Convert Pandas Dataframe to nested JSON
Question:
I am trying to convert a Pandas Dataframe to a nested JSON. The function .to_json() doesn’t give me enough flexibility for my aim.
Here are some data points of the dataframe (in csv, comma separated):
,ID,Location,Country,Latitude,Longitude,timestamp,tide
0,1,BREST,FRA,48.383,-4.495,1807-01-01,6905.0
1,1,BREST,FRA,48.383,-4.495,1807-02-01,6931.0
2,1,BREST,FRA,48.383,-4.495,1807-03-01,6896.0
3,1,BREST,FRA,48.383,-4.495,1807-04-01,6953.0
4,1,BREST,FRA,48.383,-4.495,1807-05-01,7043.0
2508,7,CUXHAVEN 2,DEU,53.867,8.717,1843-01-01,7093.0
2509,7,CUXHAVEN 2,DEU,53.867,8.717,1843-02-01,6688.0
2510,7,CUXHAVEN 2,DEU,53.867,8.717,1843-03-01,6493.0
2511,7,CUXHAVEN 2,DEU,53.867,8.717,1843-04-01,6723.0
2512,7,CUXHAVEN 2,DEU,53.867,8.717,1843-05-01,6533.0
4525,9,MAASSLUIS,NLD,51.918,4.25,1848-02-01,6880.0
4526,9,MAASSLUIS,NLD,51.918,4.25,1848-03-01,6700.0
4527,9,MAASSLUIS,NLD,51.918,4.25,1848-04-01,6775.0
4528,9,MAASSLUIS,NLD,51.918,4.25,1848-05-01,6580.0
4529,9,MAASSLUIS,NLD,51.918,4.25,1848-06-01,6685.0
6540,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-07-01,6957.0
6541,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-08-01,6944.0
6542,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-09-01,7084.0
6543,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-10-01,6898.0
6544,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-11-01,6859.0
8538,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-07-01,6909.0
8539,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-08-01,6940.0
8540,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-09-01,6961.0
8541,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-10-01,6952.0
8542,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-11-01,6952.0
There is a lot of repetitive information and I would like to have a JSON like this:
[
{
"ID": 1,
"Location": "BREST",
"Latitude": 48.383,
"Longitude": -4.495,
"Country": "FRA",
"Tide-Data": {
"1807-02-01": 6931,
"1807-03-01": 6896,
"1807-04-01": 6953,
"1807-05-01": 7043
}
},
{
"ID": 5,
"Location": "HOLYHEAD",
"Latitude": 53.31399999999999,
"Longitude": -4.62,
"Country": "GBR",
"Tide-Data": {
"1807-02-01": 6931,
"1807-03-01": 6896,
"1807-04-01": 6953,
"1807-05-01": 7043
}
}
]
How could I achieve this?
Code to reproduce the dataframe:
# input json
json_str = '[{"ID":1,"Location":"BREST","Country":"FRA","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-01-01","tide":6905},{"ID":1,"Location":"BREST","Country":"FRA","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-02-01","tide":6931},{"ID":1,"Location":"BREST","Country":"DEU","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-03-01","tide":6896},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-01-01","tide":7093},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-02-01","tide":6688},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-03-01","tide":6493}]'
# load json object
data_list = json.loads(json_str)
# create dataframe
df = pd.json_normalize(data_list, None, None)
Answers:
UPDATE:
j = (df.groupby(['ID','Location','Country','Latitude','Longitude'])
.apply(lambda x: x[['timestamp','tide']].to_dict('records'))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json(orient='records'))
Result (formatted):
In [103]: print(json.dumps(json.loads(j), indent=2, sort_keys=True))
[
{
"Country": "FRA",
"ID": 1,
"Latitude": 48.383,
"Location": "BREST",
"Longitude": -4.495,
"Tide-Data": [
{
"tide": 6905.0,
"timestamp": "1807-01-01"
