I need to convert a csv file into a json file. I have tried some python examples that are available on-line but none seem to fit my needs.
My csv file contains a header then multiple rows for each date. Im not entirely sure on the terminology but I think I need each unique id in the first field in the csv (NA, NE, SE) to have its own object in the json.
Any help would be appreciated. Cheers!
Example of input
A1,sDate,eDate,A2
NA,01/01/2023,01/05/2023,2
NE,01/01/2023,01/05/2023,3
SE,01/01/2023,01/05/2023,4
NA,02/01/2023,02/05/2023,5
NE,02/01/2023,02/05/2023,6
SE,02/01/2023,02/05/2023,7
My desired output would be
{
"NA": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"a2": 2
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"a2": 5
}
],
"NE": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"a2": 3
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"a2": 6
}
],
"SE": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"a2": 4
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"a2": 7
}
]
I was using the pandas library to help with this but its not giving the results I need.
import pandas
import json
df = pandas.read_csv('file.csv', names=("A1","sDate","eDate","A2"))
df.to_json('file.json', orient='records')
with open('file.json', 'w') as f:
json.dump({'NA': df.to_dict(orient='records')}, f, indent=4)
{
"NA": [
{
"A1": "NA",
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": "2"
},
{
"A1": "NE",
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": "3"
},
"A1": "SE",
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": "4"
},
{
"A1": "NA",
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": "5"
},
{
"A1": "NE",
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": "6"
},
"A1": "SE",
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": "7"
}
]
defaultdict is very useful for this kind of processing
def build_structure(reader: typing.List[dict]) -> dict:
structure = collections.defaultdict(list)
for d in reader:
structure[d["A1"]].append(
{"sDate": d["sDate"], "eDate": d["eDate"], "a2": d["A2"]}
)
return structure
Read the file and create a csv.DictReader of the file and convert it to a list,
Send the list to the build_structure function.
You have a defaultdict, you can dumps it with json.
import collections
import csv
import json
import typing
def read_csv(file_name: str) -> list:
with open(file_name, "r") as f:
reader = csv.DictReader(f)
return list(reader)
def build_structure(reader: typing.List[dict]) -> dict:
structure = collections.defaultdict(list)
for d in reader:
structure[d["A1"]].append(
{"sDate": d["sDate"], "eDate": d["eDate"], "a2": d["A2"]}
)
return structure
data = read_csv("data.csv")
structure = build_structure(data)
print(json.dumps(structure))
# {'NA': [{'a2': '2', 'eDate': '01/05/2023', 'sDate': '01/01/2023'},
# {'a2': '5', 'eDate': '02/05/2023', 'sDate': '02/01/2023'}],
# 'NE': [{'a2': '3', 'eDate': '01/05/2023', 'sDate': '01/01/2023'},
# {'a2': '6', 'eDate': '02/05/2023', 'sDate': '02/01/2023'}],
# 'SE': [{'a2': '4', 'eDate': '01/05/2023', 'sDate': '01/01/2023'},
# {'a2': '7', 'eDate': '02/05/2023', 'sDate': '02/01/2023'}]}
If you want a beautified json string, you can use json.dumps(structure, sort_keys=True, indent=4) instead:
>>> print(json.dumps(structure, sort_keys=True, indent=4))
{
"NA": [
{
"a2": "2",
"eDate": "01/05/2023",
"sDate": "01/01/2023"
},
{
"a2": "5",
"eDate": "02/05/2023",
"sDate": "02/01/2023"
}
],
"NE": [
{
"a2": "3",
"eDate": "01/05/2023",
"sDate": "01/01/2023"
},
{
"a2": "6",
"eDate": "02/05/2023",
"sDate": "02/01/2023"
}
],
"SE": [
{
"a2": "4",
"eDate": "01/05/2023",
"sDate": "01/01/2023"
},
{
"a2": "7",
"eDate": "02/05/2023",
"sDate": "02/01/2023"
}
]
}
You can use pandas and groupby:
import pandas as pd
import json
df = pd.read_csv("your_file.csv", keep_default_na=False)
res = {}
for a1, df_gp in df.groupby('A1'):
res[a1] = df_gp.drop(columns='A1').to_dict(orient='records')
print(json.dumps(res, indent=4))
Output:
{
"NA": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": 2
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": 5
}
],
"NE": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": 3
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": 6
}
],
"SE": [
{
"sDate": "01/01/2023",
"eDate": "01/05/2023",
"A2": 4
},
{
"sDate": "02/01/2023",
"eDate": "02/05/2023",
"A2": 7
}
]
}
Related
I am filtering in ElasticSearch. I want doc_count to return 0 on non-data dates, but it doesn't print those dates at all, only dates with data are returned to me. do you know how i can do it? Here is the Python output:
0 NaN
1 NaN
2 NaN
3 NaN
4 NaN
...
