Pandas version checks
-
[x] I have checked that this issue has not already been reported.
-
[x] I have confirmed this bug exists on the latest version of pandas.
-
[x] I have confirmed this bug exists on the main branch of pandas.
Reproducible Example
import pandas as pd
import pytest
sample_json = [
{
"customer_id": 1,
12: 20,
13: [{"a": [1, 2,3]}, {"a": [4, 5]}],
14: [{1000: [1, 2,3]}, {1000: [4, 5]}],
"name": "Alice",
"purchases": [
{
"purchase_id": 301,
"date": "2024-06-01",
"waffles": [
{"waffle_id": "W1", "type": "Belgian", "flavor": "Vanilla", "quantity": 2},
{"waffle_id": "W2", "type": "Chocolate", "flavor": "Chocolate", "quantity": 1}
]
},
{
"purchase_id": 302,
"date": "2024-06-10",
"waffles": [
{"waffle_id": "W3", "type": "Strawberry", "flavor": "Strawberry", "quantity": 3}
]
}
]
}
]
@pytest.mark.parametrize(
"args",
[
pytest.param({}, id="no args (base case)"),
pytest.param( dict(record_path=[13]), id="int as record path"),
pytest.param( dict(record_path=[13, "a"]), id="int and str as record path"),
pytest.param( dict(record_path=[14, 1_000]), id="int + int as record path"),
pytest.param(dict(meta=[12]), id="int as meta field"),
pytest.param(dict(meta=[12, 13]), id="int + int as meta field"),
pytest.param(dict(meta=[12, "name"]), id="int + string as meta fields"),
pytest.param(dict(meta=["name", 12]), id="int + string as meta fields (2)"),
pytest.param(dict(record_path=["purchases"], meta=[12]), id="int as meta & record path"),
pytest.param(dict(record_path=["purchases"], meta=[12, 13]), id="int +int as meta & record path"),
pytest.param(dict(record_path=["purchases"], meta=[12, "name"]), id="int + string as meta fields & record path"),
pytest.param(dict(record_path=["purchases"], meta=["name", 12]), id="int + string as meta fields & record path(2)"),
pytest.param(
]
)
def test_normalize_df(args: dict, data: dict = sample_json):
""""
Load from nested object into a dataframe
"""
df = pd.json_normalize(data, **args)
Issue Description
Specifying an integer as a meta
field while specifying a record_path
results in TypeError.
meta_vals: DefaultDict = defaultdict(list)
> meta_keys = [sep.join(val) for val in _meta]
^^^^^^^^^^^^^
E TypeError: sequence item 0: expected str instance, int found
Details:
* This error only happens when the record_path
argument is provided.
* No error with ints as keys in record_path
* Yes error when a single int is passed as meta
arg, or when multiple fields are passes (and one of them is an int)
Expected Behavior
pd.json_normalize
should use integers as keys in the meta
argument.
Installed Versions
>>> import pandas as pd
>>> pd.show_versions()
INSTALLED VERSIONS
------------------
commit : 4665c10899bc413b639194f6fb8665a5c70f7db5
python : 3.12.7
python-bits : 64
OS : Darwin
OS-release : 24.6.0
Version : Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8132
machine : arm64
processor : arm
byteorder : little
LC_ALL : None
LANG : None
LOCALE : None.UTF-8
pandas : 2.3.2
numpy : 2.3.2
pytz : 2025.2
dateutil : 2.9.0.post0
pip : None
Cython : None
sphinx : None
IPython : None
adbc-driver-postgresql: None
adbc-driver-sqlite : None
bs4 : None
blosc : None
bottleneck : None
dataframe-api-compat : None
fastparquet : None
fsspec : None
html5lib : None
hypothesis : None
gcsfs : None
jinja2 : None
lxml.etree : None
matplotlib : None
numba : None
numexpr : None
odfpy : None
openpyxl : None
pandas_gbq : None
psycopg2 : None
pymysql : None
pyarrow : None
pyreadstat : None
pytest : 8.4.2
python-calamine : None
pyxlsb : None
s3fs : None
scipy : None
sqlalchemy : None
tables : None
tabulate : None
xarray : None
xlrd : None
xlsxwriter : None
zstandard : None
tzdata : 2025.2
qtpy : None
pyqt5 : None