#Load package
require(dplyr)## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionrequire(tidyr)## Loading required package: tidyrrequire(magrittr)## Loading required package: magrittr##
## Attaching package: 'magrittr'## The following object is masked from 'package:tidyr':
##
## extract#Data Input
setwd("C:/Users/Dell/Downloads")
bw=read.csv("birthwt.csv")
head(bw)## X low age lwt race smoke ptl ht ui ftv bwt
## 1 85 0 19 182 2 0 0 0 1 0 2523
## 2 86 0 33 155 3 0 0 0 0 3 2551
## 3 87 0 20 105 1 1 0 0 0 1 2557
## 4 88 0 21 108 1 1 0 0 1 2 2594
## 5 89 0 18 107 1 1 0 0 1 0 2600
## 6 91 0 21 124 3 0 0 0 0 0 2622#Select= selecting rows from dataframe
temp= bw %>% select(low,bwt,lwt,age)
head(temp)## low bwt lwt age
## 1 0 2523 182 19
## 2 0 2551 155 33
## 3 0 2557 105 20
## 4 0 2594 108 21
## 5 0 2600 107 18
## 6 0 2622 124 21#Filter= filtering data based on condition
temp2=bw%>%filter(race==1,bwt<2500)
head(temp2)## X low age lwt race smoke ptl ht ui ftv bwt
## 1 10 1 29 130 1 0 0 0 1 2 1021
## 2 20 1 21 165 1 1 0 1 0 1 1790
## 3 22 1 32 105 1 1 0 0 0 0 1818
## 4 23 1 19 91 1 1 2 0 1 0 1885
## 5 26 1 25 92 1 1 0 0 0 0 1928
## 6 27 1 20 150 1 1 0 0 0 2 1928temp3=bw %>% filter(race %in% c(1,2))%>% select(,age,low,race,bwt)
head(temp3)## age low race bwt
## 1 19 0 2 2523
## 2 20 0 1 2557
## 3 21 0 1 2594
## 4 18 0 1 2600
## 5 22 0 1 2637
## 6 29 0 1 2663#Mutate= creates new variables
temp4=mutate(bw, mother.wt=lwt*0.453592, weight=bwt/1000)
head(temp4)## X low age lwt race smoke ptl ht ui ftv bwt mother.wt weight
## 1 85 0 19 182 2 0 0 0 1 0 2523 82.55374 2.523
## 2 86 0 33 155 3 0 0 0 0 3 2551 70.30676 2.551
## 3 87 0 20 105 1 1 0 0 0 1 2557 47.62716 2.557
## 4 88 0 21 108 1 1 0 0 1 2 2594 48.98794 2.594
## 5 89 0 18 107 1 1 0 0 1 0 2600 48.53434 2.600
## 6 91 0 21 124 3 0 0 0 0 0 2622 56.24541 2.622#Mutate= coding data
temp6=bw%>%mutate(group=recode(low,"0"="No","1"="Yes"),ethnic=recode(race,"1"="White", "2"="Black", "3"="Hispanics"))
head(temp6)## X low age lwt race smoke ptl ht ui ftv bwt group ethnic
## 1 85 0 19 182 2 0 0 0 1 0 2523 No Black
## 2 86 0 33 155 3 0 0 0 0 3 2551 No Hispanics
## 3 87 0 20 105 1 1 0 0 0 1 2557 No White
## 4 88 0 21 108 1 1 0 0 1 2 2594 No White
## 5 89 0 18 107 1 1 0 0 1 0 2600 No White
## 6 91 0 21 124 3 0 0 0 0 0 2622 No Hispanics#Arrange= sorting data
arrange(temp4,mother.wt,weight)## X low age lwt race smoke ptl ht ui ftv bwt mother.wt weight
