Python dataclass from a nested dict

If your goal is to produce JSON from and to existing, predefined dataclasses, then just write custom encoder and decoder hooks. Do not use dataclasses.asdict() here, instead record in JSON a (safe) reference to the original dataclass.

jsonpickle is not safe because it stores references to arbitrary Python objects and passes in data to their constructors. With such references I can get jsonpickle to reference internal Python data structures and create and execute functions, classes and modules at will. But that doesn’t mean you can’t handle such references unsafely. Just verify that you only import (not call) and then verify that the object is an actual dataclass type, before you use it.

The framework can be made generic enough but still limited only to JSON-serialisable types plus dataclass-based instances:

import dataclasses
import importlib
import sys

def dataclass_object_dump(ob):
    datacls = type(ob)
    if not dataclasses.is_dataclass(datacls):
        raise TypeError(f"Expected dataclass instance, got '{datacls!r}' object")
    mod = sys.modules.get(datacls.__module__)
    if mod is None or not hasattr(mod, datacls.__qualname__):
        raise ValueError(f"Can't resolve '{datacls!r}' reference")
    ref = f"{datacls.__module__}.{datacls.__qualname__}"
    fields = (f.name for f in dataclasses.fields(ob))
    return {**{f: getattr(ob, f) for f in fields}, '__dataclass__': ref}

def dataclass_object_load(d):
    ref = d.pop('__dataclass__', None)
    if ref is None:
        return d
    try:
        modname, hasdot, qualname = ref.rpartition('.')
        module = importlib.import_module(modname)
        datacls = getattr(module, qualname)
        if not dataclasses.is_dataclass(datacls) or not isinstance(datacls, type):
            raise ValueError
        return datacls(**d)
    except (ModuleNotFoundError, ValueError, AttributeError, TypeError):
        raise ValueError(f"Invalid dataclass reference {ref!r}") from None

This uses JSON-RPC-style class hints to name the dataclass, and on loading this is verified to still be a data class with the same fields. No type checking is done on the values of the fields (as that’s a whole different kettle of fish).

Use these as the default and object_hook arguments to json.dump[s]() and json.dump[s]():

>>> print(json.dumps(c, default=dataclass_object_dump, indent=4))
{
    "mylist": [
        {
            "x": 0,
            "y": 0,
            "__dataclass__": "__main__.Point"
        },
        {
            "x": 10,
            "y": 4,
            "__dataclass__": "__main__.Point"
        }
    ],
    "__dataclass__": "__main__.C"
}
>>> json.loads(json.dumps(c, default=dataclass_object_dump), object_hook=dataclass_object_load)
C(mylist=[Point(x=0, y=0), Point(x=10, y=4)])
>>> json.loads(json.dumps(c, default=dataclass_object_dump), object_hook=dataclass_object_load) == c
True

or create instances of the JSONEncoder and JSONDecoder classes with those same hooks.

Instead of using fully qualifying module and class names, you could also use a separate registry to map permissible type names; check against the registry on encoding, and again on decoding to ensure you don’t forget to register dataclasses as you develop.

You can use mashumaro for creating dataclass object from a dict according to the scheme. Mixin from this library adds convenient from_dict and to_dict methods to dataclasses:

from dataclasses import dataclass
from typing import List
from mashumaro import DataClassDictMixin

@dataclass
class Point(DataClassDictMixin):
     x: int
     y: int

@dataclass
class C(DataClassDictMixin):
     mylist: List[Point]

p = Point(10, 20)
tmp = {'x': 10, 'y': 20}
assert p.to_dict() == tmp
assert Point.from_dict(tmp) == p

c = C([Point(0, 0), Point(10, 4)])
tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}
assert c.to_dict() == tmp
assert C.from_dict(tmp) == c

I’m the author of dacite – the tool that simplifies creation of data classes from dictionaries.

