AI - 机器学习GBDT算法

from sklearn.datasets import load_boston
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
 
# 加载波士顿房价数据集
data = load_boston()
X, y = data.data, data.target
 
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
# 创建GBDT回归模型
gbdt = GradientBoostingRegressor(n_estimators=100, learning_rate=0.1, max_depth=3, random_state=42)
 
# 训练模型
gbdt.fit(X_train, y_train)
 
# 预测测试集
y_pred = gbdt.predict(X_test)
 
# 计算均方误差
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

import joblib
import numpy as np
import xgboost as xgb
import pandas as pd
import numpy as np
from collections import Counter
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.model_selection import StratifiedKFold
 
def test01():
 
    
    data = pd.read_csv('wine.csv')
    x = data.iloc[:, :-1]
    y = data.iloc[:, -1] - 3
 
    
    x_train, x_valid, y_train, y_valid = train_test_split(x, y, test_size=0.2, stratify=y, random_state=22)
 
    # 存储数据
    pd.concat([x_train, y_train], axis=1).to_csv('data-train.csv')
    pd.concat([x_valid, y_valid], axis=1).to_csv('data-valid.csv')
 
# 模型训练
def test02():
 
    
    train_data = pd.read_csv('data类-train.csv')
    valid_data = pd.read_csv('data-valid.csv')
 
    # 训练集
    x_train = train_data.iloc[:, :-1]
    y_train = train_data.iloc[:, -1]
 
    # 测试集
    x_valid = valid_data.iloc[:, :-1]
    y_valid = valid_data.iloc[:, -1]
 
    
    estimator = xgb.XGBClassifier(n_estimators=100,
                                  objective='multi:softmax',
                                  eval_metric='merror',
                                  eta=0.1,
                                  use_label_encoder=False,
                                  random_state=22)
    estimator.fit(x_train, y_train)
 
    
    y_pred = estimator.predict(x_valid)
    print(classification_report(y_true=y_valid, y_pred=y_pred))
 
    # 模型保存
    joblib.dump(estimator, 'model/xgboost.pth')

from sklearn.utils import class_weight
classes_weights = class_weight.compute_sample_weight(class_weight='balanced',y=y_train)
 
estimator.fit(x_train, y_train,sample_weight = classes_weights)
y_pred = estimator.predict(x_valid)
print(classification_report(y_true=y_valid, y_pred=y_pred))
 
# 交叉验证网格搜索
train_data = pd.read_csv('data-train.csv')
valid_data = pd.read_csv('data-valid.csv')
 
 
x_train = train_data.iloc[:, :-1]
y_train = train_data.iloc[:, -1]
 
x_valid = valid_data.iloc[:, :-1]
y_valid = valid_data.iloc[:, -1]
 
spliter = StratifiedKFold(n_splits=5, shuffle=True)
param_grid = {'max_depth': np.arange(3, 5, 1),
              'n_estimators': np.arange(50, 150, 50),
              'eta': np.arange(0.1, 1, 0.3)}
estimator = xgb.XGBClassifier(n_estimators=100,
                              objective='multi:softmax',
                              eval_metric='merror',
                              eta=0.1,
                              use_label_encoder=False,
                              random_state=22)
cv = GridSearchCV(estimator,param_grid,cv=spliter)
y_pred = cv.predict(x_valid)
print(classification_report(y_true=y_valid, y_pred=y_pred))

from sklearn.metrics import classification_report
from sklearn.model_selection import StratifiedKFold
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
 
# 加载数据集
data = load_iris()
X, y = data.data, data.target
 
# 创建分层抽样的交叉验证对象
skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
 
# 初始化分类器
clf = LogisticRegression()
 
# 存储预测结果和真实标签
y_true = []
y_pred = []
 
# 进行交叉验证
for train_index, test_index in skf.split(X, y):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
 
    # 训练模型
    clf.fit(X_train, y_train)
 
    # 预测测试集
    y_pred_test = clf.predict(X_test)
 
    # 更新预测结果和真实标签
    y_true.extend(y_test)
    y_pred.extend(y_pred_test)
 
# 输出分类报告
print(classification_report(y_true, y_pred))