我使用了 决策树分类器，我想将我的 输入 作为 字符串 输入，而不是提供 整数 值，但它给我返回了这样的 错误：

Traceback (most recent call last):  File "D:/backup code for odoo project/New folder/New folder/main.py", line 38, in <module>    theme_res = lebel_encoder.transform(theme_input)  File "C:\Users\Dell\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\preprocessing\_label.py", line 277, in transform    _, y = _encode(y, uniques=self.classes_, encode=True)  File "C:\Users\Dell\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\preprocessing\_label.py", line 121, in _encode    return _encode_numpy(values, uniques, encode,  File "C:\Users\Dell\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\preprocessing\_label.py", line 50, in _encode_numpy    raise ValueError("y contains previously unseen labels: %s"ValueError: y contains previously unseen labels: ['Food', 'cafe', 'sticky'] 

代码：

import pandas as pdfrom sklearn.preprocessing import LabelEncoderfrom sklearn import treedf = pd.read_csv("new_data.csv", encoding='latin1')inputs = df.drop('selected_theme', axis='columns')target = df['selected_theme']lebel_encoder = LabelEncoder()inputs['main_cat_n'] = lebel_encoder.fit_transform(inputs['main_cat'])inputs['sub_cat_n'] = lebel_encoder.fit_transform(inputs['sub_cat'])inputs['nav_bar_n'] = lebel_encoder.fit_transform(inputs['nav_bar'])inputs_n = inputs.drop(['main_cat', 'sub_cat', 'nav_bar'], axis='columns') model = tree.DecisionTreeClassifier() model.fit(inputs_n, target) print(model.score(inputs_n, target)) theme_input = ['Food', 'cafe', 'sticky'] theme_res = lebel_encoder.transform(theme_input) result_theme = model.predict(theme_res) print(result_theme)

回答：

错误发生在分类器 之前，具体在这一行：

 theme_res = lebel_encoder.transform(theme_input)

错误消息告诉你，你的 label_encoder 从未见过像 “Food”、”cafe”、”sticky” 这样的类别。这是因为你重写了你的 LabelEncoders。你应该为不同的特征使用单独的 LabelEncoders，例如：

categorical_features = ['main_cat', 'sub_cat', 'nav_bar']encoders = dict()for cat in categorical_features:    encoders[cat] = LabelEncoder()    inputs[f'{cat}_n'] = encoders[cat].fit_transform(inputs[cat])inputs_n = inputs.drop(['main_cat', 'sub_cat', 'nav_bar'], axis='columns')...