We Keep Coding

Python - Get Nested Data from Multiple Levels

Wasn't sure how to title this question but I am working with the Quickbooks Online API and when querying a report like BalanceSheet or GeneralLedger the API returns data rows in multiple nested levels which is quite frustrating to parse through.
Example of the BalanceSheet return included below. I am only interested in the data from "Row" objects but as you can see that can be returned in 1, 2, 3 or more different levels of data. I am thinking of going through each level to check for Rows and then get each Row but that seems overly complex as I would need multiple for loops for each level.
I'm wondering if there is a better way to get each "Row" in that data without regard to which level it is on? Any ideas would be appreciated!
Here's an example of a return from their sandbox data:
{
"Header": {
"Time": "2021-04-28T14:12:17-07:00",
"ReportName": "BalanceSheet",
"DateMacro": "this calendar year-to-date",
"ReportBasis": "Accrual",
"StartPeriod": "2021-01-01",
"EndPeriod": "2021-04-28",
"SummarizeColumnsBy": "Month",
"Currency": "USD",
"Option": [
{
"Name": "AccountingStandard",
"Value": "GAAP"
},
{
"Name": "NoReportData",
"Value": "false"
}
]
},
"Columns": {
"Column": [
{
"ColTitle": "",
"ColType": "Account",
"MetaData": [
{
"Name": "ColKey",
"Value": "account"
}
]
},
{
"ColTitle": "Jan 2021",
"ColType": "Money",
"MetaData": [
{
"Name": "StartDate",
"Value": "2021-01-01"
},
{
"Name": "EndDate",
"Value": "2021-01-31"
},
{
"Name": "ColKey",
"Value": "Jan 2021"
}
]
},
{
"ColTitle": "Feb 2021",
"ColType": "Money",
"MetaData": [
{
"Name": "StartDate",
"Value": "2021-02-01"
},
{
"Name": "EndDate",
"Value": "2021-02-28"
},
{
"Name": "ColKey",
"Value": "Feb 2021"
}
]
},
{
"ColTitle": "Mar 2021",
"ColType": "Money",
"MetaData": [
{
"Name": "StartDate",
"Value": "2021-03-01"
},
{
"Name": "EndDate",
"Value": "2021-03-31"
},
{
"Name": "ColKey",
"Value": "Mar 2021"
}
]
},
{
"ColTitle": "Apr 1-28, 2021",
"ColType": "Money",
"MetaData": [
{
"Name": "StartDate",
"Value": "2021-04-01"
},
{
"Name": "EndDate",
"Value": "2021-04-28"
},
{
"Name": "ColKey",
"Value": "Apr 1-28, 2021"
}
]
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "ASSETS"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Current Assets"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Bank Accounts"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Checking",
"id": "35"
},
{
"value": "1201.00"
},
{
"value": "1201.00"
},
{
"value": "1201.00"
},
{
"value": "1201.00"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Savings",
"id": "36"
},
{
"value": "800.00"
},
{
"value": "800.00"
},
{
"value": "800.00"
},
{
"value": "800.00"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Bank Accounts"
},
{
"value": "2001.00"
},
{
"value": "2001.00"
},
{
"value": "2001.00"
},
{
"value": "2001.00"
}
]
},
"type": "Section",
"group": "BankAccounts"
},
{
"Header": {
"ColData": [
{
"value": "Accounts Receivable"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Accounts Receivable (A/R)",
"id": "84"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Accounts Receivable"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
},
{
"value": "5281.52"
}
]
},
"type": "Section",
"group": "AR"
},
{
"Header": {
"ColData": [
{
"value": "Other Current Assets"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Inventory Asset",
"id": "81"
},
{
"value": "596.25"
},
{
"value": "596.25"
},
{
"value": "596.25"
},
{
"value": "596.25"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Undeposited Funds",
"id": "4"
},
{
"value": "2062.52"
},
{
"value": "2062.52"
},
{
"value": "2062.52"
},
{
"value": "2062.52"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Other Current Assets"
},
{
"value": "2658.77"
},
{
"value": "2658.77"
},
{
"value": "2658.77"
},
{
"value": "2658.77"
}
]
},
"type": "Section",
"group": "OtherCurrentAssets"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Current Assets"
},
{
"value": "9941.29"
},
{
"value": "9941.29"
},
{
"value": "9941.29"
},
{
"value": "9941.29"
}
]
},
"type": "Section",
"group": "CurrentAssets"
},
{
"Header": {
"ColData": [
{
"value": "Fixed Assets"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Truck",
"id": "37"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Original Cost",