},
{
"tide": 6931.0,
"timestamp": "1807-02-01"
},
{
"tide": 6896.0,
"timestamp": "1807-03-01"
},
{
"tide": 6953.0,
"timestamp": "1807-04-01"
},
{
"tide": 7043.0,
"timestamp": "1807-05-01"
}
]
},
{
"Country": "DEU",
"ID": 7,
"Latitude": 53.867,
"Location": "CUXHAVEN 2",
"Longitude": 8.717,
"Tide-Data": [
{
"tide": 7093.0,
"timestamp": "1843-01-01"
},
{
"tide": 6688.0,
"timestamp": "1843-02-01"
},
{
"tide": 6493.0,
"timestamp": "1843-03-01"
},
{
"tide": 6723.0,
"timestamp": "1843-04-01"
},
{
"tide": 6533.0,
"timestamp": "1843-05-01"
}
]
},
{
"Country": "DEU",
"ID": 8,
"Latitude": 53.899,
"Location": "WISMAR 2",
"Longitude": 11.458,
"Tide-Data": [
{
"tide": 6957.0,
"timestamp": "1848-07-01"
},
{
"tide": 6944.0,
"timestamp": "1848-08-01"
},
{
"tide": 7084.0,
"timestamp": "1848-09-01"
},
{
"tide": 6898.0,
"timestamp": "1848-10-01"
},
{
"tide": 6859.0,
"timestamp": "1848-11-01"
}
]
},
{
"Country": "NLD",
"ID": 9,
"Latitude": 51.918,
"Location": "MAASSLUIS",
"Longitude": 4.25,
"Tide-Data": [
{
"tide": 6880.0,
"timestamp": "1848-02-01"
},
{
"tide": 6700.0,
"timestamp": "1848-03-01"
},
{
"tide": 6775.0,
"timestamp": "1848-04-01"
},
{
"tide": 6580.0,
"timestamp": "1848-05-01"
},
{
"tide": 6685.0,
"timestamp": "1848-06-01"
}
]
},
{
"Country": "USA",
"ID": 10,
"Latitude": 37.807,
"Location": "SAN FRANCISCO",
"Longitude": -122.465,
"Tide-Data": [
{
"tide": 6909.0,
"timestamp": "1854-07-01"
},
{
"tide": 6940.0,
"timestamp": "1854-08-01"
},
{
"tide": 6961.0,
"timestamp": "1854-09-01"
},
{
"tide": 6952.0,
"timestamp": "1854-10-01"
},
{
"tide": 6952.0,
"timestamp": "1854-11-01"
}
]
}
]
OLD answer:
You can do it using groupby(), apply() and to_json() methods:
j = (df.groupby(['ID','Location','Country','Latitude','Longitude'], as_index=False)
.apply(lambda x: dict(zip(x.timestamp,x.tide)))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json(orient='records'))
Output:
In [112]: print(json.dumps(json.loads(j), indent=2, sort_keys=True))
[
{
"Country": "FRA",
"ID": 1,
"Latitude": 48.383,
"Location": "BREST",
"Longitude": -4.495,
"Tide-Data": {
"1807-01-01": 6905.0,
"1807-02-01": 6931.0,
"1807-03-01": 6896.0,
"1807-04-01": 6953.0,
"1807-05-01": 7043.0
}
},
{
"Country": "DEU",
"ID": 7,
"Latitude": 53.867,
"Location": "CUXHAVEN 2",
"Longitude": 8.717,
"Tide-Data": {
"1843-01-01": 7093.0,
"1843-02-01": 6688.0,
"1843-03-01": 6493.0,
"1843-04-01": 6723.0,
"1843-05-01": 6533.0
}
},
{
"Country": "DEU",
"ID": 8,
"Latitude": 53.899,
"Location": "WISMAR 2",
"Longitude": 11.458,
"Tide-Data": {
"1848-07-01": 6957.0,
"1848-08-01": 6944.0,
"1848-09-01": 7084.0,
"1848-10-01": 6898.0,
"1848-11-01": 6859.0
}
},
{
"Country": "NLD",
"ID": 9,
"Latitude": 51.918,
"Location": "MAASSLUIS",
"Longitude": 4.25,
"Tide-Data": {
"1848-02-01": 6880.0,
"1848-03-01": 6700.0,
"1848-04-01": 6775.0,
"1848-05-01": 6580.0,
"1848-06-01": 6685.0
}
},
{
"Country": "USA",
"ID": 10,
"Latitude": 37.807,
"Location": "SAN FRANCISCO",
"Longitude": -122.465,
"Tide-Data": {
"1854-07-01": 6909.0,
"1854-08-01": 6940.0,
"1854-09-01": 6961.0,
"1854-10-01": 6952.0,
"1854-11-01": 6952.0
}
}
]
PS if you don’t care of idents you can write directly to JSON file:
(df.groupby(['ID','Location','Country','Latitude','Longitude'], as_index=False)
.apply(lambda x: dict(zip(x.timestamp,x.tide)))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json('/path/to/file_name.json', orient='records'))
