python训练营day12

常见算法：遗传算法；粒子群算法；退火算法...

# 先运行之前预处理好的代码
import pandas as pd
import pandas as pd    #用于数据处理和分析，可处理表格数据。
import numpy as np     #用于数值计算，提供了高效的数组操作。
import matplotlib.pyplot as plt    #用于绘制各种类型的图表
import seaborn as sns   #基于matplotlib的高级绘图库，能绘制更美观的统计图形。
 
 # 设置中文字体（解决中文显示问题）
plt.rcParams['font.sans-serif'] = ['SimHei']  # Windows系统常用黑体字体
plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号
data = pd.read_csv('data.csv')    #读取数据

# 先筛选字符串变量 
discrete_features = data.select_dtypes(include=['object']).columns.tolist()
# Home Ownership 标签编码
home_ownership_mapping = {
    'Own Home': 1,
    'Rent': 2,
    'Have Mortgage': 3,
    'Home Mortgage': 4
}
data['Home Ownership'] = data['Home Ownership'].map(home_ownership_mapping)

# Years in current job 标签编码
years_in_job_mapping = {
    '< 1 year': 1,
    '1 year': 2,
    '2 years': 3,
    '3 years': 4,
    '4 years': 5,
    '5 years': 6,
    '6 years': 7,
    '7 years': 8,
    '8 years': 9,
    '9 years': 10,
    '10+ years': 11
}
data['Years in current job'] = data['Years in current job'].map(years_in_job_mapping)

# Purpose 独热编码，记得需要将bool类型转换为数值
data = pd.get_dummies(data, columns=['Purpose'])
data2 = pd.read_csv("data.csv") # 重新读取数据，用来做列名对比
list_final = [] # 新建一个空列表，用于存放独热编码后新增的特征名
for i in data.columns:
    if i not in data2.columns:
       list_final.append(i) # 这里打印出来的就是独热编码后的特征名
for i in list_final:
    data[i] = data[i].astype(int) # 这里的i就是独热编码后的特征名



# Term 0 - 1 映射
term_mapping = {
    'Short Term': 0,
    'Long Term': 1
}
data['Term'] = data['Term'].map(term_mapping)
data.rename(columns={'Term': 'Long Term'}, inplace=True) # 重命名列
continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()  #把筛选出来的列名转换成列表
 
 # 连续特征用中位数补全
for feature in continuous_features:     
    mode_value = data[feature].mode()[0]            #获取该列的众数。
    data[feature].fillna(mode_value, inplace=True)          #用众数填充该列的缺失值，inplace=True表示直接在原数据上修改。

# 最开始也说了 很多调参函数自带交叉验证，甚至是必选的参数，你如果想要不交叉反而实现起来会麻烦很多
# 所以这里我们还是只划分一次数据集
from sklearn.model_selection import train_test_split
X = data.drop(['Credit Default'], axis=1)  # 特征，axis=1表示按列删除
y = data['Credit Default'] # 标签
# 按照8:2划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # 80%训练集，20%测试集


from sklearn.ensemble import RandomForestClassifier #随机森林分类器

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score # 用于评估分类器性能的指标
from sklearn.metrics import classification_report, confusion_matrix #用于生成分类报告和混淆矩阵
import warnings #用于忽略警告信息
warnings.filterwarnings("ignore") # 忽略所有警告信息
# --- 1. 默认参数的随机森林 ---
# 评估基准模型，这里确实不需要验证集
print("--- 1. 默认参数随机森林 (训练集 -> 测试集) ---")
import time # 这里介绍一个新的库，time库，主要用于时间相关的操作，因为调参需要很长时间，记录下会帮助后人知道大概的时长
start_time = time.time() # 记录开始时间
rf_model = RandomForestClassifier(random_state=42)
rf_model.fit(X_train, y_train) # 在训练集上训练
rf_pred = rf_model.predict(X_test) # 在测试集上预测
end_time = time.time() # 记录结束时间

