Convert multiple csv to another csv format - python

I am trying to convert my old CSV files to another format and a new name (_new.csv). All files are in the folder with the date stamp. e.g Filename_05_08_2021.csv. Almost I have 63 files from today date to back. The problem is I have to provide each file name one by one while call function. Is there any way I can convert all of them? I am not sure what I am doing wrong here.
def new_csv(file_path):
c = csv.reader(open(file_path))
c_list = []
c_list.extend(c)
out_csv = open(file_path.replace('.csv','_new.csv'), "w")
for line in c_list:
if len(line) == 10:
out_csv.write(str(line[0]+','+line[1]+','+(line[2]).upper()+','+''+','+
(line[3][1:]).upper()+','+line[4]+','+line[5]+','+
line[6]+','+line[7]+','+line[9])+'\n')
if len(line) > 10:
out_csv.write(str(line[0]+','+line[1]+','+(line[2]).upper()+','+
(line[3][1:]).upper()+','+line[4][1:]+','+line[5]+','+
line[6]+','+line[7]+','+line[8]+','+line[10])+'\n')
out_csv.close()
print ("new .csv written")
if __name__ == '__main__':
new_csv('C:\\Myfolder\\Filename_05_08_2021.csv')

Just iterate within the directory. You can use glob:
import glob
def new_csv(file_path):
c = csv.reader(open(file_path))
c_list = []
c_list.extend(c)
out_csv = open(file_path.replace('.csv','_new.csv'), "w")
for line in c_list:
if len(line) == 10:
out_csv.write(str(line[0]+','+line[1]+','+(line[2]).upper()+','+''+','+
(line[3][1:]).upper()+','+line[4]+','+line[5]+','+
line[6]+','+line[7]+','+line[9])+'\n')
if len(line) > 10:
out_csv.write(str(line[0]+','+line[1]+','+(line[2]).upper()+','+
(line[3][1:]).upper()+','+line[4][1:]+','+line[5]+','+
line[6]+','+line[7]+','+line[8]+','+line[10])+'\n')
out_csv.close()
print ("new .csv written")
if __name__ == '__main__':
for filepath in glob.iglob('C:\\Myfolder\\*.csv'):
new_csv(filepath)

Your statements composing the string by adding commas is a bit clumsy. Consider modifying the list so each field has what you want, then using join to put it all together:
def new_csv(file_path):
out_csv = open(file_path.replace('.csv','_new.csv'), "w")
for line in csv.reader(open(file_path)):
line[2] = line[2].upper()
line[3] = line[3][1:].upper()
if len(line) == 10:
line.pop(8)
else:
line[4] = line[4][1:]
line.pop(9)
print( ','.join(line), file=out_csv )
out_csv.close()
print ("new .csv written")

