python+sklearn做支持向量机多元化分类

本文所用文件的链接

链接：https://pan.baidu.com/s/1RWNVHuXMQleOrEi5vig_bQ
提取码：p57s

支持向量机也可以做多元分类.

案例: 交通流量预测(回归)

支持向量机也可以做回归业务. traffic.txt

"""
支持向量机
"""
import numpy as np
import sklearn.preprocessing as sp
import sklearn.model_selection as ms
import sklearn.svm as svm
import sklearn.metrics as sm

class DigitEncoder():

    def fit_transform(self, y):
        return y.astype(int)

    def transform(self, y):
    	return y.astype(int)

    def inverse_transform(self, y):
    	return y.astype(str)

data = np.loadtxt('../ml_data/traffic.txt', 
	delimiter=',', dtype='U20')
data = data.T
encoders, x = [], []
for row in range(len(data)):
	if data[row][0].isdigit():
		encoder = DigitEncoder()
	else:
		encoder = sp.LabelEncoder()
	encoders.append(encoder)
	# 整理输入集
	if row < len(data)-1:
		x.append(
			encoder.fit_transform(data[row]))
	else:
		y = encoder.fit_transform(data[row])
# 整理数据集
x = np.array(x).T
# 拆分测试集 训练集 
train_x, test_x, train_y, test_y = \
    ms.train_test_split(x, y, test_size=0.25, 
	random_state=7)
# 创建模型, 模型训练
model = svm.SVR(kernel='rbf', C=10)
model.fit(train_x, train_y)
pred_test_y = model.predict(test_x)
print(sm.r2_score(test_y, pred_test_y))

# 结果预测
data=[['Tuesday','13:35','San Francisco','yes']]
data = np.array(data).T

x = []
for row in range(len(data)):
	encoder = encoders[row]
	x.append(encoder.transform(data[row]))
x = np.array(x).T
pred_y = model.predict(x)
print(int(pred_y))

输出结果：

0.6478692163198654
22