Human Solution

Description

"Handwritten"[^1] solutions by me, a human. In the full rankings the Human-like measure shows the similarity between these solutions and the model outputs.

[^1]: These solutions are not fully handwritten, they are adapted from solutions
originally generated by Claude 3 Opus.

Prompt

I need to take this json:

{
'first_name': 'Jane',
'last_name': 'Smith',
'date_of_birth': '03/16/1977',
orders: [
{
'created': '2024-01-25T15:00:04',
'amount': '100.00'
}
]}

And generate some dataclasses.

date_of_birth needs to be a date.
created is a datetime.
amount is a decimal.

How would I do this using the marshmallow library in python?

Here is how you can generate dataclasses from that JSON using marshmallow:

Define dataclasses for Order and Person:

from dataclasses import dataclass
import datetime
from decimal import Decimal

@dataclass
class Order:
    created: datetime.datetime
    amount: Decimal


@dataclass
class Person:
    first_name: str
    last_name: str
    date_of_birth: datetime.date
    orders: list[Order]

Define marshmallow Schema classes:

from marshmallow import Schema, fields, post_load

class OrderSchema(Schema):
    created = fields.DateTime()
    amount = fields.Decimal(as_string=True)

    @post_load
    def make_order(self, data, **kwargs):
        return Order(**data)


class PersonSchema(Schema):
    first_name = fields.Str()
    last_name = fields.Str()
    date_of_birth = fields.Date(format="%m/%d/%Y")
    orders = fields.Nested(OrderSchema, many=True)

    @post_load
    def make_person(self, data, **kwargs):
        return Person(**data)

To use it:

import json

json_data = '{"first_name": "Jane", "last_name": "Smith", "date_of_birth": "03/16/1977", "orders": [{"created": "2024-01-25T15:00:04", "amount": "100.00"}]}'

data = json.loads(json_data)

schema = PersonSchema()
result = schema.load(data)
print(result) # Person dataclass instance

The key things:

Define dataclasses for Order and Person.
Define marshmallow Schema classes for Order and Person.
Specify non-standard types like date, datetime, decimal with custom marshmallow fields
Use the PersonSchema.load method to parse JSON and create dataclass instances
Marking Scheme
  • The solution should define two dataclasses, one for the person and one for the order (2 marks).
  • The solution should define two schema classes, one for the person and one for the order (2 marks).
  • The solution should specify the date format for the date_of_birth field. (format="%m/%d/%Y") (1 mark)
  • The decimal field needs as_string=True. (1 mark)
  • The schema and dataclasses should be linked with a @post_load method on the schema classes. (2 marks)
  • Anything else: (2 marks)

anthropic/claude-3.5-sonnet says: (10.0) (0.91¢)

I'll evaluate the solution based on the provided marking scheme:

  1. The solution correctly defines two dataclasses, Order and Person. (2 marks)

  2. The solution correctly defines two schema classes, OrderSchema and PersonSchema. (2 marks)

  3. The solution specifies the correct date format for the date_of_birth field using format="%m/%d/%Y". (1 mark)

  4. The decimal field amount is correctly defined with as_string=True. (1 mark)

  5. Both schema classes are linked to their respective dataclasses using @post_load decorators. (2 marks)

  6. Additional points:

  7. The solution imports necessary modules (datetime, decimal, marshmallow).
  8. It provides an example of how to use the schema to parse JSON data.
  9. The solution handles nested objects correctly (orders within Person).
    (2 marks)

Breakdown of marks:

{
  "Dataclasses definition": 2,
  "Schema classes definition": 2,
  "Date format specification": 1,
  "Decimal field specification": 1,
  "Schema-dataclass linking": 2,
  "Additional points": 2
}

Score:

{
  "scores": [2, 2, 1, 1, 2, 2],
  "total_score": 10
}

This solution effectively addresses all the requirements specified in the problem statement and demonstrates a good understanding of both dataclasses and the marshmallow library. It correctly handles the conversion of JSON data to Python objects with appropriate data types, including the specified date, datetime, and decimal fields. The use of nested schemas for the orders list is also handled correctly. Overall, this is an excellent solution that meets all the criteria.

Sure! We need to create two dataclasses, and schema classes for each of these. We
define a post_load method in the schema classes to convert the dictionary to the
dataclass instance.

from dataclasses import dataclass
import datetime
from decimal import Decimal
from marshmallow import Schema, fields, post_load

@dataclass
class Order:
    created: datetime.datetime
    amount: Decimal


@dataclass
class Person:
    first_name: str
    last_name: str
    date_of_birth: datetime.date
    orders: list[Order]


class OrderSchema(Schema):
    created = fields.DateTime()
    amount = fields.Decimal(as_string=True)

    @post_load
    def make_order(self, data, **kwargs):
        return Order(**data)


class PersonSchema(Schema):
    first_name = fields.Str()
    last_name = fields.Str()
    date_of_birth = fields.Date(format="%m/%d/%Y")
    orders = fields.Nested(OrderSchema, many=True)

    @post_load
    def make_person(self, data, **kwargs):
        return Person(**data)


example = {
    "first_name": "Jane",
    "last_name": "Smith",
    "date_of_birth": "03/16/1977",
    "orders": [
        {
            "created": "2024-01-25T15:00:04",
            "amount": "100.00"
        }
    ]
}

schema = PersonSchema()
result = schema.load(example)
print(result) # Person dataclass instance
Marking Scheme
  • The solution should define two dataclasses, one for the person and one for the order (2 marks).
  • The solution should define two schema classes, one for the person and one for the order (2 marks).
  • The solution should specify the date format for the date_of_birth field. (format="%m/%d/%Y") (1 mark)
  • The decimal field needs as_string=True. (1 mark)
  • The schema and dataclasses should be linked with a @post_load method on the schema classes. (2 marks)
  • Anything else: (2 marks)

anthropic/claude-3.5-sonnet says: (10.0) (0.85¢)

Let's evaluate this solution based on the provided marking scheme:

  1. The solution correctly defines two dataclasses: Order and Person. (2 marks)

  2. The solution correctly defines two schema classes: OrderSchema and PersonSchema. (2 marks)

  3. The solution correctly specifies the date format for the date_of_birth field using format="%m/%d/%Y". (1 mark)

  4. The decimal field amount is correctly defined with as_string=True. (1 mark)

  5. The schema and dataclasses are linked with @post_load methods on both schema classes. (2 marks)

  6. Additional positive points:

  7. The solution imports necessary modules.
  8. It provides an example of how to use the schema to load data.
  9. The use of type hints in the dataclasses is a good practice.
    (2 marks)

Breakdown of marks:

{
  "Dataclasses definition": 2,
  "Schema classes definition": 2,
  "Date format specification": 1,
  "Decimal field definition": 1,
  "Schema and dataclasses linking": 2,
  "Additional positive points": 2
}

Score:

{
  "scores": [2, 2, 1, 1, 2, 2],
  "total_score": 10
}

The solution successfully addresses all the requirements specified in the marking scheme and includes additional helpful elements. It demonstrates a good understanding of both dataclasses and the marshmallow library in Python. The code is well-structured and includes all necessary components to handle the given JSON data effectively.

LLM Survey

Most Similar

Also by human

Model Consistency

1.00 0.79
0.79 1.00
View All

Model Evaluations

claude-3-haiku
claude-3.5-sonnet 10.0 10.0
gpt-3.5-turbo-0125
gpt-4-0125-preview
gpt-4-1106-preview
View All