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(dslabs)
data(heights)
library(ggplot2)#checks if x is in c sorta like membership
x<-c(1,3,5,"ready")
x %in% c(1,2,3,4)[1] TRUE TRUE FALSE FALSE#adds a new column w/ murder rate
murders <- mutate(murders, rate = total/population)
head(murders) state abb region population total rate
1 Alabama AL South 4779736 135 2.824424e-05
2 Alaska AK West 710231 19 2.675186e-05
3 Arizona AZ West 6392017 232 3.629527e-05
4 Arkansas AR South 2915918 93 3.189390e-05
5 California CA West 37253956 1257 3.374138e-05
6 Colorado CO West 5029196 65 1.292453e-05#filters out states w murder rates less than 0.7
murder1 <- filter(murders, rate<=0.2)
murder1 state abb region population total rate
1 Alabama AL South 4779736 135 2.824424e-05
2 Alaska AK West 710231 19 2.675186e-05
3 Arizona AZ West 6392017 232 3.629527e-05
4 Arkansas AR South 2915918 93 3.189390e-05
5 California CA West 37253956 1257 3.374138e-05
6 Colorado CO West 5029196 65 1.292453e-05
7 Connecticut CT Northeast 3574097 97 2.713972e-05
8 Delaware DE South 897934 38 4.231937e-05
9 District of Columbia DC South 601723 99 1.645275e-04
10 Florida FL South 19687653 669 3.398069e-05
11 Georgia GA South 9920000 376 3.790323e-05
12 Hawaii HI West 1360301 7 5.145920e-06
13 Idaho ID West 1567582 12 7.655102e-06
14 Illinois IL North Central 12830632 364 2.836961e-05
15 Indiana IN North Central 6483802 142 2.190073e-05
16 Iowa IA North Central 3046355 21 6.893484e-06
17 Kansas KS North Central 2853118 63 2.208111e-05
18 Kentucky KY South 4339367 116 2.673201e-05
19 Louisiana LA South 4533372 351 7.742581e-05
20 Maine ME Northeast 1328361 11 8.280881e-06
21 Maryland MD South 5773552 293 5.074866e-05
22 Massachusetts MA Northeast 6547629 118 1.802179e-05
23 Michigan MI North Central 9883640 413 4.178622e-05
24 Minnesota MN North Central 5303925 53 9.992600e-06
25 Mississippi MS South 2967297 120 4.044085e-05
26 Missouri MO North Central 5988927 321 5.359892e-05
27 Montana MT West 989415 12 1.212838e-05
28 Nebraska NE North Central 1826341 32 1.752137e-05
29 Nevada NV West 2700551 84 3.110476e-05
30 New Hampshire NH Northeast 1316470 5 3.798036e-06
31 New Jersey NJ Northeast 8791894 246 2.798032e-05
32 New Mexico NM West 2059179 67 3.253724e-05
33 New York NY Northeast 19378102 517 2.667960e-05
34 North Carolina NC South 9535483 286 2.999324e-05
35 North Dakota ND North Central 672591 4 5.947151e-06
36 Ohio OH North Central 11536504 310 2.687123e-05
37 Oklahoma OK South 3751351 111 2.958934e-05
38 Oregon OR West 3831074 36 9.396843e-06
39 Pennsylvania PA Northeast 12702379 457 3.597751e-05
40 Rhode Island RI Northeast 1052567 16 1.520093e-05
41 South Carolina SC South 4625364 207 4.475323e-05
42 South Dakota SD North Central 814180 8 9.825837e-06
43 Tennessee TN South 6346105 219 3.450936e-05
44 Texas TX South 25145561 805 3.201360e-05
45 Utah UT West 2763885 22 7.959810e-06
46 Vermont VT Northeast 625741 2 3.196211e-06
47 Virginia VA South 8001024 250 3.124600e-05
48 Washington WA West 6724540 93 1.382994e-05
49 West Virginia WV South 1852994 27 1.457101e-05
50 Wisconsin WI North Central 5686986 97 1.705649e-05
51 Wyoming WY West 563626 5 8.871131e-06#keeps the selected columns
new_table <- select(murders, state, region, rate)
new_table state region rate
1 Alabama South 2.824424e-05
2 Alaska West 2.675186e-05
3 Arizona West 3.629527e-05
4 Arkansas South 3.189390e-05
5 California West 3.374138e-05
6 Colorado West 1.292453e-05
7 Connecticut Northeast 2.713972e-05
8 Delaware South 4.231937e-05
9 District of Columbia South 1.645275e-04
10 Florida South 3.398069e-05
11 Georgia South 3.790323e-05
12 Hawaii West 5.145920e-06
13 Idaho West 7.655102e-06
14 Illinois North Central 2.836961e-05
15 Indiana North Central 2.190073e-05
16 Iowa North Central 6.893484e-06
17 Kansas North Central 2.208111e-05
18 Kentucky South 2.673201e-05
19 Louisiana South 7.742581e-05
20 Maine Northeast 8.280881e-06
21 Maryland South 5.074866e-05
22 Massachusetts Northeast 1.802179e-05
23 Michigan North Central 4.178622e-05
24 Minnesota North Central 9.992600e-06
25 Mississippi South 4.044085e-05
26 Missouri North Central 5.359892e-05
27 Montana West 1.212838e-05
28 Nebraska North Central 1.752137e-05
29 Nevada West 3.110476e-05
30 New Hampshire Northeast 3.798036e-06
31 New Jersey Northeast 2.798032e-05
32 New Mexico West 3.253724e-05
33 New York Northeast 2.667960e-05
34 North Carolina South 2.999324e-05
35 North Dakota North Central 5.947151e-06
36 Ohio North Central 2.687123e-05
37 Oklahoma South 2.958934e-05
38 Oregon West 9.396843e-06
39 Pennsylvania Northeast 3.597751e-05
40 Rhode Island Northeast 1.520093e-05
41 South Carolina South 4.475323e-05
42 South Dakota North Central 9.825837e-06
43 Tennessee South 3.450936e-05
44 Texas South 3.201360e-05
45 Utah West 7.959810e-06
46 Vermont Northeast 3.196211e-06
47 Virginia South 3.124600e-05
48 Washington West 1.382994e-05
49 West Virginia South 1.457101e-05
50 Wisconsin North Central 1.705649e-05
51 Wyoming West 8.871131e-06#filters out all regions not in south
no_south <- filter(murders, region != "South")
no_south state abb region population total rate
1 Alaska AK West 710231 19 2.675186e-05
2 Arizona AZ West 6392017 232 3.629527e-05
3 California CA West 37253956 1257 3.374138e-05
4 Colorado CO West 5029196 65 1.292453e-05
5 Connecticut CT Northeast 3574097 97 2.713972e-05
