Write number of rows to file name - python

I dont have any idea how to update my code below to the level that I can write the amount of changed row - in the CSV - to the file name.
I have did some stuff with count and row, but it is making any sense.
Can somebody give me some tips
import csv
import glob
import os
rows = []
for in_csv in glob.glob('C:/code/convert/Image/In/*.csv'):
print in_csv
with open(in_csv, 'rb') as f_input:
reader = csv.reader(f_input)
try:
all = []
row = next(reader)
row.insert(0, 'l_panoramic')
all.append(row)
for k, row in enumerate(reader):
all.append(['l_panoramic_{:06}'.format(k)] + row)
name, ext = os.path.splitext(in_csv)
with open("{}_{}{}".format(name, len(rows), ext), 'wb') as f_output:
writer = csv.writer(f_output, delimiter = ';')
writer.writerows(all)
print " {} lines found".format(len(rows))
except StopIteration as e:
print " No lines found"

This could be done using the glob library to create your list of CSV files. Use splitext() to take then existing filename and split it into a filename and extension, the number of rows can then be easily added using a format() statement as follows:
import csv
import glob
import os
rows = []
for in_csv in glob.glob('a*.csv'):
print in_csv
with open(in_csv, 'rb') as f_input:
reader = csv.reader(f_input)
try:
row = next(reader)
row.insert(0, 'L_panoramic')
rows.append(row)
for k, row in enumerate(reader):
rows.append(['l_panoramic_{:06}'.format(k)] + row)
name, ext = os.path.splitext(in_csv)
with open("{}_{}{}".format(name, len(rows), ext), 'wb') as f_output:
writer = csv.writer(f_output, delimiter = ';')
writer.writerows(rows)
print " {} lines found".format(len(rows))
except StopIteration as e:
print " No lines found"
You were already creating a list of rows to be written, so once this list is complete, you will know how many rows there are. With this you can then open the output file with the number of rows added to the name, and write all the rows to it.

Related

Find duplicates in a column, then add values in adjacent column

I have a csv file that has a one word title and a description that is always a number.
My current code extracts just the title an description to another csv file and then converts the csv into an excel file.
import csv
import output
f = open("Johnny_Test-punch_list.csv")
csv_f = csv.reader(f)
m = open('data.csv', "w")
for row in csv_f:
m.write(row[1])
m.write(",")
m.write(row[3])
m.write("\n")
m.close()
output.toxlsx()
How can I look for matching Titles and then add the descriptions of the titles?
import csv
import output
f = open("Johnny_Test-punch_list.csv")
csv_f = csv.reader(f)
m = open('data.csv', "w")
dict_out = {}
for row in csv_f:
if row[1] in dict_out:
dict_out[row[1]] += row[3]
else:
dict_out[row[1]] = row[3]
for title, value in dict_out.iteritems():
m.write('{},{}\n'.format(title, value))
If I understood you correctly, you need to write in a single line as a string.
can you try with below code:
for row in csv_f:
m.write(row[1] + "," + str(row[3]) + "\n")

