【问题标题】:Yellowbrick prediction error graph edit lables and legendsYellowbrick 预测错误图编辑标签和图例
【发布时间】:2020-09-22 11:26:43
【问题描述】:
我想使用 Yellowbrick 可视化工具绘制预测误差,但我没有得到想要的结果。该图类似于不正确的 pp 图或 qq 图。此外,我无法更改轴的标签并添加标题,默认情况下我也无法获得任何标签和图例。
谁能告诉我我该怎么做。
这是可视化工具的代码:
def predict_error(model):
visualizer = PredictionError(model)
visualizer.fit(X_train, Y_train) # Fit the training data to the visualizer
visualizer.score(X_test, Y_test) # Evaluate the model on the test data
visualizer.show()
这是我得到的输出:
【问题讨论】:
标签:
python
machine-learning
visualization
yellowbrick
【解决方案1】:
我们最近有一个贡献者向我们的ResidualsPlot 添加了一个 QQ 绘图功能,虽然该提交尚未部署相当,但在那之前,您可以使用 these instructions 分叉和克隆 Yellowbrick,然后创建QQ图如下:
from sklearn.linear_model import Ridge
from sklearn.model_selection import train_test_split as tts
from yellowbrick.datasets import load_concrete
from yellowbrick.regressor import ResidualsPlot
# Load a regression dataset
X, y = load_concrete()
# Create the train and test data
X_train, X_test, y_train, y_test = tts(
X, y, test_size=0.2, random_state=37
)
# Instantiate the visualizer,
# setting the `hist` param to False and the `qqplot` parameter to True
visualizer = ResidualsPlot(
Ridge(),
hist=False,
qqplot=True,
train_color="gold",
test_color="maroon"
)
visualizer.fit(X_train, y_train)
visualizer.score(X_test, y_test)
visualizer.show()
结果如下: