逻辑回归_训练超大规模训练集

逻辑回归_训练超大规模训练集

solver=“sag” 随机平均梯度更适合 大规模训练集

# 训练超大规模数据量分类器
from sklearn.linear_model import LogisticRegression
from sklearn import datasets
from sklearn.preprocessing import StandardScaler

iris = datasets.load_iris()
features = iris.data
target = iris.target

scaler = StandardScaler()
features_standardized = scaler.fit_transform(features)
# 使用随机平均梯度训练  solver="sag"
logistic_regression = LogisticRegression(random_state=0, solver="sag") # stochastic average gradient (SAG) solver
model = logistic_regression.fit(features_standardized, target)