Convert csv to json - column1 as a key (nested dict) - python

I need column1 to be used as a KEY and its value to be a dict of column2 (as key) & column3 (as value) so that output will become a nested dictonary.
For example:
I have a csv file as shown below:
customer1,subkey1,val1
customer2,subkey2,val2
customer2,subkey3,val3
customer2,subkey4,val4
customer3,subkey5,val5
customer3,subkey6,val6
expecting output to be:
{
customer1: {
subkey1:val1
},
customer2: {
subkey2:val2,
subkey3:val3,
subkey4:val4
},
customer3: {
subkey5:val5,
subkey6:val6
}
}
I have tried to convert below sample code as per my requirement, but no luck:
import csv
import json
def csv_to_json(csvFilePath, jsonFilePath):
jsonArray = []
#read csv file
with open(csvFilePath, encoding='utf-8') as csvf:
#load csv file data using csv library's dictionary reader
csvReader = csv.DictReader(csvf)
#convert each csv row into python dict
for row in csvReader:
#add this python dict to json array
jsonArray.append(row)
#convert python jsonArray to JSON String and write to file
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
jsonString = json.dumps(jsonArray, indent=4)
jsonf.write(jsonString)
csvFilePath = r'data.csv'
jsonFilePath = r'data.json'
csv_to_json(csvFilePath, jsonFilePath)

Try this
worked for me I used the csv.reader for this and changed the variable into a dict object
import csv
import json
def csv_to_json(csvFilePath, jsonFilePath):
jsonDict = {}
# read csv file
with open(csvFilePath, encoding='utf-8') as csvf:
# load csv file data using csv library's dictionary reader
csvReader = csv.reader(csvf, delimiter=',')
# convert each csv row into python dict
for row in csvReader:
# add this python dict to json array
if row[0] in jsonDict:
jsonDict[row[0]][row[1]] = row[2]
else:
jsonDict[row[0]] = {row[1]: row[2]}
# convert python jsonArray to JSON String and write to file
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
jsonString = json.dumps(jsonDict, indent=4)
jsonf.write(jsonString)
csvFilePath = r'data.csv'
jsonFilePath = r'data.json'
csv_to_json(csvFilePath, jsonFilePath)
output
{
"customer1": {
"subkey1": "val1"
},
"customer2": {
"subkey2": "val2",
"subkey3": "val3",
"subkey4": "val4"
},
"customer3": {
"subkey5": "val5",
"subkey6": "val6"
}
}

import collections
import csv
with open('file.csv') as f:
reader = csv.reader(f, delimiter=',')
dict_1 = collections.defaultdict(dict)
for row in reader:
dict_1[row[0]][row[1]] = row[2]
print(dict(dict_1))
# Output
{
customer1: {
subkey1:val1
},
customer2: {
subkey2:val2,
subkey3:val3,
subkey4:val4
},
customer3: {
subkey5:val5,
subkey6:val6
}
}

In this case, DictReader doesn't really help you because it gives each row as a dict in the form:
{"column1": "customer1", "column2": "subkey1", "column3": "val1"}
So it will actually be simpler to use a regular reader and parse manually. You just need to expand existing customers, so it will be helpful to use a defaultdict:
import csv
import json
from collections import defaultdict
def csv_to_json(csvFilePath, jsonFilePath):
jsonDict = defaultdict(dict)
# read csv file
with open(csvFilePath, encoding='utf-8') as csvf:
# load csv file data using csv library's reader
csvReader = csv.reader(csvf)
# convert each csv row into a list
for row in csvReader:
# add this list to json dict
jsonDict[row[0]][row[1]] = row[2]
# write python jsonDict to JSON file
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
json.dump(jsonDict, jsonf, indent=4)
Note that the json file can be written simpler by using dump instead of dumps.

Related

CSV to JSON converter (Grouping by same keys values)