csv value modification for certain cells on odd rows on a particular column

Hi I'm trying to finish this small piece of code for modifying csv files, I've got this far with some help:
edit... some more info.
Basically what I’m looking to do is make some small changes to the csv file depending on the project and parent issue in JIRA. Python will then make the changes to the csv file before it is then read into JIRA - that’s the second part of the program I’ve not even really looked at yet.
I’m only looking to change the BOX-123 type cells and leave the blank ones blank.
But the idea of the program is that I can use it to make some small changes to a template which will then automatically create some issues in JIRA.
import os
import csv
project = 'Dudgeon'
parent = 'BOX-111'
rows = (1,1007)
current = os.getcwd()
filename = 'test.csv'
filepath = os.path.join(os.getcwd(), filename)
#print(current)
#print(filename)
print(filepath)
with open(filepath, 'r') as csvfile:
readCSV = csv.reader(csvfile)
next(readCSV, None)
for row in readCSV:
print(row[16])
row_count =sum(1 for row in readCSV)
print(row_count)
with open(filepath, 'r') as infile, open('out.csv', 'w') as outfile:
outfile.write(infile.readline()) # write out the 1st line
for line in infile:
cols = line.strip().split(',')
cols[16] = project
outfile.write(','.join(cols) + '\n')
with open('out.csv', 'r') as infile, open('out1.csv', 'w') as outfile:
for row in infile:
if row % 2 != 0:
cols [15] = parent
outfile.write()
Any help really appreciated.
You want to use the row's index when comparing to 0. Use enumerate():
with open('out.csv', 'r') as infile, open('out1.csv', 'w') as outfile:
for rowidx,row in enumerate(infile):
cols = row.strip().split(',')
if rowidx % 2 != 0:
cols[15] = parent
outfile.write(cols)
You really should be using the csv module here, though. Untested but should get you started.
with open('out.csv', 'r') as infile, open('out1.csv', 'w') as outfile:
reader = csv.reader(infile)
writer = csv.writer(outfile)
for rowidx,row in enumerate(reader):
if rowidx % 2 != 0:
row[15] = parent
writer.write_row(row)
A friend helped me last night and this is what they came up with:
with open(filepath, 'r') as infile, open('out.csv', 'w') as outfile:
outfile.write(infile.readline()) # write out the 1st line
for line in infile:
cols = line.strip().split(',')
cols[16] = project
outfile.write(','.join(cols) + '\n')
with open('out.csv', 'r') as infile, open('out1.csv', 'w') as outfile:
outfile.write(infile.readline()) # write out the 1st line
lineCounter = 0
for line in infile:
lineCounter += 1
cols = line.strip().split(',')
if lineCounter % 2 != 0:
cols[15] = parent
outfile.write(','.join(cols) + '\n')

(Simple Python) CSV input to usernames

I have a CSV file names.csv
First_name, Last_name
Mike, Hughes
James, Tango
, Stoke
Jack,
....etc
What I want is to be able to take the first letter of the First_name and the full Last_name and output it on screen as usernames but not include the people with First_name and Last_name property's empty. I'm completely stuck any help would be greatly appreciated
import csv
ifile = open('names.csv', "rb")
reader = csv.reader(ifile)
rownum = 0
for row in reader:
if rownum == 0:
header = row
else:
colnum = 0
for col in row:
print '%-8s: %s' % (header[colnum], col)
colnum += 1
rownum += 1
ifile.close()
Attempt #2
import csv
dataFile = open('names.csv','rb')
reader = csv.reader(dataFile)
next(reader, None)
for row in reader:
if (row in reader )
print (row[0])
I haven't saved many attempts because none of them have worked :S
import csv
dataFile = open('names.csv','rb')
reader = csv.reader(dataFile, delimiter=',', quoting=csv.QUOTE_NONE)
for row in reader:
if not row[0] or not row[1]:
continue
print (row[0][0] + row[1]).lower()
Or
import csv
dataFile = open('names.csv','rb')
reader = csv.reader(dataFile, delimiter=',', quoting=csv.QUOTE_NONE)
[(row[0][0] + row[1]).lower() for row in reader if
row[0] and row[1]]
Once you get the text from the .csv you can use the split() function to break up the text by the new lines. Your sample text is a little inconsistent, but if I understand you question correctly you can say
import csv
dataFile = open('names.csv','rb')
reader = csv.reader(dataFile)
reader = reader.split('\n')
for x in reader
print(reader[x])
Or if you want to break it up by commas just replace the '\n' with ','
Maybe like this
from csv import DictReader
with open('names.csv') as f:
dw = DictReader(f, skipinitialspace=True)
fullnames = filter(lambda n: n['First_name'] and n['Last_name'], dw)
for f in fullnames:
print('{}{}'.format(f['First_name'][0], f['Last_name']))
You have headings in your csv so use a DictReader and just filter out those whose with empty first or last names and display the remaining names.

How to split code into smaller functions

I have an application that works. But in the interest of attempting to understand functions and python better. I am trying to split it out into various functions.
I"m stuck on the file_IO function. I'm sure the reason it does not work is because the main part of the application does not understand reader or writer. To better explain. Here is a full copy of the application.
Also I'm curious about using csv.DictReader and csv.DictWriter. Do either provide any advantages/disadvantages to the current code?
I suppose another way of doing this is via classes which honestly I would like to know how to do it that way as well.
#!/usr/bin/python
""" Description This script will take a csv file and parse it looking for specific criteria.
A new file is then created based of the original file name containing only the desired parsed criteria.
"""
import csv
import re
import sys
searched = ['aircheck', 'linkrunner at', 'onetouch at']
def find_group(row):
"""Return the group index of a row
0 if the row contains searched[0]
1 if the row contains searched[1]
etc
-1 if not found
"""
for col in row:
col = col.lower()
for j, s in enumerate(searched):
if s in col:
return j
return -1
#Prompt for File Name
def file_IO():
print "Please Enter a File Name, (Without .csv extension): ",
base_Name = raw_input()
print "You entered: ",base_Name
in_Name = base_Name + ".csv"
out_Name = base_Name + ".parsed.csv"
print "Input File: ", in_Name
print "OutPut Files: ", out_Name
#Opens Input file for read and output file to write.
in_File = open(in_Name, "rU")
reader = csv.reader(in_File)
out_File = open(out_Name, "wb")
writer = csv.writer(out_File, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL)
return (reader, writer)
file_IO()
# Read header
header = reader.next()
stored = []
writer.writerow([header[0], header[3]])
for i, row in enumerate(reader):
g = find_group(row)
if g >= 0:
stored.append((g, i, row))
stored.sort()
for g, i, row in stored:
writer.writerow([row[0], row[3]])
# Closing Input and Output files.
in_File.close()
out_File.close()
If I were you, I'd only separate find_group.
import csv
def find_group(row):
GROUPS = ['aircheck', 'linkrunner at', 'onetouch at']
for idx, group in enumerate(GROUPS):
if group in map(str.lower, row):
return idx
return -1
def get_filenames():
# this might be the only other thing you'd want to factor
# into a function, and frankly I don't really like getting
# user input this way anyway....
basename = raw_input("Enter a base filename (no extension): ")
infilename = basename + ".csv"
outfilename = basename + ".parsed.csv"
return infilename, outfilename
# notice that I don't open the files yet -- let main handle that
infilename, outfilename = get_filenames()
with open(infilename, 'rU') as inf, open(outfilename, 'wb') as outf:
reader = csv.reader(inf)
writer = csv.writer(outf, delimiter=',',
quotechar='"', quoting=csv.QUOTE_ALL)
header = next(reader)
writer.writerow([[header[0], header[3]])
stored = sorted([(find_group(row),idx,row) for idx,row in
enumerate(reader)) if find_group(row) >= 0])
for _, _, row in stored:
writer.writerow([row[0], row[3]])

Adding a column in csv using python

I have hundreds of .csv files with 40 rows and 34 columns each. I want to add a column at position 26 and column 26-34 should shift to make space for the new one. First row of the file is empty and second row has the titles and rest have the values. The new column should have a title in row two and rest of the rows can be zero.
Please help me with this code in python.
import csv
infilename = r'C:\Users\Sulabh Kumra\Desktop\input.csv'
outfilename = r'C:\Users\Sulabh Kumra\Desktop\output.csv'
with open(infilename, 'rb') as fp_in, open(outfilename, 'wb') as fp_out:
reader = csv.reader(fp_in, delimiter=",")
headers = next(reader) # read first row
writer = csv.writer(fp_out, delimiter=",")
writer.writerow(headers)
for row in reader:
row.append(row[2])
writer.writerow(row)
Inserting into a python list is pretty easy: some_list[2:2] = ['stuff','to','insert']
So your code would look like the following:
import csv
infilename = r'C:\Users\Sulabh Kumra\Desktop\input.csv'
outfilename = r'C:\Users\Sulabh Kumra\Desktop\output.csv'
with open(infilename, 'rb') as fp_in, open(outfilename, 'wb') as fp_out:
reader = csv.reader(fp_in, delimiter=",")
writer = csv.writer(fp_out, delimiter=",")
blank_line = next(reader)
writer.writerow(blank_line)
headers = next(reader) # read title row
headers[26:26] = ['New Label']
writer.writerow(headers)
for row in reader:
row[26:26] = [0]
writer.writerow(row)

Categories

Resources