0

我正在尝试调整黄砖图形的轴限制。但是，我似乎无法调整它。我可以更改轴标签和标题，但不能更改限制。如果我不渲染图形，它会起作用，visualizer.show()但我会丢失标签、标题、图例等。

from sklearn.linear_model import RidgeClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OrdinalEncoder, LabelEncoder
from yellowbrick.classifier import ROCAUC
from yellowbrick.datasets import load_game
import matplotlib.pyplot as plt

X, y = load_game()

X = OrdinalEncoder().fit_transform(X)
y = LabelEncoder().fit_transform(y)

fig, ax = plt.subplots()
ax.set_xlim([-0.05, 1.0])
ax.set_ylim([0.0, 1.05])

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

fig, ax = plt.subplots(figsize = (10,6))

model = RidgeClassifier()
visualizer = ROCAUC(model, classes=["win", "loss", "draw"], ax = ax)

visualizer.fit(X_train, y_train)       
visualizer.score(X_test, y_test)        
visualizer.show()
4

1 回答 1

1

visualizer.show()您可以尝试调用该visualizer.finalize()方法，然后访问底层 matplotlib 轴以更改限制，而不是调用该方法。你也在覆盖ax这对你没有任何好处。

这是完整的代码示例：

from sklearn.linear_model import RidgeClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OrdinalEncoder, LabelEncoder
from yellowbrick.classifier import ROCAUC
from yellowbrick.datasets import load_game
import matplotlib.pyplot as plt

X, y = load_game()

X = OrdinalEncoder().fit_transform(X)
y = LabelEncoder().fit_transform(y)

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

fig, ax = plt.subplots(figsize = (10,6))

model = RidgeClassifier()
visualizer = ROCAUC(model, classes=["win", "loss", "draw"], ax=ax)

visualizer.fit(X_train, y_train)       
visualizer.score(X_test, y_test)        
visualizer.finalize()   
ax.set_xlim([-0.05, 1.0])
ax.set_ylim([0.0, 1.05])
于 2021-07-16T04:03:17.910 回答