how to add the headers to csv file only one in python - python-3.x

I tried many ways/combinations to insert headers (I need to add two column headers) but the file doesn't accept headers at file creation. At best, I get headers as rows come into the file one after the other. I can't see how to enter the headers only once persistently. Can you see in the code below where I could make some change please? Thanks.
with open(MYFILE, "w", newline='') as csvWriter, open('read.csv', 'r', newline='') as csvReader:
if keyword != "q":
fieldnames = [engine, keyword]
#fieldnames = ['Engine', 'Keywords']
# writer = csv.DictWriter(csvWriter, fieldnames=[engine, keyword], extrasaction='ignore')
writer = csv.DictWriter(csvWriter, fieldnames=fieldnames)
writer.writeheader()
reader = csv.DictReader(csvReader, fieldnames=fieldnames)
writer.writerow({"Engine": engine, "Keywords": keyword})
writer.writerows(reader)
I'm trying to save data into a csv file. I have two columns but no headers currently. I'd need some column titles like in any spreadsheet basically.
UPDATE ==============================================
I've tried to insert to no avail the first block hereafter before and after the 2nd one. There is certainly something I'm not doing right but I don't know. Any suggestion, please?
STATUS = "quit"
print("Press [q] to quit at any time")
menu_engine = {}
menu_engine['1'] = "Google Search - Large Results"
menu_engine['2'] = "Google Search - Small Results"
menu_engine['3'] = "Yahoo Search - Large Results"
menu_engine['4'] = "Yahoo Search - Small Results"
while True:
options = menu_engine.keys()
for entry in options:
print(entry, menu_engine[entry])
engine = input("Enter your Type of Search: ")
while STATUS != "q":
keyword = input("Enter keyword(s): ")
with open(MYFILE, "a", newline='') as csvWriter:
if keyword != "q":
fieldnames = [engine, keyword]
writer = csv.DictWriter(csvWriter, fieldnames=fieldnames, extrasaction='ignore')
writer.writeheader()
THE EXPECTED OUTPUT in the CSV File:
Engine Number,Keywords
4,man man
4,mate mate

you write the header with writeheader() then you can just write the rows
import csv
with open('new.dat', "w", newline='') as csvWriter, open('test.dat', 'r', newline='') as csvReader:
fieldnames = ['Engine', 'Keywords']
writer = csv.DictWriter(csvWriter, fieldnames=fieldnames)
reader = csv.DictReader(csvReader, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(reader)
INPUT FILE
sef,56
sfd,67
eryt,67
sdfsf,34
OUTPUT FILE
Engine,Keywords
sef,56
sfd,67
eryt,67
sdfsf,34
UPDATE
I felt there should be an easier way to do this and seems you can use fileinput module from the standard python library to edit the same file inplace and insert the record at the start. this will save you having to the move or rename files.
import fileinput
headers = ['Engine','Type']
with fileinput.input('test.dat', inplace=1) as my_file:
for line in my_file:
if my_file.isfirstline():
print(",".join(headers))
print(line, end='')

Try:
df["new_column"]=" "
df.to_csv("your_file.csv", index= False)
print(df) #to see if it's what you need

Related

When editing data in a CSV how do you exclude/only include certain columns?

