建模调参前期

#导入数据
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from operator import itemgetter

%matplotlib inline

##载入训练集合测试集
test_data = pd.read_csv(r'C:\Users\MUJI\Desktop\二手车预测\used_car_testA_20200313.csv',sep=' ')
train_data = pd.read_csv(r'C:\Users\MUJI\Desktop\二手车预测\used_car_train_20200313.csv',sep=' ')

线性回归

# 简单的线性建模
from sklearn.linear_model import LinearRegression
model = LinearRegression(normalize=True)
model = model.fit(train_X, train_y)
print('intercept:'+ str(model.intercept_))
print(sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True))

贝叶斯调参

from bayes_opt import BayesianOptimization

def rf_cv(num_leaves, max_depth, subsample, min_child_samples):
val = cross_val_score(
LGBMRegressor(objective = ‘regression_l1’,
num_leaves=int(num_leaves),
max_depth=int(max_depth),
subsample = subsample,
min_child_samples = int(min_child_samples)
),
X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)
).mean()
return 1 - val

rf_bo = BayesianOptimization(
rf_cv,
{
‘num_leaves’: (2, 100),
‘max_depth’: (2, 100),
‘subsample’: (0.1, 1),
‘min_child_samples’ : (2, 100)
}
)

模型验证

五折交叉验证

# 交叉验证
from sklearn.model_selection import cross_val_score
from sklearn.metrics import mean_absolute_error,  make_scorer

def log_transfer(func):
    def wrapper(y, yhat):
        result = func(np.log(y), np.nan_to_num(np.log(yhat)))
        return result
    return wrapper
# 使用线性模型对未经过 log 变换的数据进行预测
scores = cross_val_score(model, X=train_X, y=train_y_org, verbose=1, cv = 5, scoring=make_scorer(log_transfer(mean_absolute_error)))
print('AVG-org:', np.mean(scores))
# 使用线性模型对 log 变换后的数据进行预测
scores = cross_val_score(model, X=train_X, y=train_y, verbose=1, cv = 5, scoring=make_scorer(log_transfer(mean_absolute_error)))
print('AVG:', np.mean(scores))