GaussianHMM和ensemble.bagging的例程

import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn.linear_model import RidgeCV, LassoCV
from sklearn.model_selection import train_test_split
from sklearn.ensemble import BaggingRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
import pandas as pd
import csv


def f(x):
    return 0.5*np.exp(-(x+3) **2) + np.exp(-x**2) + + 0.5*np.exp(-(x-3) ** 2)

if __name__ == "__main__":
    np.random.seed(0)
    N = 200
    x = np.random.rand(N) * 10 - 5  # [-5,5),將數組的元素值控制在一定的範圍之內,限定數組元素的定義域
    x = np.sort(x)   #對數組元素進行排序
    y = f(x) + 0.05*np.random.randn(N)   #引入高斯隨機噪聲，增強模型魯棒性和泛化性能
    x.shape = -1, 1

    ridge = RidgeCV(alphas=np.logspace(-3, 2, 10), fit_intercept=False)
    ridged = Pipeline([('poly', PolynomialFeatures(degree=10)), ('Ridge', ridge)])
    bagging_ridged = BaggingRegressor(ridged, n_estimators=100, max_samples=0.3)
    dtr = DecisionTreeRegressor(max_depth=5)
    regs = [
        ('DecisionTree Regressor', dtr),
        ('Ridge Regressor(6 Degree)', ridged),
        ('Bagging Ridge(6 Degree)', bagging_ridged),
        ('Bagging DecisionTree Regressor', BaggingRegressor(dtr, n_estimators=100, max_samples=0.3))]
    x_test = np.linspace(1.1*x.min(), 1.1*x.max(), 1000)
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(12, 8), facecolor='w')
    plt.plot(x, y, 'ro', label=u'訓練數據')
    plt.plot(x_test, f(x_test), color='k', lw=3.5, label=u'真實值')
    clrs = 'bmyg'
    for i, (name, reg) in enumerate(regs):
        reg.fit(x, y)
        y_test = reg.predict(x_test.reshape(-1, 1))
        plt.plot(x_test, y_test.ravel(), color=clrs[i], lw=i+1, label=name, zorder=6-i)
    plt.legend(loc='upper left')
    plt.xlabel('X', fontsize=15)
    plt.ylabel('Y', fontsize=15)
    plt.title(u'迴歸曲線擬合', fontsize=21)
    plt.ylim((-0.2, 1.2))
    plt.tight_layout(2)
    plt.grid(True)
    plt.show()

import numpy as np
from hmmlearn import hmm
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn.metrics.pairwise import pairwise_distances_argmin
import warnings

def expand(a, b):
    d = (b - a) * 0.05
    return a-d, b+d

if __name__ == "__main__":
    warnings.filterwarnings("ignore")   # hmmlearn(0.2.0) < sklearn(0.18)

    # 0日期  1開盤  2最高  3最低  4收盤  5成交量  6成交額
    x = np.loadtxt('../SH600000.txt', delimiter='\t', skiprows=2, usecols=(4, 5, 6, 2, 3))
    close_price = x[:, 0]
    volumn = x[:, 1]
    amount = x[:, 2]
    amplitude_price = x[:, 3] - x[:, 4] # 每天的最高價與最低價的差
    diff_price = np.diff(close_price)   # 漲跌值,2-1,3-2,...
    volumn = volumn[1:]                 # 成交量
    amount = amount[1:]                 # 成交額
    amplitude_price = amplitude_price[1:]   # 每日振幅
    sample = np.column_stack((diff_price, volumn, amount, amplitude_price))    # 觀測值,數組(行向量)的豎直方向的堆疊
    n = 5
    model = hmm.GaussianHMM(n_components=n, covariance_type='full')
    model.fit(sample)
    y = model.predict_proba(sample)
    np.set_printoptions(suppress=True)
    print(y)

    t = np.arange(len(diff_price))
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(10,8), facecolor='w')
    plt.subplot(421)
    plt.plot(t, diff_price, 'r-')  #前後兩天的價格差
    plt.grid(True)
    plt.title(u'漲跌幅')
    plt.subplot(422)
    plt.plot(t, volumn, 'g-')
    plt.grid(True)
    plt.title(u'交易量')

    clrs = plt.cm.terrain(np.linspace(0, 0.8, n))
    plt.subplot(423)
    for i, clr in enumerate(clrs):
        print(clr)
        plt.plot(t, y[:, i], '-', color=clr, alpha=0.7)
    plt.title(u'所有組分')
    plt.grid(True)
    for i, clr in enumerate(clrs):
        axes = plt.subplot(4, 2, i+4)
        plt.plot(t, y[:, i], '-', color=clr)
        plt.title(u'組分%d' % (i+1))
        plt.grid(True)
    plt.suptitle(u'SH600000股票：GaussianHMM分解隱變量', fontsize=18)
    plt.tight_layout()
    plt.subplots_adjust(top=0.9)
    plt.show()