scikit-learn常用库与函数整理

需要提前导入的库：

numpy

import numpy as np

绘图

import matplotlib.pyplot as plt

数据集

from sklearn import datasets

各种机器学习库：

kNN算法

from sklearn.neighbors import KNeighborsClassifier

线性回归

from sklearn.linear_model import LinearRegression

PCA

from sklearn.decomposition import PCA
pca = PCA(n_components=2)
pca.fit(X_train)
X_train_reduction = pca.transform(X_train)
X_test_reduction = pca.transform(X_test)

逻辑回归

from sklearn.linear_model import LogisticRegression

SVM

from sklearn.svm import LinearSVC

使用多项式核函数的SVM

from sklearn.svm import SVC
SVC(kernel='poly', degree=degree, C=C)

SVM解决回归问题

from sklearn.svm import LinearSVR

OvO

log_reg = LogisticRegression(multi_class='multinomial', solver='newton-cg')

 OvR

from sklearn.multiclass import OneVsRestClassifier
ovr = OneVsRestClassifier(log_reg)

决策树

from sklearn.tree import DecisionTreeClassifier

解决回归问题的决策树

from sklearn.tree import DecisionTreeRegressor

集成学习

from sklearn.ensemble import VotingClassifier

Bagging

from sklearn.ensemble import BaggingClassifier

随机森林

from sklearn.ensemble import RandomForestClassifier

数据处理方法：

train_test_split

from sklearn.model_selection import train_test_split

计算准确度

from sklearn.metrics import accuracy_score

网格搜索

from sklearn.model_selection import GridSearchCV
param_grid = [
 { 'weights':['uniform'],  'n_neighbors':[i for i in range(1, 11)]},
{ 'weights':['distance'], 'n_neighbors':[i for i in range(1, 11)],'p':[i for i in range(1, 6)]}
]
knn_clf = KNeighborsClassifier()
grid_search = GridSearchCV(knn_clf, param_grid)
grid_search.fit(X_train, y_train)

均值方差归一化

from sklearn.preprocessing import StandardScaler
standardScaler = StandardScaler()
standardScaler.fit(X_train)

MSE

from sklearn.metrics import mean_squared_error

MAE

from sklearn.metrics import mean_absolute_error

R Square

from sklearn.metrics import r2_score

添加多项式特征

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2) # 添加二次幂特征​
poly.fit(X)
X2 = poly.transform(X)

Pipeline

from sklearn.pipeline import Pipeline
# 传入每一步骤所对应的类 1.多项式的特征 2.数据归一化 3.线性回归
poly_reg = Pipeline([
 ("poly", PolynomialFeatures(degree=2)),
 ("std_scaler", StandardScaler()),
 ("lin_reg", LinearRegression())
])
poly_reg.fit(X, y)
y_predict = poly_reg.predict(X)

交叉验证

from sklearn.model_selection import cross_val_score

岭回归

from sklearn.linear_model import Ridge

LASSO

from sklearn.linear_model import Lasso

绘制决策边界

def plot_decision_boundary(model, axis):
x0, x1 = np.meshgrid(
 np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1,1),
np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1,1)
）
X_new = np.c_[x0.ravel(), x1.ravel()]
 
y_predict = model.predict(X_new)
zz = y_predict.reshape(x0.shape)

from matplotlib.colors import ListedColormap
custom_cmap = ListedColormap(['#EF9A9A', '#FFF59D','#90CAF9'])

plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)

混淆矩阵

from sklearn.metrics import confusion_matrix

精准率

from sklearn.metrics import precision_score

召回率

from sklearn.metrics import recall_score

F1 Score

from sklearn.metrics import f1_score

ROC

from sklearn.metrics import roc_curve

ROC_SCORE

from sklearn.metrics import roc_auc_score