Part I – Workflows using pipes
- Read in the patients dataset and rewrite the following cleaning steps as a workflow using the
%>% operator.
library(tidyverse)
patients <- read_tsv("patient-data.txt")
patients <- mutate(patients, Smokes = Smokes %in% c("TRUE", "Yes"))
patients <- mutate(patients, Height = as.numeric(str_remove(Height, pattern = "cm$")))
patients <- mutate(patients, Weight = as.numeric(str_remove(Weight, pattern = "kg$")))
patients <- mutate(patients, BMI = Weight / (Height / 100) ** 2)
patients <- mutate(patients, Overweight = BMI > 25)
library(tidyverse)
## ── Attaching packages ──────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──
## ✔ ggplot2 3.1.0 ✔ purrr 0.3.1
## ✔ tibble 2.0.1 ✔ dplyr 0.8.0.1
## ✔ tidyr 0.8.3 ✔ stringr 1.4.0
## ✔ readr 1.3.1 ✔ forcats 0.4.0
## ── Conflicts ─────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
patients <- read_tsv("patient-data.txt") %>%
mutate(Smokes = Smokes %in% c("TRUE", "Yes")) %>%
mutate(Height = as.numeric(str_remove(Height, pattern = "cm$"))) %>%
mutate(Weight = as.numeric(str_remove(Weight, pattern = "kg$"))) %>%
mutate(BMI = Weight / (Height / 100) ** 2) %>%
mutate(Overweight = BMI > 25)
## Parsed with column specification:
## cols(
## ID = col_character(),
## Name = col_character(),
## Sex = col_character(),
## Smokes = col_character(),
## Height = col_character(),
## Weight = col_character(),
## Birth = col_date(format = ""),
## State = col_character(),
## Grade_Level = col_double(),
## Died = col_logical(),
## Count = col_double(),
## Date.Entered.Study = col_date(format = "")
## )
patients
## # A tibble: 100 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl>
## 1 AC/A… Mich… Male FALSE 183. 76.6 1972-02-06 Geor… 2
## 2 AC/A… Derek Male FALSE 179. 80.4 1972-06-15 Colo… 2
## 3 AC/A… Todd Male FALSE 169. 75.5 1972-07-09 New … 2
## 4 AC/A… Rona… Male FALSE 176. 94.5 1972-08-17 Colo… 1
## 5 AC/A… Chri… Fema… FALSE 164. 71.8 1973-06-12 Geor… 2
## 6 AC/A… Dana Fema… TRUE 158. 69.9 1973-07-01 Indi… 2
## 7 AC/A… Erin Fema… FALSE 162. 68.8 1972-03-26 New … 1
## 8 AC/A… Rach… Fema… FALSE 166. 70.4 1973-05-11 Colo… 1
## 9 AC/A… Rona… Male FALSE 181. 76.9 1971-12-31 Geor… 1
## 10 AC/A… Bryan Male FALSE 167. 79.1 1973-07-19 New … 2
## # … with 90 more rows, and 5 more variables: Died <lgl>, Count <dbl>,
## # Date.Entered.Study <date>, BMI <dbl>, Overweight <lgl>
- Add a step to the workflow to round the Height, Weight and BMI to 1 decimal place.
patients <- read_tsv("patient-data.txt") %>%
mutate(Smokes = Smokes %in% c("TRUE", "Yes")) %>%
mutate(Height = as.numeric(str_remove(Height, pattern = "cm$"))) %>%
mutate(Weight = as.numeric(str_remove(Weight, pattern = "kg$"))) %>%
mutate(BMI = Weight / (Height / 100) ** 2) %>%
mutate(Overweight = BMI > 25) %>%
mutate_at(vars(Height, Weight, BMI), round, digits = 1)
## Parsed with column specification:
## cols(
## ID = col_character(),
## Name = col_character(),
## Sex = col_character(),
## Smokes = col_character(),
## Height = col_character(),
## Weight = col_character(),
## Birth = col_date(format = ""),
## State = col_character(),
## Grade_Level = col_double(),
## Died = col_logical(),
## Count = col_double(),
## Date.Entered.Study = col_date(format = "")
## )
patients
## # A tibble: 100 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl>
## 1 AC/A… Mich… Male FALSE 183. 76.6 1972-02-06 Geor… 2
## 2 AC/A… Derek Male FALSE 179. 80.4 1972-06-15 Colo… 2
## 3 AC/A… Todd Male FALSE 169. 75.5 1972-07-09 New … 2
## 4 AC/A… Rona… Male FALSE 176. 94.5 1972-08-17 Colo… 1
## 5 AC/A… Chri… Fema… FALSE 164. 71.8 1973-06-12 Geor… 2
## 6 AC/A… Dana Fema… TRUE 158. 69.9 1973-07-01 Indi… 2
## 7 AC/A… Erin Fema… FALSE 162. 68.8 1972-03-26 New … 1
## 8 AC/A… Rach… Fema… FALSE 166. 70.4 1973-05-11 Colo… 1
## 9 AC/A… Rona… Male FALSE 181. 76.9 1971-12-31 Geor… 1
## 10 AC/A… Bryan Male FALSE 167. 79.1 1973-07-19 New … 2
## # … with 90 more rows, and 5 more variables: Died <lgl>, Count <dbl>,
## # Date.Entered.Study <date>, BMI <dbl>, Overweight <lgl>
Part II - Filtering rows
- Filter for female patients from New York or New Jersey.