6 Hawaii HI West 1360301 7 5.145920e-06
7 Idaho ID West 1567582 12 7.655102e-06
8 Illinois IL North Central 12830632 364 2.836961e-05
9 Indiana IN North Central 6483802 142 2.190073e-05
10 Iowa IA North Central 3046355 21 6.893484e-06
11 Kansas KS North Central 2853118 63 2.208111e-05
12 Maine ME Northeast 1328361 11 8.280881e-06
13 Massachusetts MA Northeast 6547629 118 1.802179e-05
14 Michigan MI North Central 9883640 413 4.178622e-05
15 Minnesota MN North Central 5303925 53 9.992600e-06
16 Missouri MO North Central 5988927 321 5.359892e-05
17 Montana MT West 989415 12 1.212838e-05
18 Nebraska NE North Central 1826341 32 1.752137e-05
19 Nevada NV West 2700551 84 3.110476e-05
20 New Hampshire NH Northeast 1316470 5 3.798036e-06
21 New Jersey NJ Northeast 8791894 246 2.798032e-05
22 New Mexico NM West 2059179 67 3.253724e-05
23 New York NY Northeast 19378102 517 2.667960e-05
24 North Dakota ND North Central 672591 4 5.947151e-06
25 Ohio OH North Central 11536504 310 2.687123e-05
26 Oregon OR West 3831074 36 9.396843e-06
27 Pennsylvania PA Northeast 12702379 457 3.597751e-05
28 Rhode Island RI Northeast 1052567 16 1.520093e-05
29 South Dakota SD North Central 814180 8 9.825837e-06
30 Utah UT West 2763885 22 7.959810e-06
31 Vermont VT Northeast 625741 2 3.196211e-06
32 Washington WA West 6724540 93 1.382994e-05
33 Wisconsin WI North Central 5686986 97 1.705649e-05
34 Wyoming WY West 563626 5 8.871131e-06#filtering only south and west, bind with c when there is more than one
murders_sw <- filter(murders, region %in% c("South","West"))
murders_sw state abb region population total rate
1 Alabama AL South 4779736 135 2.824424e-05
2 Alaska AK West 710231 19 2.675186e-05
3 Arizona AZ West 6392017 232 3.629527e-05
4 Arkansas AR South 2915918 93 3.189390e-05
5 California CA West 37253956 1257 3.374138e-05
6 Colorado CO West 5029196 65 1.292453e-05
7 Delaware DE South 897934 38 4.231937e-05
8 District of Columbia DC South 601723 99 1.645275e-04
9 Florida FL South 19687653 669 3.398069e-05
10 Georgia GA South 9920000 376 3.790323e-05
11 Hawaii HI West 1360301 7 5.145920e-06
12 Idaho ID West 1567582 12 7.655102e-06
13 Kentucky KY South 4339367 116 2.673201e-05
14 Louisiana LA South 4533372 351 7.742581e-05
15 Maryland MD South 5773552 293 5.074866e-05
16 Mississippi MS South 2967297 120 4.044085e-05
17 Montana MT West 989415 12 1.212838e-05
18 Nevada NV West 2700551 84 3.110476e-05
19 New Mexico NM West 2059179 67 3.253724e-05
20 North Carolina NC South 9535483 286 2.999324e-05
21 Oklahoma OK South 3751351 111 2.958934e-05
22 Oregon OR West 3831074 36 9.396843e-06
23 South Carolina SC South 4625364 207 4.475323e-05
24 Tennessee TN South 6346105 219 3.450936e-05
25 Texas TX South 25145561 805 3.201360e-05
26 Utah UT West 2763885 22 7.959810e-06
27 Virginia VA South 8001024 250 3.124600e-05
28 Washington WA West 6724540 93 1.382994e-05
29 West Virginia WV South 1852994 27 1.457101e-05
30 Wyoming WY West 563626 5 8.871131e-06#find how many observations and variables
data(heights)
str(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 65#load datasets
data(heights)
str(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 ...#from dataset heights take the ones with the sex of male and the height of over 70
#== doesnt remove those that arent true, just shows as false
tall_males <- heights$sex == "Male" & heights$height >70
tall_males [1] TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE
[13] FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE
[25] TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE
[37] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE FALSE
[49] FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE FALSE
[61] FALSE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE
[73] FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[85] FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE
[97] FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[109] FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE
[121] FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE
[133] TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE TRUE
[145] TRUE TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
[157] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[169] FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE
[181] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
[193] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE FALSE
[205] FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE
[217] FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[229] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[241] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[253] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[265] FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE
[277] TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[289] FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE
[301] TRUE TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE
[313] FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE
[325] TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE FALSE
[337] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE
[349] FALSE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[361] FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE
[373] TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE FALSE
