def compute_likeness(A, B, masks):
""" Predicts the likelihood that each pixel in B belongs to a phase based
on the histogram of A.
Parameters
------------
A : ndarray
B : ndarray
masks : list of ndarrays
Returns
--------------
likelihoods : list of ndarrays
"""
# generate the pdf or pmf for each of the phases
pdfs = []
for m in masks:
K, mu, std = exponnorm.fit(np.ravel(A[m > 0]))
print((K, mu, std))
# for each reconstruciton, plot the likelihood that this phase
# generates that pixel
pdfs.append(exponnorm.pdf(B, K, mu, std))
# determine the probability that it belongs to its correct phase
pdfs_total = sum(pdfs)
return pdfs / pdfs_total
def standardize(df, method='z-score'):
n=0
df['standardized_RT'] = np.nan
print('megvan az ures oszlop')
subjects = df.Subject.unique()
if method == 'z-score':
for subject in subjects:
n+=1
x = np.asarray(df[df.Subject == subject].firstRT)
# we check whether we have all datapoints
if np.isnan(x)[np.isnan(x) == True].size > 0:
# if we miss some, we leave them out, so that fitting does not crash
print('WARNING! This subject had missing datapoints.')
x = [n for n in x if str(n) != 'nan']
# get parameters of the subject
m=np.mean(x)
stdev=np.std(x)
# compute standardized scores
for index, row in df[df.Subject == subject].iterrows():
raw_RT = row['firstRT']
standardized_value = (raw_RT - m) / stdev
df.loc[index, 'standardized_RT'] = standardized_value
print "we are ready with " + str(n) + " subjects"
elif method == 'exgauss':
for subject in subjects:
n+=1
x = np.asarray(df[df.Subject == subject].firstRT)
# we check whether we have all datapoints
if np.isnan(x)[np.isnan(x) == True].size > 0:
# if we miss some, we leave them out, so that fitting does not crash
print('WARNING! This subject had missing datapoints.')
x = [n for n in x if str(n) != 'nan']
# we get the parameters of the subject
shape_,loc_,scale_=exponnorm.fit(x)
lambda_=(shape_*scale_)**(-1)
tau_=1/lambda_
# compute standardized scores
for index, row in df[df.Subject == subject].iterrows():
raw_RT = row['firstRT']
standardized_value = (raw_RT - loc_) / scale_
df.loc[index, 'standardized_RT'] = standardized_value
print "we are ready with " + str(n) + " subjects"
return df
def make_params_df(RTs,all_high_low):
params_df=pd.DataFrame()
subjects=[]
age_groups=[]
locs=[]
scales=[]
ts=[]
ps=[]
for group,values in RTs.iteritems():
for subject in values:
x = np.asarray(RTs[group][subject])
print 'Reaction time data of the participant - for fitting'
print x
# we check whether we have all datapoints
if np.isnan(x)[np.isnan(x) == True].size > 0:
# if we miss some, we leave them out, so that fitting does not crash
print('WARNING! This subject had missing datapoints.')
x = [n for n in x if str(n) != 'nan']
# ExGaussian parameters for subject
shape_,loc_,scale_=exponnorm.fit(x)
lambda_=(shape_*scale_)**(-1)
tau_=1/lambda_
# test goodness of fit with Kolgomorov-Smirnov
d,p = stats.kstest(x, 'exponnorm', args=(shape_,loc_,scale_))
subjects.append(subject)
age_groups.append(group)
locs.append(loc_)
scales.append(scale_)
ts.append(tau_)
ps.append(p)
# add the results to the df
params_df['Subject'] = np.asarray(subjects)
params_df['age_group'] = np.asarray(age_groups)
params_df['mu_'+all_high_low] = np.asarray(locs)
params_df['sigma_'+all_high_low] = np.asarray(scales)
params_df['tau_'+all_high_low] = np.asarray(ts)
params_df['goodness_'+all_high_low] = np.asarray(ps)
return params_df
def main():
symbol = 'BTCUSDT'
start = int(datetime.datetime.timestamp(datetime.datetime(2019, 6, 1))) * 1000 - 365 * 24 * 60 * 60 * 1000
previous = start
trades = []
total_trades = 0
max_trades = 0
time_step = 1
with open('../Binance/' + symbol + '.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile)
for line in reader:
if int(line['Timestamp']) > previous + time_step * 60 * 60 * 1000:
previous += time_step * 60 * 60 * 1000
trades.append(total_trades)
if max_trades < total_trades:
max_trades = total_trades
total_trades = 0
total_trades += 1
mean = np.mean(trades)
print(mean)
trades = [t for t in trades if t != 1]
#mean, scale = norm.fit(np.log(trades))
a, loc, scale = skewnorm.fit(np.log(trades))
loc_n, scale_n = norm.fit(np.log(trades))
k, loc_ne, scale_ne = exponnorm.fit(np.log(trades))
plt.hist(np.log(trades), bins=100, density=True)
x = np.linspace(6, 12, 100)
plt.plot(x, skewnorm.pdf(x, a, loc=loc, scale=scale), label='skewnorm')
plt.plot(x, norm.pdf(x, loc=loc_n, scale=scale_n), label='norm')
plt.plot(x, exponnorm.pdf(x, k, loc=loc_n, scale=scale_n), label='Exponentially modified Gaussian')
plt.xlabel('Log Trades')
plt.ylabel('Density')
plt.legend()
#plt.plot([i for i in range(1, max_trades)], poisson_density(np.array([i for i in range(1, max_trades)]), mean))
#plt.plot([i for i in range(0, max_trades)], norm.pdf([i for i in range(max_trades)], loc=mean, scale=np.sqrt(mean)))
plt.savefig(symbol + ' log Trades')
plt.show()