Develop Reference

convert a CSV file to JSON file

I am trying to convert CSV file to JSON file based on a column value. The csv file looks somewhat like this.
ID Name Age
CSE001 John 18
CSE002 Marie 20
ECE001 Josh 22
ECE002 Peter 23
currently I am using the following code to obtain json file.
import csv
import json
def csv_to_json(csv_file_path, json_file_path):
data_dict = {}
with open(csv_file_path, encoding = 'utf-8') as csv_file_handler:
csv_reader = csv.DictReader(csv_file_handler)
for rows in csv_reader:
key = rows['ID']
data_dict[key] = rows
with open(json_file_path, 'w', encoding = 'utf-8') as json_file_handler:
json_file_handler.write(json.dumps(data_dict, indent = 4))
OUTPUT:
**{
"CSE001":{
"ID":"CSE001",
"Name":"John",
"Age":18
}
"CSE002":{
"ID":"CSE002",
"Name":"Marie",
"Age":20
}
"ECE001":{
"ID":"ECE001",
"Name":"Josh",
"Age":22
}
"ECE002":{
"ID":"ECE002",
"Name":"Peter",
"Age":23
}
}**
I want my output to generate two separate json files for CSE and ECE based on the ID value. Is there a way to achieve this output.
Required Output:
CSE.json:
{
"CSE001":{
"ID":"CSE001",
"Name":"John",
"Age":18
}
"CSE002":{
"ID":"CSE002",
"Name":"Marie",
"Age":20
}
}
ECE.json:
{
"ECE001":{
"ID":"ECE001",
"Name":"Josh",
"Age":22
}
"ECE002":{
"ID":"ECE002",
"Name":"Peter",
"Age":23
}
}

I would suggest you to use pandas, that way will be more easier.
Code may look like:
import pandas as pd
def csv_to_json(csv_file_path):
df = pd.read_csv(csv_file_path)
df_CSE = df[df['ID'].str.contains('CSE')]
df_ECE = df[df['ID'].str.contains('ECE')]
df_CSE.to_json('CSE.json')
df_ECE.to_json('ESE.json')

You can create dataframe and then do the following operation
import pandas as pd
df = pd.DataFrame.from_dict({
"CSE001":{
"ID":"CSE001",
"Name":"John",
"Age":18
},
"CSE002":{
"ID":"CSE002",
"Name":"Marie",
"Age":20
},
"ECE001":{
"ID":"ECE001",
"Name":"Josh",
"Age":22
},
"ECE002":{
"ID":"ECE002",
"Name":"Peter",
"Age":23
}
},orient='index')
df["id_"] = df["ID"].str[0:2] # temp column for storing first two chars
grps = df.groupby("id_")[["ID", "Name", "Age"]]
for k, v in grps:
print(v.to_json(orient="index")) # you can create json file as well

You could store each row into two level dictionary with the top level being the first 3 characters of the ID.
These could then be written out into separate files with the key being part of the filename:
from collections import defaultdict
import csv
import json
def csv_to_json(csv_file_path, json_base_path):
data_dict = defaultdict(dict)
with open(csv_file_path, encoding = 'utf-8') as csv_file_handler:
csv_reader = csv.DictReader(csv_file_handler)
for row in csv_reader:
key = row['ID'][:3]
data_dict[key][row['ID']] = row
for key, values in data_dict.items():
with open(f'{json_base_path}_{key}.json', 'w', encoding='utf-8') as json_file_handler:
json_file_handler.write(json.dumps(values, indent = 4))
csv_to_json('input.csv', 'output')
The defaultdict is used to avoid needing to first test if a key is already present before using it.
This would create output_CSE.json and output_ECE.json, e.g.
{
"ECE001": {
"ID": "ECE001",
"Name": "Josh",
"Age": "22"
},
"ECE002": {
"ID": "ECE002",
"Name": "Peter",
"Age": "23"
}
}

How to delete an element in a json file python

I am trying to delete an element in a json file,
here is my json file:
before:
{
"names": [
{
"PrevStreak": false,
"Streak": 0,
"name": "Brody B#3719",
"points": 0
},
{
"PrevStreak": false,
"Streak": 0,
"name": "XY_MAGIC#1111",
"points": 0
}
]
}
after running script:
{
"names": [
{
"PrevStreak": false,
"Streak": 0,
"name": "Brody B#3719",
"points": 0
}
]
}
how would I do this in python? the file is stored locally and I am deciding which element to delete by the name in each element
Thanks

I would load the file, remove the item, and then save it again. Example:
import json
with open("filename.json") as f:
data = json.load(f)
f.pop(data["names"][1]) # or iterate through entries to find matching name
with open("filename.json", "w") as f:
json.dump(data, f)