[385] FALSE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE FALSE TRUE FALSE
[397] FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE
[409] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE
[421] FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE
[433] FALSE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE
[445] TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
[457] TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[469] FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE TRUE FALSE
[481] TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[493] TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE
[505] TRUE TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
[517] FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[529] FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE
[541] FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE TRUE
[553] FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE FALSE
[565] TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[577] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE
[589] FALSE FALSE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[601] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[613] FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE FALSE FALSE
[625] TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE TRUE
[637] TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE
[649] FALSE FALSE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE
[661] FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE FALSE TRUE
[673] FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE
[685] FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE
[697] FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[709] TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
[721] FALSE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE
[733] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[745] TRUE TRUE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[757] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[769] FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
[781] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[793] TRUE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[805] FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE
[817] FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE TRUE
[829] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE
[841] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE FALSE
[853] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE
[865] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[877] FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[889] FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE
[901] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE
[913] FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
[925] TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE
[937] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE
[949] TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE FALSE
[961] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE
[973] FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE
[985] TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE FALSE
[997] TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE TRUE
[1009] FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE FALSE
[1021] FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[1033] FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[1045] FALSE FALSE FALSE FALSE FALSE FALSE#filters out the obs with the variable Female and summarizes it
s<- heights %>% filter(sex == "Female") %>% summarize(average=mean(height), standard_deviation = sd(height))
#displays the accessed results
s$average[1] 64.93942s$standard_deviation[1] 3.760656#seperates dataset into 2 by gender
height_grp <- heights %>% group_by(sex)
height_grp %>% summarize(avg=mean(height), stdev =sd(height))# A tibble: 2 × 3
sex avg 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"#arranges by small to large
murders %>% arrange(population) %>% head() state abb region population total rate
1 Wyoming WY West 563626 5 8.871131e-06
2 District of Columbia DC South 601723 99 1.645275e-04
3 Vermont VT Northeast 625741 2 3.196211e-06
4 North Dakota ND North Central 672591 4 5.947151e-06
5 Alaska AK West 710231 19 2.675186e-05
6 South Dakota SD North Central 814180 8 9.825837e-06#organanizes in decending order
murders %>% arrange(desc(total)) %>% head() state abb region population total rate
1 California CA West 37253956 1257 3.374138e-05
2 Texas TX South 25145561 805 3.201360e-05
3 Florida FL South 19687653 669 3.398069e-05
4 New York NY Northeast 19378102 517 2.667960e-05
5 Pennsylvania PA Northeast 12702379 457 3.597751e-05
6 Michigan MI North Central 9883640 413 4.178622e-05#gives counts for sex
table(heights$sex)
Female Male
238 812 #counts the amount of observations in each region
table(murders$region)
Northeast South North Central West
9 17 12 13 #plots as a bar graph
heights %>% ggplot(aes(sex, fill = sex)) +geom_bar()
#gives the percentage
heights %>% count(sex) %>% mutate(proportion = n/sum(n)) sex n proportion
1 Female 238 0.2266667
2 Male 812 0.7733333#creates bar plot
murders %>% ggplot(aes(region, fill = region)) + geom_bar() +scale_fill_manual(values=c("red","blue","purple","lightblue"))
heights %>% ggplot(aes(sex,height,fill=sex)) + geom_boxplot()