This library has only one function from_dict – this is a quick example of usage:

from dataclasses import dataclass
from dacite import from_dict

@dataclass
class User:
    name: str
    age: int
    is_active: bool

data = {
    'name': 'john',
    'age': 30,
    'is_active': True,
}

user = from_dict(data_class=User, data=data)

assert user == User(name='john', age=30, is_active=True)

Moreover dacite supports following features:

• nested structures
• (basic) types checking
• optional fields (i.e. typing.Optional)
• unions
• collections
• values casting and transformation
• remapping of fields names

… and it’s well tested – 100% code coverage!

To install dacite, simply use pip (or pipenv):

$ pip install dacite

All it takes is a five-liner:

def dataclass_from_dict(klass, d):
    try:
        fieldtypes = {f.name:f.type for f in dataclasses.fields(klass)}
        return klass(**{f:dataclass_from_dict(fieldtypes[f],d[f]) for f in d})
    except:
        return d # Not a dataclass field

Sample usage:

from dataclasses import dataclass, asdict

@dataclass
class Point:
    x: float
    y: float

@dataclass
class Line:
    a: Point
    b: Point

line = Line(Point(1,2), Point(3,4))
assert line == dataclass_from_dict(Line, asdict(line))

Full code, including to/from json, here at gist: https://gist.github.com/gatopeich/1efd3e1e4269e1e98fae9983bb914f22

undictify is a library which could be of help. Here is a minimal usage example:

import json
from dataclasses import dataclass
from typing import List, NamedTuple, Optional, Any

from undictify import type_checked_constructor


@type_checked_constructor(skip=True)
@dataclass
class Heart:
    weight_in_kg: float
    pulse_at_rest: int


@type_checked_constructor(skip=True)
@dataclass
class Human:
    id: int
    name: str
    nick: Optional[str]
    heart: Heart
    friend_ids: List[int]


tobias_dict = json.loads('''
    {
        "id": 1,
        "name": "Tobias",
        "heart": {
            "weight_in_kg": 0.31,
            "pulse_at_rest": 52
        },
        "friend_ids": [2, 3, 4, 5]
    }''')

tobias = Human(**tobias_dict)

Validobj does just that. Compared to other libraries, it provides a simpler interface (just one function at the moment) and emphasizes informative error messages. For example, given a schema like

import dataclasses
from typing import Optional, List


@dataclasses.dataclass
class User:
    name: str
    phone: Optional[str] = None
    tasks: List[str] = dataclasses.field(default_factory=list)

One gets an error like

>>> import validobj
>>> validobj.parse_input({
...      'phone': '555-1337-000', 'address': 'Somewhereville', 'nme': 'Zahari'}, User
... )
Traceback (most recent call last):
...
WrongKeysError: Cannot process value into 'User' because fields do not match.
The following required keys are missing: {'name'}. The following keys are unknown: {'nme', 'address'}.
Alternatives to invalid value 'nme' include:
  - name

All valid options are:
  - name
  - phone
  - tasks

for a typo on a given field.

I would like to suggest using the Composite Pattern to solve this,
the main advantage is that you could continue adding classes to this pattern
and have them behave the same way.

from dataclasses import dataclass
from typing import List


@dataclass
class CompositeDict:
    def as_dict(self):
        retval = dict()
        for key, value in self.__dict__.items():
            if key in self.__dataclass_fields__.keys():
                if type(value) is list:
                    retval[key] = [item.as_dict() for item in value]
                else:
                    retval[key] = value
        return retval

@dataclass
class Point(CompositeDict):
    x: int
    y: int


@dataclass
class C(CompositeDict):
    mylist: List[Point]


c = C([Point(0, 0), Point(10, 4)])
tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}
assert c.as_dict() == tmp

as a side note, you could employ a factory pattern within the CompositeDict class that would handle other cases like nested dicts, tuples and such, which would save much boilerplate.