Related

Python coding for opening and saving data to a file

I am having an issue getting the train function to work correctly in python. I can not modify the def function. I am at the point where I need to get the second file to read lines one at a time for PosList and i need to match the value of movieWordCount[z] in OpenPos. If the file is there, then I am good to incrment column 2 by one of t hat line (segmented by a space). If it is not, then I need the else to append it to the file end. It does not work. It does not append the values if it is missing and I am not sure if it will find the value if it is there. I have been stuck getting thsi to work for two days.
Here is my code segment I am working with:
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
#Now use tokenize to split it apart by space and set to new array for me to call column2
else:
print "not found"
lines.append(movieWordCount[z] + " 1" + "\n")
Here is my full code:
#!/usr/bin/python
#Import Counter
import collections
from collections import Counter
#Was already here but pickle is used for data input and export
import math, os, pickle, re
class Bayes_Classifier:
def __init__(self, trainDirectory = "movie_reviews/"):
#If file listing exists skip to train
if os.path.isfile('iFileList'):
print "file found"
self.train()
#self.classify()
#If file listing does not exist skip to train
if not os.path.isfile('iFileList'):
print "no file"
newfile = 'iFileList'
tempList = set()
subDir = './movie_reviews'
for filenames in os.listdir(subDir):
my_sub_path = os.path.join(os.sep,subDir,filenames)
tempList.add(filenames)
self.save("filenames", "try3")
f = []
for fFileObj in os.walk("movie_reviews/"):
f.extend(fFileObj)
break
pickle.dump(f, open( "save.p", "wb" ))
self.save(f, "try4")
with open(newfile, 'wb') as fi:
pickle.dump(tempList, fi)
#print tempList
self.train()
#self.classify()
def train(self):
'''Trains the Naive Bayes Sentiment Classifier.'''
print "File ready for training"
#Open iFileList to use as input for opening movie files
x = 0
OpenIFileList = open('iFileList','r')
print "iFileList now Open"
#Loop through the file
for line in OpenIFileList:
#print "Ready to read lines"
#print "reading line " + line
if x > 4:
if x % 2 == 0:
#print line
s = line
if '-' in s:
comp = s.split("'")
#print comp[2]
print comp[1] #This is What you need for t he movie file
compValue1 = comp[1]
#Determine Positive/Negative.
#compType is the variable I am storing it to.
compType = compValue1.split("-",2)[1]
#print compType #Prints that middle value like 5 or 1
# This will do the work based on the value.
if compType == '5':
# print "you have a five" #Confirms the loop I am in.
#If file does not exists create it
if not os.path.exists('PosList'):
print "no file"
file('PosList', 'w').close()
#Open file that needs to be reviewed for word count
compValue2 = "movie_reviews/" + compValue1
print compValue2 #Prints the directory and file path
OpenMovieList = open(compValue2,'r')
for commentLine in OpenMovieList:
commentPositive = commentLine.split(" ")
commentPositiveCounter = Counter(commentPositive)
#print commentPositiveCounter # " Comment Pos goes here"
#if commentLine != '' or commentLine != ' ':
#Get first word, second word, ....
if commentLine and (not commentLine.isspace()):
movieWordCount = self.tokenize(commentLine)
y = len(movieWordCount) #determines length of string
print y
z = 0
#print movieWordCount[0] # Shows the zero position in the file.
while z < y:
print "position " + str(z) + " word is " + movieWordCount[z] # Shows the word we are at and position id
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
else:
print "not found"
lines.append(movieWordCount)
z = z + 1
#Close the files
OpenMovieList.close()
OpenPos.close()
x += 1
#for line2 in OpenIFileList.readlines():
#for line in open('myfile','r').readlines():
#do_something(line)
#Save results
#Close the File List
OpenIFileList.close()
def loadFile(self, sFilename):
'''Given a file name, return the contents of the file as a string.'''
f = open(sFilename, "r")
sTxt = f.read()
f.close()
return sTxt
def save(self, dObj, sFilename):
'''Given an object and a file name, write the object to the file using pickle.'''
f = open(sFilename, "w")
p = pickle.Pickler(f)
p.dump(dObj)
f.close()
def load(self, sFilename):
'''Given a file name, load and return the object stored in the file.'''
f = open(sFilename, "r")
u = pickle.Unpickler(f)
dObj = u.load()
f.close()
return dObj
def tokenize(self, sText):
'''Given a string of text sText, returns a list of the individual tokens that
occur in that string (in order).'''
lTokens = []
sToken = ""
for c in sText:
if re.match("[a-zA-Z0-9]", str(c)) != None or c == "\'" or c == "_" or c == '-':
sToken += c
else:
if sToken != "":
lTokens.append(sToken)
sToken = ""
if c.strip() != "":
lTokens.append(str(c.strip()))
if sToken != "":
lTokens.append(sToken)
return lTokens
To open a file for writing, you can use
with open('PosList', 'w') as Open_Pos
As you are using the with form, you do not need to close the file; Python will do that for you at the end of the with-block.
So assuming that the way you add data to the lines variable is correct, you could remove the superfluous code OpenMovieList.close() and OpenPos.close(), and append 2 lines to your code:
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
else:
print "not found"
lines.append(movieWordCount)
with open("PosList", "w") as OpenPos:
OpenPos.write(lines)

Writing to file limitation on line length

I've been trying to write lines to a file based on specific file names from the same directory, a search of the file names in another log file(given as an input), and the modified date of the files.
The output is limiting me to under 80 characters per line.
def getFiles(flag, file):
if (flag == True):
file_version = open(file)
if file_version:
s = mmap.mmap(file_version.fileno(), 0, access=mmap.ACCESS_READ)
file_version.close()
file = open('AllModules.txt', 'wb')
for i, values in dict.items():
# search keys in version file
if (flag == True):
index = s.find(bytes(i))
if index > 0:
s.seek(index + len(i) + 1)
m = s.readline()
line_new = '{:>0} {:>12} {:>12}'.format(i, m, values)
file.write(line_new)
s.seek(0)
else:
file.write(i +'\n')
file.close()
if __name__ == '__main__':
dict = {}
for file in os.listdir(os.getcwd()):
if os.path.splitext(file)[1] == '.psw' or os.path.splitext(file)[1] == '.pkw':
time.ctime(os.path.getmtime(file))
dict.update({str(os.path.splitext(file)[0]).upper():time.strftime('%d/%m/%y')})
if (len(sys.argv) > 1) :
if os.path.exists(sys.argv[1]):
getFiles(True, sys.argv[1])
else:
getFiles(False, None)
The output is always like:
BW_LIB_INCL 13.1 rev. 259 [20140425 16:28]
16/05/14
The interpretation of data is correct, then again the formatting is not correct as the time is put on the next line (not on the same).
This is happening to all the lines of my new file.
Could someone give me a hint?
m = s.readline() has \n at the end of line. Then you're doing .format(i, m, values) which writes m in the middle of the string.
I leave it as exercise to the reader to find out what's happening when you're writing such line to a file. :-)
(hint: m = s.readline().rstrip('\n'))

