# 分类算法

1.KNN

from sklearn.neighbors import KNeighborsClassifier

2.朴素贝叶斯

from sklearn.naive_bayes import BernoulliNB  # 特征值是二分类
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB

3.逻辑回归【二分类】

from sklearn.linear_model import LogisticRegression

4.决策树

from sklearn.tree import DecisionTreeClassifier

5.随机森林

from sklearn.ensemble import RandomForestClassifier

6.XGboost【极端的梯度提升树】

from xgboost import XGBClassifier

# 回归算法

1.KNN

from sklearn.neighbors import KNeighborsRegressor

2. 线性回归

from sklearn.linear_model import LinearRegression  # 正规方程解法
from sklearn.linear_model import SGDRegressor  # 随机梯度下降
from sklearn.linear_model import Ridge  # 岭回归【L2，趋近于0】
from sklearn.linear_model import Lasso  # 套索回归【L1, 等于0】

3.决策树

from sklearn.tree import DecisionTreeRegressor

4.随机森林

from sklearn.ensemble import RandomForestRegressor

5.XGBoost【极端的梯度提升树】

from xgboost import XGBRegressor

# 聚类算法[聚类不仅仅只有一个]

1. k-means

from sklearn.cluster import KMeans

# 交叉验证

from sklearn.model_selection import cross_val_score  # 交叉验证得分
from sklearn.model_selection import GridSearchCV  # 网络搜索
from sklearn.model_selection import KFold  # K折交叉验证
from sklearn.model_selection import StratifiedKFold# 等比例K折交叉验证（仅分类有等比例）
from sklearn.model_selection import ShuffleSplit # 随机分
from sklearn.model_selection import StratifiedShuffleSplit# 等比例随机分
from sklearn.model_selection import RepeatedKFold # P次K折交叉验证
from sklearn.model_selection import LeaveOneOut # 留一法
from sklearn.model_selection import LeavePOut# 留P法
from sklearn.model_selection import GroupKFold # 分组的K折交叉验证
from sklearn.model_selection import LeaveOneGroupOut# 留一组法
from sklearn.model_selection import LeavePGroupsOutt# 留P组法
from sklearn.model_selection import GroupShuffleSplit# 随机分组

# 特征和标签处理

1. 数据拆分

# 分类算法有stratify参数，回归算法没有
X_train, X_test, y_train, y_test = train_test_split(
    X,  # 整个数据集的特征
    y,  # 整个数据集的标签
    test_size=0.2,  # 分多少数据给测试集；20%的数据集作为测试集
    # train_size=0.8, # 新版本建议使用test_size,
    random_state=1,  # 随机拆分
    stratify=y,  # 分层, 拆分后和拆分前的类别比例一致
)

2. 数据标准化

from sklearn.preprocessing import MaxAbsScaler # 小数标准化
from sklearn.preprocessing import MinMaxScaler # 离差标准化
from sklearn.preprocessing import StandardScaler  #标准差标准化

3. 特征多项式处理【x--> 0 x x**2】

from sklearn.preprocessing import PolynomialFeatures

4. 将类别类型特征 转换为数值特征 【比如转换 female male  ===> 0 1】

X["部门"] = X["部门"].astype('category').cat.codes
name=df["部门"].astype('category').cat.categories

5. 将文本转换为特征

from sklearn.feature_extraction.text import CountVectorizer  # 词频向量化
from sklearn.feature_extraction.text import TfidfVectorizer  # TF-IDF向量化

6. 主成分分析 降维

from sklearn.decomposition import PCA

# 评估

1. 分类算法

from sklearn.metrics import accuracy_score  # 准确率
from sklearn.metrics import recall_score  # 查全率【召回率】
from sklearn.metrics import precision_score  # 查准率[精确率]
from sklearn.metrics import f1_score  # F1-score
from sklearn.metrics import plot_precision_recall_curve  # PR曲线
from sklearn.metrics import plot_roc_curve  # ROC和AUC指标
from sklearn.metrics import classification_report  # 分类报告
from sklearn.metrics import confusion_matrix # 混淆矩阵

2.聚类算法

from sklearn.metrics import silhouette_score  # 轮廓系数

3. 回归算法

from sklearn.metrics import r2_score  # [R2]
from sklearn.metrics import mean_squared_error  # [mse]
from sklearn.metrics import mean_absolute_error  # [mae]
# RMSE,需要根据mse计算