egeulgen

##################################################
## Project: pathfindR
## Script purpose: Try to resolve issue 22
## Date: Oct 15, 2019
## Author: Ege Ulgen
##################################################

options(stringsAsFactors = FALSE)

# Create M.musculus KEGG Gene Sets ----------------------------------------

egeulgen

FUN <- function(x) {
    x <- as.integer(x)
    div <- seq_len(abs(x))
    factors <- div[x %% div == 0L]
    factors <- list(neg = -factors, pos = factors)
    return(factors)
}

egeulgen

Extract fields 2, 4, and 5 from file.txt:

awk '{print $2,$4,$5}' input.txt

Print each line where the 5th field is equal to ‘abc123’:

awk '$5 == "abc123"' file.txt

Print each line where the 5th field is not equal to ‘abc123’:

egeulgen

multimerge <- function(mypath){
  filenames <- list.files(path=mypath, full.names=TRUE)
  datalist <- lapply(filenames, function(x) read.csv(file=x,header=T))
  result_df <- Reduce(function(x,y) merge(x,y), datalist)
  return(result_df)
}

### Cleaner and faster
# import files
files <- list.files(pattern="*.csv")

egeulgen

class ProgressPercentage(object):
    ''' Progress Class
    Class for calculating and displaying download progress
    '''
    def __init__(self, client, bucket, filename):
        ''' Initialize
        initialize with: file name, file size and lock.
        Set seen_so_far to 0. Set progress bar length
        '''
        self._filename = filename

egeulgen

def indexExcelColumnFinder(self, idx):
        ''' Find Excel-style Column Name
        Given a 0-based index 'idx', returns the
        corresponding Excel-style column naming
        (eg. 3 >> D, 26 >> AA, 27 >> AB etc.)
        '''
        excelColumnNameList = []
        alphabet = map(chr, range(65, 91))

        if idx < 26:

egeulgen

def splitDataFrameList(df,target_column,separator):
    ''' df = dataframe to split,
    target_column = the column containing the values to split
    separator = the symbol used to perform the split
    returns: a dataframe with each entry for the target column separated, with each element moved into a new row. 
    The values in the other columns are duplicated across the newly divided rows.
    '''
    def splitListToRows(row,row_accumulator,target_column,separator):
        split_row = row[target_column].split(separator)
        for s in split_row: