# 数据集的切分，交叉验证，网格搜索
from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV

# 数据集的预处理，归一化，标准化, PCA, 编码, 独热编码
from sklearn.preprocessing import MinMaxScaler, StandardScaler, OrdinalEncoder, OneHotEncoder
from sklearn.decomposition import PCA

# 空缺值的填充
from sklearn.impute import SimpleImputer

# 第一周算法, KNN, KMeans, 分类树，回归树
from sklearn.neighbors import KNeighborsClassifier
from sklearn.cluster import KMeans
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor

# 第二周算法，线性回归，RIdge, Lasso, ElasticNet, 逻辑回归, 贝叶斯包(一般用的不多)
from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet, LogisticRegression
from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB

# 第三周算法, 随机森林,Adaboost,梯度提升,XGBOOST, SVM
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor, AdaBoostClassifier, AdaBoostRegressor
from sklearn.ensemble import GradientBoostingClassifier, GradientBoostingRegressor
from xgboost import XGBClassifier, XGBRFRegressor
from sklearn.svm import SVC

# 评估指标
# 分类, 二分类优先使用roc_auc_score
from sklearn.metrics import accuracy_score,recall_score,precision_score,f1_score,roc_auc_score

# 回归
from sklearn.metrics import r2_score, mean_squared_error


from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split