Datawhale 零基礎(chǔ)入門數(shù)據(jù)挖掘-Task4 建模調(diào)參
四响委、建模與調(diào)參
4.1 學(xué)習(xí)目標(biāo)
- 了解常用的機(jī)器學(xué)習(xí)模型吏颖，并掌握機(jī)器學(xué)習(xí)模型的建模與調(diào)參流程
- 完成相應(yīng)學(xué)習(xí)打卡任務(wù)
4.2 內(nèi)容介紹
- 線性回歸模型：
- 線性回歸對(duì)于特征的要求刨啸；
- 處理長尾分布泉孩；
- 理解線性回歸模型漫拭；
- 模型性能驗(yàn)證：
- 評(píng)價(jià)函數(shù)與目標(biāo)函數(shù)避消；
- 交叉驗(yàn)證方法；
- 留一驗(yàn)證方法顽冶；
- 針對(duì)時(shí)間序列問題的驗(yàn)證欺抗；
- 繪制學(xué)習(xí)率曲線；
- 繪制驗(yàn)證曲線强重；
- 嵌入式特征選擇：
- Lasso回歸绞呈；
- Ridge回歸；
- 決策樹间景；
- 模型對(duì)比：
- 常用線性模型佃声；
- 常用非線性模型；
- 模型調(diào)參：
- 貪心調(diào)參方法倘要；
- 網(wǎng)格調(diào)參方法圾亏；
- 貝葉斯調(diào)參方法；
4.4 代碼示例
4.4.1 讀取數(shù)據(jù)
import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings('ignore')
reduce_mem_usage 函數(shù)通過調(diào)整數(shù)據(jù)類型碗誉，幫助我們減少數(shù)據(jù)在內(nèi)存中占用的空間
def reduce_mem_usage(df):
""" iterate through all the columns of a dataframe and modify the data type
to reduce memory usage.
"""
start_mem = df.memory_usage().sum()
print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
for col in df.columns:
col_type = df[col].dtype
if col_type != object:
c_min = df[col].min()
c_max = df[col].max()
if str(col_type)[:3] == 'int':
if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
df[col] = df[col].astype(np.int8)
elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
df[col] = df[col].astype(np.int16)
elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
df[col] = df[col].astype(np.int32)
elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
df[col] = df[col].astype(np.int64)
else:
if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
df[col] = df[col].astype(np.float16)
elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
df[col] = df[col].astype(np.float32)
else:
df[col] = df[col].astype(np.float64)
else:
df[col] = df[col].astype('category')
end_mem = df.memory_usage().sum()
print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
return df
sample_feature = reduce_mem_usage(pd.read_csv('data_for_tree.csv'))
Memory usage of dataframe is 60507328.00 MB
Memory usage after optimization is: 15724107.00 MB
Decreased by 74.0%
continuous_feature_names = [x for x in sample_feature.columns if x not in ['price','brand','model','brand']]
4.4.2 線性回歸 & 五折交叉驗(yàn)證 & 模擬真實(shí)業(yè)務(wù)情況
sample_feature = sample_feature.dropna().replace('-', 0).reset_index(drop=True)
sample_feature['notRepairedDamage'] = sample_feature['notRepairedDamage'].astype(np.float32)
train = sample_feature[continuous_feature_names + ['price']]
train_X = train[continuous_feature_names]
train_y = train['price']
4.4.2 - 1 簡(jiǎn)單建模
from sklearn.linear_model import LinearRegression
model = LinearRegression(normalize=True)
model = model.fit(train_X, train_y)
查看訓(xùn)練的線性回歸模型的截距（intercept）與權(quán)重(coef)
'intercept:'+ str(model.intercept_)
sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True)
[('v_6', 3342612.384537345),
('v_8', 684205.534533214),
('v_9', 178967.94192530424),
('v_7', 35223.07319016895),
('v_5', 21917.550249749802),
('v_3', 12782.03250792227),
('v_12', 11654.925634146672),
('v_13', 9884.194615297649),
('v_11', 5519.182176035517),
('v_10', 3765.6101415594258),
('gearbox', 900.3205339198406),
('fuelType', 353.5206495542567),
('bodyType', 186.51797317460046),
('city', 45.17354204168846),
('power', 31.163045441455335),
('brand_price_median', 0.535967111869784),
