update decisiontree regression problem details

2025-01-24 18:17:26 +08:00
parent 875fb417a7 efff4fc131
commit 6b5d9f232e
63 changed files with 2536 additions and 260 deletions
--- a/source/_posts/machinelearning/decisiontree.md
+++ b/source/_posts/machinelearning/decisiontree.md
@@ -106,6 +106,7 @@ print(f"转换后的数据:\n{new_data}")


 ### 回归决策树
+<<<<<<< HEAD
 #### 决策树算法的应用 （泰坦尼克号沉船幸存者预测）
 ```python
 import seaborn as sns
@@ -168,6 +169,9 @@ 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
+=======
+[Webgraphviz](http://webgraphviz.com/)
+>>>>>>> efff4fc1310b4d2f201748d9b976f5efbb4a42bf

 ```python
 import numpy as np
--- a/source/_posts/machinelearning/knn.md
+++ b/source/_posts/machinelearning/knn.md
@@ -1,6 +1,7 @@
 ---
 title: k近邻算法（K-Nearest Neighbors）KNN
-tags: machinelearning
+tags: KNN
+categories: machinelearning
 abbrlink: 29139
 mathjax: true
 date: 2025-01-13 17:20:59
--- a/source/_posts/machinelearning/linearreression.md
+++ b/source/_posts/machinelearning/linearreression.md
@@ -0,0 +1,200 @@
+---
+title: 线性回归
+tags: linear-regression
+categories: machinelearning
+mathjax: true
+abbrlink: 52662
+date: 2025-01-19 16:46:51
+---
+
+### 线性回归简介
+>用于预测一个连续的目标变量（因变量），与一个或多个特征（自变量）之间存在线性关系。
+
+假设函数：  
+$$y = w_1x_1 + w_2x_2 + \cdot\cdot\cdot+w_nx_n$$
+- $y$ 是目标变量（因变量），即我们希望预测的值。
+- $x1,x2,…,xn$ 是特征变量（自变量），即输入的值。
+### 损失函数
+
+为了找到最佳的线性模型，我们需要通过最小化损失函数来优化模型参数。在线性回归中，常用的损失函数是 **均方误差（MSE）**：
+$$MSE = \frac{1}{m} \sum_{i=1}^{m} (y_i - \hat{y}_i)^2$$
+- m 是样本的数量。
+- $y_i$ 是第 i 个样本的真实值。
+- $\hat{y}_i$ 是模型预测的第 i 个样本的值。
+
+### 线性回归优化
+
+- 梯度下降法
+    ```python
+    from sklearn.datasets import fetch_california_housing
+    from sklearn.model_selection import train_test_split
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.linear_model import SGDRegressor
+    from sklearn.metrics import mean_squared_error
+
+    # 1. 获取数据集
+    housing = fetch_california_housing()
+
+    # 2. 数据集处理
+    # 2.1 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target, test_size=0.25)
+
+    # 3. 特征工程
+    # 3.1 标准化
+    transfer = StandardScaler()
+    X_train = transfer.fit_transform(X_train)
+    X_test = transfer.transform(X_test)  # 使用 transform() 而不是 fit_transform()
+
+    # 4.机器学习- 梯度下降法
+    estimater = SGDRegressor(max_iter=1000, eta0=0.01)
+    estimater.fit(X_train, y_train)
+    print(f"SGD模型的偏置是：{estimater.intercept_}")
+    print(f"SGD模型的系数是：{estimater.coef_}")
+
+    # 5. 模型评估
+    y_pred = estimater.predict(X_test)
+    print(f"SGD模型预测值：{y_pred}")
+    mse = mean_squared_error(y_test, y_pred)
+    print(f"SGD模型均方误差:{mse}")
+    ```
+
+- 正规方程
+    ```python
+    from sklearn.datasets import fetch_california_housing
+    from sklearn.model_selection import train_test_split
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.linear_model import LinearRegression
+    from sklearn.metrics import mean_squared_error
+
+    # 1. 获取数据集
+    housing = fetch_california_housing()
+
+    # 2. 数据集处理
+    # 2.1 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target, test_size=0.25)
+
+    # 3. 特征工程
+    # 3.1 标准化
+    transfer = StandardScaler()
+    X_train = transfer.fit_transform(X_train)
+    X_test = transfer.fit_transform(X_test)
+
+    # 4.机器学习- 线性回归
+    estimater = LinearRegression()
+    estimater.fit(X_train, y_train)
+    print(f"模型的偏置是：{estimater.intercept_}")
+    print(f"模型的系数是：{estimater.coef_}")
+
+    # 5. 模型评估
+    y_pred = estimater.predict(X_test)
+    print(f"模型预测值：{y_pred}")
+    mse = mean_squared_error(y_test, y_pred)
+    print(f"模型均方误差:{mse}")
+    ```
+
+- 岭回归
+    ```python
+    from sklearn.datasets import fetch_california_housing
+    from sklearn.model_selection import train_test_split
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.linear_model import Ridge, RidgeCV
+    from sklearn.metrics import mean_squared_error
+
+    # 1. 获取数据集
+    housing = fetch_california_housing()
+
+    # 2. 数据集处理
+    # 2.1 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target, test_size=0.25)
+
+    # 3. 特征工程
+    # 3.1 标准化
+    transfer = StandardScaler()
+    X_train = transfer.fit_transform(X_train)
+    X_test = transfer.transform(X_test)  # 使用 transform() 而不是 fit_transform()
+
+    # 4.机器学习- 岭回归 使用了Ridge的alpha的搜索
+    # estimater = Ridge(alpha=1.0)
+    estimater = RidgeCV(alphas=[0.001, 0.01, 0.1, 1, 10, 100])
+    estimater.fit(X_train, y_train)
+    print(f"Ridge模型的偏置是：{estimater.intercept_}")
+    print(f"Ridge模型的系数是：{estimater.coef_}")
+
+    # 查看最佳 alpha
+    print(f"最佳 alpha 值是：{estimater.alpha_}")
+
+    # 5. 模型评估
+    y_pred = estimater.predict(X_test)
+    print(f"Ridge模型预测值：{y_pred}")
+    mse = mean_squared_error(y_test, y_pred)
+    print(f"Ridge模型均方误差:{mse}")
+    ```
+
+这样每个代码块的缩进保持一致，便于阅读和理解。如果有其他优化需求，随时告诉我！
+
+
+![](/img/machinelearning/linear.png)
+
+![](/img/machinelearning/fitting.png)
+### 模型保存和加载
+```python
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import Ridge, RidgeCV
+from sklearn.metrics import mean_squared_error
+import joblib
+
+def save_model():
+    # 1. 获取数据集
+    housing = fetch_california_housing()
+    # 2. 数据集处理
+    # 2.1 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target, test_size=0.25)
+    # 3. 特征工程
+    # 3.1 标准化
+    transfer = StandardScaler()
+    X_train = transfer.fit_transform(X_train)
+    X_test = transfer.transform(X_test)  # 使用 transform() 而不是 fit_transform()
+    # 4. 机器学习 - 岭回归 使用了Ridge的alpha的搜索
+    estimater = RidgeCV(alphas=[0.001, 0.01, 0.1, 1, 10, 100])
+    estimater.fit(X_train, y_train)
+    print(f"Ridge模型的偏置是：{estimater.intercept_}")
+    print(f"Ridge模型的系数是：{estimater.coef_}")
+    # 保存模型
+    joblib.dump(estimater, 'ridge_model.pkl')
+    # 查看最佳 alpha
+    print(f"最佳 alpha 值是：{estimater.alpha_}")
+    # 5. 模型评估
+    y_pred = estimater.predict(X_test)
+    mse = mean_squared_error(y_test, y_pred)
+    print(f"Ridge模型均方误差:{mse}")
+
+def load_model():
+    # 1. 获取数据集
+    housing = fetch_california_housing()
+    # 2. 数据集处理
+    # 2.1 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target, test_size=0.25)
+    # 3. 特征工程
+    # 3.1 标准化
+    transfer = StandardScaler()
+    X_train = transfer.fit_transform(X_train)
+    X_test = transfer.transform(X_test)  # 使用 transform() 而不是 fit_transform()
+    # 加载模型
+    estimater = joblib.load('ridge_model.pkl')
+    print(f"Ridge模型的偏置是：{estimater.intercept_}")
+    print(f"Ridge模型的系数是：{estimater.coef_}")
+    # 查看最佳 alpha
+    print(f"最佳 alpha 值是：{estimater.alpha_}")
+    # 5. 模型评估
+    y_pred = estimater.predict(X_test)
+    mse = mean_squared_error(y_test, y_pred)
+    print(f"Ridge模型预测值：{y_pred}")
+    print(f"Ridge模型均方误差:{mse}")
+
+print("训练并保存模型：")
+save_model()
+print("加载模型")
+load_model()
+```
--- a/source/_posts/machinelearning/logisticregression.md
+++ b/source/_posts/machinelearning/logisticregression.md
@@ -0,0 +1,173 @@
+---
+title: 逻辑回归
+tags: logistic-regression
+categories: machinelearning
+mathjax: true
+abbrlink: 60504
+date: 2025-01-20 15:30:08
+---
+
+### logistic regression code
+
+```python
+import pandas as pd
+import numpy as np
+from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
+# 1. 加载乳腺癌数据集
+data = load_breast_cancer()
+# 2.1  数据集基本处理
+df = pd.DataFrame(data.data, columns=data.feature_names)
+df['target'] = data.target
+for i in df.columns:
+    # 检查列是否有缺失值
+    if np.any(pd.isnull(df[i])):
+        print(f"Filling missing values in column: {i}")
+#2.2 确认特征值、目标值
+X = df.iloc[:,0:df.shape[1] - 1]
+y = df.loc[:,"target"]
+# 2.3 分割数据
+X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3)
