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:
col_vals.append(x)
model_data = dSet.drop_columns(feat_df, col_vals)
# Retrieve model
best_model_name = "SVM"
best_model_segment = "segment-0"
#best_model_name = system_dict["best_model"]
file_title = "fit-model-" + best_model_name + "-IS-" + system_name + "-" + best_model_segment +".sav"
file_name = os.path.join(system_directory, file_title)
model = pickle.load(open(file_name, 'rb'))
'transform': ['Normalized', 50]
},
'f5': {
'fname': 'UltimateOscillator',
'params': [10, 20, 30],
'transform': ['Normalized', 50]
},
'f6': {
'fname': 'ROC',
'params': [30],
'transform': ['Normalized', 50]
}
}
dataSet = featureGen.generate_features(dataSet, input_dict)
dataSet = transf.normalizer(dataSet, 'Volume', 50)
# save Dataset of analysis
print("====Saving dataSet====\n")
modelname = 'RF'
file_title = issue + "_insample_feature_dataSet_" + modelname + ".pkl"
file_name = os.path.join(
r'C:\Users\kruegkj\Documents\GitHub\QuantTradingSys\Code\models\model_data',
file_title)
dataSet.to_pickle(file_name)
# set date splits
isOosDates = timeUtil.is_oos_data_split(issue, pivotDate, is_oos_ratio,
oos_months, segments)
dataLoadStartDate = isOosDates[0]
is_start_date = isOosDates[1]