数据集划分方法

划分基本准则：保持训练集和验证集之间的互斥性

准则解释：测试样本尽量不在训练样本中出现，以保证验证集上的表现能代表模型的泛化能力

留出法

直接将数据集划分成两个互斥的集合，其中一个做训练集，一个做验证集
常用划分比例： 7:3 、7.5:2.5 、8:2

交叉验证法（cv）

将数据集划分为k个大小相似的互斥子集，每一次以 k-1 个子集做训练，1个子集做验证，训练k次，最终返回的是k次训练结果的均值，因此交叉验证法又称为k折交叉法（k-fold）

数据集划分案例

用到房价预测数据：https://download.csdn.net/download/d1240673769/20910882

数据加载

# 基本数据读取

import pandas as pd
import matplotlib.pyplot as plt

# 样本数据读取
df = pd.read_excel('realestate_sample_preprocessed.xlsx')

# 根据共线性矩阵，保留与房价相关性最高的日间人口，将夜间人口和20-39岁夜间人口进行比例处理
def age_percent(row):
    if row['nightpop'] == 0:
        return 0
    else:
        return row['night20-39']/row['nightpop']
    
df['per_a20_39'] = df.apply(age_percent,axis=1)
df = df.drop(columns=['nightpop','night20-39'])


# 数据集基本情况查看
print(df.shape)
print(df.dtypes)
print(df.isnull().sum())

构建模型

 构建模型
import numpy as np
from sklearn.linear_model import LinearRegression, LassoCV
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler, PowerTransformer
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline

# 构建模型工作流
pipe_lm = Pipeline([
        ('sc',StandardScaler()),
        ('power_trans',PowerTransformer()),
        ('polynom_trans',PolynomialFeatures(degree=3)),
        ('lasso_regr', LassoCV(alphas=(
                list(np.arange(8, 10) * 10)
            ),
    cv=KFold(n_splits=3, shuffle=True),
    n_jobs=-1))
        ])
print(pipe_lm)

留出法进行数据集划分

# 载入sklearn中数据集划分的方法
from sklearn.model_selection import train_test_split

# 将数据集划分成训练集和验证集：划分比例0.75训练，0.25验证
training, testing = train_test_split(df, test_size=0.25, random_state=1)

# 提取训练集中的x与y
x_train=training.copy()[['complete_year', 'area', 'daypop', 'sub_kde', 'bus_kde', 'kind_kde', 'per_a20_39']]
y_train=training.copy()['average_price']

# 提取验证集中的x与y
x_test=testing.copy()[['complete_year', 'area', 'daypop', 'sub_kde', 'bus_kde', 'kind_kde', 'per_a20_39']]
y_test=testing.copy()['average_price']

print('the shape of training set is: {}'.format(training.shape))
print('the shape of testing set is: {}'.format(testing.shape))

# 查看留出法验证集上模型的表现
import warnings
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
warnings.filterwarnings('ignore')

pipe_lm.fit(x_train,y_train)
y_predict = pipe_lm.predict(x_test)
print(f'mean squared error is: {mean_squared_error(y_test,y_predict)}')
print(f'mean absolute error is: {mean_absolute_error(y_test,y_predict)}')
print(f'R Squared is: {r2_score(y_test,y_predict)}')

交叉验证法进行数据集划分

## 交叉验证法进行数据集划分
from sklearn.model_selection import KFold

x = df[['complete_year', 'area', 'daypop', 'sub_kde', 'bus_kde', 'kind_kde', 'per_a20_39']]
y = df['average_price']
k = 10
kf = KFold(n_splits=k, shuffle=True)

查看交叉验证法模型表现

# 查看交叉验证法模型表现
mse = []
mae = []
r_s2=[]

for train_index, test_index in kf.split(df):  # 拆分
    x_traincv,  x_testcv = x.loc[train_index],  x.loc[test_index]
    y_traincv,  y_testcv = y.loc[train_index],  y.loc[test_index]
    pipe_lm.fit(x_traincv, y_traincv)  # 训练
    y_predictcv = pipe_lm.predict(x_testcv)  # 预测
    
    k_mse = mean_squared_error(y_testcv, y_predictcv)
    mse.append(k_mse)
    print('mean squared error is :{}'.format(k_mse))
    
    k_mae = mean_absolute_error(y_testcv, y_predictcv)
    mae.append(k_mae)
    print('mean absoulte error is :{}'.format(k_mae))
    
    k_r_s2 = r2_score(y_testcv, y_predictcv)
    r_s2.append(k_r_s2)
    print('R Squared error is :{}'.format(k_r_s2))
    
    print('--------------------')

# 计算平均值
import numpy as np
print('mean squared error is {}'.format(np.array(mse).mean()))
print('mean absolute error is {}'.format(np.array(mae).mean()))
print('R Squared is {}'.format(np.array(r_s2).mean()))