Convert CSV to well-structured JSON in Python - python

I have a CSV file that is structured as below :
Store, Region, District, MallName, Location
1234,90,910,MallA,GMT
4567,87,902,MallB,EST
2468,90,811,MallC,PST
1357,87,902,MallD,CST
What I was able to accomplish with my iterative brow-beating was getting a format like so:
{
"90": {
"910": {
"1234": {
"name": "MallA",
"location": "GMT"
}
},
"811": {
"2468": {
"name": "MallB",
"location": "PST"
}
}
},
"87": {
"902": {
"4567": {
"name": "MallB",
"location": "EST"
},
"1357": {
"name": "MallD",
"location": "CST"
}
}
}
}
The code below is stripped down to match the sample data set I provided but you get the idea as to what is happening. Again, it's very iterative and non-pythonic which I'm trying to also move towards. (If anyone feels the defined procedures would be worthwhile to post I can).
#************
# Main()
#************
dictHierarchy = {}
with open(getFilePath(), 'r') as f:
content = [line.strip('\n') for line in f.readlines()]
for data in content:
data = data.split(",")
myRegion = data[1]
myDistrict = data[2]
myName = data[3]
myLocation = data[4]
myStore = data[0]
if myRegion in dictHierarchy:
#check for District
if myDistrict in dictHierarchy[myRegion]:
#checkforStore
dictHierarchy[myRegion][myDistrict].update({myStore:addStoreDetails(data)})
else:
#add district
dictHierarchy[myRegion].update({myDistrict:addStore(data)})
else:
#add region
dictHierarchy.update({myRegion:addDistrict(data)})
with open('hierarchy.json', 'w') as outfile:
json.dump(dictHierarchy, outfile)
Obsessive compulsive me looked at the JSON output above and thought that to someone blindly opening the file it looks like a hodge-podge. What I was hoping to do for plain-text readability is group the data and throw it into JSON format as so:
{"Regions":[
{"Region":"90", "Districts":[
{"District":"910", "Stores":[
{"Store":"1234", "name":"MallA", "location":"GMT"}]},
{"District":"811", "Stores":[
{"Store":"2468", "name":"MallC", "location":"PST"}]}]},
{"Region":"87", "Districts":[
{"District":"902", "Stores":[
{"Store":"4567", "name":"MallB", "location":"EST"},
{"Store":"1357", "name":"MallD", "location":"CST"}]}]}]}
Long story short I wasted quite some time today trying to sort out how to actually populate the data structure in Python and essentially ended up no where. Is there a clean, pythonic way to achieve this? Is it even worth the effort?

I've added headers to your input like:
Store,Region,District,name,location
1234,90,910,MallA,GMT
4567,87,902,MallB,EST
2468,90,811,MallC,PST
1357,87,902,MallD,CST
then used python csv reader and group by like this:
import csv
from itertools import groupby, ifilter
from operator import itemgetter
data = []
with open('in.csv') as csvfile:
reader = csv.DictReader(csvfile)
regions = []
regions_dict = sorted(list(reader), key=itemgetter('Region'))
for region_id, region_group in groupby(regions_dict, itemgetter('Region')):
districts = []
regions.append({'Region': region_id, 'Districts': districts})
districts_dict = sorted(region_group, key=itemgetter('District'))
for district_id, district_group in groupby(districts_dict, itemgetter('District')):
districts.append({'District': district_id, 'Stores': list(district_group)})
print regions

Related

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 write a variable in a json file?

I searched for a long time but I am not really familiar with python and json and I can't find the answer of my problem.
Here is my Python script
import json
jsonFile = open("config.json", "r")
data = json.load(jsonFile)
data.format(friendly, teaching, leader, target)
print(data)
Here is json the file:
{
"commend": {
"friendly": {},
"teaching": {},
"leader": {}
},
"account": {
"username": "",
"password": "",
"sharedSecret": ""
},
"proxy": {
"enabled": false,
"file": "proxies.txt",
"switchProxyEveryXaccounts": 5
},
"type": "COMMEND",
"method": "SERVER",
"target": "https://steamcommunity.com/id/{}",
"perChunk": 20,
"betweenChunks": 300000,
"cooldown": 28800000,
"steamWebAPIKey": "{}",
"disableUpdateCheck": false
}
I tried .format but we can't use this method with with a dictionary.
With your help I managed to find the answer A big thank you for your speed and your help ! Here is what I did:
import json
jsonFile = open("config.json", "r")
data = json.load(jsonFile)
(data['commend']['friendly']) = nbfriendly
(data['commend']['teaching']) = nbteaching
(data['commend']['leader']) = nbleader
print(data)
print(data)
A json file is a dictionary, so you can use dict methods with it. Here is the code:
import json
with open("config.json", "r") as json_file:
data = json.load(json_file)
# Let's say you want to add the string "Hello, World!" to the "password" key
data["account"]["password"] += "Hello, World!"
# Or you can use this way to overwrite anything already written inside the key
data["account"]["password"] = "Hello, World!"
print(data)
You can add data by tranversing through it like a dictionary:
data['key'] = value
Example:
dic["commend"]["friendly"]={'a':1}