## 1 44 1 20 80 3 1 0 0 1 0 2211 36.28736 2.211
## 2 15 1 25 85 3 0 0 0 1 0 1474 38.55532 1.474
## 3 137 0 22 85 3 1 0 0 0 0 3090 38.55532 3.090
## 4 32 1 25 89 3 0 2 0 0 1 2055 40.36969 2.055
## 5 118 0 24 90 1 1 1 0 0 1 2948 40.82328 2.948
## 6 132 0 18 90 1 1 0 0 1 0 3062 40.82328 3.062
## 7 133 0 18 90 1 1 0 0 1 0 3062 40.82328 3.062
## 8 23 1 19 91 1 1 2 0 1 0 1885 41.27687 1.885
## 9 26 1 25 92 1 1 0 0 0 0 1928 41.73046 1.928
## 10 82 1 23 94 3 1 0 0 0 0 2495 42.63765 2.495
## 11 79 1 28 95 1 1 0 0 0 2 2466 43.09124 2.466
## 12 96 0 19 95 3 0 0 0 0 0 2722 43.09124 2.722
## 13 98 0 22 95 3 0 0 1 0 0 2751 43.09124 2.751
## 14 141 0 30 95 1 1 0 0 0 2 3147 43.09124 3.147
## 15 188 0 25 95 1 1 3 0 1 0 3637 43.09124 3.637
## 16 216 0 16 95 3 0 0 0 0 1 3997 43.09124 3.997
## 17 54 1 26 96 3 0 0 0 0 0 2325 43.54483 2.325
## 18 17 1 23 97 3 0 0 0 1 1 1588 43.99842 1.588
## 19 102 0 15 98 2 0 0 0 0 0 2778 44.45202 2.778
## 20 52 1 21 100 3 0 1 0 0 4 2301 45.35920 2.301
## 21 81 1 14 100 3 0 0 0 0 2 2495 45.35920 2.495
## 22 100 0 18 100 1 1 0 0 0 0 2769 45.35920 2.769
## 23 101 0 18 100 1 1 0 0 0 0 2769 45.35920 2.769
## 24 107 0 31 100 1 0 0 0 1 3 2835 45.35920 2.835
## 25 78 1 14 101 3 1 1 0 0 0 2466 45.81279 2.466
## 26 33 1 19 102 1 0 0 0 0 2 2082 46.26638 2.082
## 27 56 1 31 102 1 1 1 0 0 1 2353 46.26638 2.353
## 28 30 1 21 103 3 0 0 0 0 0 1970 46.71998 1.970
## 29 93 0 17 103 3 0 0 0 0 1 2637 46.71998 2.637
## 30 146 0 20 103 3 0 0 0 0 0 3203 46.71998 3.203
## 31 13 1 25 105 3 0 1 1 0 0 1330 47.62716 1.330
## 32 22 1 32 105 1 1 0 0 0 0 1818 47.62716 1.818
## 33 46 1 25 105 3 0 1 0 0 1 2240 47.62716 2.240
## 34 61 1 24 105 2 1 0 0 0 0 2381 47.62716 2.381
## 35 76 1 20 105 3 0 0 0 0 3 2450 47.62716 2.450
## 36 87 0 20 105 1 1 0 0 0 1 2557 47.62716 2.557
## 37 181 0 19 105 3 0 0 0 0 0 3572 47.62716 3.572
## 38 89 0 18 107 1 1 0 0 1 0 2600 48.53434 2.600
## 39 99 0 30 107 3 0 1 0 1 2 2750 48.53434 2.750
## 40 88 0 21 108 1 1 0 0 1 2 2594 48.98794 2.594
## 41 47 1 20 109 3 0 0 0 0 0 2240 49.44153 2.240
## 42 127 0 33 109 1 1 0 0 0 1 3033 49.44153 3.033
## 43 45 1 17 110 1 1 0 0 0 0 2225 49.89512 2.225
## 44 50 1 18 110 2 1 1 0 0 0 2296 49.89512 2.296
## 45 57 1 15 110 1 0 0 0 0 0 2353 49.89512 2.353
## 46 69 1 23 110 1 1 1 0 0 0 2424 49.89512 2.424
## 47 143 0 16 110 3 0 0 0 0 0 3175 49.89512 3.175
## 48 144 0 21 110 3 1 0 0 1 0 3203 49.89512 3.203
## 49 150 0 24 110 3 0 0 0 0 0 3232 49.89512 3.232
## 50 176 0 30 110 3 0 0 0 0 0 3544 49.89512 3.544
## 51 196 0 24 110 1 0 0 0 0 1 3728 49.89512 3.728
## 52 199 0 24 110 3 0 1 0 0 0 3770 49.89512 3.770
## 53 200 0 23 110 1 0 0 0 0 1 3770 49.89512 3.770
## 54 34 1 19 112 1 1 0 0 1 0 2084 50.80230 2.084
## 55 162 0 22 112 1 1 2 0 0 0 3317 50.80230 3.317
## 56 166 0 16 112 2 0 0 0 0 0 3374 50.80230 3.374
## 57 203 0 30 112 1 0 0 0 0 1 3799 50.80230 3.799
## 58 95 0 26 113 1 1 0 0 0 0 2665 51.25590 2.665
## 59 116 0 17 113 2 0 0 0 0 1 2920 51.25590 2.920
## 