【机器学习】python机器学习使用scikit-learn对模型进行微调：RandomizedSearchCV的分布参数设置-EW帮帮网

import numpy as np
#这两个值决定了reciprocal返回的最大及最小值
reciprocal_distrib = reciprocal(52000, 200000)
samples = reciprocal_distrib.rvs(10000, random_state=42)
plt.figure(figsize=(10, 4))
plt.subplot(121)
plt.title("Reciprocal distribution (scale=1.0)")
#直方图，一种特殊的柱状图。
#将统计值的范围分段，即将整个值的范围分成一系列间隔，然后计算每个间隔中有
#多少值。
plt.hist(samples, bins=50)
plt.subplot(122)
plt.title("Log of this distribution")
# 取对数之后不会改变数据的性质和相关关系，但压缩了变量的尺度
#右图可以看出倒数分布较为均匀，可以用于不知道具体值的情况
plt.hist(np.log(samples), bins=50)
plt.show()

在这里插入图片描述
2.几何的离散分布及指数分布

from scipy.stats import geom, expon
#几何离散分布，大部分取值范围是0到8左右
geom_distrib=geom(0.5).rvs(10000, random_state=42)
#连续分布，scale=1时，大部分取值范围是0.1到7.5左右
expon_distrib=expon(scale=1).rvs(10000, random_state=42)
plt.hist(geom_distrib, bins=50)
plt.show()
plt.hist(expon_distrib, bins=50)
plt.show()

几何离散分布在这里插入图片描述
综上，最优参数取值较为确定时，使用geom或expon，不确定时使用reciprocal。

例子：
进行数据准备：

import os

HOUSING_PATH = os.path.join("datasets", "housing")
import pandas as pd

def load_housing_data(housing_path=HOUSING_PATH):
    csv_path = os.path.join(housing_path, "housing.csv")
    return pd.read_csv(csv_path)
housing=load_housing_data()
housing2=housing.copy()
import numpy as np

#预处理前去掉带文字的指定列
from sklearn.preprocessing import MinMaxScaler,StandardScaler,OneHotEncoder

from sklearn.impute import SimpleImputer
housing_num = housing2.drop("ocean_proximity", axis=1)
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
num_pipeline = Pipeline([
        ('imputer', SimpleImputer(strategy="median")),
        ('std_scaler', StandardScaler())
    ])



from sklearn.compose import ColumnTransformer
#返回所有列名
num_attribs = list(housing_num)

cat_attribs = ["ocean_proximity"]
#找出待独热编码列的最大分类数，不然在进行测试集划分处理时，
#容易造成独热向量因测试集构成不同而列数不一致的情况
categories=housing2['ocean_proximity'].unique()
full_pipeline = ColumnTransformer([
        ("num", num_pipeline, num_attribs),
        ("cat", OneHotEncoder(categories=[categories]), cat_attribs),
    ])
#抽样后的数据，去除预测目标列，并拿出对应目标列准备数据训练
housing_labels = housing2["median_house_value"]

housing_prepared = full_pipeline.fit_transform(housing2)
from sklearn.model_selection import train_test_split
train_set, test_set,train_sety, test_sety = train_test_split(housing_prepared,housing_labels, test_size=0.1, random_state=42)

进行随机搜索：

from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import randint
from scipy.stats import expon, reciprocal
from sklearn.svm import SVR
import matplotlib.pyplot as plt
import numpy as np
reciprocal_distrib = reciprocal(52000, 200000)
from scipy.stats import geom, expon
geom_distrib=geom(0.5).rvs(10, random_state=42)
print(geom_distrib)

param_distribs = {
    #对于搜索范围是list的超参数，在给定的list中等概率采样
        'kernel': ['linear', 'rbf'],
        'C': reciprocal(20, 200),
        'gamma': expon(scale=1.0),
    }

svm_reg = SVR()
rnd_search = RandomizedSearchCV(svm_reg, param_distributions=param_distribs,
                                n_iter=2, cv=2, scoring='neg_mean_squared_error',
                                verbose=2, random_state=42)
rnd_search.fit(train_set[:1000], train_sety[:1000])
#均方根误
negative_mse = rnd_search.best_score_
rmse = np.sqrt(-negative_mse)
rmse
#最优参数
rnd_search.best_params_

输出结果为：

[1 5 2 2 1 1 1 3 2 2]
Fitting 2 folds for each of 2 candidates, totalling 4 fits
[CV] END C=47.37727900728156, gamma=3.010121430917521, kernel=linear; total time=   0.0s
[CV] END C=47.37727900728156, gamma=3.010121430917521, kernel=linear; total time=   0.0s
[CV] END C=120.42620370295205, gamma=0.9084469696321253, kernel=rbf; total time=   0.0s
[CV] END C=120.42620370295205, gamma=0.9084469696321253, kernel=rbf; total time=   0.0s
#最优参数
{'C': 47.37727900728156, 'gamma': 3.010121430917521, 'kernel': 'linear'}

【机器学习】python机器学习使用scikit-learn对模型进行微调：RandomizedSearchCV的分布参数设置

网站公告

今日签到

热门文章

最新发布