# load heart.csv directly from my website
library(tidyverse)
Heart <- read_csv("https://nmimoto.github.io/datasets/heart.csv")
# Description of the data is here:
# https://nmimoto.github.io/datasets/heart.txt
# print(Heart, n=100) # use this if you want to see more rows
# print(Heart, width=1000) # use this if you want to see more columns
Heart # shows you a bit of data with some info.## # A tibble: 303 × 15
## index Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng Oldpeak
## <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 63 1 typical 145 233 1 2 150 0 2.3
## 2 2 67 1 asymptomatic 160 286 0 2 108 1 1.5
## 3 3 67 1 asymptomatic 120 229 0 2 129 1 2.6
## 4 4 37 1 nonanginal 130 250 0 0 187 0 3.5
## 5 5 41 0 nontypical 130 204 0 2 172 0 1.4
## 6 6 56 1 nontypical 120 236 0 0 178 0 0.8
## 7 7 62 0 asymptomatic 140 268 0 2 160 0 3.6
## 8 8 57 0 asymptomatic 120 354 0 0 163 1 0.6
## 9 9 63 1 asymptomatic 130 254 0 2 147 0 1.4
## 10 10 53 1 asymptomatic 140 203 1 2 155 1 3.1
## # ℹ 293 more rows
## # ℹ 4 more variables: Slope <dbl>, Ca <dbl>, Thal <chr>, AHD <chr>## [1] "spec_tbl_df" "tbl_df" "tbl" "data.frame"## [1] TRUE## [1] "index" "Age" "Sex" "ChestPain" "RestBP" "Chol"
## [7] "Fbs" "RestECG" "MaxHR" "ExAng" "Oldpeak" "Slope"
## [13] "Ca" "Thal" "AHD"## [1] "data.frame"## [1] TRUE## [1] FALSElibrary(tidyverse)
iris = as_tibble(iris) # turn it into a tibble
is.tibble(iris) # now it’s a tibble## Warning: `is.tibble()` was deprecated in tibble 2.0.0.
## ℹ Please use `is_tibble()` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## [1] TRUE## [1] TRUE## # A tibble: 150 × 5
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## # ℹ 140 more rowsHeart # this is a tibble
Heart["index"] # select column with name “index”
Heart[1] # select 1st column (note that there’s no comma)
Heart[ ,1] # select 1st column (same as the case of matrix)
Heart[1, ] # select 1st row (same as the case of matrix)
Heart$index # another way
## You can also use pipe operator “%>%”
## and function select to do the same
Heart %>% select(index) # select column with name index
Heart %>% select("index") # quotes are optional## Make a table of ChestPain column in Heart data
table(Heart["ChestPain"]) # old school way
table(Heart$ChestPain) # also an old school way## ChestPain
## asymptomatic nonanginal nontypical typical
## 144 86 50 23# Method 1
# Apply class() to each column of Heart. Answer is a list, and hard to read.
Heart %>% lapply(class)## $index
## [1] "numeric"
##
## $Age
## [1] "numeric"
##
## $Sex
## [1] "numeric"
##
## $ChestPain
## [1] "character"
##
## $RestBP
## [1] "numeric"
##
## $Chol
## [1] "numeric"
##
## $Fbs
## [1] "numeric"
##
## $RestECG
## [1] "numeric"
##
## $MaxHR
## [1] "numeric"
##
## $ExAng
## [1] "numeric"
##
## $Oldpeak
## [1] "numeric"
##
## $Slope
## [1] "numeric"
##
## $Ca
## [1] "numeric"
##
## $Thal
## [1] "character"
##
## $AHD
## [1] "character"## index Age Sex ChestPain RestBP Chol
## "numeric" "numeric" "numeric" "character" "numeric" "numeric"
## Fbs RestECG MaxHR ExAng Oldpeak Slope
## "numeric" "numeric" "numeric" "numeric" "numeric" "numeric"
## Ca Thal AHD
## "numeric" "character" "character"## # A tibble: 303 × 15
## index Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng Oldpeak
## <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 63 1 typical 145 233 1 2 150 0 2.3
## 2 2 