unionai-oss/pandera v0.10.0

0.10.0: Pyspark.pandas Support, PydanticModel datatype, Performance Improvements

on GitHub

import pyspark.pandas as ps
import pandas as pd
import pandera as pa

from pandera.typing.pyspark import DataFrame, Series


class Schema(pa.SchemaModel):
    state: Series[str]
    city: Series[str]
    price: Series[int] = pa.Field(in_range={"min_value": 5, "max_value": 20})


# create a pyspark.pandas dataframe that's validated on object initialization
df = DataFrame[Schema](
    {
        'state': ['FL','FL','FL','CA','CA','CA'],
        'city': [
            'Orlando',
            'Miami',
            'Tampa',
            'San Francisco',
            'Los Angeles',
            'San Diego',
        ],
        'price': [8, 12, 10, 16, 20, 18],
    }
)
print(df)

from pydantic import BaseModel

import pandera as pa


class Record(BaseModel):
    name: str
    xcoord: str
    ycoord: int

import pandas as pd
from pandera.engines.pandas_engine import PydanticModel


class PydanticSchema(pa.SchemaModel):
    """Pandera schema using the pydantic model."""

    class Config:
        """Config with dataframe-level data type."""

        dtype = PydanticModel(Record)
        coerce = True  # this is required, otherwise a SchemaInitError is raised