Refactor the source file into multiple files

[boratonAJ]

Refactor the source file into multiple files so that each file either solves a specific problem or is a python module to be loaded as needed

SACEMA_Scientific_Task/script/wordfreq.py

Lines 18 to 36 in e2df1ba

	# Reads in text files and writes out word frequency data
	# This python function will display the content of the file whose name you pass in the first argument like that:
	def frequency_of_words(argv):
	for filename in argv[1:]:
	freq = collections.defaultdict(int)
	freq = collections.Counter()
	for line in open(filename, encoding='utf-8'):
	words = line.strip().lower().split(' ')
	for word in words:
	freq.update([''.join(char for char in word if char.isalnum())])
	del freq['']
	output_filename = 'Data/output/' + filename.split("/")[2][:-3] +'freq' # substring the filename (slicing)
	with open(output_filename, 'w') as my_file:
	for word_ct in freq.most_common():
	my_file.write(word_ct[0] + ' ' + str(word_ct[1]) + '\n') # write (word_ct[0], word_ct[1]) to file
	for word in sorted(freq.items(), key=operator.itemgetter(1), reverse=True): #Sort by dict value - descending
	print("{0}:{1}".format(word[0], word[1]))

[boratonAJ]

Each of the source files is now created and they are now a python module

1.

SACEMA_Scientific_Task/script/frequency_of_words.py

Lines 12 to 32 in 6f9e1f6

	import collections
	import operator
	import sys
	def words_frequency(argv):
	for filename in argv[1:]:
	freq = collections.defaultdict(int)
	freq = collections.Counter()
	for line in open(filename, encoding='utf-8'):
	words = line.strip().lower().split(' ')
	for word in words:
	freq.update([''.join(char for char in word if char.isalnum())])
	del freq['']
	output_filename = 'Data/output/' + filename.split("/")[2][:-3] +'freq' # substring the filename (slicing)
	with open(output_filename, 'w') as my_file:
	for word_ct in freq.most_common():
	my_file.write(word_ct[0] + ' ' + str(word_ct[1]) + '\n') # write (word_ct[0], word_ct[1]) to file
	for word in sorted(freq.items(), key=operator.itemgetter(1), reverse=True): #Sort by dict value - descending
	print("{0}:{1}".format(word[0], word[1]))

2.

SACEMA_Scientific_Task/script/frequency_of_words.py

Lines 16 to 32 in 6f9e1f6

	def words_frequency(argv):
	for filename in argv[1:]:
	freq = collections.defaultdict(int)
	freq = collections.Counter()
	for line in open(filename, encoding='utf-8'):
	words = line.strip().lower().split(' ')
	for word in words:
	freq.update([''.join(char for char in word if char.isalnum())])
	del freq['']
	output_filename = 'Data/output/' + filename.split("/")[2][:-3] +'freq' # substring the filename (slicing)
	with open(output_filename, 'w') as my_file:
	for word_ct in freq.most_common():
	my_file.write(word_ct[0] + ' ' + str(word_ct[1]) + '\n') # write (word_ct[0], word_ct[1]) to file
	for word in sorted(freq.items(), key=operator.itemgetter(1), reverse=True): #Sort by dict value - descending
	print("{0}:{1}".format(word[0], word[1]))