"id": "38"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Truck"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
}
]
},
"type": "Section"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Fixed Assets"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
},
{
"value": "13495.00"
}
]
},
"type": "Section",
"group": "FixedAssets"
}
]
},
"Summary": {
"ColData": [
{
"value": "TOTAL ASSETS"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
}
]
},
"type": "Section",
"group": "TotalAssets"
},
{
"Header": {
"ColData": [
{
"value": "LIABILITIES AND EQUITY"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Liabilities"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Current Liabilities"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"Header": {
"ColData": [
{
"value": "Accounts Payable"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Accounts Payable (A/P)",
"id": "33"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Accounts Payable"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
},
{
"value": "1602.67"
}
]
},
"type": "Section",
"group": "AP"
},
{
"Header": {
"ColData": [
{
"value": "Credit Cards"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Mastercard",
"id": "41"
},
{
"value": "157.72"
},
{
"value": "157.72"
},
{
"value": "157.72"
},
{
"value": "157.72"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Credit Cards"
},
{
"value": "157.72"
},
{
"value": "157.72"
},
{
"value": "157.72"
},
{
"value": "157.72"
}
]
},
"type": "Section",
"group": "CreditCards"
},
{
"Header": {
"ColData": [
{
"value": "Other Current Liabilities"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Arizona Dept. of Revenue Payable",
"id": "89"
},
{
"value": "0.00"
},
{
"value": "0.00"
},
{
"value": "0.00"
},
{
"value": "0.00"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Board of Equalization Payable",
"id": "90"
},
{
"value": "370.94"
},
{
"value": "370.94"
},
{
"value": "370.94"
},
{
"value": "370.94"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Loan Payable",
"id": "43"
},
{
"value": "4000.00"
},
{
"value": "4000.00"
},
{
"value": "4000.00"
},
{
"value": "4000.00"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Other Current Liabilities"
},
{
"value": "4370.94"
},
{
"value": "4370.94"
},
{
"value": "4370.94"
},
{
"value": "4370.94"
}
]
},
"type": "Section",
"group": "OtherCurrentLiabilities"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Current Liabilities"
},
{
"value": "6131.33"
},
{
"value": "6131.33"
},
{
"value": "6131.33"
},
{
"value": "6131.33"
}
]
},
"type": "Section",
"group": "CurrentLiabilities"
},
{
"Header": {
"ColData": [
{
"value": "Long-Term Liabilities"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Notes Payable",
"id": "44"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
}
],
"type": "Data"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Long-Term Liabilities"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
},
{
"value": "25000.00"
}
]
},
"type": "Section",
"group": "LongTermLiabilities"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Liabilities"
},
{
"value": "31131.33"
},
{
"value": "31131.33"
},
{
"value": "31131.33"
},
{
"value": "31131.33"
}
]
},
"type": "Section",
"group": "Liabilities"
},
{
"Header": {
"ColData": [
{
"value": "Equity"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
]
},
"Rows": {
"Row": [
{
"ColData": [
{
"value": "Opening Balance Equity",
"id": "34"
},
{
"value": "-9337.50"
},
{
"value": "-9337.50"
},
{
"value": "-9337.50"
},
{
"value": "-9337.50"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Retained Earnings",
"id": "2"
},
{
"value": "1642.46"
},
{
"value": "1642.46"
},
{
"value": "1642.46"
},
{
"value": "1642.46"
}
],
"type": "Data"
},
{
"ColData": [
{
"value": "Net Income"
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
},
{
"value": ""
}
],
"type": "Data",
"group": "NetIncome"
}
]
},
"Summary": {
"ColData": [
{
"value": "Total Equity"
},
{
"value": "-7695.04"
},
{
"value": "-7695.04"
},
{
"value": "-7695.04"
},
{
"value": "-7695.04"
}
]
},
"type": "Section",
"group": "Equity"
}
]
},
"Summary": {
"ColData": [
{
"value": "TOTAL LIABILITIES AND EQUITY"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
},
{
"value": "23436.29"
}
]
},
"type": "Section",
"group": "TotalLiabilitiesAndEquity"
}
]
}
}

