Question

使用.predict时出现未拟合错误，在拟合期间没有错误

试图将数据框转换为仍然错误的数组

输入：

rfg(n_estimators=500,random_state=42).fit(X=data_withoutnull1.iloc[:,1:8],y=data_withoutnull1['LotFrontage'])
rfg(n_estimators=500,random_state=42).predict(datawithnull1.iloc[:,1:8])

输出：

Traceback (most recent call last):

  File "<ipython-input-477-10c6d72bcc12>", line 2, in <module>
    rfg(n_estimators=500,random_state=42).predict(datawithnull1.iloc[:,1:8])

  File "/home/sinikoibra/miniconda3/envs/pv36/lib/python3.6/site-packages/sklearn/ensemble/forest.py", line 691, in predict
    check_is_fitted(self, 'estimators_')

  File "/home/sinikoibra/miniconda3/envs/pv36/lib/python3.6/site-packages/sklearn/utils/validation.py", line 914, in check_is_fitted
    raise NotFittedError(msg % {'name': type(estimator).__name__})

NotFittedError: This RandomForestRegressor instance is not fitted yet. Call 'fit' with appropriate arguments before using this method.

Answer 1

尝试这样：

# Define X and y
X=data_withoutnull1.iloc[:,1:8].values
y=data_withoutnull1['LotFrontage']

您可以使用训练测试拆分将数据分为训练集和测试集，然后将测试集传递给预测。

#pass X_train to fit -- training the model, fit(X_train)
#pass X_test to predict -- can be used for prediction, predict(X_test )

或将随机森林回归拟合到数据集

from sklearn.ensemble import RandomForestRegressor
rfg= RandomForestRegressor(n_estimators = 500, random_state = 42)
rfg.fit(X, y)

# Predicting a new result
y_pred = rfg.predict([[some value here]] or testing set or dataset to be predicted)

通过训练数据拟合模型时没有错误，但通过测试集进行预测时则为NotFittedError

1 个答案: