add ensemble learning details

source/_posts/machinelearning/decisiontree.md

@@ -169,6 +169,8 @@ graph.view(output_path)  # 打开图像，path为保存路径，不需要加后
 
 [Webgraphviz](http://webgraphviz.com/)，这个网站可以将`tree.dot`文件的内容生成对应的可视化树
 
+
+#### 回归决策树与线性回归的对比
 ```python
 import numpy as np
 import matplotlib.pyplot as plt

source/_posts/machinelearning/ensemblelearning.md

@@ -0,0 +1,127 @@
+---
+title: 集成学习
+tags: ensemble-learning
+categories: machinelearning
+abbrlink: 8816
+date: 2025-01-25 15:12:08
+---
+
+### Bagging
+
+### 随机森林
+> `Random-Forest` 就是`Bagging + Decisiontree`
+```python
+import seaborn as sns
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split,GridSearchCV
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.ensemble import RandomForestClassifier
+# 1.获取数据集 - 加载 Titanic 数据集
+titanic = sns.load_dataset('titanic')
+missing_age_count = titanic['age'].isna().sum()
+# print(f"缺失的 age 数量: {missing_age_count}")
+# 2. 数据基本处理
+# 2.1 确认特征值、目标值
+X = titanic[['pclass','age','sex']]
+y = titanic['survived']
+# 2.2 缺失值处理
+X.loc[:, 'age'] = X['age'].fillna(value=X['age'].mean())  # 使用 .loc 进行修改
+# 2.3 划分数据集
+X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=22)
+# 3. 特征工程（字典特征提取）
+X_train = X_train.to_dict(orient="records")
+X_test= X_test.to_dict(orient="records")
+transfer = DictVectorizer()
+X_train = transfer.fit_transform(X_train)
+X_test = transfer.transform(X_test)
+# 4. 机器学习 随机森林
+rf = RandomForestClassifier()
+gc = GridSearchCV(estimator=rf ,param_grid={"n_estimators":[100,120,300],"max_depth":[3,7,11]},cv=3)
+gc.fit(X_train,y_train)
+y_pred = gc.predict(X_test)
+print(f"模型的测试集的预测值：{y_pred}")
+ret = gc.score(X_test,y_test)
+print(f"最佳模型在测试集上的评分:{ret}")
+print(f"最佳模型的参数：{gc.best_estimator_}")
+print(f"最佳模型在训练集上的评分：{gc.best_score_}")
+print(X_test.toarray())
+```
+![](/img/machinelearning/random-forest.png)
+
+### ott案例
+```python
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from imblearn.under_sampling import RandomUnderSampler
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import log_loss
+from sklearn.preprocessing import OneHotEncoder
+# 1. 获取数据集
+data = pd.read_csv('./data/train.csv')
+# 查看目标值分类
+import seaborn as sns
+sns.countplot(data=data, x='target', hue='target', palette="Set2", legend=False)  # 使用 hue='target' 替代 palette
+plt.show()
+
+# 2. 数据集的基本处理
+# 2.1 确定特征值、目标值
+x = data.drop(["id", "target"], axis=1)
+y = data['target']
+
+# 2.2 使用随机欠采样进行平衡
+undersampler = RandomUnderSampler(sampling_strategy='auto', random_state=0)
+x_resampled, y_resampled = undersampler.fit_resample(x, y)
+
+# 查看欠采样后的类别分布
+# print(f"欠采样后训练集中的类别分布：\n{y_train_resampled.value_counts()}")
+
+# 2.3. 将标签转换为数字
+le = LabelEncoder()
+y_resampled = le.fit_transform(y_resampled)
+
+# 2.4. 划分训练集和测试集
+x_train, x_test, y_train, y_test = train_test_split(x_resampled, y_resampled, test_size=0.2)
+
+ # 3. 机器学习
+rf = RandomForestClassifier(oob_score = True)
+rf.fit(x_train,y_train)
+y_pred = rf.predict(x_test)
+print(f"预测值:{y_pred}")
+print(f"评分：{rf.score(x_test,y_test)}")
+
+# # 4. 模型评估 （解决二分类预测问题）
+# import numpy as np
+# from sklearn.metrics import log_loss
+# # 假设 y_pred_prob 是通过 predict_proba 得到的预测概率
+# # 对预测概率进行裁剪，将其限制在 [eps, 1-eps] 范围内
+# eps = 1e-15  # 设置一个小的eps值，避免极端值
+# y_pred_prob = rf.predict_proba(x_test)
+# y_pred_prob = np.clip(y_pred_prob, eps, 1 - eps)
+
+# # 计算 log_loss
+# loss = log_loss(y_test, y_pred_prob, normalize=True)
+# print(f"Log Loss: {loss}")
+
+# 4. 模型评估 （解决多分类预测问题）
+
+# 获取预测的概率
+y_pred_prob = rf.predict_proba(x_test)
+
+# 使用 OneHotEncoder 对 y_test 进行 One-Hot 编码
+encoder = OneHotEncoder(sparse_output=False)  # 确保返回的是密集矩阵
+y_test_one_hot = encoder.fit_transform(y_test.reshape(-1, 1))
+
+# 对预测概率进行裁剪，将其限制在 [eps, 1-eps] 范围内
+eps = 1e-15
+y_pred_prob = np.clip(y_pred_prob, eps, 1 - eps)
+
+# 计算 log_loss
+loss = log_loss(y_test_one_hot, y_pred_prob, normalize=True)
+print(f"Log Loss: {loss}")
+
+```
+![](/img/machinelearning/ott.png)