Merge lists of complex dicts with arbitrary keys

I have this code:
dotteds = ["apple.orange.banana", "a.b.c", "a.b.d"]
name = "name"
avtype = "type"
fields = "fields"
main_dictionary_list = []
for x in dotteds:
split_name = x.split('.')
if len(split_name) > 1:
value = {name: split_name[-1], avtype: 'string'}
dicts = []
for y in split_name:
dicts.append({name: y, avtype: {name: y, avtype: "record", fields: []}})
dicts[-1] = value
value = value['name']+split_name[-1]
for z in reversed(range(len(dicts))):
if z != 0:
dicts[z - 1]['type']['fields'].append(dicts[z])
main_dictionary_list.append(dicts[0])
else:
dicts = []
value = {name: split_name[-1], avtype: 'string'}
dicts.append(value)
main_dictionary_list.append(dicts[0])
print(main_dictionary_list)
Which gives me an output like this:
[{
'name': 'apple',
'type': {
'name': 'apple',
'type': 'record',
'fields': [{
'name': 'orange',
'type': {
'name': 'orange',
'type': 'record',
'fields': [{
'name': 'banana',
'type': 'string'
}
]
}
}
]
}
}, {
'name': 'a',
'type': {
'name': 'a',
'type': 'record',
'fields': [{
'name': 'b',
'type': {
'name': 'b',
'type': 'record',
'fields': [{
'name': 'c',
'type': 'string'
}
]
}
}
]
}
}, {
'name': 'a',
'type': {
'name': 'a',
'type': 'record',
'fields': [{
'name': 'b',
'type': {
'name': 'b',
'type': 'record',
'fields': [{
'name': 'd',
'type': 'string'
}
]
}
}
]
}
}
]
Ideally I need:
[{
'name': 'apple',
'type': {
'name': 'apple',
'type': 'record',
'fields': [{
'name': 'orange',
'type': {
'name': 'orange',
'type': 'record',
'fields': [{
'name': 'banana',
'type': 'string'
}
]
}
}
]
}
}, {
'name': 'a',
'type': {
'name': 'a',
'type': 'record',
'fields': [{
'name': 'b',
'type': {
'name': 'b',
'type': 'record',
'fields': [{
'name': 'c',
'type': 'string'
},
{
'name': 'd',
'type': 'string'
}
]
}
}
]
}
}
]
I need to be able to do this with any number of combinations:
apple.orange.banana, a.b.c, a.b.d, a.b.q.e.a.s.d, etc.
I cannot figure out how to combine the similar 'name: key' combinations. It's intended to be avro format.
I have also tried making the dotted values into a dictionary which is a bit of trouble on its own.