Using no additional modules, you can make use of the __post_init__ function to automatically convert the dict values to the correct type. This function is called after __init__.

from dataclasses import dataclass, asdict


@dataclass
class Bar:
    fee: str
    far: str

@dataclass
class Foo:
    bar: Bar

    def __post_init__(self):
        if isinstance(self.bar, dict):
            self.bar = Bar(**self.bar)

foo = Foo(bar=Bar(fee="La", far="So"))

d= asdict(foo)
print(d)  # {'bar': {'fee': 'La', 'far': 'So'}}
o = Foo(**d)
print(o)  # Foo(bar=Bar(fee='La', far='So'))

This solution has the added benefit of being able to use non-dataclass objects. As long as its str function can be converted back, it’s fair game. For example, it can be used to keep str fields as IP4Address internally.

from validated_dc import ValidatedDC
from dataclasses import dataclass

from typing import List, Union


@dataclass
class Foo(ValidatedDC):
    foo: int


@dataclass
class Bar(ValidatedDC):
    bar: Union[Foo, List[Foo]]


foo = {'foo': 1}
instance = Bar(bar=foo)
print(instance.get_errors())  # None
print(instance)               # Bar(bar=Foo(foo=1))

list_foo = [{'foo': 1}, {'foo': 2}]
instance = Bar(bar=list_foo)
print(instance.get_errors())  # None
print(instance)               # Bar(bar=[Foo(foo=1), Foo(foo=2)])

validated_dc:
https://github.com/EvgeniyBurdin/validated_dc

And see a more detailed example:
https://github.com/EvgeniyBurdin/validated_dc/blob/master/examples/detailed.py

Simple solution that supports lists as well (and can be extended for other generic uses)

from dataclasses import dataclass, asdict, fields, is_dataclass
from typing import List
from types import GenericAlias

def asdataclass(klass, d):
    if not is_dataclass(klass):
        return d
    values = {}
    for f in fields(klass):
        if isinstance(f.type, GenericAlias) and f.type.__origin__ == list:
            values[f.name] = [asdataclass(f.type.__args__[0], d2) for d2 in d[f.name]]
        else:
            values[f.name] = asdataclass(f.type,d[f.name])
    return klass(**values)

@dataclass
class Point:
    x: int
    y: int

@dataclass
class C:
    mylist: list[Point]
    title: str = ""

c = C([Point(0, 0), Point(10, 4)])

assert c == asdataclass(C, asdict(c))

Based on https://stackoverflow.com/a/54769644/871166

A possible solution that I haven’t seen mentioned yet is to use dataclasses-json. This library provides conversions of dataclass instances to/from JSON, but also to/from dict (like dacite and mashumaro, which were suggested in earlier answers).

dataclasses-json requires decorating the classes with @dataclass_json in addition to @dataclass. The decorated classes then get a couple of member functions for conversions to/from JSON and to/from dict:

• from_dict(...)
• from_json(...)
• to_dict(...)
• to_json(...)

Here is a slightly modified version of the original code in the question. I’ve added the required @dataclass_json decorators and asserts for the conversion from dicts to instances of Point and C:

from dataclasses import dataclass, asdict
from dataclasses_json import dataclass_json
from typing import List

@dataclass_json
@dataclass
class Point:
     x: int
     y: int

@dataclass_json
@dataclass
class C:
     mylist: List[Point]

p = Point(10, 20)

assert asdict(p) == {'x': 10, 'y': 20}
assert p == Point.from_dict({'x': 10, 'y': 20})

c = C([Point(0, 0), Point(10, 4)])

tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}

assert asdict(c) == tmp
assert c == C.from_dict(tmp)

I really think that concept presented by gatopeich in this answer is the best approach for this question.

