sklearn机器学习之SVM样本均衡以及ROC与AUC

1.导入相应包

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs

2.准备数据集

#样本数
class_1 = 500
class_2 = 50
#这里设置了特征数
centers = [[0, 0], [2, 2]]
clusters_std = [1.5, 0.5]
X, y = make_blobs(n_samples=[class_1, class_2], centers=centers, cluster_std=clusters_std, random_state=0, shuffle=False)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap='rainbow', s=10)

绘制散点图如下：

3.设置class_weight对比

clf = svm.SVC(kernel='linear', C=1.0)
clf.fit(X, y)

wclf = svm.SVC(kernel='linear', class_weight={1:10})
wclf.fit(X, y)
clf.score(X, y)
wclf.score(X, y)

clf和wclf的精度分别为0.94和0.91

4.绘制两者决策边界

#首先要有数据分布
plt.figure(figsize=(6,5))
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="rainbow",s=10)
ax = plt.gca() #获取当前的子图，如果不存在，则创建新的子图
xlim = ax.get_xlim()
ylim = ax.get_ylim()
XX = np.linspace(xlim[0], xlim[1], 30)
YY = np.linspace(ylim[0], ylim[1], 30)
#这里不懂可以看上篇博客
XX, YY = np.meshgrid(XX, YY)
xy = np.vstack([XX.ravel(), YY.ravel()]).T

Z_clf = clf.decision_function(xy).reshape(XX.shape)
a = ax.contour(XX, YY, Z_clf, levels=[0], colors='k', alpha=0.5, linestyles=['-'])

Z_wclf = wclf.decision_function(xy).reshape(XX.shape)
b = ax.contour(XX, YY, Z_wclf, levels=[0], colors='red', alpha=0.5, linestyles=['-'])
#设置图例这里collections[0]为一条线的对象
plt.legend([a.collections[0], b.collections[0]], ['non weighted', 'weighted'], loc='upper right')

绘制图像如下：

5.判定概率

准备数据集

class_1_ = 7
class_2_ = 4
centers_ = [[0.0, 0.0], [1,1]]
clusters_std = [0.5, 1]
X_, y_ = make_blobs(n_samples=[class_1_, class_2_],
                  centers=centers_,
                  cluster_std=clusters_std,
                  random_state=0, shuffle=False)
plt.scatter(X_[:, 0], X_[:, 1], c=y_, cmap="rainbow",s=30)

绘制散点图如下：

6.逻辑斯蒂回归获得概率

from sklearn.linear_model import LogisticRegression as LR
clf_lo = LR().fit(X_, y_)
prob = clf_lo.predict_proba(X_)
import pandas as pd
prob = pd.DataFrame(prob)
#判定为0和判定为1的概率
prob.columns = ['0', '1']
prob

7.通过概率分类

#以0.5为阈值
for i in range(prob.shape[0]):
    if prob.loc[i, "1"] > 0.5:
        prob.loc[i, "pred"] = 1
    else:
        prob.loc[i, "pred"] = 0
prob["y_true"] = y_
prob = prob.sort_values(by='1', ascending=False)
prob

8.获得混淆矩阵

from sklearn.metrics import confusion_matrix as CM, precision_score as P, recall_score as R
CM(prob.loc[:, "y_true"], prob.loc[:, 'pred'], labels=[1, 0])

9.获得精准度和召回率

P(prob.loc[:, "y_true"], prob.loc[:, 'pred'], labels=[1, 0])
R(prob.loc[:, "y_true"], prob.loc[:, 'pred'], labels=[1, 0])

10.SVM中获得概率probability参数设置

clf_proba = svm.SVC(kernel="linear", C=1.0, probability=True).fit(X, y)
clf_proba.predict_proba(X)

11.绘制曲线ROC曲线

#开始绘图
recall = []
FPR = []
probrange = np.linspace(clf_proba.predict_proba(X)[:,1].min(), clf_proba.predict_proba(X)[:,1].max(), num=50, endpoint=False)
for i in probrange:
    y_predict = []
    for j in range(X.shape[0]):
        if clf_proba.predict_proba(X)[j,1] > i:
            y_predict.append(1)
        else:
            y_predict.append(0)
    cm = CM(y, y_predict,labels=[1,0])
    recall.append(cm[0, 0] / cm[0, :].sum())
    FPR.append(cm[1, 0] / cm[1, :].sum())
recall.sort()
FPR.sort()
plt.plot(FPR, recall, c="red")
plt.plot(probrange+0.05, probrange+0.05, c="black", linestyle="--")
plt.show()

绘制曲线如下：

12.快捷计算

from sklearn.metrics import roc_curve
FPR, recall, threshold = roc_curve(y, clf_proba.decision_function(X), pos_label=1)
#计算AUC面积
from sklearn.metrics import roc_auc_score
area = roc_auc_score(y, clf_proba.decision_function(X))
area

输出面积为0.97