60 117 0 17 113 2 0 0 0 0 1 2920 51.25590 2.920
## 61 24 1 25 115 3 0 0 0 0 0 1893 52.16308 1.893
## 62 62 1 15 115 3 0 0 0 1 0 2381 52.16308 2.381
## 63 136 0 24 115 1 0 0 0 0 2 3090 52.16308 3.090
## 64 142 0 19 115 3 0 0 0 0 0 3175 52.16308 3.175
## 65 156 0 24 115 3 0 0 0 0 2 3274 52.16308 3.274
## 66 164 0 23 115 3 1 0 0 0 1 3331 52.16308 3.331
## 67 219 0 21 115 1 0 0 0 0 1 4054 52.16308 4.054
## 68 225 0 24 116 1 0 0 0 0 1 4593 52.61667 4.593
## 69 35 1 26 117 1 1 1 0 0 0 2084 53.07026 2.084
## 70 210 0 33 117 1 0 0 0 1 1 3912 53.07026 3.912
## 71 92 0 22 118 1 0 0 0 0 1 2637 53.52386 2.637
## 72 103 0 25 118 1 1 0 0 0 3 2782 53.52386 2.782
## 73 147 0 17 119 3 0 0 0 0 0 3225 53.97745 3.225
## 74 148 0 17 119 3 0 0 0 0 0 3225 53.97745 3.225
## 75 149 0 23 119 3 0 0 0 0 2 3232 53.97745 3.232
## 76 4 1 28 120 3 1 1 0 1 0 709 54.43104 0.709
## 77 40 1 20 120 2 1 0 0 0 3 2126 54.43104 2.126
## 78 63 1 23 120 3 0 0 0 0 0 2410 54.43104 2.410
## 79 68 1 17 120 1 1 0 0 0 3 2414 54.43104 2.414
## 80 71 1 17 120 2 0 0 0 0 2 2438 54.43104 2.438
## 81 104 0 20 120 3 0 0 0 1 0 2807 54.43104 2.807
## 82 105 0 28 120 1 1 0 0 0 1 2821 54.43104 2.821
## 83 109 0 28 120 3 0 0 0 0 0 2863 54.43104 2.863
## 84 111 0 25 120 3 0 0 0 1 2 2877 54.43104 2.877
## 85 138 0 22 120 1 0 0 1 0 1 3100 54.43104 3.100
## 86 180 0 17 120 3 1 0 0 0 0 3572 54.43104 3.572
## 87 201 0 20 120 3 0 0 0 0 0 3770 54.43104 3.770
## 88 205 0 18 120 1 1 0 0 0 2 3856 54.43104 3.856
## 89 208 0 18 120 3 0 0 0 0 1 3884 54.43104 3.884
## 90 215 0 25 120 1 0 0 0 0 2 3983 54.43104 3.983
## 91 222 0 31 120 1 0 0 0 0 2 4167 54.43104 4.167
## 92 224 0 19 120 1 1 0 0 0 0 4238 54.43104 4.238
## 93 51 1 20 121 1 1 1 0 1 0 2296 54.88463 2.296
## 94 106 0 32 121 3 0 0 0 0 2 2835 54.88463 2.835
## 95 119 0 35 121 2 1 1 0 0 1 2948 54.88463 2.948
## 96 172 0 20 121 2 1 0 0 0 0 3444 54.88463 3.444
## 97 60 1 20 122 2 1 0 0 0 0 2381 55.33822 2.381
## 98 113 0 17 122 1 1 0 0 0 0 2906 55.33822 2.906
## 99 94 0 29 123 1 1 0 0 0 1 2663 55.79182 2.663
## 100 179 0 23 123 3 0 0 0 0 0 3544 55.79182 3.544
## 101 226 0 45 123 1 0 0 0 0 1 4990 55.79182 4.990
## 102 91 0 21 124 3 0 0 0 0 0 2622 56.24541 2.622
## 103 125 0 27 124 1 1 0 0 0 0 2922 56.24541 2.922
## 104 31 1 20 125 3 0 0 0 1 0 2055 56.69900 2.055
## 105 121 0 25 125 2 0 0 0 0 0 2977 56.69900 2.977
## 106 184 0 22 125 1 0 0 0 0 1 3614 56.69900 3.614
## 107 177 0 20 127 3 0 0 0 0 0 3487 57.60618 3.487
## 108 18 1 24 128 2 0 1 0 0 1 1701 58.05978 1.701
## 109 139 0 23 128 3 0 0 0 0 0 3104 58.05978 3.104
## 110 220 0 22 129 1 0 0 0 0 0 4111 58.51337 4.111
## 111 10 1 29 130 1 0 0 0 1 2 1021 58.96696 1.021
## 112 25 1 16 130 3 0 0 0 0 1 1899 58.96696 