You will have to read the file, convert it to python native data type (e.g. dictionary), then delete the element and save the file. In your case something like this could work:
import json
filepath = 'data.json'
with open(filepath, 'r') as fp:
data = json.load(fp)
del data['names'][1]
with open(filepath, 'w') as fp:
json.dump(data, fp)

Try this:
# importing the module
import ast
# reading the data from the file
with open('dictionary.txt') as f:
data = f.read()
print("Data type before reconstruction : ", type(data))
# reconstructing the data as a dictionary
a_dict = ast.literal_eval(data)
{"names":[a for a in a_dict["names"] if a.get("name") !="XY_MAGIC#1111"]}

import json
with open("test.json",'r') as f:
data = json.loads(f.read())
names=data.get('names')
for idx,name in enumerate(names):
if name['name']=='XY_MAGIC#1111':
del names[idx]
break
print(names)
In order to read the file best approach would be using the with statement after which you could just use pythons json library and convert json string to python dict. once you get dict you can access the values and do your operations as required. you could convert it as json using json.dumps() then save it

This does the right thing useing the python json module, and prettyprints the json back to the file afterwards:
import json
jsonpath = '/path/to/json/file.json'
with open(jsonpath) as file:
j = json.loads(file.read())
names_to_remove = ['XY_MAGIC#1111']
for element in j['names']:
if element['name'] in names_to_remove:
j['names'].remove(element)
with open(jsonpath, 'w') as file:
file.write(json.dumps(j, indent=4))

Extract certain information from json into csv

I have a json file that look like this:
{
"issueInfo" : [ {
"cid" : 494960,
"occurrences" : [ {
"file" : "/components/applications/diag/_common/src/diag_il.c",
"function" : "diag_il_u8StopLoopbackMicIn",
"mainEventLineNumber" : 6018,
"mainEventDescription" : "Assigning value \"10\" to \"u8ResData\" here, but that stored value is overwritten before it can be used.",
} ],
"triage" : {
"classification" : "Unclassified"
},
}
I want to extract out the information like cid, firstDetectedDateTime, file, function, mainEventLineNumber, mainEventDescription and classification. All of these information needed will be put into a csv file. The following is my coding:
import csv
import json
with open ("a.log","r") as file:
data=json.load(file)
f=csv.writer(open("test.csv", "w", newline=''))
f.writerow(["cid", "firstDetectedDateTime", "file", "function",
"mainEventLineNumber", "mainEventDescription", "classification"])
for data in file:
f.writerow(data["issueInfo"]["cid"],
data["issueInfo"]["firstDetectedDateTime"],
data["issueInfo"]["occurrences"]["file"],
data["issueInfo"]["occurrences"]["function"],
data["issueInfo"]["occurrences"]["mainEventLineNumber"],
data["issueInfo"]["occurrences"]["mainEventDescription"],
data["issueInfo"]["triage"]["classification"])
The error shown after I run the command is :
TypeError: string indices must be integers
Anyone can help me to solve this problem? Thanks

Check the type of data (It must be a dictionary). Also, there is an invalid key error firstDetectedDateTime.
Try this,
import csv
import json
with open ("a.log","r") as file:
data=json.load(file)
f=csv.writer(open("test.csv", "w", newline=''))
f.writerow(["cid", "firstDetectedDateTime", "file", "function","mainEventLineNumber","mainEventDescription", "classification"])
f.writerow([data["issueInfo"][0]["cid"],
"",
data["issueInfo"][0]["occurrences"][0]["file"],
data["issueInfo"][0]["occurrences"][0]["function"],
data["issueInfo"][0]["occurrences"][0]["mainEventLineNumber"],
data["issueInfo"][0]["occurrences"][0]["mainEventDescription"],
data["issueInfo"][0]["triage"]["classification"]])
Output CSV looks like,
cid,firstDetectedDateTime,file,function,mainEventLineNumber,mainEventDescription,classification
494960,,/components/applications/diag/_common/src/diag_il.c,diag_il_u8StopLoopbackMicIn,6018,"Assigning value ""10"" to ""u8ResData"" here, but that stored value is overwritten before it can be used.",Unclassified
If the page contains many JSON sets eg:data_sets here, Keep the headers fixed only change the portion below that.
for data in data_sets:
f.writerow([data["issueInfo"][0]["cid"],
"",
data["issueInfo"][0]["occurrences"][0]["file"],
data["issueInfo"][0]["occurrences"][0]["function"],
data["issueInfo"][0]["occurrences"][0]["mainEventLineNumber"],
data["issueInfo"][0]["occurrences"][0]["mainEventDescription"],
data["issueInfo"][0]["triage"]["classification"]])