Copy 'N' lines from one file to another in python?

Essentially what I am attempting to do is read 'n' number of lines from a file and then write them to a separate file. This program essentially should take a file that has 100 lines and separate that file into 50 separate files.
def main():
from itertools import islice
userfile = raw_input("Please enter the file you wish to open\n(must be in this directory): ")
file1 = open(userfile, "r+")
#print "Name: ", file1.name
#print "Closed or not", file1.closed
#print "Opening mode: ", file1.mode
#print "Softspace flag: ", file1.softspace
jcardtop = file1.read(221);
#print jcardtop
n = 2
count = 0
while True:
next_n_lines = list(islice(file1,n))
print next_n_lines
count = count + 1
fileout = open(str(count)+ ".txt", "w+")
fileout.write(str(jcardtop))
fileout.write(str(next_n_lines))
fileout.close()
break
if not next_n_lines:
break
I do have the file printing as well to show what is in the variable next_n_lines.
*['\n', "randomtext' more junk here\n"]
I would like it instead to look like
randomtext' more junk here
Is this a limitatoin of the islice function? Or am I missing a portion of the syntax?
Thanks for your time!
Where you call str() or print, you want to ''.join(next_n_lines) instead:
print ''.join(next_n_lines)
and
fileout.write(''.join(next_n_lines))
You can store the flattened string in a variable if you don't want to call join twice.
Did you mean something like this?
f = open(userfile,"r")
start = 4
n_lines = 100
for line in f.readlines()[start:(start + n_lines)]:
print line
#do stuff with line
or maybe this rough, yet effective code:
f = open(userfile,"r")
start = 4
end = start + 100
count = start
while count != end:
for line in f.readlines()[count:(count + 2)]:
fileout = open(str(count)+ ".txt", "w+")
fileout.write(str(line))
fileout.close()
count = count + 2

