result = np.concatenate((result, col), axis=1)
return result
avg_window_size = 3
btc_window_size = 4
avg = [10, 22, 30, 42, 50, 62, 70, 82, 90, 102]
btc = [110, 123, 130, 143, 150, 163, 170, 183, 190, 203]
trend = [212, 224, 232, 244, 252, 264, 272, 284, 292, 304]
df = DataFrame({'btc': btc,
'trend': trend})
print(btc)
avg_diff = data_misc.difference(avg, 1)
avg_supervised = data_misc.timeseries_to_supervised(avg_diff, avg_window_size)
print(avg_supervised)
btc_supervised = supervised_diff_dt(df, btc_window_size)
# We pair the avg_supervised column with the weight_supervised
cut_beginning = [avg_window_size, btc_window_size]
cut_beginning = max(cut_beginning)
avg_supervised = avg_supervised.values[cut_beginning:, :]
btc_supervised = btc_supervised[cut_beginning:, :]
# Concatenate with numpy
supervised = np.concatenate((btc_supervised, avg_supervised), axis=1)
from Util import misc
window_size = 5 # 15
path = 'C:/tmp/bitcoin/'
input_file = 'bitcoin_usd_bitcoin_block_chain_trend_by_day.csv'
series = read_csv(path + input_file, header=0, sep=',', nrows=1438)
series = series.iloc[::-1]
for i in range(0, 30):
corr = series['Avg'].autocorr(lag=i)
print('Corr: %.2f Lang: %i' % (corr, i))
avg = series['Avg']
avg_values = avg.values
# Stationary Data
diff_values = data_misc.difference(avg_values, 1)
avg_values = diff_values
print("Diff values")
supervised = data_misc.timeseries_to_supervised(avg_values, window_size)
# print(raw_values)
supervised = supervised.values[window_size:, :]
# supervised = list(range(1, 101))
size_supervised = len(supervised)
split_train_val = int(size_supervised * 0.60)
split_val_test = int(size_supervised * 0.20)
train = supervised[0:split_train_val]
val = supervised[split_train_val:split_train_val + split_val_test]
test = supervised[split_train_val + split_val_test:]
return rmse, predictions
print('main_passangers.py, stationary.')
series = read_csv('../data/airline-passengers.csv', header=0, sep='\t')
date = series['Date'].values
date = numpy.delete(date, (0), axis=0)
raw_values = series['Passangers'].values
size_raw_values = len(raw_values)
split = int(size_raw_values * 0.80) # 0.80
print('raw_values:' + str(len(raw_values)))
diff_values = data_misc.difference(raw_values, 1)
print('Diff:' + str(len(diff_values)))
print('Raw values total size: %i, Train size: %i, Test size: %i ' %
(size_raw_values, split, size_raw_values - split))
supervised = data_misc.timeseries_to_supervised(diff_values, 1)
supervised_values = supervised.values
# supervised_values = supervised_values[1:, :]
# raw_values = numpy.delete(raw_values, (-1), axis=0)
print('Supervised:' + str(len(supervised_values)))
print('Raw values:' + str(len(raw_values)))