The json library in python can parse JSON from strings or files. The library parses JSON into a Python dictionary or list
json.loads() function parses the json string data and it can be used as a normal dictionary in python. And we can access the values using keys.
import json
import csv
employee_data = '{"employee_details":[{"employee_name": "James", "email": "james#gmail.com", "job_profile": "Sr. Developer"},{"employee_name": "Smith", "email": "Smith#gmail.com", "job_profile": "Project Lead"}]}'
employee_parsed = json.loads(employee_data)
emp_data = employee_parsed['employee_details']
# open a file for writing
employ_data = open('..../EmployData.csv', 'w')
# create the csv writer object
csvwriter = csv.writer(employ_data)
count = 0
for emp in emp_data:
if count == 0:
header = emp.keys()
csvwriter.writerow(header)
count += 1
csvwriter.writerow(emp.values())
employ_data.close()

How can I use jsonpath in python to change an element value in the json object

I have the following json object (Say car_details.json):
{
"name":"John",
"age":30,
"cars":
[
{
"car_model": "Mustang",
"car_brand": "Ford"
},
{
"car_model": "cx-5",
"car_brand": "Mazda"
}
}
I want to change the value of car_model from cx-5 to cx-9 through python code.
I am providing the json path to this element, through an external file. The json-path expression is basically represented as a string. Something like this:
'cars[2].car_model'
And the new value is also provided through an external file as a string:
'cx-9'
Now how do I parse through car_details.json using the jsonpath expression, and change its value to the one provided as string, and finally return the modified json object
P.S I want to do this through python code

This is an approach without using json module. Load your data in variable. Then iterate over cars key/values. If you find the key that is the value you are looking for set it to new value.
Also note: you need to close your array block, otherwise your above json is not valid. Generally I use an online json parser to check if my data is valid etc. (may be helpful in future).
data = {
"name":"John",
"age":30,
"cars":
[
{
"car_model": "Mustang",
"car_brand": "Ford"
},
{
"car_model": "cx-5",
"car_brand": "Mazda"
}
]
}
for cars in data['cars']:
for key, value in cars.items():
if key == "car_model" and value == "cx-5":
cars[key] = "cx-9"
print(data)
If you want to load your json object from a file, let's assume it is called "data.json" and is in the same directory as the python script you are going to run:
import json
with open('data.json') as json_data:
data = json.load(json_data)
for cars in data['cars']:
for key, value in cars.items():
if key == "car_model" and value == "cx-5":
cars[key] = "cx-9"
print(data)
Now if you'd like to write the content to the original file or new file, in this case I am writing to a file called "newdata.json":
import json
import re
with open('data.json') as json_data:
data = json.load(json_data)
print(data)
with open('external.txt') as f:
content = f.read()
print(content)
for cars in data['cars']:
for key, value in cars.items():
if key == "car_model" and value == "cx-5":
cars[key] = content
with open('newdata.json', 'w') as outfile:
json.dump(data, outfile)

How to write a python code to print a result in excel sheet using .out file?

I have a bench-memcpy.out file. It contains input like below.
{
"timing_type": "hp_timing",
"functions": {
"memset": {
"bench-variant": "",
"ifuncs": ["builtin_memset", "simple_memset",
"__memset_sse2_unaligned",
"__memset_sse2_unaligned_erms", "__memset_erms",
"__memset_avx2_unaligned", "__memset_avx2_unaligned_erms"],
"results": [
{
"length": 1,
"alignment": 0,
"char": -65,
"timings": [101.812, 50.0625, 50.625, 46.6875, 60.1875, 55.125,
50.625]
},
{
"length": 2,
"alignment": 0,
"char": -65,
"timings": [61.3125, 45.5625, 47.25, 44.4375, 59.625, 50.0625,
48.9375]
}]
}
}
}
I have to print the timings value in excel sheet.How can I do that?
Can anyone please help me to solve this problem.

An easy path is to use Excel's ability to open XML files.
Below is the code to produce timings.xml that Excel can open.
import json
#JSON loaded via a file (for instance)
f=open('bench-memcpy.out','r')
json_input = f.read()
f.close()
#defining XML header
output = '<?xml version="1.0"?><ss:Workbook xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet"><ss:Worksheet ss:Name="Timings"><ss:Table>'
#Load info as JSON data
json_data = json.loads(json_input)
#loop data
for r in range (0,len(json_data['functions']['memset']['results'])):
output = output + '<ss:Row>'
for t in range (0,len(json_data['functions']['memset']['results'][r]['timings'])):
output += '<ss:Cell><ss:Data ss:Type="String">' + str(json_data['functions']['memset']['results'][r]['timings'][t]) + '</ss:Data></ss:Cell>'
output += '</ss:Row>'
output += '</ss:Table></ss:Worksheet></ss:Workbook>'
f=open('timings.xml','w')
f.write(output)
f.close

You can use python pandas library for your desired operation. You can refer this link : Kaggle flatten json
Here, there is a nested json file. Author is flattening the file to extract his desired fields.