python打卡day23@浙大疏锦行

知识回顾:

1.  转化器和估计器的概念

2.  管道工程

3.  ColumnTransformer和Pipeline类

作业：

整理下全部逻辑的先后顺序，看看能不能制作出适合所有机器学习的通用pipeline

一、导入数据库

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import time # 导入 time 库
import warnings
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

 二、导入pipeline

from sklearn.pipeline import Pipeline 
from sklearn.compose import ColumnTransformer 
from sklearn.preprocessing import OrdinalEncoder, OneHotEncoder, StandardScaler 
from sklearn.impute import SimpleImputer 
from sklearn.ensemble import RandomForestClassifier 
from sklearn.metrics import classification_report, confusion_matrix 
data = pd.read_csv('heart.csv')
print("原始数据加载完成，形状为:", data.shape)
y = data['target'] # 标签
X = data.drop(['target'], axis=1) 
print("\n特征和标签分离完成。")
print("特征 X 的形状:", X.shape)
print("标签 y 的形状:", y.shape)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) 
print("\n数据集划分完成 (预处理之前)。")
print("X_train 形状:", X_train.shape)
print("X_test 形状:", X_test.shape)
print("y_train 形状:", y_train.shape)
print("y_test 形状:", y_test.shape)
object_cols = X.select_dtypes(include=['object']).columns.tolist()
numeric_cols = X.select_dtypes(exclude=['object']).columns.tolist()
ordinal_features = ['cp',  'restecg',  'slope', 'ca', 'thal']

ordinal_categories = [
    [0, 1, 2, 3], # Home Ownership 的顺序 (对应1, 2, 3, 4)
    [0, 1, 2], # Years in current job 的顺序 (对应1-11)
    [0, 1, 2], # Term 的顺序 (对应0, 1)
    [0, 1, 2, 3, 4],
    [0, 1, 2, 3],
]

三、构建有序特征pipeline

ordinal_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')), 
    ('encoder', OrdinalEncoder(categories=ordinal_categories, handle_unknown='use_encoded_value', unknown_value=-1)) 
])
print("有序特征处理 Pipeline 定义完成。")
nominal_features = ['sex','fbs','exang']

四、构建标称特征pipeline

nominal_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')), 
    ('onehot', OneHotEncoder(handle_unknown='ignore', sparse_output=False)) 
])
print("标称特征处理 Pipeline 定义完成。")
continuous_features = [f for f in X.columns if f not in ordinal_features + nominal_features]
continuous_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('scaler', StandardScaler()) 
print("连续特征处理 Pipeline 定义完成。")

五、串联预处理器和模型

preprocessor = ColumnTransformer(
    transformers=[
        ('ordinal', ordinal_transformer, ordinal_features), 
        ('nominal', nominal_transformer, nominal_features), 
        ('continuous', continuous_transformer, continuous_features) 
    ],
    remainder='passthrough' # 如何处理没有在上面列表中指定的列。
)
print("\nColumnTransformer (预处理器) 定义完成。")
pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor), 
    ('classifier', RandomForestClassifier(random_state=42)) 
])
print("\n完整的 Pipeline 定义完成。")
print("\n--- 1. 默认参数随机森林 (训练集 -> 测试集) ---") 
start_time = time.time() 
pipeline.fit(X_train, y_train)
pipeline_pred = pipeline.predict(X_test)
end_time = time.time() 
print(f"训练与预测耗时: {end_time - start_time:.4f} 秒") 
print("\n默认随机森林 在测试集上的分类报告：") 
print(classification_report(y_test, pipeline_pred))
print("默认随机森林 在测试集上的混淆矩阵：") 
print(confusion_matrix(y_test, pipeline_pred))