Reading json in python separated by newlines

I am trying to read some json with the following format. A simple pd.read_json() returns ValueError: Trailing data. Adding lines=True returns ValueError: Expected object or value. I've tried various combinations of readlines() and load()/loads() so far without success.
Any ideas how I could get this into a dataframe?
{
"content": "kdjfsfkjlffsdkj",
"source": {
"name": "jfkldsjf"
},
"title": "dsldkjfslj",
"url": "vkljfklgjkdlgj"
}
{
"content": "djlskgfdklgjkfgj",
"source": {
"name": "ldfjkdfjs"
},
"title": "lfsjdfklfldsjf",
"url": "lkjlfggdflkjgdlf"
}
The sample you have above isn't valid JSON. To be valid JSON these objects need to be within a JS array ([]) and be comma separated, as follows:
[{
"content": "kdjfsfkjlffsdkj",
"source": {
"name": "jfkldsjf"
},
"title": "dsldkjfslj",
"url": "vkljfklgjkdlgj"
},
{
"content": "djlskgfdklgjkfgj",
"source": {
"name": "ldfjkdfjs"
},
"title": "lfsjdfklfldsjf",
"url": "lkjlfggdflkjgdlf"
}]
I just tried on my machine. When formatted correctly, it works
>>> pd.read_json('data.json')
content source title url
0 kdjfsfkjlffsdkj {'name': 'jfkldsjf'} dsldkjfslj vkljfklgjkdlgj
1 djlskgfdklgjkfgj {'name': 'ldfjkdfjs'} lfsjdfklfldsjf lkjlfggdflkjgdlf
Another solution if you do not want to reformat your files.
Assuming your JSON is in a string called my_json you could do:
import json
import pandas as pd
splitted = my_json.split('\n\n')
my_list = [json.loads(e) for e in splitted]
df = pd.DataFrame(my_list)
Thanks for the ideas internet. None quite solved the problem in the way I needed (I had lots of newline characters in the strings themselves which meant I couldn't split on them) but they helped point the way. In case anyone has a similar problem, this is what worked for me:
with open('path/to/original.json', 'r') as f:
data = f.read()
data = data.split("}\n")
data = [d.strip() + "}" for d in data]
data = list(filter(("}").__ne__, data))
data = [json.loads(d) for d in data]
with open('path/to/reformatted.json', 'w') as f:
json.dump(data, f)
df = pd.read_json('path/to/reformatted.json')
If you can use jq then solution is simpler:
jq -s '.' path/to/original.json > path/to/reformatted.json

convert csv file to multiple nested json format

I have written a code to convert csv file to nested json format. I have multiple columns to be nested hence assigning separately for each column. The problem is I'm getting 2 fields for the same column in the json output.
import csv
import json
from collections import OrderedDict
csv_file = 'data.csv'
json_file = csv_file + '.json'
def main(input_file):
csv_rows = []
with open(input_file, 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter='|')
for row in reader:
row['TYPE'] = 'REVIEW', # adding new key, value
row['RAWID'] = 1,
row['CUSTOMER'] = {
"ID": row['CUSTOMER_ID'],
"NAME": row['CUSTOMER_NAME']
}
row['CATEGORY'] = {
"ID": row['CATEGORY_ID'],
"NAME": row['CATEGORY']
}
del (row["CUSTOMER_NAME"], row["CATEGORY_ID"],
row["CATEGORY"], row["CUSTOMER_ID"]) # deleting since fields coccuring twice
csv_rows.append(row)
with open(json_file, 'w') as f:
json.dump(csv_rows, f, sort_keys=True, indent=4, ensure_ascii=False)
f.write('\n')
The output is as below:
[
{
"CATEGORY": {
"ID": "1",
"NAME": "Consumers"
},
"CATEGORY_ID": "1",
"CUSTOMER_ID": "41",
"CUSTOMER": {
"ID": "41",
"NAME": "SA Port"
},
"CUSTOMER_NAME": "SA Port",
"RAWID": [
1
]
}
]
I'm getting 2 entries for the fields I have assigned using row[''].
Is there any other way to get rid of this? I want only one entry for a particular field in each record.
Also how can I convert the keys to lower case after reading from csv.DictReader(). In my csv file all the columns are in upper case and hence I'm using the same to assign. But I want to convert all of them to lower case.
In order to convert the keys to lower case, it would be simpler to generate a new dict per row. BTW, it should be enough to get rid of the duplicate fields:
for row in reader:
orow = collection.OrderedDict()
orow['type'] = 'REVIEW', # adding new key, value
orow['rawid'] = 1,
orow['customer'] = {
"id": row['CUSTOMER_ID'],
"name": row['CUSTOMER_NAME']
}
orow['category'] = {
"id": row['CATEGORY_ID'],
"name": row['CATEGORY']
}
csv_rows.append(orow)

