input_dict = {} # initialize
input_dict = {
'f1': {
'fname': 'OBV',
'params': [9],
'transform': ['Scaler', 'Robust']
},
'f2': {
'fname': 'OBV',
'params': [],
'transform': ['Normalized', 10]
}
}
dataSet = featureGen.generate_features(df, input_dict)
#dataSet = transf.normalizer(dataSet, 'Volume', 50)
# Plot price and indicators
startDate = "2019-01-20"
endDate = "2019-02-12"
plotDataSet = dataSet[startDate:endDate]
plot_dict = {}
plot_dict['Issue'] = issue
plot_dict['Plot_Vars'] = list(feature_dict.keys())
plot_dict['Volume'] = 'Yes'
plotIt.price_Ind_Vol_Plot(plot_dict, plotDataSet)
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)
startDate = dataLoadStartDate
endDate = dataLoadEndDate
plotDF = dataSet[startDate:endDate]
# Set up dictionary and plot HigherClose
plot_dict = {}
plot_dict['Issue'] = issue
plot_dict['Plot_Vars'] = list(feature_dict.keys())
plot_dict['Volume'] = 'Yes'
plotIt.price_Ind_Vol_Plot(plot_dict, plotDF)
y_label="Frequency",
title="beLong distribution for " + issue)
plt.show(block=False)
# Stationarity tests
# stationarity_tests(mmData, 'Close', issue)
# cols = [k for k,v in feature_dict.items() if v == 'Keep']
# for x in cols:
# stationarity_tests(mmData, x, issue)
plot_dict = {}
plot_dict['Issue'] = issue
plot_vars = [k for k, v in feature_dict.items() if v == 'Keep']
plot_dict['Plot_Vars'] = plot_vars
plot_dict['Volume'] = 'Yes'
plotIt.price_Ind_Vol_Plot(plot_dict, mmData)
# EV related
evData = dataSet.loc[modelStartDate:modelEndDate].copy()
col_vals = [k for k, v in feature_dict.items() if v == 'Drop']
to_drop = ['Open', 'High', 'Low', 'gainAhead', 'Close', 'Volume']
for x in to_drop:
col_vals.append(x)
mmData = dSet.drop_columns(mmData, col_vals)
names = mmData.columns.values.tolist()
# with open('columns_to_keep.json', 'w') as outfile:
# json.dump(names, outfile)