groupby.apply forces data manipulations on each group to create the nested structure which is really slow. A simple for-loop approach using itertuples and a list comprehension to create the nested structure and serializing it via json.dumps is much faster. If the groups are small-ish, then this approach is especially useful because groupby.apply is really slow for those.1
import json
keys = ['ID', 'Location', 'Country', 'Latitude', 'Longitude']
mydict = {}
for row in df.itertuples(index=False):
mydict.setdefault(row[:5], {})[row.timestamp] = row.tide
mylist = [{**dict(zip(keys, k)), 'Tide-Data': v} for k, v in mydict.items()]
j = json.dumps(mylist)
Note that groupby.apply approach of MaxU should be changed slightly (the lambda passed to apply should be a bit different) to produce the expected output:
j = df.groupby(keys).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
Both produce the following output for the given input:
[
{
"ID": 1,
"Location": "BREST",
"Country": "FRA",
"Latitude": 48.383,
"Longitude": -4.495,
"Tide-Data": {
"1807-01-01": 6905.0,
"1807-02-01": 6931.0,
"1807-03-01": 6896.0,
"1807-04-01": 6953.0,
"1807-05-01": 7043.0
}
},
{
"ID": 7,
"Location": "CUXHAVEN 2",
"Country": "DEU",
"Latitude": 53.867,
"Longitude": 8.717,
"Tide-Data": {
"1843-01-01": 7093.0,
"1843-02-01": 6688.0,
"1843-03-01": 6493.0,
"1843-04-01": 6723.0,
"1843-05-01": 6533.0
}
},
{
"ID": 9,
"Location": "MAASSLUIS",
"Country": "NLD",
"Latitude": 51.918,
"Longitude": 4.25,
"Tide-Data": {
"1848-02-01": 6880.0,
"1848-03-01": 6700.0,
"1848-04-01": 6775.0,
"1848-05-01": 6580.0,
"1848-06-01": 6685.0
}
},
{
"ID": 8,
"Location": "WISMAR 2",
"Country": "DEU",
"Latitude": 53.899,
"Longitude": 11.458,
"Tide-Data": {
"1848-07-01": 6957.0,
"1848-08-01": 6944.0,
"1848-09-01": 7084.0,
"1848-10-01": 6898.0,
"1848-11-01": 6859.0
}
},
{
"ID": 10,
"Location": "SAN FRANCISCO",
"Country": "USA",
"Latitude": 37.807,
"Longitude": -122.465,
"Tide-Data": {
"1854-07-01": 6909.0,
"1854-08-01": 6940.0,
"1854-09-01": 6961.0,
"1854-10-01": 6952.0,
"1854-11-01": 6952.0
}
}
]
1 Benchmark result: On a frame with 100k rows, the loop approach is approx. 50 times faster than the groupby.apply approach if each group is relatively small.
import numpy as np
def jsonify(df, groupers):
res = {}
for row in df.itertuples(index=False):
res.setdefault(row[:5], {})[row.timestamp] = row.tide
j = json.dumps([dict(zip(groupers, k)) | {'Tide-Data': v} for k, v in res.items()])
return j
df = pd.DataFrame(np.random.default_rng().choice(10, size=(100000, 7)), columns=['ID','Location','Country','Latitude','Longitude', 'timestamp', 'tide'])
groupers = ['ID','Location','Country','Latitude','Longitude']
%timeit jsonify(df, groupers)
# 502 ms ± 17.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
%timeit df.groupby(groupers).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
# 25 s ± 1.38 s per loop (mean ± std. dev. of 7 runs, 1 loop each)
If the groups are large, then the difference is much smaller but the loop implementation is still faster than groupby.apply:
df = pd.DataFrame(np.random.default_rng().choice(3, size=(100000, 7)), columns=['ID','Location','Country','Latitude','Longitude', 'timestamp', 'tide'])
%timeit jsonify(df, groupers)
# 155 ms ± 6.45 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
%timeit df.groupby(groupers).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
# 201 ms ± 6.63 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
I am trying to convert a Pandas Dataframe to a nested JSON. The function .to_json() doesn’t give me enough flexibility for my aim.
