Sorting a csv file by column - python

I want to sort the data in a csv file alphabetically according to the contents in the first column. For example, if the file contained:
city/month,Jan,Feb,Mar,Apr
Melbourne,41.2,35.5,37.4,29.3
Brisbane,31.3,40.2,37.9,29
Darwin,34,34,33.2,34.5
it would be sorted as:
city/month,Jan,Feb,Mar,Apr
Brisbane,31.3,40.2,37.9,29
Darwin,34,34,33.2,34.5
Melbourne,41.2,35.5,37.4,29.3
what I've done so far, sorts correctly but it doesn't return the answer correctly, instead of returning it in the table format, it returns everything as a list - any idea why that is?
import csv
import operator
def sort_records(csv_filename, new_filename):
f = open(csv_filename)
csv1 = csv.reader(f, delimiter = ',')
new_filename = sorted(csv1)
return new_filename
f.close()

>>> import csv
>>> import operator
>>> def sort_records(csv_filename, new_filename):
... with open(csv_filename, 'r') as i, open(new_filename, 'w') as o:
... reader = csv.reader(i, delimiter = ',')
... writer = csv.writer(o, delimiter=',')
... writer.writerow(next(reader)) # header row
... writer.writerows(sorted(reader, key=operator.itemgetter(0)))
>>> sort_records('a.csv', 'b.csv')

Related

converting TXT to CSV python

I have a txt data. it looks as follows
time pos
0.02 1
0.1 2
...
and so on. so the each line is separated with a space. I need to convert it in to a CSV file. like
time,pos
0.02,1
0.1,2
0.15,3
How can I do it with python ? This is what I have tried
time = []
pos = []
def get_data(filename):
with open(filename, 'r') as csvfile:
csvFileReader = csv.reader(csvfile)
next(csvFileReader)
for row in csvFileReader:
time.append((row[0].split(' ')[0]))
pos.append((row[1]))
return
with open(filename) as infile, open('outfile.csv','w') as outfile:
for line in infile:
outfile.write(line.replace(' ',','))
From here:
import csv
with open(filename, newline='') as f:
reader = csv.reader(f, delimiter=' ')
for row in reader:
print(row)
For writing just use default options and it would save file with comma as a delimiter.
try:
import pandas as pd
with open(filename, 'r') as fo:
data = fo.readlines()
for d in range(len(data)):
if d==0:
column_headings = data[d].split()
data_to_insert = data[d].split()
pd.DataFrame(data_to_insert).to_excel('csv_file.csv', header=False, index=False, columns = column_headings))
You can use this:
import csv
time = []
pos = []
def get_data(filename):
with open(filename, 'r') as csvfile:
csvfile1 = csv.reader(csvfile, delimiter=' ')
with open(filename.replace('.txt','.csv'), 'w') as csvfile:
writer = csv.writer(csvfile, delimiter=',')
for row in csvfile1:
writer.writerow(row)

Python read CSV file columns and write file name and column name in a csv file

I have many CSV files, need to read all the files in loop and write file name and all the columns (header in row 1) in an output file.
Example
Input csv file 1 (test1.csv)
Id, Name, Age, Location
1, A, 25, India
Input csv file 2 (test2.csv)
Id, ProductName
1, ABC
Outputfile
test1.csv Id
test1.csv Name
test1.csv Age
test1.csv Location
test2.csv Id
test2.csv ProductName
Many thanks for your help.
Update:
This code works fine for this purpose:
import os
import csv
ofile = open('D:\Anuj\Personal\OutputFile/AHS_File_Columns_Info.csv', 'w')
directory = os.path.join('D:\Anuj\Personal\Python')
for root, dirs, files in os.walk(directory):
for file in files:
fullfilepath = directory + "/" + file
with open(fullfilepath,'r') as f:
output = file +','+ f.readline()
ofile.write(output)
clean solution using csv module for reading and writing
open output file and create a csv.writer instance on its handle
open each input file and create a csv.reader instance on their handle
get first row using next on the csv.reader iterator: gets titles as list (with a small post-processing to remove the spaces)
write titles alongside the current filename in a loop
code:
import csv
files=["test1.csv","test2.csv"]
with open("output.tsv","w",newline='') as fw:
cw = csv.writer(fw,delimiter="\t") # output is tab delimited
for filename in files:
with open(filename,'r') as f:
cr = csv.reader(f)
# get title
for column_name in (x.strip() for x in next(cr)):
cw.writerow([filename,column_name])
There are several advantages using csv module, the most important being that quoting & multi-line fields/titles are managed properly.
But I'm not sure I understand you correctly.
import csv
from typing import List
from typing import Tuple
TableType = List[List[str]]
def load_csv_table(file_name: str) -> Tuple[List[str], TableType]:
with open(file_name) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
headers = next(csv_reader)
data_table = list(csv_reader)
return headers, data_table
def save_csv_table(file_name: str, headers: List[str], data_table: TableType):
with open(file_name, 'w', newline='') as csv_file:
writer = csv.writer(csv_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
writer.writerow(headers)
for row in data_table:
writer.writerow(row)
input_files = ['file1.csv', 'file2.csv', 'file3.csv']
new_table = []
new_headers = []
for file_name in input_files:
headers, data_table = load_csv_table(file_name)
if not new_headers:
new_headers = ['Source'] + headers
new_table.extend(([file_name] + line for line in data_table))
save_csv_table('output.csv', new_headers, new_table)
A simple method is to use readline() on the file object:
files=["test1.csv","test2.csv"]
for my_file in files:
with open(my_file,'r') as f:
print my_file, f.readline()

JSON like data to CSV file in python - not showing headers correctly

I am transforming JSON like data to CSV and having a few issues.
The code is here:
import json
import csv
def parse_file(inputed_file):
with open(input_file, 'r') as inputed_file:
content = inputed_file.readlines()
split_file = open('test.csv', 'w')
for line in content:
lines = line.split('\t')
data = json.loads(lines[0])
writer = csv.DictWriter(split_file, fieldnames = ["title", "firstname"], delimiter = ',')
writer.writeheader()
The problem is this is adding a header on each row for the data, I want to only have the header displayed once. Then add this for the data to go below the headers:
writer.writerow(data)
I have looked at this and tried it but failed: How can I convert JSON to CSV?.
Create the DictWriter outside the loop, and just call writer.writeheader() there. Then call writer.writerow() inside the loop.
def parse_file(inputed_file):
with open(input_file, 'r') as inputed_file:
content = inputed_file.readlines()
split_file = open('test.csv', 'w')
writer = csv.DictWriter(split_file, fieldnames = ["title", "firstname"], delimiter = ',')
writer.writeheader()
for line in content:
lines = line.split('\t')
data = json.loads(lines[0])
writer.writerow(data)

