def subsample(start, end):
start = int(start)
end = int(end)
global curr_ds
global details
# use minutes dataset if timedelta of selected period is "short" enough
# (note that this "short enough" is just arbitrary for this example)
if end-start < 43383600000:
xs = aapl_min[(aapl_min.Date > start) & (aapl_min.Date < end)]
else:
xs = aapl[(aapl.Date > start) & (aapl.Date < end)]
factor = len(xs) // FACTOR_BASE
if factor <= 1:
tss = xs.Date
resampled = xs.Price
else:
resampled = coarsen(np.mean, np.asarray(xs.Price), factor)
tss = coarsen(np.min, np.asarray(xs.Date), factor)
curr_ds = dict(
Date=[x for x in tss],
Price=[float(x) for x in resampled],
DateFmt=[fromtimestamp(x//1000) for x in tss],
)
details = {
"start": curr_ds['DateFmt'][0],
"end": curr_ds['DateFmt'][-1],
"factor": factor,
"samples_no": len(tss),
"original_samples_no": len(xs),
}
return json.jsonify(curr_ds)
def subsample(start, end):
start = int(start)
end = int(end)
global curr_ds
global details
# use minutes dataset if timedelta of selected period is "short" enough
# (note that this "short enough" is just arbitrary for this example)
if end - start < 43383600000:
xs = aapl_min[(aapl_min.Date > start) & (aapl_min.Date < end)]
else:
xs = aapl[(aapl.Date > start) & (aapl.Date < end)]
factor = len(xs) // FACTOR_BASE
if factor <= 1:
tss = xs.Date
resampled = xs.Price
else:
resampled = coarsen(np.mean, np.asarray(xs.Price), factor)
tss = coarsen(np.min, np.asarray(xs.Date), factor)
curr_ds = dict(
Date=[x for x in tss],
Price=[float(x) for x in resampled],
DateFmt=[fromtimestamp(x // 1000) for x in tss],
)
details = {
"start": curr_ds['DateFmt'][0],
"end": curr_ds['DateFmt'][-1],
"factor": factor,
"samples_no": len(tss),
"original_samples_no": len(xs),
}
return json.jsonify(curr_ds)
print ("Simulating new data...")
res = map(create_sim_data, haapl.Date, haapl.Low, haapl.High)
newdt = pd.DataFrame({'Date': [to_seconds(item[0]) for sublist in res for item in sublist],
'Price': [item[1] for sublist in res for item in sublist]})
print ("Creating new file: data/aapl_minutes_raw.csv")
newdt.to_csv('data/aapl_minutes_raw.csv')
print ("Done!")
aapl_min = pd.read_csv('data/aapl_minutes_raw.csv')
# build some data
factor = len(aapl) // FACTOR_BASE
resampled = coarsen(np.mean, np.asarray(aapl.Price), factor)
tss = coarsen(np.min, np.asarray(aapl.Date), factor)
ftss = [fromtimestamp(x//1000).strftime("%Y-%m-%d %H:%M:%S") for x in tss]
curr_ds = dict(
Date=[x for x in tss],
DateFmt=[ts for ts in ftss],
Price=[float(x) for x in resampled],
)
details = {
"start": curr_ds['DateFmt'][0],
"end": curr_ds['DateFmt'][-1],
"factor": factor,
"samples_no": len(curr_ds['DateFmt']),
"original_samples_no": len(aapl),
print("Simulating new data...")
res = map(create_sim_data, haapl.Date, haapl.Low, haapl.High)
newdt = pd.DataFrame({
'Date': [to_seconds(item[0]) for sublist in res for item in sublist],
'Price': [item[1] for sublist in res for item in sublist]
})
print("Creating new file: data/aapl_minutes_raw.csv")
newdt.to_csv('data/aapl_minutes_raw.csv')
print("Done!")
aapl_min = pd.read_csv('data/aapl_minutes_raw.csv')
# build some data
factor = len(aapl) // FACTOR_BASE
resampled = coarsen(np.mean, np.asarray(aapl.Price), factor)
tss = coarsen(np.min, np.asarray(aapl.Date), factor)
ftss = [fromtimestamp(x // 1000).strftime("%Y-%m-%d %H:%M:%S") for x in tss]
curr_ds = dict(
Date=[x for x in tss],
DateFmt=[ts for ts in ftss],
Price=[float(x) for x in resampled],
)
details = {
"start": curr_ds['DateFmt'][0],
"end": curr_ds['DateFmt'][-1],
"factor": factor,
"samples_no": len(curr_ds['DateFmt']),
"original_samples_no": len(aapl),