csv_splitter.py
No OneTemporary
Actions

Size

1 KB

Referenced Files

None

Subscribers

None

csv_splitter.py
View Options

	#!/usr/bin/env python3

	import os
	import csv
	from os import listdir
	from os.path import isfile, join

	inputPath = "./original_data"
	outputPath = "./splitted_data"
	columnsOfInterest = [0, 1]
	columnsOfInteresDataType = ["float","string"]
	fileEnding = "csv"

	filesOfInterest = [f for f in listdir(inputPath) if (isfile(join(inputPath, f)) and join(inputPath, f).endswith(fileEnding))]

	numOfColumns = len(columnsOfInterest)

	for file in filesOfInterest:
	print(file)

	fileName = os.path.splitext(file)[0]
	filePath = join(inputPath, file)

	#create results folder if it is not existing
	outputFolder = join(outputPath, fileName)
	if not os.path.exists(outputFolder):
	os.makedirs(outputFolder)

	output_cols = []

	for i in range(numOfColumns):
	output_cols.append([])

	with open(filePath, 'r') as f:
	reader = csv.reader(f)
	input_data = list(reader)

	for i in range(len(input_data)):
	input_line = input_data[i]

	for j in range(numOfColumns):
	output_cols[j].append(input_line[columnsOfInterest[j]].strip())

	# print("input: ", input_line)
	# print("output1: ", output_cols[0])
	# print("output2: ", output_cols[1])
	# input()

	for i in range(numOfColumns):
	outputFilePath = join(outputFolder + "/" + output_cols[i][0] + "." + fileEnding)

	output_cols[i].pop(0)

	writeFile = open(outputFilePath,"w")
	for output_line in output_cols[i]:
	writeFile.write(output_line + "\n")

	writeFile.close()