]
FILENAMES = pd.DataFrame({'filename': URLS})
CST = Constant(Table('filenames', data=FILENAMES), scheduler=s)
CSV = CSVLoader(index_col=False,
skipinitialspace=True,
usecols=['pickup_longitude', 'pickup_latitude'],
filter_=_filter,
scheduler=s)
CSV.input.filenames = CST.output.table
PR = Every(scheduler=s)
PR.input.df = CSV.output.table
SCATTERPLOT = MCScatterPlot(scheduler=s,
classes=[('Scatterplot', 'pickup_longitude',
'pickup_latitude')],
approximate=True)
SCATTERPLOT.create_dependent_modules(CSV, 'table')
s.set_interaction_opts(starving_mods=SCATTERPLOT.get_starving_mods(),
max_iter=3,
max_time=1.5)
if __name__ == '__main__':
s.start()
while True:
time.sleep(2)
s.to_json()
SCATTERPLOT.to_json() # simulate a web query
#SCATTERPLOT.get_image()
s.join()
print(len(CSV.table()))
CSV = CSVLoader(index_col=False,
skipinitialspace=True,
usecols=[
'pickup_longitude', 'pickup_latitude', 'dropoff_longitude',
'dropoff_latitude'
],
filter_=_filter,
scheduler=s) # TODO: reimplement filter in read_csv.py
CSV.input.filenames = CST.output.table
PR = Every(scheduler=s)
PR.input.df = CSV.output.table
MULTICLASS = MCScatterPlot(scheduler=s,
classes=[('pickup', 'pickup_longitude',
'pickup_latitude'),
('dropoff', 'dropoff_longitude',
'dropoff_latitude')],
approximate=True)
MULTICLASS.create_dependent_modules(CSV, 'table')
s.set_interaction_opts(starving_mods=MULTICLASS.get_starving_mods(),
max_iter=3,
max_time=1.5)
if __name__ == '__main__':
s.start()
while True:
time.sleep(2)
s.to_json()
MULTICLASS.to_json() # simulate a web query
s.join()
print(len(CSV.table()))