Python - JSON to CSV table?

I was wondering how I could import a JSON file, and then save that to an ordered CSV file, with header row and the applicable data below.
Here's what the JSON file looks like:
[
{
"firstName": "Nicolas Alexis Julio",
"lastName": "N'Koulou N'Doubena",
"nickname": "N. N'Koulou",
"nationality": "Cameroon",
"age": 24
},
{
"firstName": "Alexandre Dimitri",
"lastName": "Song-Billong",
"nickname": "A. Song",
"nationality": "Cameroon",
"age": 26,
etc. etc. + } ]
Note there are multiple 'keys' (firstName, lastName, nickname, etc.). I would like to create a CSV file with those as the header, then the applicable info beneath in rows, with each row having a player's information.
Here's the script I have so far for Python:
import urllib2
import json
import csv
writefilerows = csv.writer(open('WCData_Rows.csv',"wb+"))
api_key = "xxxx"
url = "http://worldcup.kimonolabs.com/api/players?apikey=" + api_key + "&limit=1000"
json_obj = urllib2.urlopen(url)
readable_json = json.load(json_obj)
list_of_attributes = readable_json[0].keys()
print list_of_attributes
writefilerows.writerow(list_of_attributes)
for x in readable_json:
writefilerows.writerow(x[list_of_attributes])
But when I run that, I get a "TypeError: unhashable type:'list'" error. I am still learning Python (obviously I suppose). I have looked around online (found this) and can't seem to figure out how to do it without explicitly stating what key I want to print...I don't want to have to list each one individually...
Thank you for any help/ideas! Please let me know if I can clarify or provide more information.
Your TypeError is occuring because you are trying to index a dictionary, x with a list, list_of_attributes with x[list_of_attributes]. This is not how python works. In this case you are iterating readable_json which appears it will return a dictionary with each iteration. There is no need pull values out of this data in order to write them out.
The DictWriter should give you what your looking for.
import csv
[...]
def encode_dict(d, out_encoding="utf8"):
'''Encode dictionary to desired encoding, assumes incoming data in unicode'''
encoded_d = {}
for k, v in d.iteritems():
k = k.encode(out_encoding)
v = unicode(v).encode(out_encoding)
encoded_d[k] = v
return encoded_d
list_of_attributes = readable_json[0].keys()
# sort fields in desired order
list_of_attributes.sort()
with open('WCData_Rows.csv',"wb+") as csv_out:
writer = csv.DictWriter(csv_out, fieldnames=list_of_attributes)
writer.writeheader()
for data in readable_json:
writer.writerow(encode_dict(data))
Note:
This assumes that each entry in readable_json has the same fields.
Maybe pandas could do this - but I newer tried to read JSON
import pandas as pd
df = pd.read_json( ... )
df.to_csv( ... )
pandas.DataFrame.to_csv
pandas.io.json.read_json
EDIT:
data = ''' [
{
"firstName": "Nicolas Alexis Julio",
"lastName": "N'Koulou N'Doubena",
"nickname": "N. N'Koulou",
"nationality": "Cameroon",
"age": 24
},
{
"firstName": "Alexandre Dimitri",
"lastName": "Song-Billong",
"nickname": "A. Song",
"nationality": "Cameroon",
"age": 26,
}
]'''
import pandas as pd
df = pd.read_json(data)
print df
df.to_csv('results.csv')
result:
age firstName lastName nationality nickname
0 24 Nicolas Alexis Julio N'Koulou N'Doubena Cameroon N. N'Koulou
1 26 Alexandre Dimitri Song-Billong Cameroon A. Song
With pandas you can save it in csv, excel, etc (and maybe even directly in database).
And you can do some operations on data in table and show it as graph.

Categories

Resources