我还很陌生python
我制作了一个简单的脚本，从mt4
我的想法/项目是将其变成某种概率指标，即给出概率，除了出价和要价，例如：
TIME/ BID ASK
USD/CADD 22:19 1.30451 60%^ 1.30D39 40%v
并且概率在特定周期内发生变化，例如1小时周期，因此每小时都会给出一个新的方向概率
它正在寻找两种模式：A、B、
模式 A 代表看涨模式
模式 B 代表看跌模式
基本上是在寻找再次发生的可能性更高的两个中再次发生的概率A或B有多强，
这是我卡住的地方
我不知道如何把它放在一起......
这是我到目前为止所拥有的：
import datetime
import numpy as np
import pandas as pd
import sklearn
from pandas.io.data import DataReader
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.lda import LDA
from sklearn.metrics import confusion_matrix
from sklearn.qda import QDA
from sklearn.svm import LinearSVC, SVC
import dde_client as ddec
import time
QUOTE_client = ddec.DDEClient('MT4', 'QUOTE')
symbols = ['USDCAD', 'GOLD','EURUSD', 'SILVER', 'US30Cash', ]
for i in symbols:
QUOTE_client.advise(i)
def Get_quote():
while 1:
time.sleep(1)
print "Symbol\tDATE\t\tTIME\tBID\tASK"
for i in symbols:
current_quote = QUOTE_client.request(i).split(" ")
day, _time, bid, ask = (current_quote[0], current_quote[1],
current_quote[2], current_quote[3])
print i + ":\t" + day + "\t" + _time +"\t" +bid+ "\t" + ask
break
time.sleep(1)
return Get_quote()
continue
def create_lagged_series(cuurent_quote,start_time, end_time, lags=1):
ts = DataReader(cuurent_quote,symbols,
start_time-datetime.timedelta(hours=1),
end_time
)
tslag = pd.DataFrame(index=ts.index)
ts['Today'] = ts['Adj Close']
tslag["Volume"] = ts["Volume"]
for i in xrange(0, lags):
tslag["Lag%s" % str(i+1)] = ts["Adj Close"].shift(i+1)
tsret = pd.DataFrame(index=tslag.index)
tsret["Volume"] = tslag["Volume"]
tsret["Today"] = tslag["Today"].pct_change()*100.0
for i in xrange(0, lags):
if (abs(x) < 0.0001):
tsret["Today"][i] = 0.0001
for i in xrange(0,lags):
tsret["Lag%s" % str(i+1)] = \
tslag["Lag%s" % str(i+1)].pct_change()*100.0
tsret["Direction"] = np.sign(tsret["Today"])
tsret = tsret[tsret.index >= start_time]
return tsret
if __name__ == "__main__":
snpert = create_lagged_series(len('GOLD', Get_quote(), 1))
X = snpret[["Lag1","Lag2"]]
y = snpret["Direction"]
start_test = cuurernt_quote
X_train = X[X.index < start_test]
X_test = X[X.index >= start_test]
y_train = y[y.index < start_test]
y_test = y[y.index >= start_test]
print "Hit Rates/Confusion Matrices:\n"
models = [ ( "LR", LogisticRegression() ),
( "LDA", LDA() ),
( "QDA", QDA() ),
( "LSVC", LinearSVC() ),
( "RSVM", SVC( C = 1000000.0,
cache_size = 200,
class_weight = None,
coef0 = 0.0,
degree = 3,
gamma = 0.0001,
kernel = 'rbf',
max_iter = -1,
probability = False,
random_state = None,
shrinking = True,
tol = 0.001,
verbose = False
)
),
( "RF", RandomForestClassifier( n_estimators = 1000,
criterion = 'gini',
max_depth = None,
min_samples_split = 2,
min_samples_leaf = 1,
max_features = 'auto',
bootstrap = True,
oob_score = False,
n_jobs = 1,
random_state = None,
verbose = 0
)
)
]
# Iterate through the models
for m in models:
# Train each of the models on the training set
m[1].fit(X_train, y_train)
pred = m[1].predict(X_test)
print "%s:\n%0.3f" % (m[0], m[1].score(X_test, y_test))
print "%s\n" % confusion_matrix(pred, y_test)这只是我自己MT4的价格提要脚本：
import dde_client as ddec
import time
__author__ = 'forex Ticker'
print __author__
QUOTE_client = ddec.DDEClient('MT4', 'QUOTE')
symbols = ['USDCAD', 'GOLD','EURUSD', 'SILVER', 'US30Cash', ]
for i in symbols:
QUOTE_client.advise(i)
while 1:
time.sleep(1)
print "Symbol\tDATE\t\tTIME\tBID\tASK"
for i in symbols:
current_quote = QUOTE_client.request(i).split(" ")
day, _time, bid, ask = (current_quote[0], current_quote[1],
current_quote[2], current_quote[3])
print i + ":\t" + day + "\t" + _time +"\t" +bid+ "\t" + ask
break
time.sleep(1)
continue