You can use recursion with collections.defaultdict:
from collections import defaultdict
def group(vals, last=None):
if any(len(i) == 1 for i in vals):
return [{'name':last, 'type':{'name':last, 'type':'record', 'fields':[{'name':i[0], 'type':'string'} if len(i) == 1 else group([i], i[0])[0] for i in vals]}}]
_d = defaultdict(list)
for i in vals:
_d[i[0]].append(i[1:])
return [{'name':a, 'type':group(b, last=a)} if last is None else
{'name':last, 'type':'record', 'fields':group(b, last=a)} for a, b in _d.items()]
import json
vals = ['apple.orange.banana', 'a.b.c', 'a.b.d']
print(json.dumps(group([i.split('.') for i in vals]), indent=4))
Output:
[
{
"name": "apple",
"type": [
{
"name": "apple",
"type": "record",
"fields": [
{
"name": "orange",
"type": {
"name": "orange",
"type": "record",
"fields": [
{
"name": "banana",
"type": "string"
}
]
}
}
]
}
]
},
{
"name": "a",
"type": [
{
"name": "a",
"type": "record",
"fields": [
{
"name": "b",
"type": {
"name": "b",
"type": "record",
"fields": [
{
"name": "c",
"type": "string"
},
{
"name": "d",
"type": "string"
}
]
}
}
]
}
]
}
]
vals = ['asd.2', 'asd.3', 'asd.5.3.4']
print(json.dumps(group([i.split('.') for i in vals]), indent=4))
Output:
[
{
"name": "asd",
"type": [
{
"name": "asd",
"type": {
"name": "asd",
"type": "record",
"fields": [
{
"name": "2",
"type": "string"
},
{
"name": "3",
"type": "string"
},
{
"name": "5",
"type": "record",
"fields": [
{
"name": "5",
"type": "record",
"fields": [
{
"name": "3",
"type": {
"name": "3",
"type": "record",
"fields": [
{
"name": "4",
"type": "string"
}
]
}
}
]
}
]
}
]
}
}
]
}
]

merge complex list of nested dicts

I'm trying to merge nested Dicts in a list based on "name" like the following:
[
{
"name": "abc",
"metadata": [
{
"name": "foo",
"data": [
{
"version": "1.0"
}
]
},
{
"name": "foo",
"data": [
{
"version": "2.0"
}
]
},
{
"name": "bar",
"data": [
{
"version": "1.0"
}
]
}
]
},
{
"name": "xyz",
"metadata": [
{
"name": "bob",
"data": [
{
"version": "3.2"
}
]
},
{
"name": "alice",
"data": [
{
"version": "2.2"
}
]
}
]
},
{
"name": "xyz",
"metadata": [
{
"name": "mike",
"data": [
{
"version": "3.2"
}
]
},
{
"name": "alice",
"data": [
{
"version": "2.2"
}
]
}
]
}
]
Considering that the merged items should not have duplicates in the metadata, how can I do that in Python? Metadata entries should be unique, if name+data+version exist in the metadata, then the item should not be merged.
my desired output should look like this
[
{
"name": "abc",
"metadata": [
{
"name": "foo",
"data": [
{
"version": "1.0"
}
]
},
{
"name": "foo",
"data": [
{
"version": "2.0"
}
]
},
{
"name": "bar",
"data": [
{
"version": "1.0"
}
]
}
]
},
{
"name": "xyz",
"metadata": [
{
"name": "bob",
"data": [
{
"version": "3.2"
}
]
},
{
"name": "mike",
"data": [
{
"version": "3.2"
}
]
},
{
"name": "alice",
"data": [
{
"version": "2.2"
}
]
}
]
}
]

You can use itertools.groubpy:
import itertools
d = [{'name': 'abc', 'metadata': [{'name': 'foo', 'data': [{'version': '1.0'}]}, {'name': 'foo', 'data': [{'version': '2.0'}]}, {'name': 'bar', 'data': [{'version': '1.0'}]}]}, {'name': 'xyz', 'metadata': [{'name': 'bob', 'data': [{'version': '3.2'}]}, {'name': 'alice', 'data': [{'version': '2.2'}]}]}, {'name': 'xyz', 'metadata': [{'name': 'mike', 'data': [{'version': '3.2'}]}, {'name': 'alice', 'data': [{'version': '2.2'}]}]}]
new_d = [[a, list(b)] for a, b in itertools.groupby(sorted(d, key=lambda x:x['name']), key=lambda x:x['name'])]
result = [{'name':a, 'metadata':[c for j in b for c in j['metadata']]} for a, b in new_d]
final_result = [{**i, 'metadata':[c for d, c in enumerate(i['metadata']) if all(a != c for a in i['metadata'][:d])]} for i in result]
import json
print(json.dumps(final_result, indent=4))
Output:
[
{
"name": "abc",
"metadata": [
{
"name": "foo",
"data": [
{
"version": "1.0"
}
]
},
{
"name": "foo",
"data": [
{
"version": "2.0"
}
]
},
{
"name": "bar",
"data": [
{
"version": "1.0"
}
]
}
]
},
{
"name": "xyz",
"metadata": [
{
"name": "bob",
"data": [
{
"version": "3.2"
}
]
},
{
"name": "alice",
"data": [
{
"version": "2.2"
}
]
},
{
"name": "mike",
"data": [
{
"version": "3.2"
}
]
}
]
}
]

