def tst_sim_2():
k = 0.8
lmb = 2.0
s_n1n2 = 0
s_n1 = 0
s_n2 = 0
s_n1_sq = 0
s_n2_sq = 0
n_sim = 5000
for _ in range(n_sim):
intervals1 = lomax.rvs(c=k, scale=(1 / lmb), size=800)
intervals2 = lomax.rvs(c=k, scale=(1 / lmb), size=800)
#intervals = np.random.exponential(scale=1,size=1000)
time_stamps1 = np.cumsum(intervals1)
time_stamps2 = np.cumsum(intervals2)
n1 = sum((time_stamps1 > 400) * (time_stamps1 < 900))
n2 = sum((time_stamps2 > 400) * (time_stamps2 < 900))
s_n1n2 += n1 * n2
s_n1_sq += n1 * n1
s_n2_sq += n2 * n2
s_n1 += n1
s_n2 += n2
cov = s_n1n2 / n_sim - (s_n1 / n_sim) * (s_n2 / n_sim)
v_n1 = s_n1_sq / n_sim - (s_n1 / n_sim)**2
v_n2 = s_n2_sq / n_sim - (s_n2 / n_sim)**2
corln = cov / np.sqrt(v_n1 * v_n2)
print("correlation: " + str(corln))
def get_number_records_lomax(c=0.5, size=1000, discretize=True):
if discretize:
sample = np.ceil(lomax.rvs(c=c, size=size))
else:
sample = lomax.rvs(c=c, size=size)
return len(GeneralUtils.get_record_indexes(sample))
def tst_sim_3(k=7.0, theta=0.5):
s_n1n2 = 0
s_n1 = 0
s_n2 = 0
s_n1_sq = 0
s_n2_sq = 0
n_sim = 5000
for _ in range(n_sim):
intervals = lomax.rvs(c=k, scale=theta, size=2000)
#intervals = np.random.exponential(scale=1,size=1000)
time_stamps = np.cumsum(intervals)
bi_furcator = np.random.choice(2, size=len(time_stamps))
time_stamps1 = time_stamps[bi_furcator == 1]
time_stamps2 = time_stamps[bi_furcator == 0]
n1 = sum((time_stamps1 > 50) * (time_stamps1 < 90))
n2 = sum((time_stamps2 > 50) * (time_stamps2 < 90))
s_n1n2 += n1 * n2
s_n1_sq += n1 * n1
s_n2_sq += n2 * n2
s_n1 += n1
s_n2 += n2
cov = s_n1n2 / n_sim - (s_n1 / n_sim) * (s_n2 / n_sim)
v_n1 = s_n1_sq / n_sim - (s_n1 / n_sim)**2
v_n2 = s_n2_sq / n_sim - (s_n2 / n_sim)**2
corln = cov / np.sqrt(v_n1 * v_n2)
print("correlation: " + str(corln))
def lomax_exponmix():
#### Verify Lomax equivalence with exponential-mix.
k=4; theta=0.1
## In numpy's definition, the scale, theta is inverse of Ross definition.
lm = np.random.gamma(k,1/theta,size=1000)
lomax_mix=np.random.exponential(1/lm)
mean1=np.mean(lomax_mix)
lomax_direct=lomax.rvs(c=k,scale=theta,size=1000)
mean2=np.mean(lomax_direct)
mean3 = theta/(k-1)
def samples(self, k=None, lmb=None, size=1000, params=None):
'''
Generates samples for the Lomax distribution.
args:
k: Shape of Lomax.
lmb: Scale of Lomax.
size: The number of simulations to be generated.
params: A 2-d array with shape and scale parameters.