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, rf_pred))
print("默认随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, rf_pred))
#遗传算法
# pip install deap -i https://pypi.tuna.tsinghua.edu.cn/simple
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from sklearn.metrics import classification_report, confusion_matrix
import warnings
warnings.filterwarnings("ignore")
import time
from deap import base, creator, tools, algorithms # DEAP是一个用于遗传算法和进化计算的Python库
import random
import numpy as np



# --- 2. 遗传算法优化随机森林 ---
print("\n--- 2. 遗传算法优化随机森林 (训练集 -> 测试集) ---")

# 定义适应度函数和个体类型
creator.create("FitnessMax", base.Fitness, weights=(1.0,))
creator.create("Individual", list, fitness=creator.FitnessMax)

# 定义超参数范围
n_estimators_range = (50, 200)
max_depth_range = (10, 30)
min_samples_split_range = (2, 10)
min_samples_leaf_range = (1, 4)

# 初始化工具盒
toolbox = base.Toolbox()

# 定义基因生成器
toolbox.register("attr_n_estimators", random.randint, *n_estimators_range)
toolbox.register("attr_max_depth", random.randint, *max_depth_range)
toolbox.register("attr_min_samples_split", random.randint, *min_samples_split_range)
toolbox.register("attr_min_samples_leaf", random.randint, *min_samples_leaf_range)

# 定义个体生成器
toolbox.register("individual", tools.initCycle, creator.Individual,
                 (toolbox.attr_n_estimators, toolbox.attr_max_depth,
                  toolbox.attr_min_samples_split, toolbox.attr_min_samples_leaf), n=1)

# 定义种群生成器
toolbox.register("population", tools.initRepeat, list, toolbox.individual)

# 定义评估函数
def evaluate(individual):
    n_estimators, max_depth, min_samples_split, min_samples_leaf = individual
    model = RandomForestClassifier(n_estimators=n_estimators,
                                   max_depth=max_depth,
                                   min_samples_split=min_samples_split,
                                   min_samples_leaf=min_samples_leaf,
                                   random_state=42)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    accuracy = accuracy_score(y_test, y_pred)
    return accuracy,

# 注册评估函数
toolbox.register("evaluate", evaluate)

# 注册遗传操作
toolbox.register("mate", tools.cxTwoPoint)
toolbox.register("mutate", tools.mutUniformInt, low=[n_estimators_range[0], max_depth_range[0],
                                                     min_samples_split_range[0], min_samples_leaf_range[0]],
                 up=[n_estimators_range[1], max_depth_range[1],
                     min_samples_split_range[1], min_samples_leaf_range[1]], indpb=0.1)
toolbox.register("select", tools.selTournament, tournsize=3)

# 初始化种群
pop = toolbox.population(n=20)

# 遗传算法参数
NGEN = 10
CXPB = 0.5
MUTPB = 0.2

start_time = time.time()
# 运行遗传算法
for gen in range(NGEN):
    offspring = algorithms.varAnd(pop, toolbox, cxpb=CXPB, mutpb=MUTPB)
    fits = toolbox.map(toolbox.evaluate, offspring)
    for fit, ind in zip(fits, offspring):
        ind.fitness.values = fit
    pop = toolbox.select(offspring, k=len(pop))

end_time = time.time()

# 找到最优个体
best_ind = tools.selBest(pop, k=1)[0]
best_n_estimators, best_max_depth, best_min_samples_split, best_min_samples_leaf = best_ind

print(f"遗传算法优化耗时: {end_time - start_time:.4f} 秒")
print("最佳参数: ", {
    'n_estimators': best_n_estimators,
    'max_depth': best_max_depth,
    'min_samples_split': best_min_samples_split,
    'min_samples_leaf': best_min_samples_leaf
})

# 使用最佳参数的模型进行预测
best_model = RandomForestClassifier(n_estimators=best_n_estimators,
                                    max_depth=best_max_depth,
                                    min_samples_split=best_min_samples_split,
                                    min_samples_leaf=best_min_samples_leaf,
                                    random_state=42)
best_model.fit(X_train, y_train)
best_pred = best_model.predict(X_test)

print("\n遗传算法优化后的随机森林 在测试集上的分类报告：")
print(classification_report(y_test, best_pred))
print("遗传算法优化后的随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, best_pred))

@浙大疏锦行