Combine 2 JSON files into 1 file in Node or Python (i.e. longitude and latitude)

I want to append the longitude to a latitude stored in 2 separated json files
The result should be stored in a 3rd file
How can I do that on Python OR Javascript/Node?
Many thanks for your support,
LATITUDE
{
"tags": [{
"name": "LATITUDE_deg",
"results": [{
"groups": [{
"name": "type",
"type": "number"
}],
"values": [
[1123306773000, 46.9976859318, 3],
[1123306774000, 46.9976859319, 3]
],
"attributes": {
"customer": ["Acme"],
"host": ["server1"]
}
}],
"stats": {
"rawCount": 2
}
}]
}
LONGITUDE
{
"tags": [{
"name": "LONGITUDE_deg",
"results": [{
"groups": [{
"name": "type",
"type": "number"
}],
"values": [
[1123306773000, 36.9976859318, 3],
[1123306774000, 36.9976859317, 3]
],
"attributes": {
"customer": ["Acme"],
"host": ["server1"]
}
}],
"stats": {
"rawCount": 2
}
}]
}
Expected result: LATITUDE_AND_LONGITUDE
{
"tags": [{
"name": "LATITUDE_AND_LONGITUDE_deg",
"results": [{
"groups": [{
"name": "type",
"type": "number"
}],
"values": [
[1123306773000, 46.9976859318, 36.9976859318, 3],
[1123306774000, 46.9976859319, 36.9976859317, 3]
],
"attributes": {
"customer": ["Acme"],
"host": ["server1"]
}
}],
"stats": {
"rawCount": 2
}
}]
}

I have written the solution with a colleague, find the source code on github: https://gist.github.com/Abdelkrim/715eb222cc318219196c8be293c233bf

