def createModel(data):
print 'Create_model'
importr('forecast')
robj.r('''
arima_data <- function(data){
best_arima = auto.arima(data,trace=F,stepwise=T)
forecast = forecast.Arima(best_arima,h=60,level=c(99.5))
output = forecast$mean
return (output)
}
''')
features_names = ["Ret_%d_pred" % (i) for i in range(121, 181)]
predict = pd.DataFrame(columns=features_names)
i = 1
for tmp in DataFrame.iter_row(data):
if i % 100 == 0:
print i
tmp = robj.r("as.numeric")(tmp)
#tmp = robj.r('ts')(tmp,start=2)
tmp = robj.r('ts')(tmp, start=2, frequency=15)
forecast = robj.r('arima_data')(tmp)
forecast = robj.r('as.numeric')(forecast)
forecast = np.array(forecast)
predict2 = pd.DataFrame(forecast).T
predict2.columns = features_names
predict = pd.concat([predict, predict2], axis=0)
i = i + 1
print predict
predict.to_csv("tmp1.csv")
def createModel(data, param):
print 'Create_model'
importr('forecast')
robj.r('''
arima_data <- function(data){
best_arima = auto.arima(data,trace=F,stepwise=T,max.P=8,max.Q=8,max.p=10,max.q=10,max.order=10,
,start.p=1,start.q=0,start.P=1,start.Q=0,seasonal=T,ic=('bic'))
forecast = forecast.Arima(best_arima,h=60,level=c(99.5),stationary=T)
output = forecast$mean
return (output)
}
''')
print 'the frequency is %d' % (param['frequency'])
features_names = ["Ret_%d_pred" % (i) for i in range(121, 181)]
predict = pd.DataFrame(columns=features_names)
i = 1
for tmp in DataFrame.iter_row(data):
if i % 100 == 0:
print i
tmp = robj.r("as.numeric")(tmp)
#tmp = robj.r('ts')(tmp,start=2)
tmp = robj.r('ts')(tmp, start=2, frequency=param['frequency'])
forecast = robj.r('arima_data')(tmp)
forecast = robj.r('as.numeric')(forecast)
forecast = np.array(forecast)
predict2 = pd.DataFrame(forecast).T
predict2.columns = features_names
predict = pd.concat([predict, predict2], axis=0)
i = i + 1
#this way I will get forecast_data , train_data
raw_data.to_csv("raw.csv")
predict.to_csv("predict.csv")
data = predict.join(raw_data, rsuffix='_2')
data.to_csv("data.raw.csv")
data['Ret_120_price'] = price_train['Ret_120_price']
transform_format(data)
Ret_1 = data['Ret_MinusTwo']
Ret_2 = 1 - (1.0 / ((1.0 / (1 - data['Ret_MinusOne'])) *
data['Ret_120_price'] * data['Ret_180_price']))
data['Ret_PlusOne_pred'] = 0.5 * Ret_1 + 0.5 * Ret_2
data['Ret_PlusTwo_pred'] = 0.5 * Ret_2 + 0.5 * data['Ret_PlusOne_pred']
data.to_csv("data.csv")
WMAE_model(data)
mase = np.sum(data['error']) / (40000 * 62)
print 'loss:%f' % (mase)
return {'loss': mase, 'status': STATUS_OK}