67 1 asymptomatic 160 286 0 2 108 1 1.5
## 3 3 67 1 asymptomatic 120 229 0 2 129 1 2.6
## 4 4 37 1 nonanginal 130 250 0 0 187 0 3.5
## 5 5 41 0 nontypical 130 204 0 2 172 0 1.4
## 6 6 56 1 nontypical 120 236 0 0 178 0 0.8
## 7 7 62 0 asymptomatic 140 268 0 2 160 0 3.6
## 8 8 57 0 asymptomatic 120 354 0 0 163 1 0.6
## 9 9 63 1 asymptomatic 130 254 0 2 147 0 1.4
## 10 10 53 1 asymptomatic 140 203 1 2 155 1 3.1
## # ℹ 293 more rows
## # ℹ 4 more variables: Slope <dbl>, Ca <dbl>, Thal <chr>, AHD <chr>## # A tibble: 303 × 7
## index Age Sex ChestPain RestBP Chol Fbs
## <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl>
## 1 1 63 1 typical 145 233 1
## 2 2 67 1 asymptomatic 160 286 0
## 3 3 67 1 asymptomatic 120 229 0
## 4 4 37 1 nonanginal 130 250 0
## 5 5 41 0 nontypical 130 204 0
## 6 6 56 1 nontypical 120 236 0
## 7 7 62 0 asymptomatic 140 268 0
## 8 8 57 0 asymptomatic 120 354 0
## 9 9 63 1 asymptomatic 130 254 0
## 10 10 53 1 asymptomatic 140 203 1
## # ℹ 293 more rows## # A tibble: 303 × 8
## RestECG MaxHR ExAng Oldpeak Slope Ca Thal AHD
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 2 150 0 2.3 3 0 fixed No
## 2 2 108 1 1.5 2 3 normal Yes
## 3 2 129 1 2.6 2 2 reversable Yes
## 4 0 187 0 3.5 3 0 normal No
## 5 2 172 0 1.4 1 0 normal No
## 6 0 178 0 0.8 1 0 normal No
## 7 2 160 0 3.6 3 2 normal Yes
## 8 0 163 1 0.6 1 0 normal No
## 9 2 147 0 1.4 2 1 reversable Yes
## 10 2 155 1 3.1 3 0 reversable Yes
## # ℹ 293 more rows## Rows: 303
## Columns: 15
## $ index <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1…
## $ Age <dbl> 63, 67, 67, 37, 41, 56, 62, 57, 63, 53, 57, 56, 56, 44, 52, …
## $ Sex <dbl> 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, …
## $ ChestPain <chr> "typical", "asymptomatic", "asymptomatic", "nonanginal", "no…
## $ RestBP <dbl> 145, 160, 120, 130, 130, 120, 140, 120, 130, 140, 140, 140, …
## $ Chol <dbl> 233, 286, 229, 250, 204, 236, 268, 354, 254, 203, 192, 294, …
## $ Fbs <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, …
## $ RestECG <dbl> 2, 2, 2, 0, 2, 0, 2, 0, 2, 2, 0, 2, 2, 0, 0, 0, 0, 0, 0, 0, …
## $ MaxHR <dbl> 150, 108, 129, 187, 172, 178, 160, 163, 147, 155, 148, 153, …
## $ ExAng <dbl> 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ Oldpeak <dbl> 2.3, 1.5, 2.6, 3.5, 1.4, 0.8, 3.6, 0.6, 1.4, 3.1, 0.4, 1.3, …
## $ Slope <dbl> 3, 2, 2, 3, 1, 1, 3, 1, 2, 3, 2, 2, 2, 1, 1, 1, 3, 1, 1, 1, …
## $ Ca <dbl> 0, 3, 2, 0, 0, 0, 2, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ Thal <chr> "fixed", "normal", "reversable", "normal", "normal", "normal…
## $ AHD <chr> "No", "Yes", "Yes", "No", "No", "No", "Yes", "No", "Yes", "Y…## # A tibble: 303 × 15
## ix_new Age Sex Cpain RestBP Chol Fbs RestECG MaxHR ExAng Oldpeak Slope
## <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 63 1 typi… 145 233 1 2 150 0 2.3 3
## 2 2 67 1 asym… 160 286 0 2 108 1 1.5 2
## 3 3 67 1 asym… 120 229 0 2 129 1 2.6 2
## 4 4 37 1 nona… 130 250 0 0 187 0 3.5 3
## 5 5 41 0 nont… 130 204 0 2 172 0 1.4 1
## 6 6 56 1 nont… 120 236 0 0 178 0 0.8 1
## 7 7 62 0 asym… 140 268 0 2 160 0 3.6 3
## 8 8 57 0 asym… 120 354 0 0 163 1 0.6 1
## 9 9 63 1 asym… 130 254 0 2 147 0 1.4 2
## 10 10 53 1 asym… 140 203 1 2 155 1 3.1 3
## # ℹ 293 more rows
## # ℹ 3 more variables: Ca <dbl>, Thal <chr>, AHD <chr>## # A tibble: 303 × 15
## AHD index Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng
