結合實用資料分析該書，整理了下程式碼，記錄以作備忘和分享：

注：其中用到mlpy（機器學習庫）,安裝會出現問題，可參考文末引用文章的處理方法。

  1 # -*- coding: utf-8 -*-
  2 """
  3 Created on Wed Oct 17 21:14:44 2018
  4 
  5 @author: Luove
  6 """
  7 # KRR適合分類和迴歸訓練集很少時，非線性方法
  8 import os
  9 import numpy as np
 10 import matplotlib.pyplot as plt
 11 import dateutil.parser as dparser  #
 
 dateutil模組主要有兩個函式，parser和rrule。parser是根據字串解析成datetime，而rrule是則是根據定義的規則來生成datetime;https://blog.csdn.net/cherdw/article/details/55224341
 12 from pylab import *  # 將matplotlib和numpy封裝在一起，模擬MATLAB程式設計環境
 13 from sklearn.cross_validation import train_test_split
 14 from sklearn import linear_model
 15 from sklearn import
 
 datasets
 16 import mlpy
 17 from mlpy import KernelRidge
 18 
 19 # np.hamming 漢明窗，構造一個函式（僅處理窗內資料）。這個函式在某一區間有非零值，而在其餘區間皆為0.漢明窗就是這樣的一種函式
 20 # 階梯圖，又叫瀑布圖，可以用於企業成本、銷售等資料的變化和構成情況的分析；plot.step()
 21 x1 = np.linspace(1,100,500)
 22 x2 = np.linspace(1,100,50)
 23 y1 = np.cos(x1)
 24 y2 = np.cos(x2)
 25 
 26 axs1 = plt.subplot(211)
 
 27 axs2 = plt.subplot(212)
 28 axs1.step(x1,y1)
 29 axs2.step(x2,y2)
 30 plt.show()
 31 
 32 
 33 goldfile = "D:\Analyze\Python Matlab\Python\BookCodes\PDA_Book-master\PDA_Book-master\Chapter7\Gold.csv"
 34 # tsa,時間序列分析，將時間序列平滑化，（本身包含：趨勢T，季節性/週期性S，波動性V）
 35 def smooth(x,window_length):
 36     s = np.r_[2*x[0]-x[window_length-1::-1], x, 2*x[-1]-x[-1:-window_length:-1]]
 37     w = np.hamming(window_length)
 38     y = np.convolve(w/w.sum(), s, mode='same')  # 卷積函式，移動平均濾波（平滑方法）,第一個引數長度要大於等於第二引數長度，否則會交換位置；mode={'full','same','valid'}，預設full
 39     return y[window_length:-window_length+1]
 40 
 41 # 金價走勢,注意下面dtype變化：日期用object,值用None（各列內容識別，）
 42 x = np.genfromtxt(goldfile,dtype='object',delimiter=',',skip_header=1,usecols=(0),converters={0:dparser.parse})  # 第一列日期，dateutil.parser.parse,字串中解析出日期
 43 y = np.genfromtxt(goldfile,dtype=None,delimiter=',',skip_header=1,usecols=(1))  # 獲取第二列
 44 y_smoothed = smooth(y,len(y))
 45 plt.step(x,y,'r*',label='raw data')
 46 plt.step(x,y_smoothed,label='smoothed data')
 47 plt.legend()
 48 #x = [2,3,9,634,32,4,676,4,234,43,7,-13,0]
 49 #x = np.array(x)
 50 #np.round(smooth(x,len(x)))
 51 #[ 33.,  80., 124., 165., 189., 199., 192., 169., 137., 104.,  66., 35.,  16.]
 52 #plt.plot(x)
 53 #plt.plot(np.round(smooth(x,len(x))))  # 載入pylab,不必plt.show()?
 54 ##plt.show()
 55 #window_length=x.shape[0]
 56 
 57 house = datasets.load_boston()
 58 houseX = house.data[:,np.newaxis]  # 新增一個新軸，新增一維度，由(506, 13)轉成(506, 1，13)
 59 houseX_temp = houseX[:,:,2]
 60 
 61 x_train,xtest,ytrain,ytest=train_test_split(houseX_temp,house.target,test_size=1.0/3)
 62 lreg = linear_model.LinearRegression()
 63 lreg.fit(x_train,ytrain)
 64 plt.scatter(xtest,ytest,color='green')
 65 plt.plot(xtest,lreg.predict(xtest),color='blue',linewidth=2)
 66 
 67 np.random.seed(0)
 68 targetvalues = np.genfromtxt(goldfile,skip_header=1,dtype=None,delimiter=',',usecols=(1))  # usecols篩選感興趣列
 69 type(targetvalues)
 70 trainingpoints = np.arange(125).reshape(-1,1)  # transform ,轉換成一列，行自適應
 71 testpoint = np.arange(126).reshape(-1,1)
 72 knl = mlpy.kernel_gaussian(trainingpoints,trainingpoints,sigma=1)  # 訓練核矩陣,對稱半正定,(125, 125)
 73 knltest = mlpy.kernel_gaussian(testpoint,trainingpoints,sigma=1)  # 測試核矩陣,(126, 125)
 74 
 75 knlridge = KernelRidge(lmb=0.01)
 76 knlridge.learn(knl,targetvalues)
 77 resultpoints = knlridge.pred(knltest)
 78 
 79 fig = plt.figure(1)
 80 plt.plot(trainingpoints,targetvalues,'o') 
 81 plt.plot(testpoint,resultpoints)
 82 #plt.show()
 83 len(resultpoints)
 84 resultpoints[-5:-1]
 85 
 86 # 採用平滑後的資料,即smooth後的targetvalues
 87 targetvalues_smoothed = smooth(targetvalues,len(targetvalues))
 88 knlridge.learn(knl,targetvalues_smoothed)
 89 resultpoints_smoothed = knlridge.pred(knltest)
 90 plt.step(trainingpoints,targetvalues_smoothed,'o')
 91 plt.step(testpoint,resultpoints_smoothed)
 92 #plt.show()
 93 len(resultpoints_smoothed)
 94 resultpoints_smoothed[-5:-1]  # 平滑前126期預測值：1389.8;平滑後126期預測值1388.6
 95 #x = np.arange(0, 2, 0.05).reshape(-1, 1) # training points
 96 #y = np.ravel(np.exp(x)) + np.random.normal(1, 0.2, x.shape[0]) # target values
 97 #xt = np.arange(0, 2, 0.01).reshape(-1, 1) # testing points
 98 #K = mlpy.kernel_gaussian(x, x, sigma=1) # training kernel matrix
 99 #Kt = mlpy.kernel_gaussian(xt, x, sigma=1) # testing kernel matrix
100 #krr = KernelRidge(lmb=0.01)
101 #krr.learn(K, y)
102 #yt = krr.pred(Kt)
103 #fig = plt.figure(1)
104 #plot1 = plt.plot(x[:, 0], y, 'o')
105 #plot2 = plt.plot(xt[:, 0], yt)
106 #plt.show()

Ref:

Windows下Python模組-----mlpy（機器學習庫）的安裝（本文未按此操作，有用的可以給咱交流下啊）

pip安裝MLPY庫 （安裝推薦按此操作）

《實用資料分析》：文中資料及mlpy文件需要可自取：https://github.com/Luove/Data