可视化训练数据

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split


# 导入鸢尾花数据集
iris_dataset = load_iris()

# 切分训练数据和测试数据
X_train, X_test, y_train, y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], random_state=42)

# 将训练特征数据转成 DataFrame 结构
iris_dataframe = pd.DataFrame(X_train, columns=iris_dataset.feature_names)

# 使用 scatter_matrix 函数绘制散点图矩阵
pd.plotting.scatter_matrix(iris_dataframe, c=y_train, figsize=(15, 15), marker='o', hist_kwds={'bins': 20}, s=60, alpha=.8, cmap='plasma')

# 显示图形
plt.show()