Here are some data points of the dataframe (in csv, comma separated):
,ID,Location,Country,Latitude,Longitude,timestamp,tide
0,1,BREST,FRA,48.383,-4.495,1807-01-01,6905.0
1,1,BREST,FRA,48.383,-4.495,1807-02-01,6931.0
2,1,BREST,FRA,48.383,-4.495,1807-03-01,6896.0
3,1,BREST,FRA,48.383,-4.495,1807-04-01,6953.0
4,1,BREST,FRA,48.383,-4.495,1807-05-01,7043.0
2508,7,CUXHAVEN 2,DEU,53.867,8.717,1843-01-01,7093.0
2509,7,CUXHAVEN 2,DEU,53.867,8.717,1843-02-01,6688.0
2510,7,CUXHAVEN 2,DEU,53.867,8.717,1843-03-01,6493.0
2511,7,CUXHAVEN 2,DEU,53.867,8.717,1843-04-01,6723.0
2512,7,CUXHAVEN 2,DEU,53.867,8.717,1843-05-01,6533.0
4525,9,MAASSLUIS,NLD,51.918,4.25,1848-02-01,6880.0
4526,9,MAASSLUIS,NLD,51.918,4.25,1848-03-01,6700.0
4527,9,MAASSLUIS,NLD,51.918,4.25,1848-04-01,6775.0
4528,9,MAASSLUIS,NLD,51.918,4.25,1848-05-01,6580.0
4529,9,MAASSLUIS,NLD,51.918,4.25,1848-06-01,6685.0
6540,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-07-01,6957.0
6541,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-08-01,6944.0
6542,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-09-01,7084.0
6543,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-10-01,6898.0
6544,8,WISMAR 2,DEU,53.898999999999994,11.458,1848-11-01,6859.0
8538,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-07-01,6909.0
8539,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-08-01,6940.0
8540,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-09-01,6961.0
8541,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-10-01,6952.0
8542,10,SAN FRANCISCO,USA,37.806999999999995,-122.465,1854-11-01,6952.0
There is a lot of repetitive information and I would like to have a JSON like this:
[
{
"ID": 1,
"Location": "BREST",
"Latitude": 48.383,
"Longitude": -4.495,
"Country": "FRA",
"Tide-Data": {
"1807-02-01": 6931,
"1807-03-01": 6896,
"1807-04-01": 6953,
"1807-05-01": 7043
}
},
{
"ID": 5,
"Location": "HOLYHEAD",
"Latitude": 53.31399999999999,
"Longitude": -4.62,
"Country": "GBR",
"Tide-Data": {
"1807-02-01": 6931,
"1807-03-01": 6896,
"1807-04-01": 6953,
"1807-05-01": 7043
}
}
]
How could I achieve this?
Code to reproduce the dataframe:
# input json
json_str = '[{"ID":1,"Location":"BREST","Country":"FRA","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-01-01","tide":6905},{"ID":1,"Location":"BREST","Country":"FRA","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-02-01","tide":6931},{"ID":1,"Location":"BREST","Country":"DEU","Latitude":48.383,"Longitude":-4.495,"timestamp":"1807-03-01","tide":6896},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-01-01","tide":7093},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-02-01","tide":6688},{"ID":7,"Location":"CUXHAVEN 2","Country":"DEU","Latitude":53.867,"Longitude":-8.717,"timestamp":"1843-03-01","tide":6493}]'
# load json object
data_list = json.loads(json_str)
# create dataframe
df = pd.json_normalize(data_list, None, None)
UPDATE:
j = (df.groupby(['ID','Location','Country','Latitude','Longitude'])
.apply(lambda x: x[['timestamp','tide']].to_dict('records'))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json(orient='records'))
Result (formatted):
In [103]: print(json.dumps(json.loads(j), indent=2, sort_keys=True))
[
{
"Country": "FRA",
"ID": 1,
"Latitude": 48.383,
"Location": "BREST",
"Longitude": -4.495,
"Tide-Data": [
{
"tide": 6905.0,
"timestamp": "1807-01-01"
},
{
"tide": 6931.0,
"timestamp": "1807-02-01"
},
{
"tide": 6896.0,