1.899
## 113 37 1 17 130 3 1 1 0 1 0 2125 58.96696 2.125
## 114 42 1 22 130 1 1 1 0 1 1 2187 58.96696 2.187
## 115 43 1 27 130 2 0 0 0 1 0 2187 58.96696 2.187
## 116 67 1 22 130 1 1 0 0 0 1 2410 58.96696 2.410
## 117 84 1 21 130 1 1 0 1 0 3 2495 58.96696 2.495
## 118 130 0 23 130 2 0 0 0 0 1 3062 58.96696 3.062
## 119 140 0 22 130 1 1 0 0 0 0 3132 58.96696 3.132
## 120 182 0 23 130 1 0 0 0 0 0 3586 58.96696 3.586
## 121 209 0 29 130 1 1 0 0 0 2 3884 58.96696 3.884
## 122 214 0 28 130 3 0 0 0 0 0 3969 58.96696 3.969
## 123 221 0 25 130 1 0 0 0 0 2 4153 58.96696 4.153
## 124 174 0 22 131 1 0 0 0 0 1 3460 59.42055 3.460
## 125 19 1 24 132 3 0 0 1 0 0 1729 59.87414 1.729
## 126 134 0 32 132 1 0 0 0 0 4 3080 59.87414 3.080
## 127 135 0 19 132 3 0 0 0 0 0 3090 59.87414 3.090
## 128 154 0 26 133 3 1 2 0 0 0 3260 60.32774 3.260
## 129 185 0 24 133 1 0 0 0 0 0 3614 60.32774 3.614
## 130 170 0 32 134 1 1 1 0 0 4 3430 60.78133 3.430
## 131 186 0 21 134 3 0 0 0 0 2 3629 60.78133 3.629
## 132 212 0 28 134 3 0 0 0 0 1 3941 60.78133 3.941
## 133 167 0 16 135 1 1 0 0 0 0 3374 61.23492 3.374
## 134 189 0 16 135 1 1 0 0 0 0 3643 61.23492 3.643
## 135 190 0 29 135 1 0 0 0 0 1 3651 61.23492 3.651
## 136 213 0 14 135 1 0 0 0 0 0 3941 61.23492 3.941
## 137 195 0 30 137 1 0 0 0 0 1 3699 62.14210 3.699
## 138 36 1 24 138 1 0 0 0 0 0 2100 62.59570 2.100
## 139 124 0 19 138 1 1 0 0 0 2 2977 62.59570 2.977
## 140 123 0 29 140 1 1 0 0 0 2 2977 63.50288 2.977
## 141 151 0 28 140 1 0 0 0 0 0 3234 63.50288 3.234
## 142 169 0 25 140 1 0 0 0 0 1 3416 63.50288 3.416
## 143 160 0 20 141 1 0 2 0 1 1 3317 63.95647 3.317
## 144 65 1 30 142 1 1 1 0 0 0 2410 64.41006 2.410
## 145 83 1 17 142 2 0 0 1 0 0 2495 64.41006 2.495
## 146 192 0 19 147 1 1 0 0 0 0 3651 66.67802 3.651
## 147 193 0 19 147 1 1 0 0 0 0 3651 66.67802 3.651
## 148 49 1 18 148 3 0 0 0 0 0 2282 67.13162 2.282
## 149 16 1 27 150 3 0 0 0 0 0 1588 68.03880 1.588
## 150 27 1 20 150 1 1 0 0 0 2 1928 68.03880 1.928
## 151 97 0 19 150 3 0 0 0 0 1 2733 68.03880 2.733
## 152 114 0 29 150 1 0 0 0 0 2 2920 68.03880 2.920
## 153 163 0 31 150 3 1 0 0 0 2 3321 68.03880 3.321
## 154 145 0 30 153 3 0 0 0 0 0 3203 69.39958 3.203
## 155 75 1 26 154 3 0 1 1 0 1 2442 69.85317 2.442
## 156 191 0 29 154 1 0 0 0 0 1 3651 69.85317 3.651
## 157 29 1 24 155 1 1 1 0 0 0 1936 70.30676 1.936
## 158 86 0 33 155 3 0 0 0 0 3 2551 70.30676 2.551
## 159 120 0 25 155 1 0 0 0 0 1 2977 70.30676 2.977
## 160 161 0 22 158 2 0 1 0 0 2 3317 71.66754 3.317
## 161 217 0 20 158 1 0 0 0 0 1 3997 71.66754 3.997
## 162 131 0 21 160 1 0 0 0 0 0 3062 72.57472 3.062
## 163 218 0 26 160 3 0 0 0 0 0 4054 72.57472 4.054
## 164 20 1 21 165 1 1 0 1 0 1 1790 74.84268 