I'm trying to convert csv format to JSON, I googled I'm not getting the correct way to modify it to get the desired one.
This is my code in python:
import csv
import json
def csv_to_json(csvFilePath, jsonFilePath):
jsonArray = []
#reading csv (encoding is important)
with open(csvFilePath, encoding='utf-8') as csvf:
#csv library function
csvReader = csv.DictReader(csvf)
#convert each csv row into python dictionary
for column in csvReader:
#add this python dictionary to json array
jsonArray.append(column)
#convertion
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
jsonString = json.dumps(jsonArray, indent=4)
jsonf.write(jsonString)
csvFilePath='example.csv'
jsonFilePath='output.json'
csv_to_json(csvFilePath, jsonFilePath)
and this is my csv file format:
My actual JSON Output:
[
{
"Area": "IT",
"Employee": "Carl",
},
{
"Area": "IT",
"Employee": "Walter",
},
{
"Area": "Financial Resources",
"Employee": "Jennifer",
}
]
My desired JSON Output:
[
{
"Area": "IT",
"Employee": ["Carl","Walter"],
},
{
"Area": "Financial Resources",
"Employee": ["Jennifer"],
}
]
Thank you in advance!
Something like this should work.
def csv_to_json(csvFilePath, jsonFilePath):
areas = {}
with open(csvFilePath, encoding='utf-8') as csvf:
csvReader = csv.DictReader(csvf)
for column in csvReader:
area, employee = column["Area"], column["Employee"] # split values
if area in areas: # add all keys and values to one dictionary
areas[area].append(employee)
else:
areas[area] = [employee]
# convert dictionary to desired output format.
jsonArray = [{"Area": k, "Employee": v} for k,v in areas.items()]
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
jsonString = json.dumps(jsonArray, indent=4)
jsonf.write(jsonString)

CSV to JSON in Python takes only first and last rows

I made a function that converts data from given csv file to a json object, and the weird thing is that it only gets the first and last element of the CSV.
My csv structure is 2 columns: name,days
Example:
name,days
John,17
Fred,2
Michelle,22
When I get the json object, and print it, it gives me:
jsondata is: {
"0": {
"name": "John",
"days": "17"
},
"1": {
"name": "Michelle",
"days": "22"
}
}
Here is my code:
data = {}
with open(file, "rt") as csvf:
csvReader = csv.DictReader(csvf)
i = 0
for rows in csvReader:
data[i] = rows
i =+ 1
jsondata = json.dumps(data, indent=4)
print("jsondata is: ", jsondata)
I do not understand why would you need to use i as a counter but here a two suggestions:
data = []
with open(file, "rt") as csvf:
csvReader = csv.DictReader(csvf)
for rows in csvReader:
data.append(rows)
jsondata = json.dumps(data, indent=4)
print("jsondata is: ", jsondata)
or
data = {}
with open(file, "rt") as csvf:
csvReader = csv.DictReader(csvf)
for i, rows in enumerate(csvReader):
data[i] = rows
jsondata = json.dumps(data, indent=4)
print("jsondata is: ", jsondata)
In both cases you will be able to access by index e.g.: data[0], data[1]...

Convert CSV file to JSON with python

I am trying to covert my CSV email list to a JSON format to mass email via API. This is my code thus far but am having trouble with the output. Nothing is outputting on my VS code editor.
import csv
import json
def make_json(csvFilePath, jsonFilePath):
data = {}
with open(csvFilePath, encoding='utf-8') as csvf:
csvReader = csv.DictReader(csvf)
for rows in csvReader:
key = rows['No']
data[key] = rows
with open(jsonFilePath, 'w', encoding='utf-8') as jsonf:
jsonf.write(json.dumps(data, indent=4))
csvFilePath = r'/data/csv-leads.csv'
jsonFilePath = r'Names.json'
make_json(csvFilePath, jsonFilePath)
Here is my desired JSON format
{
"EmailAddress": "hello#youngstowncoffeeseattle.com",
"Name": "Youngstown Coffee",
"ConsentToTrack": "Yes"
},
Heres my CSV list
No,EmailAddress,ConsentToTrack
Zylberschtein's Delicatessen & Bakery,catering#zylberschtein.com,Yes
Youngstown Coffee,hello#youngstowncoffeeseattle.com,Yes
It looks like you could use a csv.DictReader to make this easier.
If I have data.csv that looks like this:
Name,EmailAddress,ConsentToTrack
Zylberschtein's Delicatessen,catering#zylberschtein.com,yes
Youngstown Coffee,hello#youngstowncoffeeseattle.com,yes
I can convert it into JSON like this:
>>> import csv
>>> import json
>>> fd = open('data.csv')
>>> reader = csv.DictReader(fd)
>>> print(json.dumps(list(reader), indent=2))
[
{
"Name": "Zylberschtein's Delicatessen",
"EmailAddress": "catering#zylberschtein.com",
"ConsentToTrack": "yes"
},
{
"Name": "Youngstown Coffee",
"EmailAddress": "hello#youngstowncoffeeseattle.com",
"ConsentToTrack": "yes"
}
]
Here I've assumed the headers in the CSV can be used verbatim. I'll update this with an exmaple if you need to modify key names (e.g. convert "No" to "Name"),.
If you need to rename a column, it might look more like this:
import csv
import json
with open('data.csv') as fd:
reader = csv.DictReader(fd)
data = []
for row in reader:
row['Name'] = row.pop('No')
data.append(row)
print(json.dumps(data, indent=2))
Given this input:
No,EmailAddress,ConsentToTrack
Zylberschtein's Delicatessen,catering#zylberschtein.com,yes
Youngstown Coffee,hello#youngstowncoffeeseattle.com,yes
This will output:
[
{
"EmailAddress": "catering#zylberschtein.com",
"ConsentToTrack": "yes",
"Name": "Zylberschtein's Delicatessen"
},
{
"EmailAddress": "hello#youngstowncoffeeseattle.com",
"ConsentToTrack": "yes",
"Name": "Youngstown Coffee"
}
]
and to print on my editor is it simply print(json.dumps(list(reader), indent=2))?
I'm not really familiar with your editor; print is how you generate console output in Python.

CSV to JSON output only if all values are present in CSV

I have a concatenated CSV file that I am attempting to output into JSON format. How should I go about implementing the logic that the CSV file only get converted to a JSON object all fields have a value ?
import glob , os
import pandas as pd
import json
import csv
with open('some.csv', 'r', newline='') as csvfile, \
open('output.json', 'w') as jsonfile:
for row in csv.DictReader(csvfile):
restructured = {
'STATION_CODE': row['STORE_CODE'],
'id': row['ARTICLE_ID'],
'name': row['ITEM_NAME'],
'data':
{
# fieldname: value for (fieldname, value) in row.items()
'STORE_CODE': row['STORE_CODE'],
'ARTICLE_ID': row['ARTICLE_ID'],
'ITEM_NAME': row['ITEM_NAME'],
'BARCODE': row['BARCODE'],
'SALE_PRICE': row['SALE_PRICE'],
'LIST_PRICE': row['LIST_PRICE'],
'UNIT_PRICE': row['UNIT_PRICE'],
}
}
json.dump(restructured, jsonfile, indent=4)
jsonfile.write('\n')
Currently this will provide all values from the CSV file into the JSON output, which is unintended behavior. Any inputs on how to correct this ?
First I loop through all the elements of CSV and add it to a JSON array. If any row element value is empty, that row will be ignored. Once I have the all rows in the JSON array, I will output it to the JSON file
import json
import csv
csvjsonarr = []
with open('some.csv', 'r', newline='') as csvfile :
for row in csv.DictReader(csvfile):
hasemptyvalues = False
for rowidx in row :
if row[rowidx] == "" :
hasemptyvalues = True
break
if hasemptyvalues == True :
continue
restructured = {
'STATION_CODE': row['STORE_CODE'],
'id': row['ARTICLE_ID'],
'name': row['ITEM_NAME'],
'data': {
'STORE_CODE': row['STORE_CODE'],
'ARTICLE_ID': row['ARTICLE_ID'],
'ITEM_NAME': row['ITEM_NAME'],
'BARCODE': row['BARCODE'],
'SALE_PRICE': row['SALE_PRICE'],
'LIST_PRICE': row['LIST_PRICE'],
'UNIT_PRICE': row['UNIT_PRICE'],
}
}
csvjsonarr.append(restructured)
if len(csvjsonarr) > 0 :
with open('output.json', 'w') as jsonfile :
json.dump(csvjsonarr, jsonfile, indent=4)

converting csv file into json format in python

I have written a code to convert my csvfile which is '|' delimited file to get specific json format.
Csv file format:
comment|address|city|country
crowded|others|others|US
pretty good|others|others|US ....
I have tried with other codes as well since I'm new to python I'm stuck in between. If somebody helps me to correct the mistake I'm doing it would be helpful.
import csv
import json
from collections import OrderedDict
csv_file = 'test.csv'
json_file = csv_file + '.json'
def main(input_file):
csv_rows = []
with open(input_file, 'r') as csvfile:
reader = csv.DictReader(csvfile)
title = reader.fieldnames
for row in reader:
entry = OrderedDict()
for field in title:
entry[field] = row[field]
csv_rows.append(entry)
with open(json_file, 'w') as f:
json.dump(csv_rows, f, sort_keys=True, indent=4, ensure_ascii=False)
f.write('\n')
if __name__ == "__main__":
main(csv_file)
I want in json format as below
{
"reviewer": {
"city": "",
"country": ""
"address": "Orlando, Florida"
},
But I'm getting output like this:
[
{
"COMMENT|\"ADDRESS\"|\"CITY\"|"COUNTRY":"Crowded"|"Others"|"Others"|
},
{
"COMMENT|\"ADDRESS\"|\"CITY\"|"COUNTRY":"pretty good"|"Others"|"Others"|
},
You're missing the separator parameter. Instead of:
reader = csv.DictReader(csvfile)
Use:
reader = csv.DictReader(csvfile, delimiter='|')

Categories