如何从 LabelEncoder 获取真实标签

Question

我有以下代码 sn-p:

df = pd.read_csv("data.csv")

X = df.drop(['label'], axis=1)
Y= df['label']

le = LabelEncoder()
Y = le.fit_transform(Y)
mapping = dict(zip(le.classes_, range(len(le.classes_))))

x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=7,stratify=Y)

##xgb model
model = XGBClassifier()
model.fit(x_train, y_train)

#predict
y_pred = model.predict(x_train)

这里y_pred 给出了编码标签。编码前如何获取真实标签？

Answer 1

使用原始标签和编码标签创建一个字典，使用该字典将 y_pred 映射到真实标签

Answer 2

你可以使用

le.inverse_transform(y_pred)

其中le 是拟合的LabelEncoder

le = LabelEncoder().fit(y)

请参阅documentation。

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from xgboost import XGBClassifier

x = np.random.normal(0, 1, (20, 2))
y = np.array(['a', 'b'] * 10)
print(y)
# ['a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b' 'a' 'b']

le = LabelEncoder().fit(y)
y_enc = le.transform(y)
print(y_enc)
# [0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1]

x_train, x_test, y_train, y_test = train_test_split(x, y_enc, test_size=0.33, random_state=7, stratify=y_enc)

model = XGBClassifier()
model.fit(x_train, y_train)

y_pred_enc = model.predict(x_train)
print(y_pred_enc)
# [1 0 0 0 0 0 0 0 1 1 1 0 1]

y_pred = le.inverse_transform(y_pred_enc)
print(y_pred)
# ['b' 'a' 'a' 'a' 'a' 'a' 'a' 'a' 'b' 'b' 'b' 'a' 'b']