## <chr> <dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 No 1 63 1 typical 145 233 1 2 150 0
## 2 Yes 2 67 1 asymptomatic 160 286 0 2 108 1
## 3 Yes 3 67 1 asymptomatic 120 229 0 2 129 1
## 4 No 4 37 1 nonanginal 130 250 0 0 187 0
## 5 No 5 41 0 nontypical 130 204 0 2 172 0
## 6 No 6 56 1 nontypical 120 236 0 0 178 0
## 7 Yes 7 62 0 asymptomatic 140 268 0 2 160 0
## 8 No 8 57 0 asymptomatic 120 354 0 0 163 1
## 9 Yes 9 63 1 asymptomatic 130 254 0 2 147 0
## 10 Yes 10 53 1 asymptomatic 140 203 1 2 155 1
## # ℹ 293 more rows
## # ℹ 4 more variables: Oldpeak <dbl>, Slope <dbl>, Ca <dbl>, Thal <chr># use .before or .after to specify
Heart %>% relocate(AHD, .after=Age) %>%
relocate(MaxHR, .before=Age)## # A tibble: 303 × 15
## index MaxHR Age AHD Sex ChestPain RestBP Chol Fbs RestECG ExAng
## <dbl> <dbl> <dbl> <chr> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 150 63 No 1 typical 145 233 1 2 0
## 2 2 108 67 Yes 1 asymptomatic 160 286 0 2 1
## 3 3 129 67 Yes 1 asymptomatic 120 229 0 2 1
## 4 4 187 37 No 1 nonanginal 130 250 0 0 0
## 5 5 172 41 No 0 nontypical 130 204 0 2 0
## 6 6 178 56 No 1 nontypical 120 236 0 0 0
## 7 7 160 62 Yes 0 asymptomatic 140 268 0 2 0
## 8 8 163 57 No 0 asymptomatic 120 354 0 0 1
## 9 9 147 63 Yes 1 asymptomatic 130 254 0 2 0
## 10 10 155 53 Yes 1 asymptomatic 140 203 1 2 1
## # ℹ 293 more rows
## # ℹ 4 more variables: Oldpeak <dbl>, Slope <dbl>, Ca <dbl>, Thal <chr>library(tidyverse)
# load fake sample data
Exam1 = read_csv("https://nmimoto.github.io/datasets/examsSample.csv")
Exam1## # A tibble: 45 × 13
## ID First Last `Grade Basis` Units `Program and Plan` Level Status E1
## <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <chr> <dbl>
## 1 609204 Marsh… Kelly ABC/NC 4 Engineering under… Juni… Enrol… 35
## 2 369128 Wicke… Jere… ABC/NC 4 Arts & Sciences u… Seni… Enrol… 42
## 3 817608 O'Nei… Nath… ABC/NC 4 Engineering under… Juni… Enrol… 45
## 4 460606 Antal… Miles ABC/NC 4 Engineering under… Seni… Enrol… 38
## 5 723419 Valai… Kree ABC/NC 4 Arts & Sciences u… Juni… Enrol… 34
## 6 593710 Child… Nich… ABC/NC 4 Arts & Sciences u… 5th … Enrol… 36
## 7 879944 Willi… David ABC/NC 4 Engineering under… 5th … Enrol… 37
## 8 204113 Wesel Elyse ABC/NC 4 Engineering under… 5th … Enrol… 45
## 9 866737 Matus… Amy ABC/NC 4 Engineering under… Juni… Enrol… 45
## 10 629622 Wheel… Alex… ABC/NC 4 The University of… Soph… Enrol… 42
## # ℹ 35 more rows
## # ℹ 4 more variables: E2 <dbl>, E3 <dbl>, E4 <dbl>, Final <dbl>## [1] "ID" "First" "Last" "Grade Basis"
## [5] "Units" "Program and Plan" "Level" "Status"
## [9] "E1" "E2" "E3" "E4"
## [13] "Final"## [1] 5## ID First Last Grade Basis
## 0 0 0 0
## Units Program and Plan Level Status
## 0 0 0 0
## E1 E2 E3 E4
## 0 1 1 1
## Final
## 2## [1] 2write.csv(Heart, file="temp.csv")
library(writexl) # install.packages("writexl")
write_xlsx(Heart, "temp.xlsx")
save(Heart, file="temp.Rdata")##------------------------------
## 1. Loaded Data is Already Tibble
# load heart.csv directly from my website
library(tidyverse)
Heart <- read_csv("https://nmimoto.github.io/datasets/heart.csv")
# Description of the data is here:
# https://nmimoto.github.io/datasets/heart.txt
# print(Heart, n=100) # use this if you want to see more rows
# print(Heart, width=1000) # use this if you want to see more columns
Heart # shows you a bit of data with some info.
