sklearn作为机器学习中一个强大的算法包,内置了许多经典的回归算法。
线性回归
线性回归拟合一个带系数的线性模型,以最小化数据中的观测值与线性预测值之间的残差平方和。
#X_train,X_test二维, y_train一维
#加载线性模型算法库
from sklearn import linear_model
# 创建线性回归模型的对象
regr = linear_model.LinearRegression()
# 利用训练集训练线性模型
regr.fit(X_train, y_train)
# 使用测试集做预测
y_pred = regr.predict(X_test)
KNN回归
在数据标签是连续变量而不是离散变量的情况下,可以使用KNN回归。分配给查询点的标签是根据其最近邻居标签的平均值计算的。
from sklearn.neighbors import KNeighborsRegressor
neigh = KNeighborsRegressor(n_neighbors=2)
neigh.fit(X_train, y_train)
y_pred=neigh.predict(X_test)
决策树回归
决策树也可以应用于回归问题
from sklearn.tree import DecisionTreeRegressor
clf = DecisionTreeRegressor()
clf = clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
随机森林回归
from sklearn.ensemble import RandomForestRegressor
regr = RandomForestRegressor(max_depth=2, random_state=0,
n_estimators=100)
regr.fit(X_train, y_train)
pred = regr.predict(X_test)
XGBoost回归
基本所有的机器学习比赛的冠军方案都使用了XGBoost算法
import xgboost as xgb
xgb_model = xgb.XGBRegressor(max_depth = 3,
learning_rate = 0.1,
n_estimators = 100,
objective = 'reg:linear',
n_jobs = -1)
xgb_model.fit(X_train, y_train,
eval_set=[(X_train, y_train)],
eval_metric='logloss',
verbose=100)
y_pred = xgb_model.predict(X_test)
支持向量回归
from sklearn.svm import SVR
#创建SVR回归模型的对象
clf = SVR()
# 利用训练集训练SVR回归模型
clf.fit(X_train, y_train)
"""
SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1,
gamma='auto_deprecated', kernel='rbf', max_iter=-1, shrinking=True,
tol=0.001, verbose=False)
"""
clf.predict(X_test)
神经网络
from sklearn.neural_network import MLPRegressor
mlp=MLPRegressor()
mlp.fit(X_train,y_train)
"""
MLPRegressor(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,
beta_2=0.999, early_stopping=False, epsilon=1e-08,
hidden_layer_sizes=(100,), learning_rate='constant',
learning_rate_init=0.001, max_iter=200, momentum=0.9,
n_iter_no_change=10, nesterovs_momentum=True, power_t=0.5,
random_state=None, shuffle=True, solver='adam', tol=0.0001,
validation_fraction=0.1, verbose=False, warm_start=False)
"""
y_pred = mlp.predict(X_test)
LightGBM回归
LightGBM作为另一个使用基于树的学习算法的梯度增强框架。相比于XGBoost,LightGBM有如下优点,训练速度更快,效率更高效;低内存的使用量。
import lightgbm as lgb
gbm = lgb.LGBMRegressor(num_leaves=31,
learning_rate=0.05,
n_estimators=20)
gbm.fit(X_train, y_train,
eval_set=[(X_train, y_train)],
eval_metric='logloss',
verbose=100)
y_pred = gbm.predict(X_test)
岭回归
岭回归通过对系数进行惩罚(L2范式)来解决普通最小二乘法的一些问题,例如,当特征之间完全共线性(有解)或者说特征之间高度相关,这个时候适合用岭回归。
from sklearn.linear_model import Ridge
# 创建岭回归模型的对象
reg = Ridge(alpha=.5)
# 利用训练集训练岭回归模型
reg.fit(X_train, y_train)
pred= reg.predict(X_test)
Lasso回归
Lasso是一个估计稀疏稀疏的线性模型。它在某些情况下很有用,由于它倾向于选择参数值较少的解,有效地减少了给定解所依赖的变量的数量。Lasso模型在最小二乘法的基础上加入L1范式作为惩罚项。
from sklearn.linear_model import Lasso
# 创建Lasso回归模型的对象
reg = Lasso(alpha=0.1)
# 利用训练集训练Lasso回归模型
reg.fit(X_train, y_train)
"""
Lasso(alpha=0.1, copy_X=True, fit_intercept=True, max_iter=1000,
normalize=False, positive=False, precompute=False, random_state=None,
selection='cyclic', tol=0.0001, warm_start=False)
"""
# 使用测试集做预测
pred=reg.predict(X_test)
Elastic Net回归
Elastic Net 是一个线性模型利用L1范式和L2范式共同作为惩罚项。这种组合既可以学习稀疏模型,同时可以保持岭回归的正则化属性.
from sklearn.linear_model import ElasticNet
#创建ElasticNet回归模型的对象
regr = ElasticNet(random_state=0)
# 利用训练集训练ElasticNet回归模型
regr.fit(X_train, y_train)
pred=regr.predict(X_test)
SGD回归
SGD回归也是一种线性回归, 它通过随机梯度下降最小化正则化经验损失.
import numpy as np
from sklearn import linear_model
n_samples, n_features = 10, 5
np.random.seed(0)
clf = linear_model.SGDRegressor(max_iter=1000, tol=1e-3)
clf.fit(X_train, y_train)
pred=clf.predict(X_test)
"""
SGDRegressor(alpha=0.0001, average=False, early_stopping=False,
epsilon=0.1, eta0=0.01, fit_intercept=True, l1_ratio=0.15,
learning_rate='invscaling', loss='squared_loss', max_iter=1000,
n_iter=None, n_iter_no_change=5, penalty='l2', power_t=0.25,
random_state=None, shuffle=True, tol=0.001, validation_fraction=0.1,
verbose=0, warm_start=False)
"""
回归竞赛问题以及解决方案
入门级比赛:
Kaggle——房价预测
这个比赛作为最基础的回归问题之一,很适合入门机器学习的小伙伴们。
网址:https://www.kaggle.com/c/house-prices-advanced-regression-techniques
经典解决方案:
XGBoost解决方案: https://www.kaggle.com/dansbecker/xgboost
Lasso解决方案: https://www.kaggle.com/mymkyt/simple-lasso-public-score-0-12102
进阶比赛:
Kaggle——销售量预测
这个比赛作为经典的时间序列问题之一,目标是为了预测下个月每种产品和商店的总销售额。
网址:https://www.kaggle.com/c/competitive-data-science-predict-future-sales
经典解决方案:
LightGBM: https://www.kaggle.com/sanket30/predicting-sales-using-lightgbm
XGBoost: https://www.kaggle.com/fabianaboldrin/eda-xgboost
第一名解决方案:https://www.kaggle.com/c/competitive-data-science-predict-future-sales/discussion/74835#latest-503740
TOP比赛方案:
Kaggle——餐厅访客预测
网址:https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting
解决方案:
1st 方案: https://www.kaggle.com/plantsgo/solution-public-0-471-private-0-505
7th 方案:https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting/discussion/49259#latest-284437
8th 方案:https://github.com/MaxHalford/kaggle-recruit-restaurant
12th 方案:https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting/discussion/49251#latest-282765
Kaggle——CorporaciónFavoritaGrocery销售预测
网址:https://www.kaggle.com/c/favorita-grocery-sales-forecasting
解决方案:
1st 方案: https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47582#latest-360306
2st 方案:https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47568#latest-278474
3st 方案:https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47560#latest-302253
4st 方案:https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47529#latest-271077
5st方案:https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47556#latest-270515
6st方案:https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47575#latest-269568