"timestamp": "1807-03-01"
},
{
"tide": 6953.0,
"timestamp": "1807-04-01"
},
{
"tide": 7043.0,
"timestamp": "1807-05-01"
}
]
},
{
"Country": "DEU",
"ID": 7,
"Latitude": 53.867,
"Location": "CUXHAVEN 2",
"Longitude": 8.717,
"Tide-Data": [
{
"tide": 7093.0,
"timestamp": "1843-01-01"
},
{
"tide": 6688.0,
"timestamp": "1843-02-01"
},
{
"tide": 6493.0,
"timestamp": "1843-03-01"
},
{
"tide": 6723.0,
"timestamp": "1843-04-01"
},
{
"tide": 6533.0,
"timestamp": "1843-05-01"
}
]
},
{
"Country": "DEU",
"ID": 8,
"Latitude": 53.899,
"Location": "WISMAR 2",
"Longitude": 11.458,
"Tide-Data": [
{
"tide": 6957.0,
"timestamp": "1848-07-01"
},
{
"tide": 6944.0,
"timestamp": "1848-08-01"
},
{
"tide": 7084.0,
"timestamp": "1848-09-01"
},
{
"tide": 6898.0,
"timestamp": "1848-10-01"
},
{
"tide": 6859.0,
"timestamp": "1848-11-01"
}
]
},
{
"Country": "NLD",
"ID": 9,
"Latitude": 51.918,
"Location": "MAASSLUIS",
"Longitude": 4.25,
"Tide-Data": [
{
"tide": 6880.0,
"timestamp": "1848-02-01"
},
{
"tide": 6700.0,
"timestamp": "1848-03-01"
},
{
"tide": 6775.0,
"timestamp": "1848-04-01"
},
{
"tide": 6580.0,
"timestamp": "1848-05-01"
},
{
"tide": 6685.0,
"timestamp": "1848-06-01"
}
]
},
{
"Country": "USA",
"ID": 10,
"Latitude": 37.807,
"Location": "SAN FRANCISCO",
"Longitude": -122.465,
"Tide-Data": [
{
"tide": 6909.0,
"timestamp": "1854-07-01"
},
{
"tide": 6940.0,
"timestamp": "1854-08-01"
},
{
"tide": 6961.0,
"timestamp": "1854-09-01"
},
{
"tide": 6952.0,
"timestamp": "1854-10-01"
},
{
"tide": 6952.0,
"timestamp": "1854-11-01"
}
]
}
]
OLD answer:
You can do it using groupby(), apply() and to_json() methods:
j = (df.groupby(['ID','Location','Country','Latitude','Longitude'], as_index=False)
.apply(lambda x: dict(zip(x.timestamp,x.tide)))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json(orient='records'))
Output:
In [112]: print(json.dumps(json.loads(j), indent=2, sort_keys=True))
[
{
"Country": "FRA",
"ID": 1,
"Latitude": 48.383,
"Location": "BREST",
"Longitude": -4.495,
"Tide-Data": {
"1807-01-01": 6905.0,
"1807-02-01": 6931.0,
"1807-03-01": 6896.0,
"1807-04-01": 6953.0,
"1807-05-01": 7043.0
}
},
{
"Country": "DEU",
"ID": 7,
"Latitude": 53.867,
"Location": "CUXHAVEN 2",
"Longitude": 8.717,
"Tide-Data": {
"1843-01-01": 7093.0,
"1843-02-01": 6688.0,
"1843-03-01": 6493.0,
"1843-04-01": 6723.0,
"1843-05-01": 6533.0
}
},
{
"Country": "DEU",
"ID": 8,
"Latitude": 53.899,
"Location": "WISMAR 2",
"Longitude": 11.458,
"Tide-Data": {
"1848-07-01": 6957.0,
"1848-08-01": 6944.0,
"1848-09-01": 7084.0,
"1848-10-01": 6898.0,
"1848-11-01": 6859.0
}
},
{
"Country": "NLD",
"ID": 9,
"Latitude": 51.918,
"Location": "MAASSLUIS",
"Longitude": 4.25,
"Tide-Data": {
"1848-02-01": 6880.0,
"1848-03-01": 6700.0,
"1848-04-01": 6775.0,
"1848-05-01": 6580.0,
"1848-06-01": 6685.0
}
},
{
"Country": "USA",
"ID": 10,
"Latitude": 37.807,
"Location": "SAN FRANCISCO",
"Longitude": -122.465,
"Tide-Data": {
"1854-07-01": 6909.0,
"1854-08-01": 6940.0,
"1854-09-01": 6961.0,
"1854-10-01": 6952.0,
"1854-11-01": 6952.0
}
}
]
PS if you don’t care of idents you can write directly to JSON file:
(df.groupby(['ID','Location','Country','Latitude','Longitude'], as_index=False)
.apply(lambda x: dict(zip(x.timestamp,x.tide)))
.reset_index()
.rename(columns={0:'Tide-Data'})
.to_json('/path/to/file_name.json', orient='records'))
