Scikit-learn 学习笔记

安装：

        在Scikit-learn中，数据通常表示为NumPy数组或Pandas DataFrame。特征数据（X）通常是一个二维数组，其中每一行代表一个样本，每一列代表一个特征。目标数据（y）通常是一个一维数组，包含了每个样本的标签或目标值。

数据预处理的工具：

标准化：StandardScaler

归一化：MinMaxScaler

缺失值处理：SimpleImputer

编码：OneHotEncoder或LabelEncoder

特征选择：SelectKBest

1. 数据清洗

   涉及处理缺失值、重复数据、异常值等
   import pandas as pd
   import numpy as np
   
   # 创建一个包含缺失值、重复数据和异常值的DataFrame
   data = {
       'Name': ['Alice', 'Bob', 'Charlie', 'Alice', 'Bob', 'Charlie', 'Alice', 'Bob', 'ZZZ', 'Alice'],
       'Age': [25, 30, 35, 25, 30, 35, 25, 30, -1, 25],
       'Score': [88, 92, np.nan, 88, 92, np.nan, 88, 92, 1000, 88]
   }
   
   # 创建DataFrame
   df = pd.DataFrame(data)
   
   # 显示原始DataFrame
   print("原始DataFrame:")
   print(df)
   
   # 处理缺失值：用平均值填充数值列的缺失值
   df['Score'] = df['Score'].fillna(df['Score'].mean())
   
   # 删除重复行
   df = df.drop_duplicates()
   
   # 处理异常值：假设年龄不可能小于0，我们将其设置为年龄列的中位数
   median_age = df['Age'].median()
   df['Age'] = df['Age'].replace(to_replace=-1, value=median_age)
   
   # 处理异常值：假设分数不可能超过100，我们将其设置为分数列的最大值
   max_score = df['Score'].max()
   df['Score'] = df['Score'].where(df['Score'] <= 100, max_score)
   
   # 显示清洗后的DataFrame
   print("\n清洗后的DataFrame:")
   print(df)

2. 特征提取与转换

   from sklearn.feature_extraction.text import CountVectorizer
   
   # 示例文本数据
   text_data = ["hello world", "hello everyone", "world of programming"]
   
   # 初始化CountVectorizer
   vectorizer = CountVectorizer()
   
   # 转换文本数据为词频矩阵
   X = vectorizer.fit_transform(text_data)
   
   print(X.toarray())//用于将稀疏矩阵（sparse matrix）转换为一个常规的 numpy 数组（dense array）

3. 标准化与归一化

   from sklearn.preprocessing import StandardScaler, MinMaxScaler
   
   # 示例数据
   data = [[1, 2], [2, 3], [3, 4]]
   
   # 标准化
   scaler = StandardScaler()
   standardized_data = scaler.fit_transform(data)
   
   # 归一化
   min_max_scaler = MinMaxScaler()
   normalized_data = min_max_scaler.fit_transform(data)
   
   print("Standardized data:", standardized_data)
   print("Normalized data:", normalized_data)

4. 缺失值处理：SimpleImputer---》》填充缺失值

   from sklearn.impute import SimpleImputer
   import numpy as np
   
   # 示例数据
   data = [[1, 2], [np.nan, 3], [7, 6]]
   
   # 初始化SimpleImputer，使用均值填充
   imputer = SimpleImputer(strategy='mean')
   
   # 填充缺失值
   imputed_data = imputer.fit_transform(data)
   
   print(imputed_data)
   
   5.数据集划分train_test_split 是一个非常常用的函数，它用于将数据集分割为训练集和测试集

from sklearn.model_selection import train_test_split

# 示例数据
X = [[1, 2], [3, 4], [5, 6], [7, 8]]
y = [0, 1, 0, 1]

# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)

print("Training data:", X_train, y_train)
print("Testing data:", X_test, y_test)s四

四.监督学习

4.1线性模型

        假设特征之间的关系可以用一条直线（对于二元分类）或超平面（对于多类分类）来表示。线性模型主要包括线性回归（用于连续目标变量）和逻辑回归（用于分类目标变量）。

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 示例数据集
# 特征矩阵X
X = np.array([[800], [1200], [1600], [2000], [2400]])
# 目标向量y
y = np.array([150000, 200000, 250000, 300000, 350000])

# 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=0)

# 创建线性回归模型并训练
model = LinearRegression()
model.fit(X_train, y_train)

# 进行预测
y_pred = model.predict(X_test)

# 计算均方误差
mse = mean_squared_error(y_test, y_pred)
print(f"均方误差为: {mse}")

# 打印训练数据
print("训练数据:")
print("特征矩阵 X_train:")
print(X_train)
print("目标向量 y_train:")
print(y_train)

# 打印测试数据
print("测试数据:")
print("特征矩阵 X_test:")
print(X_test)
print("目标向量 y_test:")
print(y_test)
print("预测值 y_pred:")
print(y_pred)

4.2支持向量机

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.metrics import classification_report, confusion_matrix

# 生成模拟数据集，调整特征数量
X, y = make_classification(n_samples=100, n_features=4, n_classes=2, n_informative=2, n_redundant=0, n_repeated=0, random_state=42)

# 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)

# 特征标准化
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 创建SVM分类器实例
model = SVC(kernel='linear')  # 使用线性核

# 训练模型
model.fit(X_train, y_train)

# 进行预测
y_pred = model.predict(X_test)

# 打印混淆矩阵
print(confusion_matrix(y_test, y_pred))

# 打印分类报告
print(classification_report(y_test, y_pred))