I've got a CSV of client details for a bank project in Python 3. I've managed to create a function in which you can edit the client details but I want to exclude the last 2 columns as and and can't figure out how.
Example of CSV data:
first_name,last_name,title,pronouns,dob,occupation,account_balance,overdraft_limit
Garner,Coupman,Ms,Male,14/04/2022,General Manager,2200.76,2.28
Jens,Eldrid,Honorable,Male,13/11/2021,Research Associate,967.64,79.15
Edit function:
if choice == "4":
editClient = int(input("Please enter the index number of the client you wish to edit: "))
print("Please enter the details for each of the following: ")
for i in range(len(existing_clients[0])):
newDetails = input("Enter new data for " + str(existing_clients[0][i]) + ": ")
existing_clients[editClient][i] = newDetails
changes = input("Are you sure you'd like to make these changes? Enter Yes or No")
if changes == ("Yes"):
# Newline fixed the spacing issue I was having
with open("mock_data.csv", "w+", newline="") as file:
reader = csv.writer(file)
for i in range(len(existing_clients)):
reader.writerow(existing_clients[i])
if changes == ("No"):
exit()
I've tried changing
for i in range(len(existing_clients[0])):
to
for i in range(len(existing_clients[0:6])):
and I thought this worked until I tried editing a client later the row 6.
I've also messed around a lot with
newDetails = input("Enter new data for " + str(existing_clients[0][i]) + ": ")
to no avail.
Edit the row with slicing and exclude the last two columns:
with open("mock_data.csv", "w", newline="") as file:
writer = csv.writer(file)
for client in existing_clients:
writer.writerow(client[:-2]) # exclude last two columns
Working example with data:
input.csv
first_name,last_name,title,pronouns,dob,occupation,account_balance,overdraft_limit
Garner,Coupman,Ms,Male,14/04/2022,General Manager,2200.76,2.28
Jens,Eldrid,Honorable,Male,13/11/2021,Research Associate,967.64,79.15
test.py
import csv
with open('input.csv', newline='') as f:
reader = csv.reader(f)
data = list(reader)
with open('output.csv', 'w', newline='') as f:
writer = csv.writer(f)
for line in data:
writer.writerow(line[:-2])
output.csv
first_name,last_name,title,pronouns,dob,occupation
Garner,Coupman,Ms,Male,14/04/2022,General Manager
Jens,Eldrid,Honorable,Male,13/11/2021,Research Associate
To select specific columns, you could concatenate different slices:
writer.writerow(line[:2] + line[5:6]) # column indexes 0, 1, and 5
Or use DictReader/DictWriter:
import csv
with open('input.csv', newline='') as f:
reader = csv.DictReader(f)
data = list(reader)
with open('output.csv', 'w', newline='') as f:
writer = csv.DictWriter(f, fieldnames=['last_name', 'occupation'], extrasaction='ignore')
writer.writeheader()
for line in data:
writer.writerow(line)
output.csv
last_name,occupation
Coupman,General Manager
Eldrid,Research Associate

How do I remove first column in csv file?

I have a CSV file where the first row in the first column is blank with some numbers in the second and third row. This whole column is useless and I need to remove it so I can convert the data into a JSON file. I just need to know how to remove the first column of data so I can parse it. Any help is greatly appreciated!
My script is as follows
#!/usr/bin/python3
import pandas as pd
import csv, json
xls = pd.ExcelFile(r'C:\Users\Andy-\Desktop\Lab2Data.xlsx')
df = xls.parse(sheetname="Sheet1", index_col=None, na_values=['NA'])
df.to_csv('file.csv')
file = open('file.csv', 'r')
lines = file.readlines()
file.close()
data = {}
with open('file.csv') as csvFile:
csvReader = csv.DictReader(csvFile)
for rows in csvReader:
id = rows['Id']
data[id] = rows
with open('Lab2.json', 'w') as jsonFile:
jsonFile.write(json.dumps(data, indent=4))
I don't know much about json files but this will remove the first column from your csv file.
with open ('new_file.csv', 'w') as out_file :
with open ('file.csv') as in_file :
for line in in_file :
test_string = line.strip ('\n').split (',')
out_file.write (','.join (test_string [1:]) + '\n')

How to read a column and write it as a row in python?

I am trying to read a csv and then transpose one column into a row.
I tried following a tutorial for reading a csv and then one for writing but the data doesnt stay saved to the list when I try to write the row.
import csv
f = open('bond-dist-rep.csv')
csv_f = csv.reader(f)
bondlength = []
with open("bond-dist-rep.csv") as f:
for row in csv_f:
bondlength.append(row[1])
print (bondlength)
print (len(bondlength))
with open('joined.csv', 'w', newline='') as csvfile:
csv_a = csv.writer (csvfile, delimiter=',',quotechar='"',
quoting=csv.QUOTE_ALL)
csv_a.writerow(['bondlength'])
with open('joined.csv') as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
for row in readCSV:
print(row)
print(row[0])
f.close()
The matter is that you only read the first value of each line and write only a string in the new file.
In order to transpose the read lines, you can use the zip function.
I also delete the first open function which is useless because of the good use of with for opening the file.
Here the final code:
import csv
bondlength = []
with open("bond-dist-rep.csv") as csv_f:
read_csv = csv.reader(csv_f)
for row in read_csv:
bondlength.append(row)
# delete the header if you have one
bondlength.pop(0)
with open('joined.csv', 'w') as csvfile:
csv_a = csv.writer (csvfile, delimiter=',')
for transpose_row in zip(*bondlength):
csv_a.writerow(transpose_row)

How to add headers when creating csv file in python

I am getting "raw" data from a csv file, and putting only what I need for a new csv file that will be used to auto add users to a different system...
I am unsure how to add the correct headers needed for the file.
I've tried looking at other examples of adding headers but have not figured this out yet...
The headers I need to add are as follows:
"ID Card Number","Name","E-Mail","User Level","Position","Status","Covered Under Insurance","Paid Insurance"
(and in that order)
import csv
def studentscsv():
with open('..\StudentEmails_and_StudentNumbers.csv') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
with open('mydirectory\student_users.csv', mode='w', newline='') as output_file:
write = csv.writer(output_file, delimiter=',', quoting=csv.QUOTE_MINIMAL)
for row in csv_reader:
a = row[0]
studentnumber = row[1]
firstname = row[2]
lastname = row[3]
grade = row[4]
studentname = firstname + " " + lastname
studentemail = firstname + "." + lastname + "#mydomain.org"
status = "Active"
position = "Student"
covered = "Yes"
paid = "Yes"
write.writerow([studentnumber, studentname, studentemail, grade, position, status, covered, paid])
def main():
"""
Controls the program execution
:param in_file: the name of the input file.
:return: None
"""
if __name__ == '__main__':
main()
The file generates fine with the way the code is written. I am just unsure what I need to change to add the headers.
Using the csv module, as you are, it's pretty straight forward. Define your headers in an array and then create a DictWriter with the fieldnames set to your array. Reference the following code and documentation:
import csv
with open('names.csv', 'w') as csvfile:
fieldnames = ['first_name', 'last_name']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
writer.writerow({'first_name': 'Baked', 'last_name': 'Beans'})
writer.writerow({'first_name': 'Lovely', 'last_name': 'Spam'})
writer.writerow({'first_name': 'Wonderful', 'last_name': 'Spam'})
Here's the documentation:
https://docs.python.org/2/library/csv.html#csv.DictWriter

Saving list to a .csv file

I have made a code that opens a .csv file and takes a user input to filter it to a new list. What I am having trouble with is saving this new list to a .csv file properly.
This is my code:
#author: Joakim
from pprint import pprint
import csv
with open ('Change_in_Unemployment_2008-2014.csv') as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
next(readCSV) #Removing header
result = []
found = False
user_input = input("Please enter a full/partial NUTS code to filter by: ")
for row in readCSV:
if row[0].startswith(user_input):
result.append(row)
found = True
if found == False:
print("There are no registered NUTS codes containing your input.. Please try again")
if found == True:
print("\n Successfully found ", len(result), "entries!""\n")
pprint (result)
#store data in a new csv file
Stored_path = "C:\data_STORED.csv"
file = open(Stored_path, 'w')
writer = csv.writer(file)
writer.writerow(["NUTS CODE", " Municipality", " value"])
for i in range(len(result)):
new_row = result[i]
NUTS_CODE = new_row[0]
Municipality = new_row[1]
Value = new_row[2]
writer.writerow([NUTS_CODE, Municipality])
csvfile.close()
If one runs my code with an input of : PL, one gets this list:
[['PL11', 'odzkie', '2.2'],
['PL12', 'Mazowieckie', '1.2'],
['PL21', 'Maopolskie', '2.9'],
['PL22', 'Slaskie', '2'],
['PL31', 'Lubelskie', '1.1'],
['PL32', 'Podkarpackie', '5.8'],
['PL33', 'Swietokrzyskie', '2.6'],
['PL34', 'Podlaskie', '2.7'],
['PL41', 'Wielkopolskie', '1.6'],
['PL42', 'Zachodniopomorskie', '-1.1'],
['PL43', 'Lubuskie', '1.8'],
['PL51', 'Dolnoslaskie', '0'],
['PL52', 'Opolskie', '1.3'],
['PL61', 'Kujawsko-Pomorskie', '1.6'],
['PL62', 'Warminsko-Mazurskie', '2.4'],
['PL63', 'Pomorskie', '3.1']]'
Now I would like to store this neatly into a new .csv file, but when I use the code above, I only get a couple of values repeated throughout.
What is my error?

Resources