Pick parts from a txt file and copy to another file with python

I'm in trouble here. I need to read a file. Txt file that contains a sequence of records, check the records that I want to copy them to a new file.
The file content is like this (this is just an example, the original file has more than 30 000 lines):
AAAAA|12|120 #begin file
00000|46|150 #begin register
03000|TO|460
99999|35|436 #end register
00000|46|316 #begin register
03000|SP|467
99999|33|130 #end register
00000|46|778 #begin register
03000|TO|478
99999|33|457 #end register
ZZZZZ|15|111 #end file
The records that begin with 03000 and have the characters 'TO' must be written to a new file. Based on the example, the file should look like this:
AAAAA|12|120 #begin file
00000|46|150 #begin register
03000|TO|460
99999|35|436 #end register
00000|46|778 #begin register
03000|TO|478
99999|33|457 #end register
ZZZZZ|15|111 #end file
Code:
file = open("file.txt",'r')
newFile = open("newFile.txt","w")
content = file.read()
file.close()
# here I need to check if the record exists 03000 characters 'TO', if it exists, copy the recordset 00000-99999 for the new file.
I did multiple searches and found nothing to help me.
Thank you!
with open("file.txt",'r') as inFile, open("newFile.txt","w") as outFile:
outFile.writelines(line for line in inFile
if line.startswith("03000") and "TO" in line)
If you need the previous and the next line, then you have to iterate inFile in triads. First define:
def gen_triad(lines, prev=None):
after = current = next(lines)
for after in lines:
yield prev, current, after
prev, current = current, after
And then do like before:
outFile.writelines(''.join(triad) for triad in gen_triad(inFile)
if triad[1].startswith("03000") and "TO" in triad[1])
import re
pat = ('^00000\|\d+\|\d+.*\n'
'^03000\|TO\|\d+.*\n'
'^99999\|\d+\|\d+.*\n'
'|'
'^AAAAA\|\d+\|\d+.*\n'
'|'
'^ZZZZZ\|\d+\|\d+.*')
rag = re.compile(pat,re.MULTILINE)
with open('fifi.txt','r') as f,\
open('newfifi.txt','w') as g:
g.write(''.join(rag.findall(f.read())))
For files with additional lines between lines beginning with 00000, 03000 and 99999, I didn't find simpler code than this one:
import re
pat = ('(^00000\|\d+\|\d+.*\n'
'(?:.*\n)+?'
'^99999\|\d+\|\d+.*\n)'
'|'
'(^AAAAA\|\d+\|\d+.*\n'
'|'
'^ZZZZZ\|\d+\|\d+.*)')
rag = re.compile(pat,re.MULTILINE)
pit = ('^00000\|.+?^03000\|TO\|\d+.+?^99999\|')
rig = re.compile(pit,re.DOTALL|re.MULTILINE)
def yi(text):
for g1,g2 in rag.findall(text):
if g2:
yield g2
elif rig.match(g1):
yield g1
with open('fifi.txt','r') as f,\
open('newfifi.txt','w') as g:
g.write(''.join(yi(f.read())))
file = open("file.txt",'r')
newFile = open("newFile.txt","w")
content = file.readlines()
file.close()
newFile.writelines(filter(lambda x:x.startswith("03000") and "TO" in x,content))
This seems to work. The other answers seem to only be writing out records that contain '03000|TO|' but you have to write out the record before and after that as well.
import sys
# ---------------------------------------------------------------
# ---------------------------------------------------------------
# import file
file_name = sys.argv[1]
file_path = 'C:\\DATA_SAVE\\pick_parts\\' + file_name
file = open(file_path,"r")
# ---------------------------------------------------------------
# create output files
output_file_path = 'C:\\DATA_SAVE\\pick_parts\\' + file_name + '.out'
output_file = open(output_file_path,"w")
# create output files
# ---------------------------------------------------------------
# process file
temp = ''
temp_out = ''
good_write = False
bad_write = False
for line in file:
if line[:5] == 'AAAAA':
temp_out += line
elif line[:5] == 'ZZZZZ':
temp_out += line
elif good_write:
temp += line
temp_out += temp
temp = ''
good_write = False
elif bad_write:
bad_write = False
temp = ''
elif line[:5] == '03000':
if line[6:8] != 'TO':
temp = ''
bad_write = True
else:
good_write = True
temp += line
temp_out += temp
temp = ''
else:
temp += line
output_file.write(temp_out)
output_file.close()
file.close()
Output:
AAAAA|12|120 #begin file
00000|46|150 #begin register
03000|TO|460
99999|35|436 #end register
00000|46|778 #begin register
03000|TO|478
99999|33|457 #end register
ZZZZZ|15|111 #end file
Does it have to be python? These shell commands would do the same thing in a pinch.
head -1 inputfile.txt > outputfile.txt
grep -C 1 "03000|TO" inputfile.txt >> outputfile.txt
tail -1 inputfile.txt >> outputfile.txt
# Whenever I have to parse text files I prefer to use regular expressions
# You can also customize the matching criteria if you want to
import re
what_is_being_searched = re.compile("^03000.*TO")
# don't use "file" as a variable name since it is (was?) a builtin
# function
with open("file.txt", "r") as source_file, open("newFile.txt", "w") as destination_file:
for this_line in source_file:
if what_is_being_searched.match(this_line):
destination_file.write(this_line)
and for those who prefer a more compact representation:
import re
with open("file.txt", "r") as source_file, open("newFile.txt", "w") as destination_file:
destination_file.writelines(this_line for this_line in source_file
if re.match("^03000.*TO", this_line))
code:
fileName = '1'
fil = open(fileName,'r')
import string
##step 1: parse the file.
parsedFile = []
for i in fil:
##tuple1 = (1,2,3)
firstPipe = i.find('|')
secondPipe = i.find('|',firstPipe+1)
tuple1 = (i[:firstPipe],\
i[firstPipe+1:secondPipe],\
i[secondPipe+1:i.find('\n')])
parsedFile.append(tuple1)
fil.close()
##search criterias:
searchFirst = '03000'
searchString = 'TO' ##can be changed if and when required
##step 2: used the parsed contents to write the new file
filout = open('newFile','w')
stringToWrite = parsedFile[0][0] + '|' + parsedFile[0][1] + '|' + parsedFile[0][2] + '\n'
filout.write(stringToWrite) ##to write the first entry
for i in range(1,len(parsedFile)):
if parsedFile[i][1] == searchString and parsedFile[i][0] == searchFirst:
for j in range(-1,2,1):
stringToWrite = parsedFile[i+j][0] + '|' + parsedFile[i+j][1] + '|' + parsedFile[i+j][2] + '\n'
filout.write(stringToWrite)
stringToWrite = parsedFile[-1][0] + '|' + parsedFile[-1][1] + '|' + parsedFile[-1][2] + '\n'
filout.write(stringToWrite) ##to write the first entry
filout.close()
I know that this solution may be a bit long. But it is quite easy to understand. And it seems an intuitive way to do it. And I have already checked this with the Data that you have provided and it works perfectly.
Please tell me if you need some more explanation on the code. I will definitely add the same.
I tip (Beasley and Joran elyase) very interesting, but it only allows to get the contents of the line 03000. I would like to get the contents of the lines 00000 to line 99999.
I even managed to do here, but I am not satisfied, I wanted to make a more cleaner.
See how I did:
file = open(url,'r')
newFile = open("newFile.txt",'w')
lines = file.readlines()
file.close()
i = 0
lineTemp = []
for line in lines:
lineTemp.append(line)
if line[0:5] == '03000':
state = line[21:23]
if line[0:5] == '99999':
if state == 'TO':
newFile.writelines(lineTemp)
else:
linhaTemp = []
i = i+1
newFile.close()
Suggestions...
Thanks to all!