Adding a new column on CSV with Python

I have the following list of numbers: ['Number', 1,2,3,4]
If I have the following CSV file:
`Name`
`First`
`Second`
`Third`
`Fourth`
How do I add my list of numbers to it and make it look like this:
`Name Number`
`First 1`
`Second 2`
`Third 3`
`Fourth 4`
You can use fileinput.input with inplace=True to modify the original file:
import fileinput
import sys
l =['Number', 1,2,3,4]
for ind, line in enumerate(fileinput.input("in.csv",inplace=True)):
sys.stdout.write("{} {}\n".format(line.rstrip(), l[ind]))
Input:
Name
First
Second
Third
Fourth
Output:
Name Number
First 1
Second 2
Third 3
Fourth 4
Or write to a tempfile and move with shutil.move to replace the original file:
l =['Number', 1,2,3,4]
from shutil import move
from tempfile import NamedTemporaryFile
with open('in.csv') as csvfile, NamedTemporaryFile("w",dir=".", delete=False) as temp:
r = csv.reader(csvfile)
wr = csv.writer(temp,delimiter=" ")
for row,new in zip(r,l):
wr.writerow(row+[new])
move(temp.name,"in.csv")
Not an elegant way but It works:
#!/usr/bin/python
import csv
import sys
def csv_to_dict(csv_file_path):
csv_file = open(csv_file_path, 'rb')
csv_file.seek(0)
sniffdialect = csv.Sniffer().sniff(csv_file.read(10000), delimiters='\t,;')
csv_file.seek(0)
dict_reader = csv.DictReader(csv_file, dialect=sniffdialect)
csv_file.seek(0)
dict_data = []
for record in dict_reader:
dict_data.append(record)
csv_file.close()
return dict_data
def dict_to_csv(csv_file_path, dict_data):
csv_file = open(csv_file_path, 'wb')
writer = csv.writer(csv_file, dialect='excel')
headers = dict_data[0].keys()
writer.writerow(headers)
for dat in dict_data:
line = []
for field in headers:
line.append(dat[field])
writer.writerow(line)
csv_file.close()
if __name__ == '__main__':
org_path = sys.argv[1]
new_path = sys.argv[2]
your_array = ['Number', 1, 2, 3, 4]
org_csv = csv_to_dict(org_path)
new_data = []
for line in org_csv:
new_line = dict()
new_line['Name'] = line['Name']
new_line[your_array[0]] = your_array[org_csv.index(line)+1]
new_data.append(new_line)
if new_data:
dict_to_csv(new_path, new_data)
Hope that will help!
import csv
with open('existing_file.csv', 'rb') as infile:
reader = csv.reader(infile)
your_list = list(reader)
list2 = ['Number', 1,2,3,4]
zipped= zip(your_list, list2)
with open("test.csv", "wb") as outfile:
writer = csv.writer(outfile)
writer.writerows(zipped)

How to convert CSV file to multiline JSON?