filter(patients, Sex == "Female", State == "New York" | State == "New Jersey")
## # A tibble: 20 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl>
## 1 AC/A… Erin Fema… FALSE 162. 68.8 1972-03-26 New … 1
## 2 AC/A… Pame… Fema… FALSE 166. 67.3 1971-11-14 New … 1
## 3 AC/A… Eliz… Fema… TRUE 164. 65.8 1972-01-12 New … 3
## 4 AC/A… Paula Fema… FALSE 161. 63.5 1973-07-02 New … 99
## 5 AC/A… Julie Fema… FALSE 160 64.3 1973-09-05 New … 1
## 6 AC/A… Kris… Fema… FALSE 160. 71.9 1973-09-28 New … 2
## 7 AC/A… Tiff… Fema… FALSE 161. 64.8 1973-02-24 New … 1
## 8 AC/A… Bran… Fema… FALSE 160. 68 1972-12-08 New … 2
## 9 AC/A… Alic… Fema… TRUE 170 66.7 1972-09-03 New … 99
## 10 AC/A… Tanya Fema… TRUE 165. 73 1972-01-31 New … 1
## 11 AC/A… Wendy Fema… FALSE 164 66.7 1971-12-29 New … 3
## 12 AC/A… Barb… Fema… FALSE 160. 65.9 1973-01-31 New … 99
## 13 AC/A… Holly Fema… TRUE 160. 68.3 1972-04-29 New … 2
## 14 AC/S… Barb… Fema… TRUE 162. 66.5 1972-02-21 New … 3
## 15 AC/S… Carr… Fema… FALSE 164. 71.5 1973-03-18 New … 3
## 16 AC/S… Laura Fema… FALSE 158. 69.7 1972-06-08 New … 3
## 17 AC/S… Holly Fema… FALSE 159. 70.7 1973-06-27 New … 3
## 18 AC/S… Jill Fema… FALSE 159. 66.2 1972-11-14 New … 1
## 19 AC/S… Rhon… Fema… FALSE 164. 70.7 1972-06-23 New … 3
## 20 AC/S… Shar… Fema… FALSE 161. 71.5 1972-11-17 New … 1
## # … with 5 more variables: Died <lgl>, Count <dbl>,
## # Date.Entered.Study <date>, BMI <dbl>, Overweight <lgl>
filter(patients, Sex == "Female", State %in% c("New York", "New Jersey"))
## # A tibble: 20 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl>
## 1 AC/A… Erin Fema… FALSE 162. 68.8 1972-03-26 New … 1
## 2 AC/A… Pame… Fema… FALSE 166. 67.3 1971-11-14 New … 1
## 3 AC/A… Eliz… Fema… TRUE 164. 65.8 1972-01-12 New … 3
## 4 AC/A… Paula Fema… FALSE 161. 63.5 1973-07-02 New … 99
## 5 AC/A… Julie Fema… FALSE 160 64.3 1973-09-05 New … 1
## 6 AC/A… Kris… Fema… FALSE 160. 71.9 1973-09-28 New … 2
## 7 AC/A… Tiff… Fema… FALSE 161. 64.8 1973-02-24 New … 1
## 8 AC/A… Bran… Fema… FALSE 160. 68 1972-12-08 New … 2
## 9 AC/A… Alic… Fema… TRUE 170 66.7 1972-09-03 New … 99
## 10 AC/A… Tanya Fema… TRUE 165. 73 1972-01-31 New … 1
## 11 AC/A… Wendy Fema… FALSE 164 66.7 1971-12-29 New … 3
## 12 AC/A… Barb… Fema… FALSE 160. 65.9 1973-01-31 New … 99
## 13 AC/A… Holly Fema… TRUE 160. 68.3 1972-04-29 New … 2
## 14 AC/S… Barb… Fema… TRUE 162. 66.5 1972-02-21 New … 3
## 15 AC/S… Carr… Fema… FALSE 164. 71.5 1973-03-18 New … 3
## 16 AC/S… Laura Fema… FALSE 158. 