数据来源于论文：Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal
预测方法：支持向量回归（Support Vector Regression）
代码如下：
# #############################################################################
# 声明需要用到的包
import numpy as np
import pandas as pd
import random
from sklearn.svm import SVR
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
%matplotlib inline
# #############################################################################
# 导入原始数据
rawData = pd.read_csv('raw_data.csv')
print("原始数据集大小：",rawData.shape)
rawData.head()
# #############################################################################
# 对所有数值类型的特征进行标准化处理
# 每一个因素的均值和方差都存储到 scaled_features 变量中。
quant_features = [ 'FC', 'Interaction_time', 'Saturation_pressure', 'Measured_UCS']
scaled_features = {}
for each in quant_features:
mean, std = rawData[each].mean(), rawData[each].std()
scaled_features[each] = [mean, std]
rawData.loc[:, each] = (rawData[each] - mean)/std
rawData.head()
# #############################################################################
# 转化为 numpy 数组
rawDataNP = rawData.values
rawDataNP[0:5,:]
完成了数据预处理过后，就可以开始进行回归预测了：
# #############################################################################
# 定义输入 输出
x=rawDataNP[:,0:3]
y=rawDataNP[:,4]
# 分割训练数据和测试数据
# 随机采样25%作为测试 75%作为训练
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=0)
线性核函数，预测结果：
# 线性核函数配置支持向量机
linear_svr = SVR(kernel="linear")
# 训练
linear_svr.fit(x_train, y_train)
# 预测 保存预测结果
linear_svr_y_predict = linear_svr.predict(x_test)
plt.plot(y_test)
plt.plot(linear_svr_y_predict)
plt.show()
线性核函数，预测结果
fig, ax = plt.subplots(figsize = (10, 7))
mean, std = scaled_features['Measured_UCS']
y = (y_test * std + mean).astype(float)
x = (linear_svr_y_predict * std + mean).astype(float)
poly = np.polyfit(x,y,deg=1)
z = np.polyval(poly, x)
ax.plot(x, y, 'o')
ax.plot(x, z,label='Linear Regression')
ax.legend()
ax.set_ylabel('Measured UCS')
ax.set_xlabel('Predicted UCS')
线性核函数，预测结果
多项式核函数，预测结果：
# 多项式核函数配置支持向量机
poly_svr = SVR(kernel='poly', C=100, gamma='auto', degree=3, epsilon=.1, coef0=1)
# 训练
poly_svr.fit(x_train, y_train)
# 预测 保存预测结果
poly_svr_y_predict = poly_svr.predict(x_test)
plt.plot(y_test)
plt.plot(poly_svr_y_predict)
plt.show()
多项式核函数，预测结果
fig, ax = plt.subplots(figsize = (10, 7))
mean, std = scaled_features['Measured_UCS']
y = (y_test * std + mean).astype(float)
x = (poly_svr_y_predict * std + mean).astype(float)
poly = np.polyfit(x,y,deg=1)
z = np.polyval(poly, x)
ax.plot(x, y, 'o')
ax.plot(x, z,label='Linear Regression')
ax.legend()
ax.set_ylabel('Measured UCS')
ax.set_xlabel('Predicted UCS')
多项式核函数，预测结果
径向基核函数，预测结果：
# 径向基核函数配置支持向量机
rbf_svr = SVR(kernel='rbf', C=100, gamma=0.1, epsilon=.1)
# 训练
rbf_svr.fit(x_train, y_train)
# 预测 保存预测结果
rbf_svr_y_predict = rbf_svr.predict(x_test)
plt.plot(y_test)
plt.plot(rbf_svr_y_predict)
plt.show()
径向基核函数，预测结果
fig, ax = plt.subplots(figsize = (10, 7))
mean, std = scaled_features['Measured_UCS']
y = (y_test * std + mean).astype(float)
x = (rbf_svr_y_predict * std + mean).astype(float)
poly = np.polyfit(x,y,deg=1)
z = np.polyval(poly, x)
ax.plot(x, y, 'o')
ax.plot(x, z,label='Linear Regression')
ax.legend()
ax.set_ylabel('Measured UCS')
ax.set_xlabel('Predicted UCS')
径向基核函数，预测结果
