【独家】周志华教授gcForest（多粒度级联森林）算法预测股指期货涨跌

$ pip3 install requirements.txt

from GCForest import *
gcf = gcForest( **kwargs )
gcf.fit(X_train, y_train)
gcf.predict(X_test)

import itertoolsimport numpy as npfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_score

__author__ = "Pierre-Yves Lablanche"__email__ = "plablanche@aims.ac.za"__license__ = "MIT"__version__ = "0.1.3"__status__ = "Development"# noinspection PyUnboundLocalVariableclass gcForest(object):
    def __init__(self, shape_1X=None, n_mgsRFtree=30, window=None, stride=1,
                 cascade_test_size=0.2, n_cascadeRF=2, n_cascadeRFtree=101, cascade_layer=np.inf,
                 min_samples_mgs=0.1, min_samples_cascade=0.05, tolerance=0.0, n_jobs=1):
        """ gcForest Classifier.

#获取当前时间from datetime import datetime
now = datetime.now()

startDate = '2010-4-16'endDate = now#获取沪深300股指期货数据，频率为1分钟df=get_price('IF88', start_date=startDate, end_date=endDate,\
             frequency='1d', fields=None, country='cn')

open = df['open'].values
close = df['close'].values
volume = df['volume'].values
high = df['high'].values
low = df['low'].values

import talib as taimport pandas as pdimport numpy as npfrom sklearn import preprocessing
ema = ta.EMA(close, timeperiod=30).tolist()
macd = ta.MACD(close, fastperiod=12, slowperiod=26, signalperiod = 9)[0].tolist()
momentum = ta.MOM(close, timeperiod=10).tolist()
rsi = ta.RSI(close, timeperiod=14).tolist()
linreg = ta.LINEARREG(close, timeperiod=14).tolist()
var = ta.VAR(close, timeperiod=5, nbdev=1).tolist()#获取当前的收盘价的希尔伯特变换cycle = ta.HT_DCPERIOD(close).tolist()#获取平均真实波动范围指标ATR,时间段为14atr = ta.ATR(high, low, close, timeperiod=14).tolist()#把每根k线的指标放入数组X中，并转置X = np.array([open,close,high,low,volume,ema, macd, linreg, momentum, rsi, var, cycle, atr]).T#输出可知数组X包含了ema, macd, linreg等13个指标数值X[2]

array([   3215. ,    3267.2,    3281.2,    3208. ,  114531. ,       nan,
             nan,       nan,       nan,       nan,       nan,       nan,
             nan])

y=[]
c=close[0]#用i遍历整个数据集for i in range(1, len(X)):    #如果高点突破参考线的1.0015倍，即上涨
    if (close[i]>close[i-1]):                #把参考点加到列表basicLine里，并且新参考点变为原来的1.0015倍，
        y.append(1)        
    elif (close[i]<close[i-1]): 
        y.append(0)         
    elif (close[i]==close[i-1]): 
        y.append(2)        #添加最后一个数据的标签为1y.append(1)#把y转化为ndarray数组y=np.array(y)#输出验证标签集是否准确print(len(y))for i in range(1, 10):
    print(close[i],y[i],i)

1663
3214.6 1 1
3267.2 0 2
3236.2 0 3
3221.2 0 4
3219.6 0 5
3138.8 0 6
3129.0 0 7
3083.8 1 8
3107.0 0 9

#shape_1X样本维度，window为多粒度扫描（Multi-Grained Scanning）算法中滑动窗口大小，\#用于扫描原始数据，tolerance为级联生长的精度差,整个级联的性能将在验证集上进行估计，\#如果没有显着的性能增益，训练过程将终止#gcf = gcForest(shape_1X=4, window=2, tolerance=0.0)#gcf = gcForest(shape_1X=[13,13], window=2, tolerance=0.0)gcf = gcForest(shape_1X=13, n_mgsRFtree=100, window=6, stride=2,
                 cascade_test_size=0.2, n_cascadeRF=4, n_cascadeRFtree=101, cascade_layer=np.inf,
                 min_samples_mgs=0.1, min_samples_cascade=0.1, tolerance=0.0, n_jobs=1)
gcf.fit(X_tr, y_tr)

Slicing Sequence...
Training MGS Random Forests...
Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.5577889447236181
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.521608040201005

#shape_1X样本维度，window为多粒度扫描（Multi-Grained Scanning）算法中滑动窗口大小，\#用于扫描原始数据，tolerance为级联生长的精度差,整个级联的性能将在验证集上进行估计，\#如果没有显着的性能增益，训练过程将终止#gcf = gcForest(shape_1X=4, window=2, tolerance=0.0)#gcf = gcForest(shape_1X=[13,13], window=2, tolerance=0.0)gcf = gcForest(shape_1X=[1,13], window=[1,6],)
gcf.fit(X_tr, y_tr)