('brand_price_std', 0.4346788365040235),
('brand_amount', 0.15308295553300566),
('brand_price_max', 0.003891831020467389),
('seller', -1.2684613466262817e-06),
('offerType', -4.759058356285095e-06),
('brand_price_sum', -2.2430642281682917e-05),
('name', -0.00042591632723759166),
('used_time', -0.012574429533889028),
('brand_price_average', -0.414105722833381),
('brand_price_min', -2.3163823428971835),
('train', -5.392535065078232),
('power_bin', -59.24591853031839),
('v_14', -233.1604256172217),
('kilometer', -372.96600915402496),
('notRepairedDamage', -449.29703564695365),
('v_0', -1490.6790578168238),
('v_4', -14219.648899108111),
('v_2', -16528.55239086934),
('v_1', -42869.43976200439)]
from matplotlib import pyplot as plt
subsample_index = np.random.randint(low=0, high=len(train_y), size=50)
繪制特征v_9的值與標(biāo)簽的散點(diǎn)圖，圖片發(fā)現(xiàn)模型的預(yù)測(cè)結(jié)果（藍(lán)色點(diǎn)）與真實(shí)標(biāo)簽（黑色點(diǎn)）的分布差異較大父晶，且部分預(yù)測(cè)值出現(xiàn)了小于0的情況哮缺，說明我們的模型存在一些問題
plt.scatter(train_X['v_9'][subsample_index], train_y[subsample_index], color='black')
plt.scatter(train_X['v_9'][subsample_index], model.predict(train_X.loc[subsample_index]), color='blue')
plt.xlabel('v_9')
plt.ylabel('price')
plt.legend(['True Price','Predicted Price'],loc='upper right')
print('The predicted price is obvious different from true price')
plt.show()
The predicted price is obvious different from true price
output_21_1.png
通過作圖我們發(fā)現(xiàn)數(shù)據(jù)的標(biāo)簽（price）呈現(xiàn)長尾分布，不利于我們的建模預(yù)測(cè)甲喝。原因是很多模型都假設(shè)數(shù)據(jù)誤差項(xiàng)符合正態(tài)分布尝苇，而長尾分布的數(shù)據(jù)違背了這一假設(shè)。參考博客：https://blog.csdn.net/Noob_daniel/article/details/76087829
import seaborn as sns
print('It is clear to see the price shows a typical exponential distribution')
plt.figure(figsize=(15,5))
plt.subplot(1,2,1)
sns.distplot(train_y)
plt.subplot(1,2,2)
sns.distplot(train_y[train_y < np.quantile(train_y, 0.9)])
It is clear to see the price shows a typical exponential distribution
output_23_2.png
在這里我們對(duì)標(biāo)簽進(jìn)行了 變換埠胖，使標(biāo)簽貼近于正態(tài)分布
train_y_ln = np.log(train_y + 1)
import seaborn as sns
print('The transformed price seems like normal distribution')
plt.figure(figsize=(15,5))
plt.subplot(1,2,1)
sns.distplot(train_y_ln)
plt.subplot(1,2,2)
sns.distplot(train_y_ln[train_y_ln < np.quantile(train_y_ln, 0.9)])
The transformed price seems like normal distribution
output_26_2.png
model = model.fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True)
intercept:23.515920686637713
[('v_9', 6.043993029165403),
('v_12', 2.0357439855551394),
('v_11', 1.3607608712255672),
('v_1', 1.3079816298861897),
('v_13', 1.0788833838535354),
('v_3', 0.9895814429387444),
('gearbox', 0.009170812023421397),
('fuelType', 0.006447089787635784),
('bodyType', 0.004815242907679581),
('power_bin', 0.003151801949447194),
('power', 0.0012550361843629999),
('train', 0.0001429273782925814),
('brand_price_min', 2.0721302299502698e-05),
('brand_price_average', 5.308179717783439e-06),
('brand_amount', 2.8308531339942507e-06),
('brand_price_max', 6.764442596115763e-07),
('offerType', 1.6765966392995324e-10),
('seller', 9.308109838457312e-12),
('brand_price_sum', -1.3473184925468486e-10),
('name', -7.11403461065247e-08),
('brand_price_median', -1.7608143661053008e-06),
('brand_price_std', -2.7899058266986454e-06),
('used_time', -5.6142735899344175e-06),
