class FunctionConfigs:
class FuncType(Enum):
DFT = 1
DFT_REAL = 2,
DFT_HERMITE = 3,
POWER_SPECTRUM = 4,
ACF = 5,
PACF = 6
lambdaContainer = {
FuncType.DFT: lambda p: np.fft.fftn(**p),
FuncType.DFT_REAL: lambda p: np.fft.rfftn(**p),
FuncType.DFT_HERMITE: lambda p: np.fft.hfft(**p),
FuncType.POWER_SPECTRUM: lambda p: periodogram(**p),
FuncType.ACF: lambda p: acf(**p),
FuncType.PACF: lambda p: pacf(**p)
}
constraintTo1D = {
FuncType.POWER_SPECTRUM: True,
FuncType.ACF: True,
FuncType.PACF: True
}
indexReturn = {FuncType.POWER_SPECTRUM: 0}
def __init__(self):
pass
def data_periodogram(dados):
freq = np.arange(0, 0.5, 1/len(dados))
periodo = 1/freq
pyplot.plot(dados)
pyplot.show()
pgram = periodogram(dados)
if len(pgram) % 2 == 0:
pgram = pgram[0:int(len(dados)/2)]
indexes = sorted(range(len(pgram)), key=lambda i: pgram[i])[-3:]
else:
pgram = pgram[0:int((len(dados))/2)+1]
indexes = sorted(range(len(pgram)), key=lambda i: pgram[i])[-3:]
print('marilia', indexes)
indexes = list(indexes)
freq_max = [freq[index] for index in indexes]
T = [len(dados)/index for index in indexes]
df_output = pd.DataFrame({'Frequencia': freq,
'Periodograma': pgram})
return pgram, freq, df_output, indexes, freq_max, T
def test_periodogram_future_warning(reset_randomstate):
with pytest.warns(FutureWarning):
periodogram(np.random.standard_normal(100))
def proxiesStats(proxy_ids):
### GET TIME SERIES
logs_df_file = os.path.join(output_dir, 'logs_df')
if os.path.isfile(logs_df_file):
logs_df = pd.read_pickle(logs_df_file)
else:
pool = multiprocessing.Pool(
processes=len(proxy_ids),
initializer=start_process,
)
pool_outputs = pool.map(helper, proxy_ids)
pool.close()
pool.join()
print 'Joined'
logs_df = pd.concat(pool_outputs, ignore_index=True)
logs_df.to_pickle(logs_df_file)
bytes_ts = pd.Series(logs_df['bytes'].set_index('ts').bytes.resample(
'60Min', how='sum'))
requests_ts = pd.Series(logs_df['bytes'].set_index('ts').bytes.resample(
'60Min', how='resampler_count'))
bytes_df = pd.DataFrame(bytes_ts)
requests_df = pd.DataFrame(requests_ts)
pdb.set_trace()
### PLOT GENERAL TIME SERIES GRAPHS
bytes_df.plot(logy=True)
plt.show()
raw_input('End')
periodogram = stattools.periodogram(bytes_df.bytes)
plotTwin(bytes_df, 'Bytes', periodogram, 'Frequency', 'Periodogram')
acf = stattools.acf(bytes_df)
plotTwin(bytes_df, 'Bytes', 'acf', 'Correlation Coefficient',
'Autocorrelation', bytes_df)
pacf = stattools.pacf(bytes_df)
plotTwin(bytes_df, 'Bytes', 'pacf', 'Partial Correlation Coefficient',
'Partial Autocorrelation', bytes_df)
decomposition = seasonal_decompose(bytes_df.values, freq=24)
decomposition.plot()
plt.show()
raw_input('End')
du_wa = stat1.durbin_watson(np.nan_to_num(decomposition.resid))
print 'Durbin-Watson test for residuals: %s' % du_wa
### EVEN/ODD ANALYSIS
#odd_mask = bytes_df.index.map(lambda x: x.day%2 ) == 1
odd_mask = bytes_df.index.map(lambda x: x.day in [15, 17, 19, 21]) == True
bytes_df_odd = bytes_df[odd_mask].shift(-7, 'D')
#even_mask = bytes_df.index.map(lambda x: x.day%2) == 0
even_mask = bytes_df.index.map(lambda x: x.day in [8, 10, 12, 14]) == True
bytes_df_even = bytes_df[even_mask]
fig, ax1 = plt.subplots()
lns1 = ax1.plot(bytes_df_odd, 'b--', label='Odd', visible=True)
lns2 = ax1.plot(bytes_df_even, 'b:', label='Even', visible=True)
ax1.set_ylabel('Bytes', color='b', fontsize=18)
ax1.set_yscale('log')
for tl in ax1.get_yticklabels():
tl.set_color('b')
#corr = pd.rolling_corr(arg1=bytes_df_odd['bytes'],arg2=bytes_df_even['bytes'].shift(-24,'H'),window=24)
#corr = pd.rolling_corr(arg1=bytes_df_odd['bytes'],arg2=bytes_df_even['bytes'],window=24)
corr = bytes_df_odd['bytes'].rolling(window=24).corr(
other=bytes_df_even['bytes'])
ax2 = ax1.twinx()
lns3 = ax2.plot(corr, 'r-', label='Correlation', visible=True)
lns = lns1 + lns2 + lns3
labs = [l.get_label() for l in lns]
ax1.legend(lns, labs, loc=0)
ax2.set_ylabel('Correlation Coefficient', color='r', fontsize=18)
for tl in ax2.get_yticklabels():
tl.set_color('r')
plt.show()
raw_input('End')
print 'Even/Odd correlation: %s' % bytes_df_odd.corrwith(
bytes_df_even).bytes
bitcoin_arima = results.forecast(steps=31)[0][1:]
bitcoin_future = pd.read_csv('bitcoin_future.csv')
np.sqrt((bitcoin_future['Closing'] - bitcoin_arima)**2).sum()
# In[41]:
bitcoin_arima
# ### q12 - Periodogram
# In[26]:
# https://www.statsmodels.org/dev/generated/statsmodels.tsa.stattools.periodogram.html
from statsmodels.tsa.stattools import periodogram
plt.plot(periodogram(bprice))
plt.show()
plt.plot(periodogram(bprice_1d))
# ### There is no seasonality
# #### Q13
# In[27]:
final_1d = final_date_2017.diff().dropna()
final_1d
from statsmodels.tsa.vector_ar import var_model
var = var_model.VAR(final_1d)
np.argmin(var.select_order().ics['aic'])
var_results = var.fit(maxlags=1)
def periodogram(timeSeries):
# Returns the periodogram for the natural frequency of X
values_periodograk = stattools.periodogram(timeSeries)