33479 {'date': '2022-04-13T08:08:00.000Z', 'value': 7}
33480 {'date': '2022-04-13T08:08:00.000Z', 'value': 7}
33481 {'date': '2022-04-13T08:08:00.000Z', 'value': 7}
33482 {'date': '2022-04-13T08:08:00.000Z', 'value': 7}
33483 {'date': '2022-04-13T08:08:00.000Z', 'value': 7}
And here is my ElasticSearch filter:
"from": 0,
"size": 0,
"query": {
"bool": {
"must":
[
{
"range": {
"#timestamp": {
"gte": "now-1M",
"lt": "now"
}
}
}
]
}
},
"aggs": {
"continent": {
"terms": {
"field": "source.geo.continent_name.keyword"
},
"aggs": {
"_source": {
"date_histogram": {
"field": "#timestamp", "interval": "8m"
}}}}}}
You need to set min_doc_count value to 0 for aggregation where you want result with zero doc_count.
{
"from": 0,
"size": 0,
"query": {
"bool": {
"must": [
{
"range": {
"#timestamp": {
"gte": "now-1M",
"lt": "now"
}
}
}
]
}
},
"aggs": {
"continent": {
"terms": {
"field": "source.geo.continent_name.keyword",
"min_doc_count": 0
},
"aggs": {
"_source": {
"date_histogram": {
"field": "#timestamp",
"interval": "8m",
"min_doc_count": 0
}
}
}
}
}
}
I have this json file loaded in Python with json.loads('myfile.json'):
[
{
"cart": {
"items": {
"3154ba405e5c5a22bbdf9bf1": {
"item": {
"_id": "3154ba405e5c5a22bbdf9bf1",
"title": "Drink alla cannella",
"price": 5.65,
"__v": 0
},
"qty": 1,
"price": 5.65
}
},
"totalQty": 1,
"totalPrice": 5.65
}
},
{
"cart": {
"items": {
"6214ba405e4c5a31bbdf9ad7": {
"item": {
"_id": "6214ba405e4c5a31bbdf9ad7",
"title": "Drink alla menta",
"price": 5.65,
"__v": 0
},
"qty": 2,
"price": 11.3
}
},
"totalQty": 2,
"totalPrice": 11.3
}
}
]
How I can access to both totalQty and totalPrice fields at same time and sum them?
How I can access to both Title fields to print it?
Let's assume that you have the JSON data available as a string then:
jdata = '''
[
{
"cart": {
"items": {
"3154ba405e5c5a22bbdf9bf1": {
"item": {
"_id": "3154ba405e5c5a22bbdf9bf1",
"title": "Drink alla cannella",
"price": 5.65,
"__v": 0
},
"qty": 1,
"price": 5.65
}
},
"totalQty": 1,
"totalPrice": 5.65
}
},
{
"cart": {
"items": {
"6214ba405e4c5a31bbdf9ad7": {
"item": {
"_id": "6214ba405e4c5a31bbdf9ad7",
"title": "Drink alla menta",
"price": 5.65,
"__v": 0
},
"qty": 2,
"price": 11.3
}
},
"totalQty": 2,
"totalPrice": 11.3
}
}
]
'''
totalQty = 0
totalPrice = 0
for d in json.loads(jdata):
c = d['cart']
totalQty += c['totalQty']
totalPrice += c['totalPrice']
for sd in c['items'].values():
print(sd['item']['title'])
print(f'{totalQty:d}', f'{totalPrice:.2f}')
Output:
3 16.95
Note:
I suspect that what you really want to do is multiply those two values
Basically I´m reading a pandas dataframe and converting it to Json. I´m a beginner in coding, but I know that is preferable to use apply function instead iterrows (and I already tried to use apply function, but some difficulties in understand the syntax and find out my solution arose)!!
