机器学习，零基础能学会的核心算法

# 导入必要库
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# 1. 生成模拟数据：房屋面积（X）与房价（y）
# 特征X需为二维数组（sklearn要求）
X = np.random.rand(100, 1) * 10  # 100个样本，面积范围0-10㎡
y = 3 * X + 5 + np.random.randn(100, 1)  # 真实关系：y=3X+5，加少量噪声

# 2. 划分训练集和测试集（70%训练，30%测试）
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 3. 训练线性回归模型
model = LinearRegression()
model.fit(X_train, y_train)  # 拟合数据，找到最佳w和b

# 4. 输出模型参数：斜率(w)和截距(b)
print(f"斜率(w)：{model.coef_[0][0]:.2f}")
print(f"截距(b)：{model.intercept_[0]:.2f}")

# 5. 预测测试集数据
y_pred = model.predict(X_test)

# 6. 评估模型：均方误差（越小越好）
mse = mean_squared_error(y_test, y_pred)
print(f"测试集均方误差：{mse:.2f}")

# 7. 可视化拟合结果
plt.scatter(X_test, y_test, label="真实数据", color="blue")
plt.plot(X_test, y_pred, label="拟合直线", color="red")
plt.xlabel("房屋面积（㎡）")
plt.ylabel("房价（万元）")
plt.legend()
plt.show()

# 导入必要库
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 1. 生成模拟二分类数据
# n_features=2：2个特征；n_classes=2：2个类别
X, y = make_classification(n_samples=200, n_features=2, n_classes=2, 
                           n_informative=2, n_redundant=0, random_state=42)

# 2. 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 3. 训练逻辑回归模型
model = LogisticRegression()
model.fit(X_train, y_train)

# 4. 预测测试集
y_pred = model.predict(X_test)
# 也可预测概率：model.predict_proba(X_test)

# 5. 评估模型：准确率（正确预测的比例）
accuracy = accuracy_score(y_test, y_pred)
print(f"模型准确率：{accuracy:.2f}")

# 导入必要库
import numpy as np
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 1. 加载经典数据集：鸢尾花数据集（分类问题）
data = load_iris()
X = data.data  # 特征：花瓣/花萼的长宽
y = data.target  # 目标值：3种鸢尾花类别

# 2. 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 3. 训练决策树模型
dt_model = DecisionTreeClassifier(max_depth=3, random_state=42)  # max_depth限制树深度，避免过拟合
dt_model.fit(X_train, y_train)
dt_pred = dt_model.predict(X_test)
dt_accuracy = accuracy_score(y_test, dt_pred)
print(f"决策树准确率：{dt_accuracy:.2f}")

# 4. 训练随机森林模型
rf_model = RandomForestClassifier(n_estimators=100, max_depth=3, random_state=42)  # n_estimators=100棵树
rf_model.fit(X_train, y_train)
rf_pred = rf_model.predict(X_test)
rf_accuracy = accuracy_score(y_test, rf_pred)
print(f"随机森林准确率：{rf_accuracy:.2f}")

# 导入必要库
import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import SVC
from sklearn.datasets import make_circles
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 1. 生成非线性可分的模拟数据（环形数据）
X, y = make_circles(n_samples=200, noise=0.1, factor=0.2, random_state=42)

# 2. 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 3. 训练SVM模型（使用RBF核函数处理非线性数据）
svm_model = SVC(kernel='rbf', random_state=42)  # kernel='linear'为线性核，适合线性可分数据
svm_model.fit(X_train, y_train)

# 4. 预测并评估
y_pred = svm_model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"SVM模型准确率：{accuracy:.2f}")

# 5. 可视化分类结果（可选）
plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap=plt.cm.Paired)
plt.title("SVM分类结果（RBF核）")
plt.show()

# 导入必要库
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 1. 加载鸢尾花数据集
data = load_iris()
X = data.data
y = data.target

# 2. 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 3. 训练KNN模型（K=5，常用默认值）
knn_model = KNeighborsClassifier(n_neighbors=5)  # n_neighbors即K值
knn_model.fit(X_train, y_train)

# 4. 预测并评估
y_pred = knn_model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"KNN模型准确率（K=5）：{accuracy:.2f}")

# 5. 尝试不同K值（可选）
for k in [3, 5, 7]:
    model = KNeighborsClassifier(n_neighbors=k)
    model.fit(X_train, y_train)
    acc = accuracy_score(y_test, model.predict(X_test))
    print(f"K={k}时准确率：{acc:.2f}")

# 导入必要库
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs

# 1. 生成模拟聚类数据（3个簇）
X, _ = make_blobs(n_samples=300, centers=3, cluster_std=0.6, random_state=42)

# 2. 训练K-Means模型（指定K=3）
kmeans_model = KMeans(n_clusters=3, random_state=42)
cluster_labels = kmeans_model.fit_predict(X)  # 输出每个样本的簇标签（0/1/2）

# 3. 获取簇中心
centroids = kmeans_model.cluster_centers_
print("簇中心坐标：\n", centroids)

# 4. 可视化聚类结果
plt.scatter(X[:, 0], X[:, 1], c=cluster_labels, cmap=plt.cm.Set1, label="样本")
plt.scatter(centroids[:, 0], centroids[:, 1], marker='*', s=200, c='black', label="簇中心")
plt.title("K-Means聚类结果（K=3）")
plt.legend()
plt.show()

# 5. 如何选择最优K值（肘部法则，可选）
inertia = []
for k in range(1, 10):
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans.fit(X)
    inertia.append(kmeans.inertia_)  # 簇内平方和，越小说明簇内越紧凑

plt.plot(range(1, 10), inertia, marker='o')
plt.xlabel("K值")
plt.ylabel("簇内平方和")
plt.title("肘部法则选择最优K值")
plt.show()