I’ve fixed and civilized his code. This is a correct function to load dataclass back from dictionary:

def dataclass_from_dict(cls: type, src: t.Mapping[str, t.Any]) -> t.Any:
    field_types_lookup = {
        field.name: field.type
        for field in dataclasses.fields(cls)
    }

    constructor_inputs = {}
    for field_name, value in src.items():
        try:
            constructor_inputs[field_name] = dataclass_from_dict(field_types_lookup[field_name], value)
        except TypeError as e:
            # type error from fields() call in recursive call
            # indicates that field is not a dataclass, this is how we are
            # breaking the recursion. If not a dataclass - no need for loading
            constructor_inputs[field_name] = value
        except KeyError:
            # similar, field not defined on dataclass, pass as plain field value
            constructor_inputs[field_name] = value

return cls(**constructor_inputs)

Then you can test with following:

@dataclass
class Point:
    x: float
    y: float


@dataclass
class Line:
    a: Point
    b: Point

p1, p2 = Point(1,1), Point(2,2)
line = Line(p1, p1)

assert line == dataclass_from_dict(Line, asdict(line))

I know there’s probably tons of JSON serialization libraries out there by now actually, and to be honest I might have stumbled upon this article a bit late. However, a newer (and well-tested) option also available is the dataclass-wizard library. This has recently (as of two weeks ago in any case) moved to the Production/Stable status as of the v0.18.0 release.

It has pretty solid support for typing generics from the typing module, as well as other niche use cases such as dataclasses in Union types and patterned dates and times. Other nice-to-have features that I have personally found quite useful, such as auto key casing transforms (i.e. camel to snake) and implicit type casts (i.e. string to annotated int) are implemented as well.

Ideal usage is with the JSONWizard Mixin class, which provides useful class methods such as:

• from_json
• from_dict / from_list
• to_dict
• to_json / list_to_json

Here’s a pretty self-explanatory usage that has been tested in Python 3.7+ with the included __future__ import:

from __future__ import annotations

from dataclasses import dataclass
from dataclass_wizard import JSONWizard


@dataclass
class C(JSONWizard):
    my_list: list[Point]


@dataclass
class Point(JSONWizard):
    x: int
    y: int


# Serialize Point instance
p = Point(10, 20)
tmp = {'x': 10, 'y': 20}
assert p.to_dict() == tmp
assert Point.from_dict(tmp) == p

c = C([Point(0, 0), Point(10, 4)])
# default case transform is 'camelCase', though this can be overridden
# with a custom Meta config supplied for the main dataclass.
tmp = {'myList': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}
assert c.to_dict() == tmp
assert C.from_dict(tmp) == c

NB: It’s worth noting that, technically, you only need to sub-class the main dataclass, i.e. the model being serialized; the nested dataclasses can be left alone if desired.

If a class inheritance model is not desired altogether, the other option is to use exported helper functions such as fromdict, asdict to convert dataclass instance to/from Python dict objects as needed.

from dataclasses import dataclass, is_dataclass

@dataclass
class test2:
    a: str = 'name'
    b: int = 222

@dataclass
class test:
    a: str = 'name'
    b: int = 222
    t: test2 = None

a = test(a = 2222222222, t=test2(a="ssss"))
print(a)

def dataclass_from_dict(schema: any, data: dict):
    data_updated = {
        key: (
            data[key]
            if not is_dataclass(schema.__annotations__[key])
            else dataclass_from_dict(schema.__annotations__[key], data[key])
        )
        for key in data.keys()
    }
    return schema(**data_updated)

print(dataclass_from_dict(test, {'a': 1111111, 't': {'a': 'nazwa'} }))

A possible alternative might be a lightweight chili library:

from dataclasses import dataclass, asdict
from typing import List

from chili import init_dataclass

@dataclass
class Point:
     x: int
     y: int

@dataclass
class C:
     mylist: List[Point]

p = Point(10, 20)
assert asdict(p) == {'x': 10, 'y': 20}

c = C([Point(0, 0), Point(10, 4)])
tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}
assert asdict(c) == tmp

assert c == init_dataclass(tmp, C)

Chili supports almost the entire typing module, including custom Generic types.
You can read more here: https://github.com/kodemore/chili

Installation can be done through pip or poetry by simply running:

pip install chili

or

poetry add chili

It has only one dependency, which is typing extensions.