Pydantic — 强大的数据校验工具，比DRF的校验器还快12倍

# Pydantic 数据校验功能
from datetime import datetime
from typing import List, Optional
from pydantic import BaseModel


class User(BaseModel):
    id: int
    name = 'John Doe'
    signup_ts: Optional[datetime] = None
    friends: List[int] = []


external_data = {
    'id': '123',
    'signup_ts': '2019-06-01 12:22',
    'friends': [1, 2, '3'],
}
user = User(**external_data)
print(user.id)
print(type(user.id))
#> 123
#> <class 'int'>
print(repr(user.signup_ts))
#> datetime.datetime(2019, 6, 1, 12, 22)
print(user.friends)
#> [1, 2, 3]
print(user.dict())
"""
{
    'id': 123,
    'signup_ts': datetime.datetime(2019, 6, 1, 12, 22),
    'friends': [1, 2, 3],
    'name': 'John Doe',
}
"""

print(user.schema_json(indent=2))
"""
{
  "title": "User",
  "type": "object",
  "properties": {
    "id": {
      "title": "Id",
      "type": "integer"
    },
    "signup_ts": {
      "title": "Signup Ts",
      "type": "string",
      "format": "date-time"
    },
    "friends": {
      "title": "Friends",
      "default": [],
      "type": "array",
      "items": {
        "type": "integer"
      }
    },
    "name": {
      "title": "Name",
      "default": "John Doe",
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}
"""

from typing import List
from sqlalchemy import Column, Integer, String
from sqlalchemy.dialects.postgresql import ARRAY
from sqlalchemy.ext.declarative import declarative_base
from pydantic import BaseModel, constr

Base = declarative_base()


class CompanyOrm(Base):
    __tablename__ = 'companies'
    id = Column(Integer, primary_key=True, nullable=False)
    public_key = Column(String(20), index=True, nullable=False, unique=True)
    name = Column(String(63), unique=True)
    domains = Column(ARRAY(String(255)))


class CompanyModel(BaseModel):
    id: int
    public_key: constr(max_length=20)
    name: constr(max_length=63)
    domains: List[constr(max_length=255)]

    class Config:
        orm_mode = True


co_orm = CompanyOrm(
    id=123,
    public_key='foobar',
    name='Testing',
    domains=['example.com', 'foobar.com'],
)
print(co_orm)
#> <models_orm_mode.CompanyOrm object at 0x7f0bdac44850>
co_model = CompanyModel.from_orm(co_orm)
print(co_model)
#> id=123 public_key='foobar' name='Testing' domains=['example.com',
#> 'foobar.com']

from sklearn.metrics import confusion_matrix
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# 1.导入数据集
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [1, 2, 3]].values
Y = dataset.iloc[:, 4].values

# 性别转化为数字
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

# 2.将数据集分成训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.25, random_state=0)

# 3.特征缩放
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# 4.训练
classifier = LogisticRegression()
classifier.fit(X_train, y_train)

# 5.预测
y_pred = classifier.predict(X_test)

# 6.评估预测

# 生成混淆矩阵
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
print(cm)