add_cols()
: Add one or more columns to an existing data frame. If
specified .before
or .after
columns does not exist, columns are
appended at the end of the data. Return a data frame with all the original
columns in .data
plus the columns declared in ...
. In
add_cols()
columns in .data
are available for the expressions.
So, it is possible to add a column based on existing data.
add_rows()
: Add one or more rows to an existing data frame. If
specified .before
or .after
rows does not exist, rows are
appended at the end of the data. Return a data frame with all the original
rows in .data
plus the rows declared in ...
argument.
add_row_id()
: Add a column with the row id as the first column in
.data
.
add_prefix()
and add_suffix()
add prefixes and suffixes,
respectively, in variable names selected in ...
argument.
all_pairs()
: Get all the possible pairs between the levels of a
factor.
colnames_to_lower()
: Translate all column names to lower case.
colnames_to_upper()
: Translate all column names to upper case.
colnames_to_title()
: Translate all column names to title case.
column_exists()
: Checks if a column exists in a data frame. Return a
logical value.
columns_to_first()
: Move columns to first positions in .data
.
columns_to_last()
: Move columns to last positions in .data
.
columns_to_rownames()
: Move a column of .data
to its row
names.
rownames_to_column()
: Move the row names of .data
to a new
column.
remove_rownames()
: Remove the row names of .data
.
concatenate()
: Concatenate columns of a data frame. If drop = TRUE
then the existing variables are dropped. If pull = TRUE
then the
concatenated variable is pull out to a vector. This is specially useful when
using concatenate
to add columns to a data frame with add_cols()
.
get_levels()
: Get the levels of a factor variable.
get_levels_comb()
: Get the combination of the levels of a factor.
get_level_size()
: Get the size of each level of a factor variable.
remove_cols()
: Remove one or more columns from a data frame.
remove_rows()
: Remove one or more rows from a data frame.
reorder_cols()
: Reorder columns in a data frame.
select_cols()
: Select one or more columns from a data frame.
select_first_col()
: Select first variable, possibly with an offset.
select_last_col()
: Select last variable, possibly with an offset.
select_numeric_cols()
: Select all the numeric columns of a data
frame.
select_non_numeric_cols()
: Select all the non-numeric columns of a
data frame.
select_rows()
: Select one or more rows from a data frame.
tidy_colnames()
: Tidy up column names with
tidy_strings()
.
add_cols(.data, ..., .before = NULL, .after = NULL)add_rows(.data, ..., .before = NULL, .after = NULL)
add_row_id(.data, var = "row_id")
all_pairs(.data, levels)
add_prefix(.data, ..., prefix, sep = "_")
add_suffix(.data, ..., suffix, sep = "_")
colnames_to_lower(.data)
colnames_to_upper(.data)
colnames_to_title(.data)
column_to_first(.data, ...)
column_to_last(.data, ...)
column_to_rownames(.data, var = "rowname")
rownames_to_column(.data, var = "rowname")
remove_rownames(.data, ...)
column_exists(.data, cols)
concatenate(
.data,
...,
prefix = NULL,
suffix = NULL,
new_var = new_var,
sep = "_",
drop = FALSE,
pull = FALSE,
.before = NULL,
.after = NULL
)
get_levels(.data, ...)
get_levels_comb(.data, ...)
get_level_size(.data, ...)
reorder_cols(.data, ..., .before = NULL, .after = NULL)
remove_cols(.data, ...)
remove_rows(.data, ...)
select_first_col(.data, offset = NULL)
select_last_col(.data, offset = NULL)
select_numeric_cols(.data)
select_non_numeric_cols(.data)
select_cols(.data, ...)
select_rows(.data, ...)
tidy_colnames(.data, sep = "_")
A data frame
The argument depends on the function used.
For add_cols()
and add_rows()
is name-value pairs. All values
must have one element for each row in .data
when using
add_cols()
or one element for each column in .data
when using
add_rows()
. Values of length 1 will be recycled when using
add_cols()
.
For remove_cols()
and select_cols()
, ...
is the
column name or column index of the variable(s) to be dropped.