+# 显示前几行数据
+df.head(1)
+
+# 3. 特征工程 标准化
+transfer = StandardScaler()
+X_train = transfer.fit_transform(X_train)
+X_test = transfer.transform(X_test)
+
+# 4 机器学习 逻辑回归
+estimator = LogisticRegression()
+estimator.fit(X_train,y_train)
+
+# 5. 模型评估
+print(f"模型准确率：{estimator.score(X_test,y_test)}")
+print(f"模型预测值为:\n{estimator.predict(X_test)}")
+```
+
+### 分类评估的参数
+- 准确率  
+  准确率是所有预测正确的样本占总样本的比例  
+  $$Accuracy = \frac{TP+TN}{TP+FN+FP+TN}$$
+
+- 精准率  
+  精准率（又称查准率）是指所有被预测为正类的样本中，真正为正类的比例  
+  $$Precision = \frac{TP}{TP+FP}$$
+
+- 召回率  
+  召回率（又称查全率）是指所有实际为正类的样本中，被正确预测为正类的比例  
+  $$Recall = \frac{TP}{TP+FN}$$
+
+- F1-score  
+  F1 值（F1 Score）是精准率和召回率的调和平均数，综合考虑了精准率和召回率的影响。  
+  $$ F1 = 2 \times \frac{\text{Precision} \times \text{Recall}}{\text{Precision} + \text{Recall}} $$
+
+- roc曲线  
+  tpr、fpr来衡量不平衡的二分类问题
+
+```python
+ import pandas as pd
+ import numpy as np
+ from sklearn.datasets import load_breast_cancer
+ from sklearn.model_selection import train_test_split
+ from sklearn.preprocessing import StandardScaler
+ from sklearn.linear_model import LogisticRegression
+ from sklearn.metrics import classification_report, roc_auc_score
+ # 1. 加载乳腺癌数据集
+ data = load_breast_cancer()
+ # 2.1  数据集基本处理
+ df = pd.DataFrame(data.data, columns=data.feature_names)
+ df['target'] = data.target
+ for i in df.columns:
+     # 检查列是否有缺失值
+     if np.any(pd.isnull(df[i])):
+         print(f"Filling missing values in column: {i}")
+ # 2.2 确认特征值、目标值
+ X = df.iloc[:, 0:df.shape[1] - 1]
+ y = df.loc[:, "target"]
+ # 2.3 分割数据
+ X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
+ # 显示前几行数据
+ df.head(1)
+ 
+ # 3. 特征工程 标准化
+ transfer = StandardScaler()
+ X_train = transfer.fit_transform(X_train)
+ X_test = transfer.transform(X_test)
+ 
+ # 4 机器学习 逻辑回归
+ estimator = LogisticRegression()
+ estimator.fit(X_train, y_train)
+ 
+ # 5. 模型评估
+ print(f"模型准确率：{estimator.score(X_test, y_test)}")
+ y_pred = estimator.predict(X_test)
+ print(f"模型预测值为:\n{y_pred}")
+ # 5.1 精确率、召回率
+ ret = classification_report(y_test, y_pred, labels=[1, 0], target_names=["良性", "恶性"])
+ roc_score = roc_auc_score(y_test, y_pred)
+ print(f"准确率、召回率：{ret}")
+ print(f"roc_score:{roc_score}")
+ ```
+
+### 类别不平衡的处理
+先准备类别不平衡的数据
+
+```python
+from imblearn.over_sampling import RandomOverSampler,SMOTE
+from imblearn.under_sampling import RandomUnderSampler
+from sklearn.datasets import make_classification
+import matplotlib.pyplot as plt
+from collections import Counter
+
+# 1.准备类别不平衡的数据
+X, y = make_classification(
+    n_samples=5000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_repeated=0,
+    n_classes=3,
+    n_clusters_per_class=1,
+    weights=[0.01, 0.05, 0.94],
+    random_state=0,
+)
+counter = Counter(y)
+plt.scatter(X[:,0],X[:,1],c=y)
+plt.show()
+```
+
+ - 过采样  
+   增加训练集的少数的类别的样本，使得正反例样本数据接近  
+   - 随机过采样（RandomOverSampler)
+  ```python
+    ros = RandomOverSampler()
+    X_resampled,y_resampled = ros.fit_resample(X,y)
+    print(Counter(y_resampled))
+    plt.scatter(X_resampled[:,0],X_resampled[:,1],c=y_resampled)
+    plt.show()
+  ```
+  ![](/img/machinelearning/over_random_sampling.png)
+   - `SMOTE`过采样（SMOTE）
+  ```python
+    smote = SMOTE()
+    X_resampled,y_resampled = smote.fit_resample(X,y)
+    print(Counter(y_resampled))
+    plt.scatter(X_resampled[:,0],X_resampled[:,1],c=y_resampled)
+    plt.show()
+  ```
+  ![](/img/machinelearning/over_smote_sampling.png)
+ - 欠采样  
+   减少训练集的多数的类别的样本，使得正反例样本数据接近
+   - 随机欠采样（RandomUnderSampler）
+  ```python
+    rus = RandomUnderSampler(random_state=0)
+    X_resampled,y_resampled = rus.fit_resample(X,y)
+    print(Counter(y_resampled))
+    plt.scatter(X_resampled[:,0],X_resampled[:,1],c=y_resampled)
+    plt.show()
+  ```
+  ![](/img/machinelearning/under_sampling.png)
+