library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(ggplot2)
data("murders")Warning in data("murders"): data set 'murders' not founddata(murders)Warning in data(murders): data set 'murders' not foundlibrary(dslabs)
data(heights)
data("heights")x <- c(1, 3, 5)
x %in% c(1, 2, 3, 4)[1] TRUE TRUE FALSEhead(murders) state abb region population total
1 Alabama AL South 4779736 135
2 Alaska AK West 710231 19
3 Arizona AZ West 6392017 232
4 Arkansas AR South 2915918 93
5 California CA West 37253956 1257
6 Colorado CO West 5029196 65murders1 <- mutate(murders, rate = total/population*100000)
filter(murders1, rate <= 0.7) state abb region population total rate
1 Hawaii HI West 1360301 7 0.5145920
2 Iowa IA North Central 3046355 21 0.6893484
3 New Hampshire NH Northeast 1316470 5 0.3798036
4 North Dakota ND North Central 672591 4 0.5947151
5 Vermont VT Northeast 625741 2 0.3196211new_table <- select(murders1, state, region, rate)
new_table state region rate
1 Alabama South 2.8244238
2 Alaska West 2.6751860
3 Arizona West 3.6295273
4 Arkansas South 3.1893901
5 California West 3.3741383
6 Colorado West 1.2924531
7 Connecticut Northeast 2.7139722
8 Delaware South 4.2319369
9 District of Columbia South 16.4527532
10 Florida South 3.3980688
11 Georgia South 3.7903226
12 Hawaii West 0.5145920
13 Idaho West 0.7655102
14 Illinois North Central 2.8369608
15 Indiana North Central 2.1900730
16 Iowa North Central 0.6893484
17 Kansas North Central 2.2081106
18 Kentucky South 2.6732010
19 Louisiana South 7.7425810
20 Maine Northeast 0.8280881
21 Maryland South 5.0748655
22 Massachusetts Northeast 1.8021791
23 Michigan North Central 4.1786225
24 Minnesota North Central 0.9992600
25 Mississippi South 4.0440846
26 Missouri North Central 5.3598917
27 Montana West 1.2128379
28 Nebraska North Central 1.7521372
29 Nevada West 3.1104763
30 New Hampshire Northeast 0.3798036
31 New Jersey Northeast 2.7980319
32 New Mexico West 3.2537239
33 New York Northeast 2.6679599
34 North Carolina South 2.9993237
35 North Dakota North Central 0.5947151
36 Ohio North Central 2.6871225
37 Oklahoma South 2.9589340
38 Oregon West 0.9396843
39 Pennsylvania Northeast 3.5977513
40 Rhode Island Northeast 1.5200933
41 South Carolina South 4.4753235
42 South Dakota North Central 0.9825837
43 Tennessee South 3.4509357
44 Texas South 3.2013603
45 Utah West 0.7959810
46 Vermont Northeast 0.3196211
47 Virginia South 3.1246001
48 Washington West 1.3829942
49 West Virginia South 1.4571013
50 Wisconsin North Central 1.7056487
51 Wyoming West 0.8871131no_south <- filter(murders1, region!="South")
no_south state abb region population total rate
1 Alaska AK West 710231 19 2.6751860
2 Arizona AZ West 6392017 232 3.6295273
3 California CA West 37253956 1257 3.3741383
4 Colorado CO West 5029196 65 1.2924531
5 Connecticut CT Northeast 3574097 97 2.7139722
6 Hawaii HI West 1360301 7 0.5145920
7 Idaho ID West 1567582 12 0.7655102
8 Illinois IL North Central 12830632 364 2.8369608
9 Indiana IN North Central 6483802 142 2.1900730
10 Iowa IA North Central 3046355 21 0.6893484
11 Kansas KS North Central 2853118 63 2.2081106
12 Maine ME Northeast 1328361 11 0.8280881
13 Massachusetts MA Northeast 6547629 118 1.8021791
14 Michigan MI North Central 9883640 413 4.1786225
15 Minnesota MN North Central 5303925 53 0.9992600
16 Missouri MO North Central 5988927 321 5.3598917
17 Montana MT West 989415 12 1.2128379
18 Nebraska NE North Central 1826341 32 1.7521372
19 Nevada NV West 2700551 84 3.1104763
20 New Hampshire NH Northeast 1316470 5 0.3798036
21 New Jersey NJ Northeast 8791894 246 2.7980319
22 New Mexico NM West 2059179 67 3.2537239
23 New York NY Northeast 19378102 517 2.6679599
24 North Dakota ND North Central 672591 4 0.5947151
25 Ohio OH North Central 11536504 310 2.6871225
26 Oregon OR West 3831074 36 0.9396843
27 Pennsylvania PA Northeast 12702379 457 3.5977513
28 Rhode Island RI Northeast 1052567 16 1.5200933
29 South Dakota SD North Central 814180 8 0.9825837
30 Utah UT West 2763885 22 0.7959810
31 Vermont VT Northeast 625741 2 0.3196211
32 Washington WA West 6724540 93 1.3829942
33 Wisconsin WI North Central 5686986 97 1.7056487
34 Wyoming WY West 563626 5 0.8871131murders_sw <- filter(murders, region%in%c("South", "West"))
murders_sw state abb region population total
1 Alabama AL South 4779736 135
2 Alaska AK West 710231 19
3 Arizona AZ West 6392017 232
4 Arkansas AR South 2915918 93
5 California CA West 37253956 1257
6 Colorado CO West 5029196 65
7 Delaware DE South 897934 38
8 District of Columbia DC South 601723 99
9 Florida FL South 19687653 669
10 Georgia GA South 9920000 376
11 Hawaii HI West 1360301 7
12 Idaho ID West 1567582 12
13 Kentucky KY South 4339367 116
14 Louisiana LA South 4533372 351
15 Maryland MD South 5773552 293
16 Mississippi MS South 2967297 120
17 Montana MT West 989415 12
18 Nevada NV West 2700551 84
19 New Mexico NM West 2059179 67
20 North Carolina NC South 9535483 286
21 Oklahoma OK South 3751351 111
22 Oregon OR West 3831074 36
23 South Carolina SC South 4625364 207
24 Tennessee TN South 6346105 219
25 Texas TX South 25145561 805
26 Utah UT West 2763885 22
27 Virginia VA South 8001024 250
28 Washington WA West 6724540 93
29 West Virginia WV South 1852994 27
30 Wyoming WY West 563626 5tall_males <- heights$sex == "Male" & heights$height>70
head(tall_males)[1] TRUE FALSE FALSE TRUE FALSE FALSEstr(heights)'data.frame': 1050 obs. of 2 variables:
$ sex : Factor w/ 2 levels "Female","Male": 2 2 2 2 2 1 1 1 1 2 ...
$ height: num 75 70 68 74 61 65 66 62 66 67 ...head(heights) sex height
1 Male 75
2 Male 70
3 Male 68
4 Male 74
5 Male 61
6 Female 65str(heights)'data.frame': 1050 obs. of 2 variables:
$ sex : Factor w/ 2 levels "Female","Male": 2 2 2 2 2 1 1 1 1 2 ...
$ height: num 75 70 68 74 61 65 66 62 66 67 ...tall_makes <- heights$sex== "Male" & heights$height>70
head(tall_males)[1] TRUE FALSE FALSE TRUE FALSE FALSEs<- heights%>%filter(sex=="Female")%>%
summarize(average=mean(height), standard_deviation=sd(height))
s average standard_deviation
1 64.93942 3.760656library(dplyr)
height_grp<- heights%>% group_by(sex)
height_grp %>%summarize(average=mean(height),stdev=(sd(height)))# A tibble: 2 × 3
sex average stdev
<fct> <dbl> <dbl>
1 Female 64.9 3.76
2 Male 69.3 3.61class(height_grp)[1] "grouped_df" "tbl_df" "tbl" "data.frame"data(murders)
murders%>%arrange(population)%>% head() state abb region population total
1 Wyoming WY West 563626 5
2 District of Columbia DC South 601723 99
3 Vermont VT Northeast 625741 2
4 North Dakota ND North Central 672591 4
5 Alaska AK West 710231 19
6 South Dakota SD North Central 814180 8murders%>%arrange(desc(total))%>%head() state abb region population total
1 California CA West 37253956 1257
2 Texas TX South 25145561 805
3 Florida FL South 19687653 669
4 New York NY Northeast 19378102 517
5 Pennsylvania PA Northeast 12702379 457
6 Michigan MI North Central 9883640 413table(heights$sex)
Female Male
238 812 table(murders$region)
Northeast South North Central West
9 17 12 13 table(heights$sex)
Female Male
238 812 heights%>%ggplot(aes(sex, fill=sex))+geom_bar()
heights%>%count(sex)%>%mutate(proportion=n/sum(n)) sex n proportion
1 Female 238 0.2266667
2 Male 812 0.7733333murders%>%ggplot(aes(region,fill=region))+geom_bar()+scale_fill_manual(values=c("pink","blue", "purple","lightblue"))
heights%>%ggplot(aes(sex,height,fill=sex))+geom_boxplot()