Searching a file for matches between two values and outputting search hits in Python

I am (attempting) to write a program that searches through a hex file for instances of a hex string between two values, eg. Between D4135B and D414AC, incrementing between the first value until the second is reached- D4135B, D4135C, D4135D etc etc.
I have managed to get it to increment etc, but it’s the search part I am having trouble with.
This is the code I have so far, it's been cobbled together from other places and I need to make it somehow output all search hits into the output file (file_out)
I have exceeded the limit of my Python understanding and I'm sure there's probably a much easier way of doing this. I would be very grateful for any help.
def search_process(hx): # searching for two binary strings
global FLAG
while threeByteHexPlusOne != threeByteHex2: #Keep incrementing until second value reached
If Flag:
if hx.find(threeByteHex2) != -1:
FLAG = False #If threeByteHex = ThreeByteHexPlusOne, end search
Print (“Reached the end of the search”,hx.find(threeByteHexPlusOne))
Else:
If hx.find(threeByteHexPlusOne) != -1:
FLAG = True
Return -1 #If no results found
if __name__ == '__main__':
try:
file_in = open(FILE_IN, "r") #opening input file
file_out = open(FILE_OUT, 'w') #opening output file
hx_read = file_in.read #read from input file
tmp = ''
found = ''
while hx_read: #reading from file till file is empty
hx_read = tmp + hx_read
pos = search_process(hx_read)
while pos != -1:
hex_read = hx_read[pos:]
if FLAG:
found = found + hx_read
pos = search_process(hx_read)
tmp = bytes_read[]
hx_read = file_in.read
file_out.write(found) #writing to output file
except IOError:
print('FILE NOT FOUND!!! Check your filename or directory/PATH')
Here's a program that looks through a hex string from a file 3 bytes at a time and if the 3-byte hex string is between the given hex bounds, it writes it to another file. It makes use of generators to make getting the bytes from the hex string a little cleaner.
import base64
import sys
_usage_string = 'Usage: python {} <input_file> <output_file>'.format(sys.argv[0])
def _to_base_10_int(value):
return int(value, 16)
def get_bytes(hex_str):
# Two characters equals one byte
for i in range(0, len(hex_str), 2):
yield hex_str[i:i+2]
def get_three_byte_hexes(hex_str):
bytes = get_bytes(hex_str)
while True:
try:
three_byte_hex = next(bytes) + next(bytes) + next(bytes)
except StopIteration:
break
yield three_byte_hex
def find_hexes_in_range(hex_str, lower_bound_hex, upper_bound_hex):
lower_bound = _to_base_10_int(lower_bound_hex)
upper_bound = _to_base_10_int(upper_bound_hex)
found = []
for three_byte_hex in get_three_byte_hexes(hex_str):
hex_value = _to_base_10_int(three_byte_hex)
if lower_bound <= hex_value < upper_bound:
found.append(three_byte_hex)
return found
if __name__ == "__main__":
try:
assert(len(sys.argv) == 3)
except AssertionError:
print _usage_string
sys.exit(2)
file_contents = open(sys.argv[1], 'rb').read()
hex_str = base64.decodestring(file_contents).encode('hex')
found = find_hexes_in_range(hex_str, 'D4135B', 'D414AC')
print('Found:')
print(found)
if found:
with open(sys.argv[2], 'wb') as fout:
for _hex in found:
fout.write(_hex)
Check out some more info on generators here

Categories