oos_months = 3
segments = 3
# get segmented dates
isOosDates = timeUtil.is_oos_data_split(issue, pivotDate, is_oos_ratio,
oos_months, segments)
dataLoadStartDate = isOosDates[0]
is_start_date = isOosDates[1]
oos_start_date = isOosDates[2]
is_months = isOosDates[3]
is_end_date = isOosDates[4]
oos_end_date = isOosDates[5]
#load data
dataSet = dSet.read_issue_data(issue)
dataSet = dSet.set_date_range(dataSet, dataLoadStartDate, pivotDate)
#set beLong level
beLongThreshold = 0.0
dataSet = ct.setTarget(dataSet, "Long", beLongThreshold)
# def stationarity_tests(s_df, signal, issue):
# print("=============================================================")
# adf_test(s_df, signal, issue)
# hurst_setup(s_df[signal][:], issue)
# print("========================================")
for i in range(segments):
modelData = dSet.set_date_range(dataSet, is_start_date, is_end_date)
print("\n\n\nIN SAMPLE")
# Stationarity tests
else:
print('no date')
tradeDate += BDay(1)
print('tradeDate: ', tradeDate)
# set trade date
tradeDate = tradeDate.strftime('%Y-%m-%d')
print(tradeDate)
# get first/last row
df_start_date = temp_raw_df.Date[0]
lastRow = temp_raw_df.shape[0]
df_end_date = temp_raw_df.Date[lastRow-1]
feat_df = dSet.set_date_range(temp_raw_df, df_start_date, df_end_date)
# Resolve any NA's for now
feat_df.fillna(method='ffill', inplace=True)
#set beLong level
beLongThreshold = 0.000
feat_df = ct.setTarget(temp_raw_df, "Long", beLongThreshold)
# Adding features with new day
input_dict = sysUtil.get_dict(system_directory, 'input_dict')
feat_df = featureGen.generate_features(feat_df, input_dict)
feat_df = transf.normalizer(feat_df, 'Volume', 50)
col_vals = [k for k,v in feature_dict.items() if v == 'Drop']
to_drop = ['Open','High','Low', 'gainAhead', 'Close', 'Volume', 'AdjClose', 'beLong']
for x in to_drop:
timeUtil = TimeUtility()
modelUtil = ModelUtility()
#timeSeriesImp = TimeSeriesSplitImproved()
dataLoadStartDate = "2014-09-26"
dataLoadEndDate = "2018-04-05"
issue = "TLT"
# Set IS-OOS parameters
pivotDate = datetime.date(2018, 4, 2)
is_oos_ratio = 2
oos_months = 4
segments = 4
dataSet = dSet.read_issue_data(issue)
dataSet = dSet.set_date_range(dataSet, dataLoadStartDate, pivotDate)
#set beLong level
beLongThreshold = 0.000
dataSet = ct.setTarget(dataSet, "Long", beLongThreshold)
input_dict = {} # initialize
input_dict = {
'f1': {
'fname': 'ATR',
'params': [5],
'transform': ['Zscore', 10]
},
'f2': {
'fname': 'RSI',
'params': [2],
'transform': ['Scaler', 'robust']
plotIt = PlotUtility()
taLibMomSt = TALibMomentumStudies()
dSet = DataRetrieve()
issue = "TLT"
df = dSet.read_issue_data(issue)
lastRow = df.shape[0]
dataLoadEndDate = df.Date[lastRow - 100]
pprint(dataLoadEndDate)
dataLoadStartDate = df.Date[lastRow - 3000]
pprint(dataLoadStartDate)
dataSet = dSet.set_date_range(df, dataLoadStartDate, dataLoadEndDate)
pprint(dataSet.tail(10))
# Resolve any NA's for now
dataSet.fillna(method='ffill', inplace=True)
dataSet = taLibMomSt.RSI(dataSet, 10)
#dataSet = taLibMomSt.RSI2(dataSet, 2)
pprint(dataSet.head(5))
pprint(dataSet.tail(5))
dataSet = taLibMomSt.PPO(dataSet, 12, 26)
# dataSet = taLibMomSt.CMO(dataSet, 20)
# dataSet = taLibMomSt.CCI(dataSet, 20)
# dataSet = taLibMomSt.UltOsc(dataSet, 7, 24, 28)
# dataSet = taLibMomSt.rate_OfChg(dataSet, 10)
'Low': raw_df.Low[index],
'Close': raw_df.Close[index],
'AdjClose': raw_df.AdjClose[index],
'Volume': raw_df.Volume[index]
},
ignore_index=True)
print(new_data_df.tail(2))
# get first row
df_start_date = new_data_df.Date[0]
# get last row
lastRow = new_data_df.shape[0]
df_end_date = new_data_df.Date[lastRow - 1]
feat_df = dSet.set_date_range(new_data_df, df_start_date, df_end_date)
# Resolve any NA's for now
feat_df.fillna(method='ffill', inplace=True)
#set beLong level
beLongThreshold = 0.000
feat_df = ct.setTarget(new_data_df, "Long", beLongThreshold)
print(feat_df.tail(2))
# Adding features with new day
input_dict = sysUtil.get_dict(system_directory, 'input_dict')
feat_df = featureGen.generate_features(feat_df, input_dict)
feat_df = transf.normalizer(feat_df, 'Volume', 50)