groupby.apply forces data manipulations on each group to create the nested structure which is really slow. A simple for-loop approach using itertuples and a list comprehension to create the nested structure and serializing it via json.dumps is much faster. If the groups are small-ish, then this approach is especially useful because groupby.apply is really slow for those.1
import json
keys = ['ID', 'Location', 'Country', 'Latitude', 'Longitude']
mydict = {}
for row in df.itertuples(index=False):
mydict.setdefault(row[:5], {})[row.timestamp] = row.tide
mylist = [{**dict(zip(keys, k)), 'Tide-Data': v} for k, v in mydict.items()]
j = json.dumps(mylist)
Note that groupby.apply approach of MaxU should be changed slightly (the lambda passed to apply should be a bit different) to produce the expected output:
j = df.groupby(keys).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
Both produce the following output for the given input:
[
{
"ID": 1,
"Location": "BREST",
"Country": "FRA",
"Latitude": 48.383,
"Longitude": -4.495,
"Tide-Data": {
"1807-01-01": 6905.0,
"1807-02-01": 6931.0,
"1807-03-01": 6896.0,
"1807-04-01": 6953.0,
"1807-05-01": 7043.0
}
},
{
"ID": 7,
"Location": "CUXHAVEN 2",
"Country": "DEU",
"Latitude": 53.867,
"Longitude": 8.717,
"Tide-Data": {
"1843-01-01": 7093.0,
"1843-02-01": 6688.0,
"1843-03-01": 6493.0,
"1843-04-01": 6723.0,
"1843-05-01": 6533.0
}
},
{
"ID": 9,
"Location": "MAASSLUIS",
"Country": "NLD",
"Latitude": 51.918,
"Longitude": 4.25,
"Tide-Data": {
"1848-02-01": 6880.0,
"1848-03-01": 6700.0,
"1848-04-01": 6775.0,
"1848-05-01": 6580.0,
"1848-06-01": 6685.0
}
},
{
"ID": 8,
"Location": "WISMAR 2",
"Country": "DEU",
"Latitude": 53.899,
"Longitude": 11.458,
"Tide-Data": {
"1848-07-01": 6957.0,
"1848-08-01": 6944.0,
"1848-09-01": 7084.0,
"1848-10-01": 6898.0,
"1848-11-01": 6859.0
}
},
{
"ID": 10,
"Location": "SAN FRANCISCO",
"Country": "USA",
"Latitude": 37.807,
"Longitude": -122.465,
"Tide-Data": {
"1854-07-01": 6909.0,
"1854-08-01": 6940.0,
"1854-09-01": 6961.0,
"1854-10-01": 6952.0,
"1854-11-01": 6952.0
}
}
]
1 Benchmark result: On a frame with 100k rows, the loop approach is approx. 50 times faster than the groupby.apply approach if each group is relatively small.
import numpy as np
def jsonify(df, groupers):
res = {}
for row in df.itertuples(index=False):
res.setdefault(row[:5], {})[row.timestamp] = row.tide
j = json.dumps([dict(zip(groupers, k)) | {'Tide-Data': v} for k, v in res.items()])
return j
df = pd.DataFrame(np.random.default_rng().choice(10, size=(100000, 7)), columns=['ID','Location','Country','Latitude','Longitude', 'timestamp', 'tide'])
groupers = ['ID','Location','Country','Latitude','Longitude']
%timeit jsonify(df, groupers)
# 502 ms ± 17.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
%timeit df.groupby(groupers).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
# 25 s ± 1.38 s per loop (mean ± std. dev. of 7 runs, 1 loop each)
If the groups are large, then the difference is much smaller but the loop implementation is still faster than groupby.apply:
df = pd.DataFrame(np.random.default_rng().choice(3, size=(100000, 7)), columns=['ID','Location','Country','Latitude','Longitude', 'timestamp', 'tide'])
%timeit jsonify(df, groupers)
# 155 ms ± 6.45 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
%timeit df.groupby(groupers).apply(lambda x: x.set_index('timestamp')['tide'].to_dict()).reset_index(name='Tide-Data').to_json(orient='records')
# 201 ms ± 6.63 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)