- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者:K同学啊
代码目标:我们希望通过鸢尾花数据,训练一个决策树模型,之后应用该模型,可以根据花萼长度、花萼宽度、花瓣长度 预测 花瓣宽度
1. 导入数据
import pandas as pd
import numpy as np
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
names = ['花萼-length', '花萼-width', '花瓣-length', '花瓣-width', 'class']
dataset = pd.read_csv(url, names=names)
dataset
2. 数据划分
X = dataset.iloc[:,[0,1,2]].values
y = dataset.iloc[:,3].values
print("X list: ", dataset.columns[[0, 1, 2]].tolist())
print("y list: ", dataset.columns[3])
3. 划分训练集和测试集
from sklearn.model_selection import train_test_split
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
4. 训练模型和预测结果
from sklearn.tree import DecisionTreeRegressor
# 初始化决策树回归模型
dtr = DecisionTreeRegressor(random_state=42)
# 训练模型
dtr.fit(X_train, y_train)
# 预测测试集结果
y_pred = dtr.predict(X_test)
5. Evaluation
from sklearn import metrics
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, y_pred))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, y_pred))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))
print('R²:', metrics.r2_score(y_test, y_pred))
6. Visualization
import matplotlib.pyplot as plt
# 可视化预测结果
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, color='blue')
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], color='red', linestyle='--')
plt.xlabel('Actual Petal Width')
plt.ylabel('Predicted Petal Width')
plt.title('Decision Tree Regression: Actual vs Predicted Petal Width')
plt.show()