Here's my code, really simple stuff...
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
out = json.dumps( [ row for row in reader ] )
jsonfile.write(out)
Declare some field names, the reader uses CSV to read the file, and the filed names to dump the file to a JSON format. Here's the problem...
Each record in the CSV file is on a different row. I want the JSON output to be the same way. The problem is it dumps it all on one giant, long line.
I've tried using something like for line in csvfile: and then running my code below that with reader = csv.DictReader( line, fieldnames) which loops through each line, but it does the entire file on one line, then loops through the entire file on another line... continues until it runs out of lines.
Any suggestions for correcting this?
Edit: To clarify, currently I have: (every record on line 1)
[{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"},{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}]
What I'm looking for: (2 records on 2 lines)
{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"}
{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}
Not each individual field indented/on a separate line, but each record on it's own line.
Some sample input.
"John","Doe","001","Message1"
"George","Washington","002","Message2"
The problem with your desired output is that it is not valid json document,; it's a stream of json documents!
That's okay, if its what you need, but that means that for each document you want in your output, you'll have to call json.dumps.
Since the newline you want separating your documents is not contained in those documents, you're on the hook for supplying it yourself. So we just need to pull the loop out of the call to json.dump and interpose newlines for each document written.
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
for row in reader:
json.dump(row, jsonfile)
jsonfile.write('\n')
You can use Pandas DataFrame to achieve this, with the following Example:
import pandas as pd
csv_file = pd.DataFrame(pd.read_csv("path/to/file.csv", sep = ",", header = 0, index_col = False))
csv_file.to_json("/path/to/new/file.json", orient = "records", date_format = "epoch", double_precision = 10, force_ascii = True, date_unit = "ms", default_handler = None)
import csv
import json
file = 'csv_file_name.csv'
json_file = 'output_file_name.json'
#Read CSV File
def read_CSV(file, json_file):
csv_rows = []
with open(file) as csvfile:
reader = csv.DictReader(csvfile)
field = reader.fieldnames
for row in reader:
csv_rows.extend([{field[i]:row[field[i]] for i in range(len(field))}])
convert_write_json(csv_rows, json_file)
#Convert csv data into json
def convert_write_json(data, json_file):
with open(json_file, "w") as f:
f.write(json.dumps(data, sort_keys=False, indent=4, separators=(',', ': '))) #for pretty
f.write(json.dumps(data))
read_CSV(file,json_file)
Documentation of json.dumps()
I took #SingleNegationElimination's response and simplified it into a three-liner that can be used in a pipeline:
import csv
import json
import sys
for row in csv.DictReader(sys.stdin):
json.dump(row, sys.stdout)
sys.stdout.write('\n')
You can try this
import csvmapper
# how does the object look
mapper = csvmapper.DictMapper([
[
{ 'name' : 'FirstName'},
{ 'name' : 'LastName' },
{ 'name' : 'IDNumber', 'type':'int' },
{ 'name' : 'Messages' }
]
])
# parser instance
parser = csvmapper.CSVParser('sample.csv', mapper)
# conversion service
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)
Edit:
Simpler approach
import csvmapper
fields = ('FirstName', 'LastName', 'IDNumber', 'Messages')
parser = CSVParser('sample.csv', csvmapper.FieldMapper(fields))
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)
I see this is old but I needed the code from SingleNegationElimination however I had issue with the data containing non utf-8 characters. These appeared in fields I was not overly concerned with so I chose to ignore them. However that took some effort. I am new to python so with some trial and error I got it to work. The code is a copy of SingleNegationElimination with the extra handling of utf-8. I tried to do it with https://docs.python.org/2.7/library/csv.html but in the end gave up. The below code worked.
import csv, json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("Scope","Comment","OOS Code","In RMF","Code","Status","Name","Sub Code","CAT","LOB","Description","Owner","Manager","Platform Owner")
reader = csv.DictReader(csvfile , fieldnames)
code = ''
for row in reader:
try:
print('+' + row['Code'])
for key in row:
row[key] = row[key].decode('utf-8', 'ignore').encode('utf-8')
json.dump(row, jsonfile)
jsonfile.write('\n')
except:
print('-' + row['Code'])
raise
Add the indent parameter to json.dumps
data = {'this': ['has', 'some', 'things'],
'in': {'it': 'with', 'some': 'more'}}
print(json.dumps(data, indent=4))
Also note that, you can simply use json.dump with the open jsonfile:
json.dump(data, jsonfile)
Use pandas and the json library:
import pandas as pd
import json
filepath = "inputfile.csv"
output_path = "outputfile.json"
df = pd.read_csv(filepath)
# Create a multiline json
json_list = json.loads(df.to_json(orient = "records"))
with open(output_path, 'w') as f:
for item in json_list:
f.write("%s\n" % item)
How about using Pandas to read the csv file into a DataFrame (pd.read_csv), then manipulating the columns if you want (dropping them or updating values) and finally converting the DataFrame back to JSON (pd.DataFrame.to_json).
Note: I haven't checked how efficient this will be but this is definitely one of the easiest ways to manipulate and convert a large csv to json.
As slight improvement to #MONTYHS answer, iterating through a tup of fieldnames:
import csv
import json
csvfilename = 'filename.csv'
jsonfilename = csvfilename.split('.')[0] + '.json'
csvfile = open(csvfilename, 'r')
jsonfile = open(jsonfilename, 'w')
reader = csv.DictReader(csvfile)
fieldnames = ('FirstName', 'LastName', 'IDNumber', 'Message')
output = []
for each in reader:
row = {}
for field in fieldnames:
row[field] = each[field]
output.append(row)
json.dump(output, jsonfile, indent=2, sort_keys=True)
def read():
noOfElem = 200 # no of data you want to import
csv_file_name = "hashtag_donaldtrump.csv" # csv file name
json_file_name = "hashtag_donaldtrump.json" # json file name
with open(csv_file_name, mode='r') as csv_file:
csv_reader = csv.DictReader(csv_file)
with open(json_file_name, 'w') as json_file:
i = 0
json_file.write("[")
for row in csv_reader:
i = i + 1
if i == noOfElem:
json_file.write("]")
return
json_file.write(json.dumps(row))
if i != noOfElem - 1:
json_file.write(",")
Change the above three parameter, everything will be done.
import csv
import json
csvfile = csv.DictReader('filename.csv', 'r'))
output =[]
for each in csvfile:
row ={}
row['FirstName'] = each['FirstName']
row['LastName'] = each['LastName']
row['IDNumber'] = each ['IDNumber']
row['Message'] = each['Message']
output.append(row)
json.dump(output,open('filename.json','w'),indent=4,sort_keys=False)

Categories

Resources