class Task_getPlot(TaskPickle):
runDate = d6tflow.DateParameter()
plottype = d6tflow.Parameter()
def run(self):
tickers, Data = self.input()
tickers, Data = tickers.load().set_index('Ticker symbol'), Data.load()
status = Data['status']
if status == 'failure':
self.save({'status': status, 'plot': None})
return None
company_timeseries = pd.read_json(Data['dataframe'])
performance_data = company_timeseries.set_index('Date')
# status, company_timeseries = Data['status'], Data['company_timeseries']
# performance_data = pd.read_sql(
# company_timeseries.statement,
# company_timeseries.session.bind).set_index('Date')
# performance_data = self.input().load().set_index('Date')
myplot = getPlot(
plottype=self.plottype,
performance_data=performance_data,
status=status,
ticker=tickers.at[self.stockticker, 'Company'],
)
self.save(myplot)
class Task_getDates(TaskJson):
runDate = d6tflow.DateParameter()
type = d6tflow.Parameter()
def run(self):
input = self.input().load()
status, timeseries = input['status'], input['timeseries']
if status == 'failure':
self.save({'status': status, 'dates': None})
return None
timeseries = pd.read_json(timeseries)
options_date_map = sorted(timeseries['date'].unique(), reverse=True)
options_date_map = pd.DataFrame({'date':options_date_map})
options_date_map['date'] = options_date_map['date'].apply(lambda x: x.strftime('%Y-%m-%d'))
out = {
'timeseries': options_date_map.to_json(),
'status': 'success'
}
self.save(out)
class Task_getData(TaskJson):
runDate = d6tflow.DateParameter()
type = d6tflow.Parameter()
def run(self):
timeseries = getTimeseries_T(self.type)
self.save(timeseries)
class Task_getData(TaskJson):
runDate = d6tflow.DateParameter()
stockticker = d6tflow.Parameter()
def run(self):
# tickers = self.input().load()
#assert self.stockticker in tickers.keys(), 'Symbol should be in ticker list'
out = getData(stockticker=self.stockticker)
self.save(out)
class TaskTrain(d6tflow.tasks.TaskPickle): # save output as pickle
model = d6tflow.Parameter(default='ols') # parameter for model selection
def run(self):
df_train = self.input().load()
if self.model == 'ols':
model = sklearn.linear_model.LogisticRegression()
elif self.model == 'svm':
model = sklearn.svm.SVC()
else:
raise ValueError('invalid model selection')
model.fit(df_train.drop('y', 1), df_train['y'])
self.save(model)
class ModelTrain(d6tflow.tasks.TaskPickle): # save output as pickle
model = d6tflow.Parameter(default='ols') # parameter for model selection
def run(self):
df_train = self.input().load()
if self.model == 'ols':
model = sklearn.linear_model.LinearRegression()
elif self.model == 'gbm':
model = sklearn.ensemble.GradientBoostingRegressor()
else:
raise ValueError('invalid model selection')
model.fit(df_train.drop('y', 1), df_train['y'])
self.save(model)
self.saveMeta(
{'score': model.score(df_train.drop('y', 1), df_train['y'])})
class ModelTrain(d6tflow.tasks.TaskPickle):
model = d6tflow.Parameter() # parameter for model selection
def run(self):
df_trainX, df_trainY = self.inputLoad() # quickly load input data
if self.model == 'ols': # select model based on parameter
model = sklearn.linear_model.LinearRegression()
elif self.model == 'gbm':
model = sklearn.ensemble.GradientBoostingRegressor()
# fit and save model with training score
model.fit(df_trainX, df_trainY)
self.save(model) # persist/cache model
self.saveMeta({'score': model.score(df_trainX,
df_trainY)}) # save model score
