Some Functionality for Strings and File Names

The function filename_split splits a file name into parts.

The function string_extract_part extracts a part of a string.

The function string_to_matrix converts a string into a matrix.

filename_split(file_name, file_sep="__", file_ext=".")
filename_split_vec( file_names, file_sep="__", file_ext=".")

string_extract_part( vec, part=1, sep="__", remove_empty=TRUE )

string_to_matrix(x, rownames=NULL, col_elim=NULL, as_numeric=FALSE,
               diag_val=NULL, extend=FALSE, col1_numeric=FALSE, split=" ")

Arguments

file_name	File name
file_names	File names
file_sep	Separator within file name
file_ext	Separator for file extension
vec	Vector with strings
part	Integer indicating the part of the string to be selected
sep	String separator
remove_empty	Logical indicating whether empty entries (" "") should be removed.
x	String vector
rownames	Column index for row names
col_elim	Indices for elimination of columns
as_numeric	Logical indicating whether numeric conversion is requested
diag_val	Optional values for inclusion in diagonal of matrix
extend	Optional indicating whether numeric matrix should be extended to become a symmetric matrix
col1_numeric	Logical indicating whether second column is selected in such a way that it has to be always a numeric (see Example 5)
split	String used for splitting

Value

List with components of the file name (see Examples).

See also

files_move

Examples

#############################################################################
# EXAMPLE 1: Demonstration example for filename_split
#############################################################################

# file name
file_name <- "pisa_all_waves_invariant_items_DATA_ITEMS_RENAMED__DESCRIPTIVES__2016-10-12_1000.csv"

# apply function
miceadds::filename_split( file_name )
  ##  $file_name
  ##  [1] "pisa_all_waves_invariant_items_DATA_ITEMS_RENAMED__DESCRIPTIVES__2016-10-12_1000.csv"
  ##  $stem
  ##  [1] "pisa_all_waves_invariant_items_DATA_ITEMS_RENAMED__DESCRIPTIVES"
  ##  $suffix
  ##  [1] "2016-10-12_1000"
  ##  $ext
  ##  [1] "csv"
  ##  $main
  ##  [1] "pisa_all_waves_invariant_items_DATA_ITEMS_RENAMED__DESCRIPTIVES.csv"

#############################################################################
# EXAMPLE 2: Example string_extract_part
#############################################################################

vec <- c("ertu__DES", "ztu__DATA", "guzeuue745_ghshgk34__INFO", "zzu78347834_ghghwuz")

miceadds::string_extract_part( vec=vec, part=1, sep="__" )
miceadds::string_extract_part( vec=vec, part=2, sep="__" )
  ##  > miceadds::string_extract_part( vec=vec, part=1, sep="__" )
  ##  [1] "ertu"                "ztu"                 "guzeuue745_ghshgk34"
  ##  [4] "zzu78347834_ghghwuz"
  ##  > miceadds::string_extract_part( vec=vec, part=2, sep="__" )
  ##  [1] "DES"  "DATA" "INFO" NA

if (FALSE) {
#############################################################################
# EXAMPLE 3: Reading descriptive information from published articles
#############################################################################
data(data.ma08)
library(stringr)

#**** reading correlations (I)
dat <- data.ma08$mat1
miceadds::string_to_matrix(dat, rownames=2, col_elim=c(1,2))

#**** reading correlations including some processing (II)
dat0 <- data.ma08$mat2
dat <- dat0[1:14]

# substitute "*"
dat <- gsub("*", "", dat, fixed=TRUE )

# replace blanks in variable names
s1 <- stringr::str_locate(dat, "[A-z] [A-z]")
start <- s1[,"start"] + 1
for (ss in 1:length(start) ){
    if ( ! is.na( start[ss] ) ){
        substring( dat[ss], start[ss], start[ss] ) <- "_"
    }
}

# character matrix
miceadds::string_to_matrix(dat)
# numeric matrix containing correlations
miceadds::string_to_matrix(dat, rownames=2, col_elim=c(1,2), as_numeric=TRUE, diag_val=1,
           extend=TRUE )
#** reading means and SDs
miceadds::string_to_matrix(dat0[ c(15,16)], rownames=1, col_elim=c(1), as_numeric=TRUE )

#**** reading correlations (III)
dat <- data.ma08$mat3
dat <- gsub(" age ", "_age_", dat, fixed=TRUE )
miceadds::string_to_matrix(dat, rownames=2, col_elim=c(1,2), as_numeric=TRUE, diag_val=1,
       extend=TRUE )

#**** reading correlations (IV)
dat <- data.ma08$mat4 <- dat0

# remove spaces in variable names
dat <- gsub(" age ", "_age_", dat, fixed=TRUE )
s1 <- stringr::str_locate_all(dat, "[A-z,.] [A-z]")
NL <- length(dat)
for (ss in 1:NL ){
    NR <- nrow(s1[[ss]])
    if (NR>1){
        start <- s1[[ss]][2,1]+1
        if ( ! is.na( start ) ){
            substring( dat[ss], start, start ) <- "_"
        }
    }
}

miceadds::string_to_matrix(dat, rownames=2, col_elim=c(1,2), as_numeric=TRUE, diag_val=1,
     extend=TRUE )

#############################################################################
# EXAMPLE 4: Input string of length one
#############################################################################


pm0 <- "
0.828
0.567 0.658
0.664 0.560 0.772
0.532 0.428 0.501 0.606
0.718 0.567 0.672 0.526 0.843"

miceadds::string_to_matrix(x=pm0, as_numeric=TRUE, extend=TRUE)

#############################################################################
# EXAMPLE 5: String with variable names and blanks
#############################################################################

tab1 <- "
Geometric Shapes .629 .021 (.483) -.049 (.472)
Plates .473 .017 (.370) .105 (.405)
Two Characteristics .601 .013 (.452) -.033 (.444)
Crossing Out Boxes .597 -.062 (.425) -.036 (.445)
Numbers/Letters .731 .004 (.564) .003 (.513)
Numbers/Letters mixed .682 .085 (.555) .082 (.514)"

miceadds::string_to_matrix(x=tab1, col1_numeric=TRUE)
}