('city', -0.0024992974087053223),
('v_14', -0.012754139659375262),
('kilometer', -0.013999175312751872),
('v_0', -0.04553774829634237),
('notRepairedDamage', -0.273686961116076),
('v_7', -0.7455902679730504),
('v_4', -0.9281349233755761),
('v_2', -1.2781892166433606),
('v_5', -1.5458846136756323),
('v_10', -1.8059217242413748),
('v_8', -42.611729973490604),
('v_6', -241.30992120503035)]
再次進(jìn)行可視化糠溜，發(fā)現(xiàn)預(yù)測(cè)結(jié)果與真實(shí)值較為接近，且未出現(xiàn)異常狀況
plt.scatter(train_X['v_9'][subsample_index], train_y[subsample_index], color='black')
plt.scatter(train_X['v_9'][subsample_index], np.exp(model.predict(train_X.loc[subsample_index])), color='blue')
plt.xlabel('v_9')
plt.ylabel('price')
plt.legend(['True Price','Predicted Price'],loc='upper right')
print('The predicted price seems normal after np.log transforming')
plt.show()
output_29_1.png
4.4.2 - 2 五折交叉驗(yàn)證
在使用訓(xùn)練集對(duì)參數(shù)進(jìn)行訓(xùn)練的時(shí)候直撤，經(jīng)常會(huì)發(fā)現(xiàn)人們通常會(huì)將一整個(gè)訓(xùn)練集分為三個(gè)部分（比如mnist手寫訓(xùn)練集）非竿。一般分為：訓(xùn)練集（train_set），評(píng)估集（valid_set）谋竖，測(cè)試集（test_set）這三個(gè)部分红柱。這其實(shí)是為了保證訓(xùn)練效果而特意設(shè)置的承匣。其中測(cè)試集很好理解，其實(shí)就是完全不參與訓(xùn)練的數(shù)據(jù)锤悄，僅僅用來觀測(cè)測(cè)試效果的數(shù)據(jù)韧骗。而訓(xùn)練集和評(píng)估集則牽涉到下面的知識(shí)了。
因?yàn)樵趯?shí)際的訓(xùn)練中零聚，訓(xùn)練的結(jié)果對(duì)于訓(xùn)練集的擬合程度通常還是挺好的（初始條件敏感）袍暴，但是對(duì)于訓(xùn)練集之外的數(shù)據(jù)的擬合程度通常就不那么令人滿意了。因此我們通常并不會(huì)把所有的數(shù)據(jù)集都拿來訓(xùn)練隶症，而是分出一部分來（這一部分不參加訓(xùn)練）對(duì)訓(xùn)練集生成的參數(shù)進(jìn)行測(cè)試政模，相對(duì)客觀的判斷這些參數(shù)對(duì)訓(xùn)練集之外的數(shù)據(jù)的符合程度。這種思想就稱為交叉驗(yàn)證（Cross Validation）
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
scores = cross_val_score(model, X=train_X, y=train_y, verbose=1, cv = 5, scoring=make_scorer(log_transfer(mean_absolute_error)))
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 1.1s finished
使用線性回歸模型沿腰，對(duì)未處理標(biāo)簽的特征數(shù)據(jù)進(jìn)行五折交叉驗(yàn)證（Error 1.36）
print('AVG:', np.mean(scores))
AVG: 1.3641908155886227
使用線性回歸模型览徒，對(duì)處理過標(biāo)簽的特征數(shù)據(jù)進(jìn)行五折交叉驗(yàn)證（Error 0.19）
scores = cross_val_score(model, X=train_X, y=train_y_ln, verbose=1, cv = 5, scoring=make_scorer(mean_absolute_error))
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 1.1s finished
print('AVG:', np.mean(scores))
AVG: 0.19382863663604424
scores = pd.DataFrame(scores.reshape(1,-1))
scores.columns = ['cv' + str(x) for x in range(1, 6)]
scores.index = ['MAE']
scores
4.4.2 - 3 模擬真實(shí)業(yè)務(wù)情況
但在事實(shí)上，由于我們并不具有預(yù)知未來的能力颂龙，五折交叉驗(yàn)證在某些與時(shí)間相關(guān)的數(shù)據(jù)集上反而反映了不真實(shí)的情況习蓬。通過2018年的二手車價(jià)格預(yù)測(cè)2017年的二手車價(jià)格，這顯然是不合理的措嵌，因此我們還可以采用時(shí)間順序?qū)?shù)據(jù)集進(jìn)行分隔躲叼。在本例中，我們選用靠前時(shí)間的4/5樣本當(dāng)作訓(xùn)練集企巢，靠后時(shí)間的1/5當(dāng)作驗(yàn)證集枫慷，最終結(jié)果與五折交叉驗(yàn)證差距不大
import datetime
sample_feature = sample_feature.reset_index(drop=True)
split_point = len(sample_feature) // 5 * 4
train = sample_feature.loc[:split_point].dropna()
val = sample_feature.loc[split_point:].dropna()
train_X = train[continuous_feature_names]
train_y_ln = np.log(train['price'] + 1)
val_X = val[continuous_feature_names]
val_y_ln = np.log(val['price'] + 1)
model = model.fit(train_X, train_y_ln)
mean_absolute_error(val_y_ln, model.predict(val_X))
0.19443858353490887
4.4.2 - 4 繪制學(xué)習(xí)率曲線與驗(yàn)證曲線
from sklearn.model_selection import learning_curve, validation_curve
