1 0
## 286 0 336000 1.20 135 1 0
## 287 0 279000 1.70 140 1 0
## 292 0 133000 1.40 139 1 0
## 293 0 382000 1.00 140 1 1
## 294 0 179000 0.90 136 1 1
## 295 1 155000 1.10 143 1 1
## 298 0 140000 1.40 140 1 1
## 299 0 395000 1.60 136 1 1# Count the occurrences of each category in categorical variables
anaemia_counts <- table(data1$anaemia)
high_bp_counts <- table(data1$high_blood_pressure)
sex_counts <- table(data1$sex)
smoking_counts <- table(data1$smoking)
diabetes_counts <- table(data1$diabetes)
# Display the counts
print(anaemia_counts)##
## 0 1
## 170 129print(high_bp_counts)##
## 0 1
## 194 105print(sex_counts)##
## 0 1
## 105 194print(smoking_counts)##
## 0 1
## 203 96print(diabetes_counts)##
## 0 1
## 174 125barplot(anaemia_counts, main = "Frequency of Anaemia", xlab = "Anaemia (0 = Yes, 1 = No)", ylab = "Frequency")
barplot(high_bp_counts, main = "Frequency of High Blood Pressure", xlab = "High Blood Pressure (0 = Yes, 1 = No)", ylab = "Frequency")
barplot(smoking_counts, main = "Frequency of Smoking", xlab = "Smoking (0 = Yes, 1 = No)", ylab = "Frequency")
# Create pie charts for binary categorical variables
pie(diabetes_counts, main = "Distribution of Diabetes Risk (0 = Yes, 1 = No)")
#Linear Regression Model
# Implement a multiple linear regression model using R Studio.
#Train the model on the training data
linearMod <- lm(serum_creatinine ~ serum_sodium+ejection_fraction , data = data1)
####build linear regression model on full data
print(linearMod)##
## Call:
## lm(formula = serum_creatinine ~ serum_sodium + ejection_fraction,
## data = data1)
##
## Coefficients:
## (Intercept) serum_sodium ejection_fraction
## 7.503218 -0.045268 0.001981summary(linearMod)##
## Call:
## lm(formula = serum_creatinine ~ serum_sodium + ejection_fraction,
## data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0484 -0.4485 -0.2403 0.0637 7.8481
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.503218 1.833586 4.092 5.52e-05 ***
## serum_sodium -0.045268 0.013590 -3.331 0.000975 ***
## ejection_fraction 0.001981 0.005067 0.391 0.696117
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.019 on 296 degrees of freedom
## Multiple R-squared: 0.03625, Adjusted R-squared: 0.02974
## F-statistic: 5.568 on 2 and 296 DF, p-value: 0.004231# Set the CRAN mirror location programmatically
options(repos = "https://cran.rstudio.com")
# Install and load the caTools package
install.packages("caTools")## Installing package into 'C:/Users/ravindu yasas/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'caTools' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\ravindu yasas\AppData\Local\Temp\RtmpsZuQla\downloaded_packageslibrary(caTools)
# Display the first few rows of the dataset
head(data1)## age anaemia creatinine_phosphokinase diabetes ejection_fraction
## 1 75 0 582 0 20
## 2 55 0 7861 0 38
## 3 65 0 146 0 20
## 4 50 1 111 0 20
## 5 65 1 160 1 20
## 6 90 1 47 0 40
## high_blood_pressure platelets serum_creatinine serum_sodium sex smoking
## 1 1 265000 1.9 130 1 0
## 2 0 263358 1.1 136 1 0
## 3 0 162000 1.3 129 1 1
## 4 0 210000 1.9 137 1 0
## 5 0 327000 2.7 116 0 0
## 6 1 204000 2.1 132 1 1# Split the data into training and testing sets
ind <- sample.split(Y = data1$age, SplitRatio = 0.8)
# Subset into training data
train <- data1[ind, ]
# Subset into testing data
test <- data1[!ind, ]
# Check the dimensions of the training and testing sets
dim(train)## [1] 244 11dim(test)## [1] 55 11# Fit the multiple linear regression model on the training data
model <- lm(age ~ ., data = train)
# Make predictions on the test data
predictions <- predict(model, newdata = test)
# Calculate Mean Square Error (MSE)
mse <- mean((test$age - predictions)^2)
# Calculate Root Mean Squared Error (RMSE)
rmse <- sqrt(mse)
# Calculate R-Squared
rsquared <- summary(model)$r.squared
# Create a dataframe with actual and predicted ejection_fraction values
comparison <- data.frame(Actual = test$ejection_fraction, Predicted = predictions)
# Display the first few rows of the comparison dataframe
head(comparison)## Actual Predicted
## 12 25 62.35362
## 16 50 62.16032
## 22 30 61.45255
## 29 38 68.99561
## 33 35 61.01248
## 35 50 61.50065