from sklearn.model_selection import KFold, cross_val_score
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

# 加載數(shù)據(jù)
data = load_iris()
X, y = data.data, data.target

# 設(shè)置K折交叉驗(yàn)證
kf = KFold(n_splits=5)
model = RandomForestClassifier()

# 使用交叉驗(yàn)證評(píng)分
scores = cross_val_score(model, X, y, cv=kf)
print("K-Fold Cross-Validation Scores:", scores)
print("Mean Score:", scores.mean())

from sklearn.model_selection import LeaveOneOut
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

# 加載數(shù)據(jù)
data = load_iris()
X, y = data.data, data.target

# 設(shè)置留一交叉驗(yàn)證
loo = LeaveOneOut()
model = RandomForestClassifier()

# 使用交叉驗(yàn)證評(píng)分
scores = cross_val_score(model, X, y, cv=loo)
print("Leave-One-Out Cross-Validation Scores:", scores)
print("Mean Score:", scores.mean())

import numpy as np
from sklearn.utils import resample
from sklearn.metrics import accuracy_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris

# 加載數(shù)據(jù)
data = load_iris()
X, y = data.data, data.target

# 設(shè)置引導(dǎo)驗(yàn)證
n_iterations = 100  # 100次引導(dǎo)采樣
model = RandomForestClassifier()
bootstrapped_scores = []

for _ in range(n_iterations):
    # 使用引導(dǎo)法抽樣
    X_train, y_train = resample(X, y, replace=True, n_samples=len(y))
    X_test = np.array([x for x in X if x.tolist() not in X_train.tolist()])
    y_test = np.array([y[i] for i, x in enumerate(X) if x.tolist() not in X_train.tolist()])
    
    # 訓(xùn)練模型并計(jì)算準(zhǔn)確率
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    score = accuracy_score(y_test, y_pred)
    bootstrapped_scores.append(score)

print("Bootstrap Validation Scores:", bootstrapped_scores)
print("Mean Score:", np.mean(bootstrapped_scores))

from sklearn.model_selection import GridSearchCV, cross_val_score, KFold
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

# 加載數(shù)據(jù)
data = load_iris()
X, y = data.data, data.target

# 設(shè)置參數(shù)網(wǎng)格
param_grid = {
    'n_estimators': [10, 50, 100],
    'max_depth': [3, 5, None]
}

# 設(shè)置嵌套交叉驗(yàn)證
outer_cv = KFold(n_splits=5)
inner_cv = KFold(n_splits=3)

# 設(shè)置網(wǎng)格搜索和嵌套交叉驗(yàn)證
model = RandomForestClassifier()
grid_search = GridSearchCV(estimator=model, param_grid=param_grid, cv=inner_cv)
nested_scores = cross_val_score(grid_search, X, y, cv=outer_cv)

print("Nested Cross-Validation Scores:", nested_scores)
print("Mean Score:", nested_scores.mean())

from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris

# 加載數(shù)據(jù)集
data = load_iris()
X, y = data.data, data.target

# 使用分層交叉驗(yàn)證
skf = StratifiedKFold(n_splits=5)
model = RandomForestClassifier()

# 計(jì)算交叉驗(yàn)證分?jǐn)?shù)
scores = cross_val_score(model, X, y, cv=skf)
print("Stratified Cross-Validation Scores:", scores)
print("Mean Score:", scores.mean())

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 創(chuàng)建時(shí)間序列數(shù)據(jù)
X = np.arange(1, 101).reshape(-1, 1)  # 1到100的時(shí)間序列
y = X.flatten() + np.random.normal(scale=5, size=X.shape[0])  # 添加噪聲

# 定義滾動(dòng)窗口的大小
window_size = 20  # 每次訓(xùn)練的窗口大小

# 初始化模型
model = LinearRegression()

# 存儲(chǔ)預(yù)測(cè)結(jié)果和誤差
predictions = []
errors = []

# 滾動(dòng)窗口法進(jìn)行預(yù)測(cè)
for i in range(len(X) - window_size - 1):
    # 定義訓(xùn)練集和測(cè)試集
    X_train = X[i : i + window_size]
    y_train = y[i : i + window_size]
    X_test = X[i + window_size : i + window_size + 1]
    y_test = y[i + window_size : i + window_size + 1]
    
    # 訓(xùn)練模型
    model.fit(X_train, y_train)
    
    # 進(jìn)行預(yù)測(cè)
    y_pred = model.predict(X_test)
    
    # 記錄預(yù)測(cè)和誤差
    predictions.append(y_pred[0])
    mse = mean_squared_error(y_test, y_pred)
    errors.append(mse)
    print(f"Window {i+1}: Predicted = {y_pred[0]:.2f}, Actual = {y_test[0]:.2f}, MSE = {mse:.2f}")

# 計(jì)算平均誤差
average_mse = np.mean(errors)
print(f"\nAverage MSE over all windows: {average_mse:.2f}")

from sklearn.model_selection import TimeSeriesSplit
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import numpy as np

# 創(chuàng)建時(shí)間序列數(shù)據(jù)
X = np.arange(1, 101).reshape(-1, 1)
y = X.flatten() + np.random.normal(scale=5, size=X.shape[0])

# 使用TimeSeriesSplit實(shí)現(xiàn)滾動(dòng)預(yù)測(cè)法
tscv = TimeSeriesSplit(n_splits=5)
model = LinearRegression()

for train_index, test_index in tscv.split(X):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]

    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
print("Test MSE:", mean_squared_error(y_test, y_pred)