#install.packages("dslabs")
library(dslabs)
data("murders")
estado_por_region <- murders %>% group_by(region) %>% summarize(num_estados = n_distinct(state))
print(estado_por_region)
#install.packages("dplyr")
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
estado_por_region <- murders %>%
group_by(region) %>%
summarize(num_estados = n_distinct(state))
print(estado_por_region)
## # A tibble: 4 × 2
## region num_estados
## <fct> <int>
## 1 Northeast 9
## 2 South 17
## 3 North Central 12
## 4 West 13
install.packages("dslabs")
## Warning: package 'dslabs' is in use and will not be installed
library(dslabs)
data(movielens)
head(movielens)
## movieId title year
## 1 31 Dangerous Minds 1995
## 2 1029 Dumbo 1941
## 3 1061 Sleepers 1996
## 4 1129 Escape from New York 1981
## 5 1172 Cinema Paradiso (Nuovo cinema Paradiso) 1989
## 6 1263 Deer Hunter, The 1978
## genres userId rating timestamp
## 1 Drama 1 2.5 1260759144
## 2 Animation|Children|Drama|Musical 1 3.0 1260759179
## 3 Thriller 1 3.0 1260759182
## 4 Action|Adventure|Sci-Fi|Thriller 1 2.0 1260759185
## 5 Drama 1 4.0 1260759205
## 6 Drama|War 1 2.0 1260759151
num_filas <-nrow(movielens)
print(num_filas)
## [1] 100004
num_variables <-ncol(movielens)
print(num_variables)
## [1] 7
names(movielens)
## [1] "movieId" "title" "year" "genres" "userId" "rating"
## [7] "timestamp"
class(movielens$title)
## [1] "character"
class(movielens$genres)
## [1] "factor"
genres_factor <- factor(movielens$genres)
num_niveles <- nlevels(genres_factor)
print(num_niveles)
## [1] 901
nlevels(movielens$genres)
## [1] 901
pop <-data.frame(murders$population)
pop <-data.frame(murders$population)
pop
## murders.population
## 1 4779736
## 2 710231
## 3 6392017
## 4 2915918
## 5 37253956
## 6 5029196
## 7 3574097
## 8 897934
## 9 601723
## 10 19687653
## 11 9920000
## 12 1360301
## 13 1567582
## 14 12830632
## 15 6483802
## 16 3046355
## 17 2853118
## 18 4339367
## 19 4533372
## 20 1328361
## 21 5773552
## 22 6547629
## 23 9883640
## 24 5303925
## 25 2967297
## 26 5988927
## 27 989415
## 28 1826341
## 29 2700551
## 30 1316470
## 31 8791894
## 32 2059179
## 33 19378102
## 34 9535483
## 35 672591
## 36 11536504
## 37 3751351
## 38 3831074
## 39 12702379
## 40 1052567
## 41 4625364
## 42 814180
## 43 6346105
## 44 25145561
## 45 2763885
## 46 625741
## 47 8001024
## 48 6724540
## 49 1852994
## 50 5686986
## 51 563626
pop_min<- min(murders$population)
murders$population[pop_min]
## [1] NA
pop_min
## [1] 563626