1 Import date, filtrare, statistici descriptive simple (exemple)
Cu tabelul stateData.csv:
- Importăm tabelul în R
state <- read.csv('stateData.csv')- Afișăm dimensiunea tabelului:
dim(state)## [1] 50 12- Afișăm structura tabelului:
str(state)## 'data.frame': 50 obs. of 12 variables:
## $ X : chr "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ state.abb : chr "AL" "AK" "AZ" "AR" ...
## $ state.area : int 51609 589757 113909 53104 158693 104247 5009 2057 58560 58876 ...
## $ state.region : int 2 4 4 2 4 4 1 2 2 2 ...
## $ population : int 3615 365 2212 2110 21198 2541 3100 579 8277 4931 ...
## $ income : int 3624 6315 4530 3378 5114 4884 5348 4809 4815 4091 ...
## $ illiteracy : num 2.1 1.5 1.8 1.9 1.1 0.7 1.1 0.9 1.3 2 ...
## $ life.exp : num 69 69.3 70.5 70.7 71.7 ...
## $ murder : num 15.1 11.3 7.8 10.1 10.3 6.8 3.1 6.2 10.7 13.9 ...
## $ highSchoolGrad: num 41.3 66.7 58.1 39.9 62.6 63.9 56 54.6 52.6 40.6 ...
## $ frost : int 20 152 15 65 20 166 139 103 11 60 ...
## $ area : int 50708 566432 113417 51945 156361 103766 4862 1982 54090 58073 ...- Afișăm primele 6 observații
head(state, 6)## X state.abb state.area state.region population income illiteracy
## 1 Alabama AL 51609 2 3615 3624 2.1
## 2 Alaska AK 589757 4 365 6315 1.5
## 3 Arizona AZ 113909 4 2212 4530 1.8
## 4 Arkansas AR 53104 2 2110 3378 1.9
## 5 California CA 158693 4 21198 5114 1.1
## 6 Colorado CO 104247 4 2541 4884 0.7
## life.exp murder highSchoolGrad frost area
## 1 69.05 15.1 41.3 20 50708
## 2 69.31 11.3 66.7 152 566432
## 3 70.55 7.8 58.1 15 113417
## 4 70.66 10.1 39.9 65 51945
## 5 71.71 10.3 62.6 20 156361
## 6 72.06 6.8 63.9 166 103766- Afișăm ultimele 4 observații
tail(state, 4)## X state.abb state.area state.region population income illiteracy
## 47 Washington WA 68192 4 3559 4864 0.6
## 48 West Virginia WV 24181 2 1799 3617 1.4
## 49 Wisconsin WI 56154 3 4589 4468 0.7
## 50 Wyoming WY 97914 4 376 4566 0.6
## life.exp murder highSchoolGrad frost area
## 47 71.72 4.3 63.5 32 66570
## 48 69.48 6.7 41.6 100 24070
## 49 72.48 3.0 54.5 149 54464
## 50 70.29 6.9 62.9 173 97203- Calculăm media variabilei
population.
mean(state$population)## [1] 4246.42- Calculăm mediana variabilei
population.
median(state$population)## [1] 2838.5- Calculăm valoarea maximă a variabilei
life.exp
max(state$life.exp)## [1] 73.6- Calculăm valoarea minimă a variabilei
state.area
min(state$state.area)## [1] 1214- Selectăm statele cu populație peste 2000 și
illiteracysub 1.
subset(state, population>2000 & illiteracy<1)## X state.abb state.area state.region population income illiteracy
## 6 Colorado CO 104247 4 2541 4884 0.7
## 13 Illinois IL 56400 3 11197 5107 0.9
## 14 Indiana IN 36291 3 5313 4458 0.7
## 15 Iowa IA 56290 3 2861 4628 0.5
## 16 Kansas KS 82264 3 2280 4669 0.6
## 20 Maryland MD 10577 2 4122 5299 0.9
## 22 Michigan MI 58216 3 9111 4751 0.9
## 23 Minnesota MN 84068 3 3921 4675 0.6
## 25 Missouri MO 69686 3 4767 4254 0.8
## 35 Ohio OH 41222 3 10735 4561 0.8
## 37 Oregon OR 96981 4 2284 4660 0.6
## 47 Washington WA 68192 4 3559 4864 0.6
## 49 Wisconsin WI 56154 3 4589 4468 0.7
## life.exp murder highSchoolGrad frost area
## 6 72.06 6.8 63.9 166 103766
## 13 70.14 10.3 52.6 127 55748
## 14 70.88 7.1 52.9 122 36097
## 15 72.56 2.3 59.0 140 55941
## 16 72.58 4.5 59.9 114 81787
## 20 70.22 8.5 52.3 101 9891
## 22 70.63 11.1 52.8 125 56817
## 23 72.96 2.3 57.6 160 79289
## 25 70.69 9.3 48.8 108 68995
## 35 70.82 7.4 53.2 124 40975
## 37 72.13 4.2 60.0 44 96184
## 47 71.72 4.3 63.5 32 66570
## 49 72.48 3.0 54.5 149 54464- Cate sunt?
## [1] 13 12sau pentru a vedea doar numărul de linii:
dim(pt11)[1]## [1] 13sau direct dimensiunea:
## [1] 13 12- Selectăm statele cu populație sub 2000 și
incomesub 4000
subset(state, population<2000 & income<4000)## X state.abb state.area state.region population income illiteracy
## 19 Maine ME 33215 1 1058 3694 0.7
## 31 New Mexico NM 121666 4 1144 3601 2.2
## 45 Vermont VT 9609 1 472 3907 0.6
## 48 West Virginia WV 24181 2 1799 3617 1.4
## life.exp murder highSchoolGrad frost area
## 19 70.39 2.7 54.7 161 30920
## 31 70.32 9.7 55.2 120 121412
## 45 71.64 5.5 57.1 168 9267
## 48 69.48 6.7 41.6 100 24070sau
state[state$population<2000 & state$income<4000,]## X state.abb state.area state.region population income illiteracy
## 19 Maine ME 33215 1 1058 3694 0.7
## 31 New Mexico NM 121666 4 1144 3601 2.2
## 45 Vermont VT 9609 1 472 3907 0.6
## 48 West Virginia WV 24181 2 1799 3617 1.4
## life.exp murder highSchoolGrad frost area
## 19 70.39 2.7 54.7 161 30920
## 31 70.32 9.7 55.2 120 121412
## 45 71.64 5.5 57.1 168 9267
## 48 69.48 6.7 41.6 100 24070sau doar prima coloană:
state[state$population<2000 & state$income<4000,1]## [1] "Maine" "New Mexico" "Vermont" "West Virginia"