69.7 1972-06-08 New … 3
## 17 AC/S… Holly Fema… FALSE 159. 70.7 1973-06-27 New … 3
## 18 AC/S… Jill Fema… FALSE 159. 66.2 1972-11-14 New … 1
## 19 AC/S… Rhon… Fema… FALSE 164. 70.7 1972-06-23 New … 3
## 20 AC/S… Shar… Fema… FALSE 161. 71.5 1972-11-17 New … 1
## # … with 5 more variables: Died <lgl>, Count <dbl>,
## # Date.Entered.Study <date>, BMI <dbl>, Overweight <lgl>
filter(patients, Sex == "Female", str_starts(State, "New "))
## # A tibble: 20 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl>
## 1 AC/A… Erin Fema… FALSE 162. 68.8 1972-03-26 New … 1
## 2 AC/A… Pame… Fema… FALSE 166. 67.3 1971-11-14 New … 1
## 3 AC/A… Eliz… Fema… TRUE 164. 65.8 1972-01-12 New … 3
## 4 AC/A… Paula Fema… FALSE 161. 63.5 1973-07-02 New … 99
## 5 AC/A… Julie Fema… FALSE 160 64.3 1973-09-05 New … 1
## 6 AC/A… Kris… Fema… FALSE 160. 71.9 1973-09-28 New … 2
## 7 AC/A… Tiff… Fema… FALSE 161. 64.8 1973-02-24 New … 1
## 8 AC/A… Bran… Fema… FALSE 160. 68 1972-12-08 New … 2
## 9 AC/A… Alic… Fema… TRUE 170 66.7 1972-09-03 New … 99
## 10 AC/A… Tanya Fema… TRUE 165. 73 1972-01-31 New … 1
## 11 AC/A… Wendy Fema… FALSE 164 66.7 1971-12-29 New … 3
## 12 AC/A… Barb… Fema… FALSE 160. 65.9 1973-01-31 New … 99
## 13 AC/A… Holly Fema… TRUE 160. 68.3 1972-04-29 New … 2
## 14 AC/S… Barb… Fema… TRUE 162. 66.5 1972-02-21 New … 3
## 15 AC/S… Carr… Fema… FALSE 164. 71.5 1973-03-18 New … 3
## 16 AC/S… Laura Fema… FALSE 158. 69.7 1972-06-08 New … 3
## 17 AC/S… Holly Fema… FALSE 159. 70.7 1973-06-27 New … 3
## 18 AC/S… Jill Fema… FALSE 159. 66.2 1972-11-14 New … 1
## 19 AC/S… Rhon… Fema… FALSE 164. 70.7 1972-06-23 New … 3
## 20 AC/S… Shar… Fema… FALSE 161. 71.5 1972-11-17 New … 1
## # … with 5 more variables: Died <lgl>, Count <dbl>,
## # Date.Entered.Study <date>, BMI <dbl>, Overweight <lgl>
- Filter for overweight smokers that are still alive.
filter(patients, Overweight, Smokes, !Died)
## # A tibble: 6 x 14
## ID Name Sex Smokes Height Weight Birth State Grade_Level Died
## <chr> <chr> <chr> <lgl> <dbl> <dbl> <date> <chr> <dbl> <lgl>
## 1 AC/A… Dana Fema… TRUE 158. 69.9 1973-07-01 Indi… 2 FALSE
## 2 AC/A… Kenn… Male TRUE 175. 92.2 1972-03-22 Colo… 3 FALSE
## 3 AC/A… Stacy Fema… TRUE 165. 75.7 1971-11-22 Colo… 1 FALSE
## 4 AC/A… Tanya Fema… TRUE 165. 73 1972-01-31 New … 1 FALSE
## 5 AC/S… Stacy Fema… TRUE 162. 67.9 1973-07-09 indi… 3 FALSE
## 6 AC/S… Barb… Fema… TRUE 162. 66.5 1972-02-21 New … 3 FALSE
## # … with 4 more variables: Count <dbl>, Date.Entered.Study <date>,
## # BMI <dbl>, Overweight <lgl>