class(Heart) # it's tibble
is.data.frame(Heart) # tibble is also a dataframe.
names(Heart) # all the column names of the tibble
##------------------------------
## 2. You can make DF a Tibble
iris # this is built-in data
class(iris) # it’s data.frame
is.data.frame(iris)
is_tibble(iris) # not a tibble
library(tidyverse)
iris = as_tibble(iris) # turn it into a tibble
is.tibble(iris) # now it’s a tibble
is.data.frame(iris) # it’s still a data.frame
# Note the difference in how it is shown on screen
iris
##------------------------------
## 3. Select a column in Tibble
Heart # this is a tibble
Heart["index"] # select column with name “index”
Heart[1] # select 1st column (note that there’s no comma)
Heart[ ,1] # select 1st column (same as the case of matrix)
Heart[1, ] # select 1st row (same as the case of matrix)
Heart$index # another way
## You can also use pipe operator “%>%”
## and function select to do the same
Heart %>% select(index) # select column with name index
Heart %>% select("index") # quotes are optional
##------------------------------
## 4. Pipe operator
## Make a table of ChestPain column in Heart data
table(Heart["ChestPain"]) # old school way
table(Heart$ChestPain) # also an old school way
# Use pipe operator and write
Heart %>% select(ChestPain) %>% table # new school
##------------------------------
## 5. Check Class
# Method 1
# Apply class() to each column of Heart. Answer is a list, and hard to read.
Heart %>% lapply(class)
# make the answer not list
Heart %>% lapply(class) %>% unlist
# Method 2
# this is a good way to check class if you can see all the columns
Heart
# If the columns are too many
Heart[1:7]
Heart[8:15]
# Method 3
# This will show all the columns and their class
glimpse(Heart)
##------------------------------
## 6. Rename Column Names
# rename a column
Heart %>% rename(Cpain = ChestPain) %>%
rename(ix_new = 1) # rename 1st col
##------------------------------
## 7. Change order of Columns
# Bring a column to 1st
Heart %>% relocate(AHD)
# use .before or .after to specify
Heart %>% relocate(AHD, .after=Age) %>%
relocate(MaxHR, .before=Age)
##------------------------------
## 8. NA handling
library(tidyverse)
# load fake sample data
Exam1 = read_csv("https://nmimoto.github.io/datasets/examsSample.csv")
Exam1
names(Exam1)
# see how many NA is in the data
sum(is.na(Exam1))
# number of NA for each column
Exam1 %>% lapply(function(x) sum(is.na(x))) %>% unlist
# number of NA for one column
Exam1 %>% select(Final) %>% is.na %>% sum
##------------------------------
## 9. View Dataframe as Spreadsheet
# view(Heart) # opens spreadsheet like viewer (not recommended)
##------------------------------
## 10. Export Dataframe
write.csv(Heart, file="temp.csv")
library(writexl) # install.packages("writexl")
write_xlsx(Heart, "temp.xlsx")
save(Heart, file="temp.Rdata")