===============================
Data that I´m reading from excel
id label id_customer label_customer part_number number_customer product label_product key country value_product
6 Sao Paulo CUST-99992 Brazil 982 10 sho1564 shoes SH-99 Chile 1.5
6 Sao Paulo CUST-99992 Brazil 982 10 sn47282 sneakers SN-71 Germany 43.8
6 Sao Paulo CUST-43535 Argentina 435 15 sk84393 skirt SK-11 Netherlands 87.1
92 Hong Hong CUST-88888 China 785 58 ca40349 cap CA-82 Russia 3.95
===============================
CODE:
import pandas as pd
import json
df = pd.read_excel(path)
result = []
for labels, df1 in df.groupby(['id', 'label'],sort=False):
id_, label = labels
record = {'id': int(id_), 'label': label, 'Customer': []}
for inner_labels, df2 in df1.groupby(['id_customer', 'label_customer'],sort=False):
id_,label = inner_labels
record['Customer'].append({
'id': id_,
'label': label,
'Number': [{'part': str(p), 'number_customer': str(s)} for p, s in zip(df2['part_number'], df2['number_customer'])]
})
result.append(record)
===============================
Json I'm getting:
[
{
"id": 6,
"label": "Sao Paulo",
"Customer": [
{
"id": "CUST-99992",
"label": "Brazil",
"Number": [
{
"part": "982",
"number_customer": "10"
},
{
"part": "982",
"number_customer": "10"
}
]
},
{
"id": "CUST-43535",
"label": "Argentina",
"Number": [
{
"part": "435",
"number_customer": "15"
}
]
}
]
},
{
"id": 92,
"label": "Hong Kong",
"Customer": [
{
"id": "CUST-88888",
"label": "China",
"Number": [
{
"part": "785",
"number_customer": "58"
}
]
}
]
}
]
===============================
Json expected:
[
{
"id": 6,
"label": "Sao Paulo",
"Customer": [
{
"id": "CUST-99992",
"label": "Brazil",
"Number": [
{
"part": "982",
"number_customer": "10",
"Procucts": [
{
"product": "sho1564",
"label_product": "shoes",
"Order": [
{
"key": "SH-99",
"country": "Chile",
"value_product": "1.5"
}
]
},
{
"product": "sn47282",
"label_product": "sneakers",
"Order": [
{
"key": "SN-71",
"country": "Germany",
"value_product": "43.8"
}
]
}
]
}
]
},
{
"id": "CUST-43535",
"label": "Argentina",
"Number": [
{
"part": "435",
"number_customer": "15",
"Procucts": [
{
"product": "sk84393",
"label_product": "skirt",
"Order": [
{
"key": "SK-11",
"country": "Netherlands",
"value_product": "87.1"
}
]
}
]
}
]
}
]
},
{
"id": 92,
"label": "Hong Kong",
"Customer": [
{
"id": "CUST-88888",
"label": "China",
"Number": [
{
"part": "785",
"number_customer": "58",
"Procucts": [
{
"product": "ca40349",
"label_product": "cap",
"Order": [
{
"key": "CA-82",
"country": "Russia",
"value_product": "3.95"
}
]
}
]
}
]
}
]
}
]
===============================
Look that id and label is group of information even as id_customer and label customer is another group, part_number and number_customer is another, product and label_product another, key, country and value_product another.
My expected Json depends of my information inside my dataframe.
Can somebody help me in any way pls?
import pandas as pd
import json
df = pd.read_excel(path)
result = []
for labels, df1 in df.groupby(['id', 'label'], sort=False):
id_, label = labels
record = {'id': int(id_), 'label': label, 'Customer': []}
for inner_labels, df2 in df1.groupby(['id_customer', 'label_customer'], sort=False):
id_, label = inner_labels
customer = {'id': id_, 'label': label, 'Number': []}
for inner_labels, df3 in df2.groupby(['part_number', 'number_customer'], sort=False):
p, s = inner_labels
number = {'part': str(p), 'number_customer': str(s), 'Products': []}
for inner_labels, df4 in df3.groupby(['product', 'label_product'], sort=False):
p, lp = inner_labels
product = {'product': p, 'label_product': lp, 'Order': []}
for k, c, v in zip(df4['key'], df4['country'], df4['value_product']):
product['Order'].append({'key': k, 'country': c, 'value_product': v})
number['Products'].append(product)
customer['Number'].append(number)
record['Customer'].append(customer)
result.append(record)
Hope this is of use!