For add_prefix()
and add_suffix()
, ...
is the column
name to add the prefix or suffix, respectively. Select helpers are allowed.
For columns_to_first()
and columns_to_last()
, ...
is
the column name or column index of the variable(s) to be moved to first or
last in .data
.
For remove_rows()
and select_rows()
, ...
is an integer
row value.
For concatenate()
, ...
is the unquoted variable names to be
concatenated.
For get_levels()
, get_level_comb()
, and
get_level_size()
...
is the unquoted variable names to get the
levels, levels combinations and levels size, respectively.
For add_cols()
, concatenate()
, and
reorder_cols()
, one-based column index or column name where to add
the new columns, default: .after last column. For add_rows()
,
one-based row index where to add the new rows, default: .after last row.
Name of column to use for rownames.
The levels of a factor or a numeric vector.
The prefix and suffix used in add_prefix()
and
add_suffix()
, respectively.
The separator to appear when using concatenate()
,
add_prefix()
, or add_suffix()
. Defaults to to "_"
.
A quoted variable name to check if it exists in .data
.
The name of the new variable containing the concatenated
values. Defaults to new_var
.
Logical argument. If TRUE
keeps the new variable
new_var
and drops the existing ones. Defaults to FALSE
.
Logical argument. If TRUE
, returns the last column (on the
assumption that's the column you've created most recently), as a vector.
Set it to n to select the nth variable from the
end (for select_last_col()
) of from the begin (for
select_first_col()
)
# NOT RUN {
library(metan)
################# Adding columns #################
# Variables x and y .after last column
data_ge %>%
add_cols(x = 10,
y = 30)
# Variables x and y .before the variable GEN
data_ge %>%
add_cols(x = 10,
y = 30,
.before = GEN)
# Creating a new variable based on the existing ones.
data_ge %>%
add_cols(GY2 = GY^2,
GY2_HM = GY2 + HM,
.after = GY)
############### Reordering columns ###############
reorder_cols(data_ge2, NKR, .before = ENV)
reorder_cols(data_ge2, where(is.factor), .after = last_col())
######## Selecting and removing columns ##########
select_cols(data_ge2, GEN, REP)
remove_cols(data_ge2, GEN, REP)
########## Selecting and removing rows ###########
select_rows(data_ge2, 2:3)
remove_rows(data_ge2, 2:3)
########### Concatenating columns ################
concatenate(data_ge, ENV, GEN, REP)
concatenate(data_ge, ENV, GEN, REP, drop = TRUE)
# Combine with add_cols() and replace_string()
data_ge2 %>%
add_cols(ENV_GEN = concatenate(., ENV, GEN, pull = TRUE),
.after = GEN) %>%
replace_string(ENV_GEN,
pattern = "H",
replacement = "HYB_")
# Use prefixes and suffixes
concatenate(data_ge2, REP, prefix = "REP", new_var = REP)
# Use prefixes and suffixes (the ear traits EH, EP, EL, and ED)
add_prefix(data_ge2, PH, EH, EP, EL, prefix = "EAR")
add_suffix(data_ge2, PH, EH, EP, EL, suffix = "EAR", sep = ".")
# Use prefixes and suffixes (colnames)
concatenate(data_ge2, REP, prefix = "REP", new_var = REP)
########### formating column names ###############
# Creating data with messy column names
df <- head(data_ge, 3)
colnames(df) <- c("Env", "gen", "Rep", "GY", "hm")
df
colnames_to_lower(df)
colnames_to_upper(df)
colnames_to_title(df)
################### Adding rows ##################
data_ge %>%
add_rows(GY = 10.3,
HM = 100.11,
.after = 1)
########## checking if a column exists ###########
column_exists(data_g, "GEN")
####### get the levels, level combinations and size of levels ########
get_levels(data_g, GEN)
get_levels_comb(data_ge, ENV, GEN)
get_level_size(data_g, GEN)
############## all possible pairs ################
all_pairs(data_g, GEN)
########## select numeric variables only #########
select_numeric_cols(data_g)
select_non_numeric_cols(data_g)
# }
Run the code above in your browser using DataLab