? learning_curve
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,n_jobs=1, train_size=np.linspace(.1, 1.0, 5 )):
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel('Training example')
plt.ylabel('score')
train_sizes, train_scores, test_scores = learning_curve(estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_size, scoring = make_scorer(mean_absolute_error))
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
plt.grid()#區(qū)域
plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
train_scores_mean + train_scores_std, alpha=0.1,
color="r")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
test_scores_mean + test_scores_std, alpha=0.1,
color="g")
plt.plot(train_sizes, train_scores_mean, 'o-', color='r',
label="Training score")
plt.plot(train_sizes, test_scores_mean,'o-',color="g",
label="Cross-validation score")
plt.legend(loc="best")
return plt
plot_learning_curve(LinearRegression(), 'Liner_model', train_X[:1000], train_y_ln[:1000], ylim=(0.0, 0.5), cv=5, n_jobs=1)
output_53_1.png
4.4.3 多種模型對(duì)比
train = sample_feature[continuous_feature_names + ['price']].dropna()
train_X = train[continuous_feature_names]
train_y = train['price']
train_y_ln = np.log(train_y + 1)
4.4.3 - 1 線性模型 & 嵌入式特征選擇
本章節(jié)默認(rèn)，學(xué)習(xí)者已經(jīng)了解關(guān)于過擬合浪规、模型復(fù)雜度或听、正則化等概念。否則請(qǐng)尋找相關(guān)資料或參考如下連接：
- 用簡(jiǎn)單易懂的語言描述「過擬合 overfitting」笋婿？ https://www.zhihu.com/question/32246256/answer/55320482
- 模型復(fù)雜度與模型的泛化能力 http://yangyingming.com/article/434/
- 正則化的直觀理解 https://blog.csdn.net/jinping_shi/article/details/52433975
在過濾式和包裹式特征選擇方法中誉裆，特征選擇過程與學(xué)習(xí)器訓(xùn)練過程有明顯的分別。而嵌入式特征選擇在學(xué)習(xí)器訓(xùn)練過程中自動(dòng)地進(jìn)行特征選擇缸濒。嵌入式選擇最常用的是L1正則化與L2正則化足丢。在對(duì)線性回歸模型加入兩種正則化方法后，他們分別變成了嶺回歸與Lasso回歸庇配。
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
models = [LinearRegression(),
Ridge(),
Lasso()]
result = dict()
for model in models:
model_name = str(model).split('(')[0]
scores = cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error))
result[model_name] = scores
print(model_name + ' is finished')
LinearRegression is finished
Ridge is finished
Lasso is finished
對(duì)三種方法的效果對(duì)比
result = pd.DataFrame(result)
result.index = ['cv' + str(x) for x in range(1, 6)]
result
model = LinearRegression().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)
intercept:23.515984499017883
output_64_2.png
L2正則化在擬合過程中通常都傾向于讓權(quán)值盡可能小斩跌，最后構(gòu)造一個(gè)所有參數(shù)都比較小的模型。因?yàn)橐话阏J(rèn)為參數(shù)值小的模型比較簡(jiǎn)單捞慌，能適應(yīng)不同的數(shù)據(jù)集耀鸦，也在一定程度上避免了過擬合現(xiàn)象⌒ピ瑁可以設(shè)想一下對(duì)于一個(gè)線性回歸方程揭糕，若參數(shù)很大萝快，那么只要數(shù)據(jù)偏移一點(diǎn)點(diǎn)，就會(huì)對(duì)結(jié)果造成很大的影響著角；但如果參數(shù)足夠小揪漩，數(shù)據(jù)偏移得多一點(diǎn)也不會(huì)對(duì)結(jié)果造成什么影響，專業(yè)一點(diǎn)的說法是『抗擾動(dòng)能力強(qiáng)』
model = Ridge().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)
intercept:5.901527844424091
output_66_2.png
L1正則化有助于生成一個(gè)稀疏權(quán)值矩陣吏口，進(jìn)而可以用于特征選擇奄容。如下圖，我們發(fā)現(xiàn)power與userd_time特征非常重要产徊。
model = Lasso().fit(train_X, train_y_ln)
print('intercept:'+ str(model.intercept_))
sns.barplot(abs(model.coef_), continuous_feature_names)
intercept:8.674427764003347
output_68_2.png
除此之外昂勒，決策樹通過信息熵或GINI指數(shù)選擇分裂節(jié)點(diǎn)時(shí)，優(yōu)先選擇的分裂特征也更加重要舟铜，這同樣是一種特征選擇的方法戈盈。XGBoost與LightGBM模型中的model_importance指標(biāo)正是基于此計(jì)算的
4.4.3 - 2 非線性模型