from io import StringIO
import pandas as pd
import json
csv = """id,label,id_customer,label_customer,part_number,number_customer,product,label_product,key,country,value_product
6,Sao Paulo,CUST-99992,Brazil,982,10,sho1564,shoes,SH-99,Chile,1.5
6,Sao Paulo,CUST-99992,Brazil,982,10,sn47282,sneakers,SN-71,Germany,43.8
6,Sao Paulo,CUST-43535,Argentina,435,15,sk84393,skirt,SK-11,Netherlands,87.1
92,Hong Hong,CUST-88888,China,785,58,ca40349,cap,CA-82,Russia,3.95"""
csv = StringIO(csv)
df = pd.read_csv(csv)
def split(df, groupby, json_func):
for x, group in df.groupby(groupby):
yield json_func(group, *x)
a = list(split(df, ['id', 'label'], lambda grp, id_, label: {"id": id_, "label": label, "Customer": list(
split(grp, ['id_customer', 'label_customer'], lambda grp_1, id_cust, label_cust: {"id": id_cust, "label": label_cust, "Number": list(
split(grp_1, ['part_number', 'number_customer'], lambda grp_2, part, num_cust: {"part": part, "number_customer": num_cust, "Products": list(
split(grp_2, ['product', 'label_product'], lambda grp_3, product, label_product: {"product": product, "label_product": label_product, "Order": list(
split(grp_3, ['key', 'country', 'value_product'], lambda _, key, country, value_product: {"key": key, "country": country, "value_product": value_product}))}
))})
)}))}))
display(a)
I would like to create a dictionary containing a nested structure of dictionaries, like bellow :
{
"Jaque": {
"ES": {
"Madrid": [
{
"experience": 9
}
]
},
"FR": {
"Lyon": [
{
"experience": 11.4
}
],
"Paris": [
{
"experience": 20
}
]
}
},
"James": {
"UK": {
"London": [
{
"experience": 10.9
}
]
}
},
"Henry": {
"UK": {
"London": [
{
"experience": 15
}
]
}
},
"Joe": {
"US": {
"Boston": [
{
"experience": 100
}
]
}
}
}
}
My input is a list of dictionaries of this format:
c = [{
"country": "US",
"city": "Boston",
"name": "Joe",
"experience": 100
},
{
"country": "FR",
"city": "Paris",
"name": "Jaque",
"experience": 20
},
{
"country": "FR",
"city": "Lyon",
"name": "Jaque",
"experience": 11.4
},
{
"country": "ES",
"city": "Madrid",
"name": "Jaque",
"experience": 9
},
{
"country": "UK",
"city": "London",
"name": "Henry",
"experience": 15
},
{
"country": "UK",
"city": "London",
"name": "James",
"experience": 10.9
}
]
My first approach was to create the nested dict, step by step:
dd = dict.fromkeys([i.get("name") for i in c],defaultdict(dict))
#will create
# dd = {'Joe': defaultdict(<class 'dict'>, {}), 'Jaque': defaultdict(<class 'dict'>, {}), 'James': defaultdict(<class 'dict'>, {}), 'Henry': defaultdict(<class 'dict'>, {})}
for i in dd:
for j in c:
#verify if name from d is in dict j
if i in j.values():
dd[i]=dict(zip([a.get("country") for a in c if i in a.values() ],[b.get("city") for b in c if i in b.values() ]))
# dd will become
#{'Joe': {'US': 'Boston'}, 'Jaque': {'FR': 'Lyon', 'ES': 'Madrid'}, 'Henry': {'UK': 'London'}, 'James': {'UK': 'London'}}
Now I can't figure a way to create/update the nested structure of dict dd. Is there a more dynamic way to create dict? Thx
You could use itertools.groupby to organize the list similarly to your expected output and then loop to convert to a dict.
