sebastianschramm

import torch
from litserve import LitAPI, LitServer
from pydantic import BaseModel, conint
from pydantic_settings import BaseSettings
from transformers import AutoModelForSequenceClassification, AutoTokenizer


class ToxicitySettings(BaseSettings):
    model_id: str = "s-nlp/roberta_toxicity_classifier"
    port: conint(ge=1024, le=65535) = 8000  # type: ignore

sebastianschramm

sebastianschramm

sebastianschramm

sebastianschramm

from typing import Union


def is_valid_type(object):
    return isinstance(object, Union[str, None])


def is_valid_type_new(object):
    return isinstance(object, str | None)

sebastianschramm

import pandas as pd
from pandas.testing import assert_frame_equal

df_one = pd.DataFrame(
    {"city": ["Tokyo", "Delhi"], "population": [13_515_271, 16_753_235]}
)
df_two = df_one[["population", "city"]].copy(deep=True)


assert_frame_equal(left=df_one, right=df_two)

sebastianschramm

names = ['a', 'b', 'c']
values = [10, 54, 2]
values_too_long = values + [10]

"""
>>> {k: v for k, v in zip(names, values_too_long, strict=True)}
ValueError: zip() argument 2 is longer than argument 1

>>> {k: v for k, v in zip(names, values_too_long, strict=False)}
{'a': 10, 'b': 54, 'c': 2}

sebastianschramm

import pandas as pd
from pandarallel import pandarallel
from sklearn.datasets import fetch_20newsgroups


def preprocess_text(row: pd.Series) -> float:
    return [word.lower() for word in row.text.split()]


def get_data() -> pd.DataFrame:

sebastianschramm

import json

import pytest


@pytest.fixture
def min_dict():
    return {"name": "foo"}

sebastianschramm

from pydantic import BaseSettings, Field, SecretStr


class Credentials(BaseSettings):
    password: SecretStr = Field(..., env="DB_PASSWORD")


"""
>>> Credentials()
pydantic.error_wrappers.ValidationError: 1 validation error for Credentials