Python - Adding fields and labels to nested json file

I have a dataframe as follows:
Name_ID | URL | Count | Rating
------------------------------------------------
ABC | www.example.com/ABC | 10 | 5
123 | www.example.com/123 | 9 | 4
XYZ | www.example.com/XYZ | 5 | 2
ABC111 | www.example.com/ABC111 | 5 | 2
ABC121 | www.example.com/ABC121 | 5 | 2
222 | www.example.com/222 | 5 | 3
abc222 | www.example.com/abc222 | 4 | 2
ABCaaa | www.example.com/ABCaaa | 4 | 2
I am trying to create a JSON as follows:
{
"name": "sampledata",
"children": [
{
"name": 9,
"children": [
{
"name": 4,
"children": [
{
"name": "123",
"size": 100
}
]
}
]
},
{
"name": 10,
"children": [
{
"name": 5,
"children": [
{
"name": "ABC",
"size": 100
}
]
}
]
},
{
"name": 4,
"children": [
{
"name": 2,
"children": [
{
"name": "abc222",
"size": 50
},
{
"name": "ABCaaa",
"size": 50
}
]
}
]
},
{
"name": 5,
"children": [
{
"name": 2,
"children": [
{
"name": "ABC",
"size": 16
},
{
"name": "ABC111",
"size": 16
},
{
"name": "ABC121",
"size": 16
}
]
},
{
"name": 3,
"children": [
{
"name": "222",
"size": 50
}
]
}
]
}
]
}
In order to do that:
I am trying to add labels such as "name" and "children" to the json while creating it.
I tried something like
results = [{"name": i, "children": j} for i,j in results.items()]
But it won't label it properly I believe.
Also, add another field with the label `"size"which I am planning to calculate based on the formula:
(Rating*Count*10000)/number_of_children_to_the_immediate_parent
Here is my dirty code:
import pandas as pd
from collections import defaultdict
import json
data =[('ABC', 'www.example.com/ABC', 10 , 5), ('123', 'www.example.com/123', 9, 4), ('XYZ', 'www.example.com/XYZ', 5, 2), ('ABC111', 'www.example.com/ABC111', 5, 2), ('ABC121', 'www.example.com/ABC121', 5, 2), ('222', 'www.example.com/222', 5, 3), ('abc222', 'www.example.com/abc222', 4, 2), ('ABCaaa', 'www.example.com/ABCaaa', 4, 2)]
df = pd.DataFrame(data, columns=['Name', 'URL', 'Count', 'Rating'])
gp = df.groupby(['Count'])
dict_json = {"name": "flare"}
children = []
for name, group in gp:
temp = {}
temp["name"] = name
temp["children"] = []
rgp = group.groupby(['Rating'])
for n, g in rgp:
temp2 = {}
temp2["name"] = n
temp2["children"] = g.reset_index().T.to_dict().values()
for t in temp2["children"]:
t["size"] = (t["Rating"] * t["Count"] * 10000) / len(temp2["children"])
t["name"] = t["Name"]
del t["Count"]
del t["Rating"]
del t["URL"]
del t["Name"]
del t["index"]
temp["children"].append(temp2)
children.append(temp)
dict_json["children"] = children
print json.dumps(dict_json, indent=4)
Though the above code does print what I need, I am looking for more efficient and cleaner way to do the same, mainly because the actual dataset might be even more nested and complicated. Any help/suggestion will be much appreciated.

Quite an interesting problem and a great question!
You can improve your approach by reorganizing the code inside the loops and using list comprehensions. No need to delete things and introduce temp variables inside loops:
dict_json = {"name": "flare"}
children = []
for name, group in gp:
temp = {"name": name, "children": []}
rgp = group.groupby(['Rating'])
for n, g in rgp:
temp["children"].append({
"name": n,
"children": [
{"name": row["Name"],
"size": row["Rating"] * row["Count"] * 10000 / len(g)}
for _, row in g.iterrows()
]
})
children.append(temp)
dict_json["children"] = children
Or, a "wrapped" version:
dict_json = {
"name": "flare",
"children": [
{
"name": name,
"children": [
{
"name": n,
"children": [
{
"name": row["Name"],
"size": row["Rating"] * row["Count"] * 10000 / len(g)
} for _, row in g.iterrows()
]
} for n, g in group.groupby(['Rating'])
]
} for name, group in gp
]
}
I'm getting the following dictionary printed for you sample input dataframe:
{
"name": "flare",
"children": [
{
"name": 4,
"children": [
{
"name": 2,
"children": [
{
"name": "abc222",
"size": 40000
},
{
"name": "ABCaaa",
"size": 40000
}
]
}
]
},
{
"name": 5,
"children": [
{
"name": 2,
"children": [
{
"name": "XYZ",
"size": 33333
},
{
"name": "ABC111",
"size": 33333
},
{
"name": "ABC121",
"size": 33333
}
]
},
{
"name": 3,
"children": [
{
"name": "222",
"size": 150000
}
]
}
]
},
{
"name": 9,
"children": [
{
"name": 4,
"children": [
{
"name": "123",
"size": 360000
}
]
}
]
},
{
"name": 10,
"children": [
{
"name": 5,
"children": [
{
"name": "ABC",
"size": 500000
}
]
}
]
}
]
}