from itertools import groupby
from operator import itemgetter
data = [{"country": "US", "city": "Boston", "name": "Joe", "experience": 100 }, {"country": "FR", "city": "Paris", "name": "Jaque", "experience": 20 }, {"country": "FR", "city": "Lyon", "name": "Jaque", "experience": 11.4 }, {"country": "ES", "city": "Madrid", "name": "Jaque", "experience": 9 }, {"country": "UK", "city": "London", "name": "Henry", "experience": 15 }, {"country": "UK", "city": "London", "name": "James", "experience": 10.9 } ]
result = {}
for key, values in groupby(sorted(data, key=itemgetter('name')), key=itemgetter('name')):
result[key] = {
v['country']: {v['city']: [{'experience': v['experience']}]} for v in values
}
print(result)
# {'Henry': {'UK': {'London': [{'experience': 15}]}}, 'James': {'UK': {'London': [{'experience': 10.9}]}}, 'Jaque': {'FR': {'Lyon': [{'experience': 11.4}]}, 'ES': {'Madrid': [{'experience': 9}]}}, 'Joe': {'US': {'Boston': [{'experience': 100}]}}}
You can use recursion with itertools.groupby:
from itertools import groupby
def group(d, keys = None):
key, *keys = keys
new_d = {a:list(b) for a, b in groupby(sorted(d, key=lambda x:x[key]), key=lambda x:x[key])}
t = {a:[{c:d for c, d in k.items() if c != key} for k in b] for a, b in new_d.items()}
return {a:group(b, keys) if not all(len(i) == 1 for i in b) else b for a, b in t.items()}
result = group(data, keys = ['name', 'country', 'city', 'experience'])
import json
print(json.dumps(result, indent=4)))
Output:
{
"Henry": {
"UK": {
"London": [
{
"experience": 15
}
]
}
},
"James": {
"UK": {
"London": [
{
"experience": 10.9
}
]
}
},
"Jaque": {
"ES": {
"Madrid": [
{
"experience": 9
}
]
},
"FR": {
"Lyon": [
{
"experience": 11.4
}
],
"Paris": [
{
"experience": 20
}
]
}
},
"Joe": {
"US": {
"Boston": [
{
"experience": 100
}
]
}
}
}
I have exhaustively reviewed/attempted implementations all the other questions on SO corresponding to this challenge and have yet to reach a solution.
Question: how do I convert employee and supervisor pairs into a hierarchical JSON structure to be used for a D3 visualization? There are an unknown number of levels, so it has to be dynamic.
I have a dataframe with five columns (yes, I realize this isn't the actual hierarchy of The Office):
Employee_FN Employee_LN Supervisor_FN Supervisor_LN Level
0 Michael Scott None None 0
1 Jim Halpert Michael Scott 1
2 Dwight Schrute Michael Scott 1
3 Stanley Hudson Jim Halpert 2
4 Pam Beasley Jim Halpert 2
5 Ryan Howard Pam Beasley 3
6 Kelly Kapoor Ryan Howard 4
7 Meredith Palmer Ryan Howard 4
Desired Output Snapshot:
{
"Employee_FN": "Michael",
"Employee_LN": "Scott",
"Level": "0",
"Reports": [{
"Employee_FN": "Jim",
"Employee_LN": "Halpert",
"Level": "1",
"Reports": [{
"Employee_FN": "Stanley",
"Employee_LN": "Hudson",
"Level": "2",
}, {
"Employee_FN": "Pam",
"Employee_LN": "Beasley",
"Level": "2",
}]
}]
}
Current State:
j = (df.groupby(['Level','Employee_FN','Employee_LN'], as_index=False)
.apply(lambda x: x[['Level','Employee_FN','Employee_LN']].to_dict('r'))
.reset_index()
.rename(columns={0:'Reports'})
.to_json(orient='records'))
print(json.dumps(json.loads(j), indent=2, sort_keys=True))
Current Output:
[
{
"Employee_FN": "Michael",
"Employee_LN": "Scott",
"Level": 0,
"Reports": [
{
"Employee_FN": "Michael",
"Employee_LN": "Scott",
"Level": 0
}
]
},
{
"Employee_FN": "Dwight",
"Employee_LN": "Schrute",
"Level": 1,
"Reports": [
{
"Employee_FN": "Dwight",
"Employee_LN": "Schrute",
"Level": 1
}
]
},
{
"Employee_FN": "Jim",
"Employee_LN": "Halpert",
"Level": 1,
"Reports": [
{
"Employee_FN": "Jim",
"Employee_LN": "Halpert",
"Level": 1
}
]
},
{
"Employee_FN": "Pam",
"Employee_LN": "Beasley",
"Level": 2,
"Reports": [
{
"Employee_FN": "Pam",
"Employee_LN": "Beasley",
"Level": 2
}
]
},
{
"Employee_FN": "Stanley",
"Employee_LN": "Hudson",
"Level": 2,
"Reports": [
{
"Employee_FN": "Stanley",
"Employee_LN": "Hudson",
"Level": 2
}
]
},
{
"Employee_FN": "Ryan",
"Employee_LN": "Howard",
"Level": 3,
"Reports": [
{
"Employee_FN": "Ryan",
"Employee_LN": "Howard",
"Level": 3
}
]
},
{
"Employee_FN": "Kelly",
"Employee_LN": "Kapoor",
"Level": 4,
"Reports": [
{
"Employee_FN": "Kelly",
"Employee_LN": "Kapoor",
"Level": 4
}
]
},
{
"Employee_FN": "Meredith",
"Employee_LN": "Palmer",
"Level": 4,
"Reports": [
{
"Employee_FN": "Meredith",
"Employee_LN": "Palmer",
"Level": 4
}
]
}
]
Problems:
Each person only has themselves as children
The whole JSON structure appears to be in a dict - I believe it has to be enclosed by {} to be readable
I have tried switched around the groupby and lambda elements in various configurations to reach the desired output as well. Any and all insight would be greatly appreciated! Thank you!
