# ref: Express Intro to dplyr
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(readr)
url <- "http://steviep42.bitbucket.org/YOUTUBE.DIR/weather.csv"
download.file(url,"weather.csv")
system("head -5 weather.csv")
## Warning: running command 'head -5 weather.csv' had status 127
weather <- read_csv("weather.csv")
## Parsed with column specification:
## cols(
## .default = col_double(),
## date = col_character(),
## precipitation_inches = col_character(),
## events = col_character(),
## zip_code = col_integer()
## )
## See spec(...) for full column specifications.
weather
## # A tibble: 3,665 × 24
## date max_temperature_f mean_temperature_f min_temperature_f
## <chr> <dbl> <dbl> <dbl>
## 1 8/29/2013 74 68 61
## 2 8/30/2013 78 69 60
## 3 8/31/2013 71 64 57
## 4 9/1/2013 74 66 58
## 5 9/2/2013 75 69 62
## 6 9/3/2013 73 67 60
## 7 9/4/2013 74 68 61
## 8 9/5/2013 72 66 60
## 9 9/6/2013 85 71 56
## 10 9/7/2013 88 73 58
## # ... with 3,655 more rows, and 20 more variables: max_dew_point_f <dbl>,
## # mean_dew_point_f <dbl>, min_dew_point_f <dbl>, max_humidity <dbl>,
## # mean_humidity <dbl>, min_humidity <dbl>,
## # max_sea_level_pressure_inches <dbl>,
## # mean_sea_level_pressure_inches <dbl>,
## # min_sea_level_pressure_inches <dbl>, max_visibility_miles <dbl>,
## # mean_visibility_miles <dbl>, min_visibility_miles <dbl>,
## # max_wind_Speed_mph <dbl>, mean_wind_speed_mph <dbl>,
## # max_gust_speed_mph <dbl>, precipitation_inches <chr>,
## # cloud_cover <dbl>, events <chr>, wind_dir_degrees <dbl>,
## # zip_code <int>
select(weather,precipitation_inches, max_temperature_f,zip_code)
## # A tibble: 3,665 × 3
## precipitation_inches max_temperature_f zip_code
## <chr> <dbl> <int>
## 1 0 74 94107
## 2 0 78 94107
## 3 0 71 94107
## 4 0 74 94107
## 5 0 75 94107
## 6 0 73 94107
## 7 0 74 94107
## 8 0 72 94107
## 9 0 85 94107
## 10 0 88 94107
## # ... with 3,655 more rows
dp_mtcars <- tbl_df(mtcars)
dp_mtcars
## # 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 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## 9 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## 10 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## # ... with 22 more rows
dp_mtcars.m<-mutate(dp_mtcars,wt=wt*1000, good_mpg=ifelse(mpg>"25","good","bad"))
tail(dp_mtcars.m)
## # A tibble: 6 × 12
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 26.0 4 120.3 91 4.43 2140 16.7 0 1 5 2
## 2 30.4 4 95.1 113 3.77 1513 16.9 1 1 5 2
## 3 15.8 8 351.0 264 4.22 3170 14.5 0 1 5 4
## 4 19.7 6 145.0 175 3.62 2770 15.5 0 1 5 6
## 5 15.0 8 301.0 335 3.54 3570 14.6 0 1 5 8
## 6 21.4 4 121.0 109 4.11 2780 18.6 1 1 4 2
## # ... with 1 more variables: good_mpg <chr>
table(dp_mtcars.m$good_mpg)
##
## bad good
## 26 6
filter(dp_mtcars,mpg >=30 | wt>1500)
## # A tibble: 4 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## 2 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## 3 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## 4 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
filter(dp_mtcars.m,mpg >= 30 & wt>1.500)
## # A tibble: 4 × 12
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 32.4 4 78.7 66 4.08 2200 19.47 1 1 4 1
## 2 30.4 4 75.7 52 4.93 1615 18.52 1 1 4 2
## 3 33.9 4 71.1 65 4.22 1835 19.90 1 1 4 1
## 4 30.4 4 95.1 113 3.77 1513 16.90 1 1 5 2
## # ... with 1 more variables: good_mpg <chr>
arrange(dp_mtcars.m,desc(wt))
## # A tibble: 32 × 12
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 10.4 8 460.0 215 3.00 5424 17.82 0 0 3 4
## 2 14.7 8 440.0 230 3.23 5345 17.42 0 0 3 4
## 3 10.4 8 472.0 205 2.93 5250 17.98 0 0 3 4
## 4 16.4 8 275.8 180 3.07 4070 17.40 0 0 3 3
## 5 19.2 8 400.0 175 3.08 3845 17.05 0 0 3 2
## 6 13.3 8 350.0 245 3.73 3840 15.41 0 0 3 4
## 7 15.2 8 275.8 180 3.07 3780 18.00 0 0 3 3
## 8 17.3 8 275.8 180 3.07 3730 17.60 0 0 3 3
## 9 14.3 8 360.0 245 3.21 3570 15.84 0 0 3 4
## 10 15.0 8 301.0 335 3.54 3570 14.60 0 1 5 8
## # ... with 22 more rows, and 1 more variables: good_mpg <chr>
dp_mtcars%>%
mutate(cyl=factor(cyl,levels=c(4,6,8)),
am=factor(am,labels=c("Auto","Manual")))
## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <fctr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <fctr> <dbl> <dbl>
## 1 21.0 6 160.0 110 3.90 2.620 16.46 0 Manual 4 4
## 2 21.0 6 160.0 110 3.90 2.875 17.02 0 Manual 4 4
## 3 22.8 4 108.0 93 3.85 2.320 18.61 1 Manual 4 1
## 4 21.4 6 258.0 110 3.08 3.215 19.44 1 Auto 3 1
## 5 18.7 8 360.0 175 3.15 3.440 17.02 0 Auto 3 2
## 6 18.1 6 225.0 105 2.76 3.460 20.22 1 Auto 3 1
## 7 14.3 8 360.0 245 3.21 3.570 15.84 0 Auto 3 4
## 8 24.4 4 146.7 62 3.69 3.190 20.00 1 Auto 4 2
## 9 22.8 4 140.8 95 3.92 3.150 22.90 1 Auto 4 2
## 10 19.2 6 167.6 123 3.92 3.440 18.30 1 Auto 4 4
## # ... with 22 more rows
dp_mtcars%>%
mutate(cyl=factor(cyl,levels=c(4,6,8)),
am=factor(am,labels=c("Auto","Manual")))%>%
ggplot(aes(x=wt,y=mpg,color=cyl))+geom_point()+facet_wrap(~am)+
xlab("Weigth of the car (1000lbs)")+
ylab("Miles per Gallon")+
ggtitle("Fuel Economy as a function of Weigh,Transmision type
and Cylinders")
