sklearn常用算法API

常用接口

from sklearn import datasets
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.preprocessing import StandardScaler
from sklearn.feature_selection import VarianceThreshold
from sklearn.decomposition import PCA
from sklearn.neighbors import KNeighborsClassifier
from scipy.stats import pearsonr

KNN K近邻算法

sklearn.neighbors.KNeighborsClassifier分类器

from sklearn.neighbors import KNeighborsClassifier
k = KNeighborsClassifier(n_neighbors=3,)

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
iris = datasets.load_iris()
x_train,x_test,y_train,y_test = train_test_split(iris.data,iris.target,train_size=0.7,random_state=0)
s =StandardScaler()
x_train = s.fit_transform(x_train)
x_test = s.transform(x_test)
k = KNeighborsClassifier(n_neighbors=5)
k.fit(x_train,y_train)
test = k.predict(x_test)
print(test == y_test)
score = k.score(x_test,y_test)
print(score)

模型选择–交叉验证与网格搜索

sklearn.model_selection.GridSearchCV

from sklearn.model_selection import GridSearchCV

k = KNeighborsClassifier()
new_k = GridSearchCV(k,param_grid={'n_neighbors':range(1,5)},cv=5)
new_k.fit(x_train,y_train)

sklearn用GridSearchCV对预估器进行封装，返回新的预估器对象，用法和原始的一样。用GridSearchCV返回新的预估器，有新的属性，如最佳得分，最佳参数等

朴素贝叶斯

决策树与随机森林

from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier

DecisionTreeClassifier分类器参数：

RandomForestClassifier随机森林分类器参数： 

线性回归