If I understand correctly what you wan't to do is put a groupby into a nested json, if that is the case then you could use pandas groupby and cast it into a nested list of lists as so:
lol = pd.DataFrame(df.groupby(['Count','Rating'])\
.apply(lambda x: list(x['Name_ID']))).reset_index().values.tolist()
lol should look something like this:
[['10', '5', ['ABC']],
['4', '2', ['abc222', 'ABCaaa']],
['5', '2', ['XYZ ', 'ABC111', 'ABC121']],
['5', '3', ['222 ']],
['9', '4', ['123 ']]]
after that you could loop over lol to put it into a dict, but since you want to set nested items you'l have to use autovivification (check it out):
class autovividict(dict):
def __missing__(self, key):
value = self[key] = type(self)()
return value
d = autovividict()
for l in lol:
d[l[0]][l[1]] = l[2]
now you can use the json pack for printing and exporting:
print json.dumps(d,indent=2)
In case you need more than one groupby, you could concat your groups with pandas, cast to lol, remove any nans, and then loop, let me know if a full example can help.

setup
from io import StringIO
import pandas as pd
txt = """Name_ID,URL,Count,Rating
ABC,www.example.com/ABC,10,5
123,www.example.com/123,9,4
XYZ,www.example.com/XYZ,5,2
ABC111,www.example.com/ABC111,5,2
ABC121,www.example.com/ABC121,5,2
222,www.example.com/222,5,3
abc222,www.example.com/abc222,4,2
ABCaaa,www.example.com/ABCaaa,4,2"""
df = pd.read_csv(StringIO(txt))
size
pre-calculate it
df['size'] = df.Count.mul(df.Rating) \
.mul(10000) \
.div(df.groupby(
['Count', 'Rating']).Name_ID.transform('count')
).astype(int)
solution
create recursive function
def h(d):
if isinstance(d, pd.Series): d = d.to_frame().T
rec_cond = d.index.nlevels > 1 or d.index.nunique() > 1
return {'name': str(d.index[0]), 'size': str(d['size'].iloc[0])} if not rec_cond else \
[dict(name=str(n), children=h(g.xs(n))) for n, g in d.groupby(level=0)]
demo
import json
my_dict = dict(name='flare', children=h(df.set_index(['Count', 'Rating', 'Name_ID'])))
json.dumps(my_dict)
'{"name": "flare", "children": [{"name": "4", "children": [{"name": "2", "children": [{"name": "ABCaaa", "children": {"name": "ABCaaa", "size": "40000"}}, {"name": "abc222", "children": {"name": "abc222", "size": "40000"}}]}]}, {"name": "5", "children": [{"name": "2", "children": [{"name": "ABC111", "children": {"name": "ABC111", "size": "33333"}}, {"name": "ABC121", "children": {"name": "ABC121", "size": "33333"}}, {"name": "XYZ", "children": {"name": "XYZ", "size": "33333"}}]}, {"name": "3", "children": {"name": "222", "size": "150000"}}]}, {"name": "9", "children": [{"name": "4", "children": {"name": "123", "size": "360000"}}]}, {"name": "10", "children": [{"name": "5", "children": {"name": "ABC", "size": "500000"}}]}]}'
my_dict
{'children': [{'children': [{'children': [{'children': {'name': 'ABCaaa',
'size': '40000'},
'name': 'ABCaaa'},
{'children': {'name': 'abc222', 'size': '40000'}, 'name': 'abc222'}],
'name': '2'}],
'name': '4'},
{'children': [{'children': [{'children': {'name': 'ABC111', 'size': '33333'},
'name': 'ABC111'},
{'children': {'name': 'ABC121', 'size': '33333'}, 'name': 'ABC121'},
{'children': {'name': 'XYZ', 'size': '33333'}, 'name': 'XYZ'}],
'name': '2'},
{'children': {'name': '222', 'size': '150000'}, 'name': '3'}],
'name': '5'},
{'children': [{'children': {'name': '123', 'size': '360000'}, 'name': '4'}],
'name': '9'},
{'children': [{'children': {'name': 'ABC', 'size': '500000'}, 'name': '5'}],
'name': '10'}],
'name': 'flare'}