def incren(ts, m, R, fd=True):
from pyentrp import entropy as ent
diff = np.diff(ts)
subvectors = ent.util_pattern_space(diff, lag=1, dim=m)
signs = np.sign(subvectors)
allqs = []
for i in range(len(subvectors)):
sd = np.std(subvectors[i, :])
row = subvectors[i, :]
qs = []
for element in row:
q = R * np.abs(element) / sd
q = np.min([R, q])
q = np.floor(q)
qs.append(q)
allqs.append(qs)
allqs = np.vstack(allqs)
words = np.multiply(signs, allqs)
unq_rows, count = np.unique(words, axis=0, return_counts=1)
out = {tuple(i): j for i, j in zip(unq_rows, count)}
freq_dict = {}
for key in out.keys():
freq = {key: out[key] / len(words)}
freq_dict.update(freq)
ent = 0
for freq in freq_dict.values():
ent += freq * np.log2(freq)
if fd == True:
return -1 * ent, freq_dict
else:
return -1 * ent, words
def test_utilSequence(self):
self.assertRaises(Exception, ent.util_pattern_space,
(TIME_SERIES, 0, 2))
self.assertRaises(Exception, ent.util_pattern_space,
(TIME_SERIES, 10, 20))
np.testing.assert_array_equal(
ent.util_pattern_space(TIME_SERIES, 2, 3),
np.array([[1, 1, 3], [1, 2, 4], [1, 3, 5]]))
import collections
import keras
from keras.layers import Dense, Bidirectional, LSTM, TimeDistributed
from keras.optimizers import Adam
##########
hist = yf.download(tickers = "DJI", period = 'max')
words = []
dow_df = ent.util_pattern_space(hist_sma, lag = 1, dim = 50)
dow_df = dow_df[:]
for i in range(len(dow_df)):
dat_znorm = znorm(dow_df[i,:])
dat_paa= paa(dat_znorm, 3)
word = ts_to_string(dat_paa, cuts_for_asize(2))
words.append(word)
print(words)
print(collections.Counter(words))
from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
sqn = le.fit_transform(words)