除了線性模型以外，還有許多我們常用的非線性模型如下谆刨，在此篇幅有限不再一一講解原理塘娶。我們選擇了部分常用模型與線性模型進(jìn)行效果比對(duì)。
from sklearn.linear_model import LinearRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.neural_network import MLPRegressor
from xgboost.sklearn import XGBRegressor
from lightgbm.sklearn import LGBMRegressor
models = [LinearRegression(),
DecisionTreeRegressor(),
RandomForestRegressor(),
GradientBoostingRegressor(),
MLPRegressor(solver='lbfgs', max_iter=100),
XGBRegressor(n_estimators = 100, objective='reg:squarederror'),
LGBMRegressor(n_estimators = 100)]
result = dict()
for model in models:
model_name = str(model).split('(')[0]
scores = cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error))
result[model_name] = scores
print(model_name + ' is finished')
LinearRegression is finished
DecisionTreeRegressor is finished
RandomForestRegressor is finished
GradientBoostingRegressor is finished
MLPRegressor is finished
XGBRegressor is finished
LGBMRegressor is finished
result = pd.DataFrame(result)
result.index = ['cv' + str(x) for x in range(1, 6)]
result
可以看到隨機(jī)森林模型在每一個(gè)fold中均取得了更好的效果
4.4.4 模型調(diào)參
在此我們介紹了三種常用的調(diào)參方法如下：
- 貪心算法 http://www.reibang.com/p/ab89df9759c8
- 網(wǎng)格調(diào)參 https://blog.csdn.net/weixin_43172660/article/details/83032029
- 貝葉斯調(diào)參 https://blog.csdn.net/linxid/article/details/81189154
## LGB的參數(shù)集合：
objective = ['regression', 'regression_l1', 'mape', 'huber', 'fair']
num_leaves = [3,5,10,15,20,40, 55]
max_depth = [3,5,10,15,20,40, 55]
bagging_fraction = []
feature_fraction = []
drop_rate = []
4.4.4 - 1 貪心調(diào)參
best_obj = dict()
for obj in objective:
model = LGBMRegressor(objective=obj)
score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
best_obj[obj] = score
best_leaves = dict()
for leaves in num_leaves:
model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0], num_leaves=leaves)
score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
best_leaves[leaves] = score
best_depth = dict()
for depth in max_depth:
model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0],
num_leaves=min(best_leaves.items(), key=lambda x:x[1])[0],
max_depth=depth)
score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
best_depth[depth] = score
sns.lineplot(x=['0_initial','1_turning_obj','2_turning_leaves','3_turning_depth'], y=[0.143 ,min(best_obj.values()), min(best_leaves.values()), min(best_depth.values())])
output_82_1.png
4.4.4 - 2 Grid Search 調(diào)參
from sklearn.model_selection import GridSearchCV
parameters = {'objective': objective , 'num_leaves': num_leaves, 'max_depth': max_depth}
model = LGBMRegressor()
clf = GridSearchCV(model, parameters, cv=5)
clf = clf.fit(train_X, train_y)
clf.best_params_
{'max_depth': 15, 'num_leaves': 55, 'objective': 'regression'}
model = LGBMRegressor(objective='regression',
num_leaves=55,
max_depth=15)
np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
0.13626164479243302
4.4.4 - 3 貝葉斯調(diào)參
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)
}
)
rf_bo.maximize()
1 - rf_bo.max['target']
0.1296693644053145
總結(jié)
在本章中痊夭，我們完成了建模與調(diào)參的工作刁岸，并對(duì)我們的模型進(jìn)行了驗(yàn)證。此外她我，我們還采用了一些基本方法來提高預(yù)測(cè)的精度虹曙，提升如下圖所示。
plt.figure(figsize=(13,5))
sns.lineplot(x=['0_origin','1_log_transfer','2_L1_&_L2','3_change_model','4_parameter_turning'], y=[1.36 ,0.19, 0.19, 0.14, 0.13])
output_97_1.png