Update:
I changed my code block to this:
j = (df.groupby(['Level','Supervisor_FN','Supervisor_LN'], as_index=False)
.apply(lambda x: x[['Level','Employee_FN','Employee_LN']].to_dict('r'))
.reset_index()
.rename(columns={0:'Reports'})
.rename(columns={'Supervisor_FN':'Employee_FN'})
.rename(columns={'Supervisor_LN':'Employee_LN'})
.to_json(orient='records'))
print(json.dumps(json.loads(j), indent=2, sort_keys=True))
The new output is this:
[
{
"Employee_FN": "Michael",
"Employee_LN": "Scott",
"Level": 1,
"Reports": [
{
"Employee_FN": "Jim",
"Employee_LN": "Halpert",
"Level": 1
},
{
"Employee_FN": "Dwight",
"Employee_LN": "Schrute",
"Level": 1
}
]
},
{
"Employee_FN": "Jim",
"Employee_LN": "Halpert",
"Level": 2,
"Reports": [
{
"Employee_FN": "Stanley",
"Employee_LN": "Hudson",
"Level": 2
},
{
"Employee_FN": "Pam",
"Employee_LN": "Beasley",
"Level": 2
}
]
},
{
"Employee_FN": "Pam",
"Employee_LN": "Beasley",
"Level": 3,
"Reports": [
{
"Employee_FN": "Ryan",
"Employee_LN": "Howard",
"Level": 3
}
]
},
{
"Employee_FN": "Ryan",
"Employee_LN": "Howard",
"Level": 4,
"Reports": [
{
"Employee_FN": "Kelly",
"Employee_LN": "Kapoor",
"Level": 4
},
{
"Employee_FN": "Meredith",
"Employee_LN": "Palmer",
"Level": 4
}
]
}
]
Problems:
The Level matches the underlying employee for both the underlying employee and the supervisor
The nesting only goes one level deep
This type of problem isn't particularly well-suited for Pandas; the data structure you're going after is recursive, not tabular.
Here is one possible solution.
from operator import itemgetter
employee_key = itemgetter('Employee_FN', 'Employee_LN')
supervisor_key = itemgetter('Supervisor_FN', 'Supervisor_LN')
def subset(dict_, keys):
return {k: dict_[k] for k in keys}
# store employee references
cache = {}
# iterate over employees sorted by level, so supervisors are cached before reports
for row in df.sort_values('Level').to_dict('records'):
# look up employee/supervisor references
employee = cache.setdefault(employee_key(row), subset(row, keys=('Employee_FN', 'Employee_LN', 'Level')))
supervisor = cache.get(supervisor_key(row), {})
# link reports to employee
supervisor.setdefault('Reports', []).append(employee)
# grab only top-level employees
[rec for key, rec in cache.iteritems() if rec['Level'] == 0]
[{'Employee_FN': 'Michael',
'Employee_LN': 'Scott',
'Level': 0,
'Reports': [{'Employee_FN': 'Jim',
'Employee_LN': 'Halpert',
'Level': 1,
'Reports': [{'Employee_FN': 'Stanley',
'Employee_LN': 'Hudson',
'Level': 2},
{'Employee_FN': 'Pam',
'Employee_LN': 'Beasley',
'Level': 2,
'Reports': [{'Employee_FN': 'Ryan',
'Employee_LN': 'Howard',
'Level': 3,
'Reports': [{'Employee_FN': 'Kelly',
'Employee_LN': 'Kapoor',
'Level': 4},
{'Employee_FN': 'Meredith',
'Employee_LN': 'Palmer',
'Level': 4}]}]}]},
{'Employee_FN': 'Dwight', 'Employee_LN': 'Schrute', 'Level': 1}]}]