python随机森林算法报错

from sklearn import metrics
from sklearn.model_selection import train_test_split, GridSearchCV
import pandas as pd

data = pd.read_excel(r'C:\Users\Administrator\Desktop\HF.xlsx')
target = data['平均日产油']
features = data.iloc[:, 0:]
X, y = features, target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=100)

param_grid = {
    'criterion': ['entropy', 'gini'],
    'max_depth': [5, 6, 7, 8],  # 深度：这里是森林中每棵决策树的深度
    'n_estimators': [11, 13, 15],  # 决策树个数-随机森林特有参数
    'max_features': [0.3, 0.4, 0.5],
    # 每棵决策树使用的变量占比-随机森林特有参数（结合原理）
    'min_samples_split': [4, 8, 12, 16]  # 叶子的最小拆分样本量
}

import sklearn.ensemble as ensemble  # ensemble learning: 集成学习

rfc = ensemble.RandomForestClassifier()
rfc_cv = GridSearchCV(estimator=rfc, param_grid=param_grid,
                      scoring='roc_auc', cv=4)
rfc_cv.fit(X_train, y_train)

# 使用随机森林对测试集进行预测
test_est = rfc_cv.predict(X_test)
print('随机森林精确度...')
print(metrics.classification_report(test_est, y_test))
print('随机森林 AUC...')
fpr_test, tpr_test, th_test = metrics.roc_curve(test_est, y_test)
# 构造 roc 曲线
print('AUC = %.4f' % metrics.auc(fpr_test, tpr_test))

报错信息：

Traceback (most recent call last):
  File "D:\PythoProject\BISHE\caogao.py", line 28, in <module>
    rfc_cv.fit(X_train, y_train)
  File "D:\envir\lib\site-packages\sklearn\model_selection\_search.py", line 874, in fit
    self._run_search(evaluate_candidates)
  File "D:\envir\lib\site-packages\sklearn\model_selection\_search.py", line 1388, in _run_search
    evaluate_candidates(ParameterGrid(self.param_grid))
  File "D:\envir\lib\site-packages\sklearn\model_selection\_search.py", line 851, in evaluate_candidates
    _warn_or_raise_about_fit_failures(out, self.error_score)
  File "D:\envir\lib\site-packages\sklearn\model_selection\_validation.py", line 367, in _warn_or_raise_about_fit_failures
    raise ValueError(all_fits_failed_message)
ValueError: 
All the 1152 fits failed.
It is very likely that your model is misconfigured.
You can try to debug the error by setting error_score='raise'.

这段代码中出现了一些问题。在从pandas读取数据之后，你需要将数据分成训练集和测试集，但是你没有使用train_test_split函数正确地分割数据。train_test_split函数需要分别将特征和目标数据集分割成训练集和测试集，因此你需要将以下代码：

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=100)

改为：

X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.1, random_state=100)

另外，由于你的目标变量'target'是连续的值，所以你应该使用随机森林回归器RandomForestRegressor而不是随机森林分类器RandomForestClassifier。因此，你需要将以下代码：

import sklearn.ensemble as ensemble
rfc = ensemble.RandomForestClassifier()

改为：

import sklearn.ensemble as ensemble
rfc = ensemble.RandomForestRegressor()

修改完毕后，你可以再次运行代码，应该就能够成功地训练和测试随机森林模型了。

点击复制后，将打开C知道体验页