1.790
## 165 112 0 28 167 1 0 0 0 0 0 2877 75.74986 2.877
## 166 115 0 26 168 2 1 0 0 0 0 2920 76.20346 2.920
## 167 155 0 20 169 3 0 1 0 1 1 3274 76.65705 3.274
## 168 204 0 22 169 1 0 0 0 0 0 3827 76.65705 3.827
## 169 175 0 32 170 1 0 0 0 0 0 3473 77.11064 3.473
## 170 206 0 16 170 2 0 0 0 0 4 3860 77.11064 3.860
## 171 211 0 20 170 1 1 0 0 0 0 3940 77.11064 3.940
## 172 223 0 35 170 1 0 1 0 0 1 4174 77.11064 4.174
## 173 183 0 36 175 1 0 0 0 0 0 3600 79.37860 3.600
## 174 85 0 19 182 2 0 0 0 1 0 2523 82.55374 2.523
## 175 197 0 19 184 1 1 0 1 0 0 3756 83.46093 3.756
## 176 128 0 21 185 2 1 0 0 0 2 3042 83.91452 3.042
## 177 207 0 32 186 1 0 0 0 0 2 3860 84.36811 3.860
## 178 11 1 34 187 2 1 0 1 0 0 1135 84.82170 1.135
## 179 59 1 23 187 2 1 0 0 0 1 2367 84.82170 2.367
## 180 129 0 19 189 1 0 0 0 0 2 3062 85.72889 3.062
## 181 77 1 26 190 1 1 0 0 0 0 2466 86.18248 2.466
## 182 173 0 23 190 1 0 0 0 0 0 3459 86.18248 3.459
## 183 28 1 21 200 2 0 0 0 1 2 1928 90.71840 1.928
## 184 108 0 36 202 1 0 0 0 0 1 2836 91.62558 2.836
## 185 126 0 31 215 1 1 0 0 0 2 3005 97.52228 3.005
## 186 168 0 18 229 2 0 0 0 0 0 3402 103.87257 3.402
## 187 187 0 19 235 1 1 0 1 0 0 3629 106.59412 3.629
## 188 202 0 25 241 2 0 0 1 0 0 3790 109.31567 3.790
## 189 159 0 28 250 3 1 0 0 0 6 3303 113.39800 3.303head(temp4)## X low age lwt race smoke ptl ht ui ftv bwt mother.wt weight
## 1 85 0 19 182 2 0 0 0 1 0 2523 82.55374 2.523
## 2 86 0 33 155 3 0 0 0 0 3 2551 70.30676 2.551
## 3 87 0 20 105 1 1 0 0 0 1 2557 47.62716 2.557
## 4 88 0 21 108 1 1 0 0 1 2 2594 48.98794 2.594
## 5 89 0 18 107 1 1 0 0 1 0 2600 48.53434 2.600
## 6 91 0 21 124 3 0 0 0 0 0 2622 56.24541 2.622#summerize, group_by()- summarizizng data by group
bygroup=group_by(bw,race,smoke)
temp5=summarize(bygroup,count=n(),mean.age=mean(age,na.rm=T),mean.lwt=mean(lwt,na.rm=T), mean.bw=mean(bwt,na.rm=T))## `summarise()` has grouped output by 'race'. You can override using the `.groups` argument.head(temp5)## # A tibble: 6 x 6
## # Groups: race [3]
## race smoke count mean.age mean.lwt mean.bw
## <int> <int> <int> <dbl> <dbl> <dbl>
## 1 1 0 44 26.0 139. 3429.
## 2 1 1 52 22.8 126. 2827.
## 3 2 0 16 19.9 149. 2854.
## 4 2 1 10 24.1 143. 2504
## 5 3 0 55 22.4 119. 2816.
## 6 3 1 12 22.5 124 2757.#Sample
d5=sample_n(bw,10)
d5## X low age lwt race smoke ptl ht ui ftv bwt
## 1 218 0 26 160 3 0 0 0 0 0 4054
## 2 121 0 25 125 2 0 0 0 0 0 2977
## 3 81 1 14 100 3 0 0 0 0 2 2495
## 4 162 0 22 112 1 1 2 0 0 0 3317
## 5 87 0 20 105 1 1 0 0 0 1 2557
## 6 96 0 19 95 3 0 0 0 0 0 2722
## 7 103 0 25 118 1 1 0 0 0 3 2782
## 8 88 0 21 108 1 1 0 0 1 2 2594
## 9 47 1 20 109 3 0 0 0 0 0 2240
## 10 97 0 19 150 3 0 0 0 0 1 2733