Slicing Sequence...
Training MGS Random Forests...
Slicing Sequence...
Training MGS Random Forests...
Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.5964125560538116
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.5695067264573991

pred_X = gcf.predict(X_te)
print(len(pred_X))
print(len(y_te))
print(pred_X)

Slicing Sequence...
Slicing Sequence...
549
549
[1 1 0 0 0 0 0 0 0 0 1 0 0 0 1 0 1 1 0 1 0 1 0 1 0 0 0 0 0 0 1 1 1 0 0 1 0等

#最近预测for i in range(1,len(pred_X)):
    print(y_te[-i],pred_X[-i],-i)

0 1 -1
0 0 -2
1 0 -3
1 0 -4
0 1 -5等

# 保存每一天预测的结果，如果某天预测对了，保存1，如果某天预测错了，保存-1result_list = []# 检查预测是否成功def checkPredict(i):
    if pred_X[i] == y_te[i]:
        result_list.append(1)        else:
        result_list.append(0)#画出最近第k+1个长度为j的时间段准确率k=0j=len(y_te)#j=100for i in range(len(y_te)-j*(k+1), len(y_te)-j*k):
    checkPredict(i)        #print(y_pred[i])
    #return result_listprint(len(y_te) ) 
print(len(result_list) )import matplotlib.pyplot as plt#将准确率曲线画出来x = range(0, len(result_list))
y = []#z=[]for i in range(0, len(result_list)):        #y.append((1 + float(sum(result_list[:i])) / (i+1)) / 2)
    y.append( float(sum(result_list[:i])) / (i+1))
print('最近',j,'次准确率',y[-1])
print(x, y)
line, = plt.plot(x, y)
plt.show

549
549
最近 549 次准确率 0.5300546448087432
range(0, 549) [0.0, 0.0, 0.3333333333333333, 0.25等

#评估准确率# evaluating accuracyaccuracy = accuracy_score(y_true=y_te, y_pred=pred_X)
print('gcForest accuracy : {}'.format(accuracy))

gcForest accuracy : 0.5300546448087432

# loading the datadigits = load_digits()
X = digits.data
y = digits.target
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.4)
gcf = gcForest(shape_1X=[7,8], window=[4,6], tolerance=0.0, min_samples_mgs=10, min_samples_cascade=7)#gcf = gcForest(shape_1X=13, window=13, tolerance=0.0, min_samples_mgs=10, min_samples_cascade=7)gcf.fit(X_tr, y_tr)

Slicing Images...
Training MGS Random Forests...
Slicing Images...
Training MGS Random Forests...
Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.9814814814814815
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.9814814814814815

# evaluating accuracyaccuracy = accuracy_score(y_true=y_te, y_pred=pred_X)
print('gcForest accuracy : {}'.format(accuracy))

gcForest accuracy : 0.980528511821975

gcf = gcForest(shape_1X=[8,8], window=5, min_samples_mgs=10, min_samples_cascade=7)
X_tr_mgs = gcf.mg_scanning(X_tr, y_tr)

Slicing Images...
Training MGS Random Forests...

gcf = gcForest(tolerance=0.0, min_samples_mgs=10, min_samples_cascade=7)
_ = gcf.cascade_forest(X_tr_mgs, y_tr)

Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.9722222222222222
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.9907407407407407
Adding/Training Layer, n_layer=3
Layer validation accuracy = 0.9814814814814815

import numpy as np
pred_proba = gcf.cascade_forest(X_te_mgs)
tmp = np.mean(pred_proba, axis=0)
preds = np.argmax(tmp, axis=1)
accuracy_score(y_true=y_te, y_pred=preds)
gcf = gcForest(tolerance=0.0, min_samples_mgs=20, min_samples_cascade=10)
_ = gcf.cascade_forest(X_tr_mgs, y_tr)
pred_proba = gcf.cascade_forest(X_te_mgs)
tmp = np.mean(pred_proba, axis=0)
preds = np.argmax(tmp, axis=1)
accuracy_score(y_true=y_te, y_pred=preds)

0.97774687065368571

Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.9629629629629629
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.9675925925925926
Adding/Training Layer, n_layer=3
Layer validation accuracy = 0.9722222222222222
Adding/Training Layer, n_layer=4
Layer validation accuracy = 0.9722222222222222

0.97218358831710705

gcf = gcForest(tolerance=0.0, min_samples_cascade=20)
_ = gcf.cascade_forest(X_tr, y_tr)pred_proba = gcf.cascade_forest(X_te)
tmp = np.mean(pred_proba, axis=0)
preds = np.argmax(tmp, axis=1)
accuracy_score(y_true=y_te, y_pred=preds)

Adding/Training Layer, n_layer=1
Layer validation accuracy = 0.9583333333333334
Adding/Training Layer, n_layer=2
Layer validation accuracy = 0.9675925925925926
Adding/Training Layer, n_layer=3
Layer validation accuracy = 0.9583333333333334

0.94297635605006958