data("mtcars")
mtcars<- as_tibble(mtcars)
myData <-read_csv ("../00_data/myData.csv")
## Rows: 27 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): film, film_rating
## dbl (2): number, run_time
## date (1): release_date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
Case of numeric variables
mtcars%>% map_dbl(.x= ., .f= ~mean(x = .x))
## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500
mtcars%>% map_dbl(.f= ~mean(x= .x))
## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500
mtcars%>% map_dbl(mean)
## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500
# adding argument
mtcars%>% map_dbl(.x= ., .f= ~mean(x = .x, trim= 0.1))
## mpg cyl disp hp drat wt
## 19.6961538 6.2307692 222.5230769 141.1923077 3.5792308 3.1526923
## qsec vs am gear carb
## 17.8276923 0.4230769 0.3846154 3.6153846 2.6538462
mtcars%>% map_dbl(mean, trim= 0.1)
## mpg cyl disp hp drat wt
## 19.6961538 6.2307692 222.5230769 141.1923077 3.5792308 3.1526923
## qsec vs am gear carb
## 17.8276923 0.4230769 0.3846154 3.6153846 2.6538462
mtcars%>% select(.data= ., mpg)
## # A tibble: 32 × 1
## mpg
## <dbl>
## 1 21
## 2 21
## 3 22.8
## 4 21.4
## 5 18.7
## 6 18.1
## 7 14.3
## 8 24.4
## 9 22.8
## 10 19.2
## # ℹ 22 more rows
mtcars%>% select(mpg)
## # A tibble: 32 × 1
## mpg
## <dbl>
## 1 21
## 2 21
## 3 22.8
## 4 21.4
## 5 18.7
## 6 18.1
## 7 14.3
## 8 24.4
## 9 22.8
## 10 19.2
## # ℹ 22 more rows
Create your own function
# double values in colums
double_by_factor<- function(x, factor) {x* factor}
10%>% double_by_factor(factor= 2)
## [1] 20
mtcars%>% map_dfr(.x= ., .f= ~double_by_factor(x= .x, factor= 10))
## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 210 60 1600 1100 39 26.2 165. 0 10 40 40
## 2 210 60 1600 1100 39 28.8 170. 0 10 40 40
## 3 228 40 1080 930 38.5 23.2 186. 10 10 40 10
## 4 214 60 2580 1100 30.8 32.2 194. 10 0 30 10
## 5 187 80 3600 1750 31.5 34.4 170. 0 0 30 20
## 6 181 60 2250 1050 27.6 34.6 202. 10 0 30 10
## 7 143 80 3600 2450 32.1 35.7 158. 0 0 30 40
## 8 244 40 1467 620 36.9 31.9 200 10 0 40 20
## 9 228 40 1408 950 39.2 31.5 229 10 0 40 20
## 10 192 60 1676 1230 39.2 34.4 183 10 0 40 40
## # ℹ 22 more rows
mtcars%>% map_dfr(double_by_factor, factor= 10)
## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 210 60 1600 1100 39 26.2 165. 0 10 40 40
## 2 210 60 1600 1100 39 28.8 170. 0 10 40 40
## 3 228 40 1080 930 38.5 23.2 186. 10 10 40 10
## 4 214 60 2580 1100 30.8 32.2 194. 10 0 30 10
## 5 187 80 3600 1750 31.5 34.4 170. 0 0 30 20
## 6 181 60 2250 1050 27.6 34.6 202. 10 0 30 10
## 7 143 80 3600 2450 32.1 35.7 158. 0 0 30 40
## 8 244 40 1467 620 36.9 31.9 200 10 0 40 20
## 9 228 40 1408 950 39.2 31.5 229 10 0 40 20
## 10 192 60 1676 1230 39.2 34.4 183 10 0 40 40
## # ℹ 22 more rows
When you have a grouping variable (factor)
mtcars%>% lm(formula= mpg~ wt, data= .)
##
## Call:
## lm(formula = mpg ~ wt, data = .)
##
## Coefficients:
## (Intercept) wt
## 37.285 -5.344
mtcars%>% distinct(cyl)
## # A tibble: 3 × 1
## cyl
## <dbl>
## 1 6
## 2 4
## 3 8
reg_coeff_tbl<- mtcars%>%
#split into list
split(.$cyl) %>%
#repeat regression
map(~lm(formula= mpg~ wt, data= .x))%>%
# extract coefficients
map(broom::tidy, conf.int= TRUE)%>%
#convert to tibble
bind_rows(.id = "cyl")%>%
#filter for WT
filter(term== "wt")
reg_coeff_tbl%>%
mutate(estimate= -estimate,
conf.low= -conf.low,
conf.high= -conf.high)%>%
ggplot(aes(x= estimate, y= cyl))+
geom_point()+
geom_errorbar(aes(xmin= conf.low, xmax= conf.high))
Choose either one of the two cases above and apply it to your data
myData%>% lm(formula= run_time~ release_date, data= .)
##
## Call:
## lm(formula = run_time ~ release_date, data = .)
##
## Coefficients:
## (Intercept) release_date
## 59.669348 0.002968
myData%>% distinct(film_rating)
## # A tibble: 4 × 1
## film_rating
## <chr>
## 1 G
## 2 PG
## 3 N/A
## 4 Not Rated
reg_results<- myData%>%
#split into list
split(.$film_rating) %>%
#repeat regression
map(~lm(formula= run_time~ release_date, data= .x))%>%
# extract coefficients
map(broom::tidy, conf.int= TRUE)%>%
#convert to tibble
bind_rows(.id = "film_rating")%>%
#filter for WT
filter(term== "release_date")
## Warning in qt(a, object$df.residual): NaNs produced
## Warning in qt(a, object$df.residual): NaNs produced
reg_results%>%
mutate(estimate= -estimate,
conf.low= -conf.low,
conf.high= -conf.high)%>%
ggplot(aes(x= estimate, y= film_rating))+
geom_point()+
geom_errorbar(aes(xmin= conf.low, xmax= conf.high))
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).