'''
[k, lmb] = self.determine_params(k, lmb, params)
return lomax.rvs(c=k, scale=(1 / lmb), size=size)
def sim_lomax():
c = 1.88
mean, var, skew, kurt = lomax.stats(c, moments='mvsk')
print(1 / mean)
catches = 0
for _ in range(10000):
j = np.random.uniform() * 1000
t_i = 0
while t_i < j + 500:
t_i += lomax.rvs(c)
if j < t_i and t_i < j + 1:
catches += 1
print(catches / 10000)
def sim_lomax(intr_strt=20):
c = 1.88
mean, var, skew, kurt = lomax.stats(c, moments='mvsk')
print(1 / mean)
catches = 0
for _ in range(10000):
j = intr_strt
t_i = 0
while t_i < j + 50:
t_i += lomax.rvs(c)
if j < t_i and t_i < j + 1:
catches += 1
print(catches / 10000)
def lomax_renewal_correlation(k=2.0, theta=1.0):
s_n1 = 0
n_sim = 5000
for _ in range(n_sim):
intervals = lomax.rvs(c=k, scale=theta, size=1200)
#intervals = np.random.exponential(scale=1,size=1000)
time_stamps = np.cumsum(intervals)
#n1 = sum((time_stamps>100) * (time_stamps<200))
n1 = sum(time_stamps < 100)
s_n1 += n1
e_n1 = s_n1 / n_sim
print("simulated mean: " + str(e_n1))
#print("actual mean-1: " +str(k*200/theta))
print("actual mean-2: " + str((k - 1) * 200 / theta))
def sim_lomax_v2():
c = 1.88
catches = 0
catches2 = 0
total_t = 0
for _ in range(20000):
j = np.random.uniform() * 1000
t_i = 0
tt = 0
catches1 = -1
while t_i < j + 100:
t_i += lomax.rvs(c)
if j < t_i and t_i < j + 30:
tt = t_i
catches += 1
catches1 += 1
total_t += max((tt - j), 0)
catches2 += max(0, catches1)
print(catches / 20000 / 30)
print(catches2 / total_t)
def _generate_timestamps(self, last=None):
"""Generate list of timestamps.
Args:
last (datetime, optional): Datetime of last message. If ``None``, defaults to current date.
Returns:
list: List with timestamps.
"""
if not last:
last = datetime.now()
last = last.replace(microsecond=0)
c = 1.0065
scale = 40.06
loc = 30
ts_ = [0] + lomax.rvs(c=c,
loc=loc,
scale=scale,
size=self.size - 1,
random_state=self.seed).cumsum().tolist()
ts = [last - timedelta(seconds=t * 60) for t in ts_]
return ts[::-1]
def comparisson_number_of_records_lomax(c):
highest = 10**6
_ns = list()
_num_records = list()
_num_integer_records = list()
for n in range(10, highest + 1, 10000):
sample = lomax.rvs(c=c, size=n)
_integer_sample = np.ceil(sample)
_index_records = GeneralUtils.get_record_indexes(sample)
_integer_index_records = GeneralUtils.get_record_indexes(
_integer_sample)
_ns.append(n)
_num_records.append(len(_index_records))
_num_integer_records.append(len(_integer_index_records))
print(_num_records)
print(_num_integer_records)
plt.scatter(_ns, _num_records)
plt.scatter(_ns, _num_integer_records)
plt.show()
def rvs_fn4(n):
return lomax.rvs(c=.9, size=n)
def samples_(k, lmb, size=1000):
return lomax.rvs(c=k, scale=(1 / lmb), size=size)
# Display the probability density function (``pdf``): x = np.linspace(lomax.ppf(0.01, c), lomax.ppf(0.99, c), 100) ax.plot(x, lomax.pdf(x, c), 'r-', lw=5, alpha=0.6, label='lomax pdf') # Alternatively, the distribution object can be called (as a function) # to fix the shape, location and scale parameters. This returns a "frozen" # RV object holding the given parameters fixed. # Freeze the distribution and display the frozen ``pdf``: rv = lomax(c) ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf') # Check accuracy of ``cdf`` and ``ppf``: vals = lomax.ppf([0.001, 0.5, 0.999], c) np.allclose([0.001, 0.5, 0.999], lomax.cdf(vals, c)) # True # Generate random numbers: r = lomax.rvs(c, size=1000) # And compare the histogram: ax.hist(r, density=True, histtype='stepfilled', alpha=0.2) ax.legend(loc='best', frameon=False) plt.show()
# 947,649,385
import matplotlib.pyplot as plt
plt.scatter(grid.predict(x_test), y_test)
# # plt.hist(alpha.rvs(1000, size = 100))
# # plt.hist(uniform.rvs(1e-20, 1e-3, size=1000))
# gamma.rvs(0.1, size = 1000)
from scipy.stats import lognorm
# plt.hist([grid.predict(x_test), y_test])
# plt.hist(gamma.rvs(10, size = 1000))
# plt.hist(gamma.rvs(100, size = 1000))
# plt.hist(gamma.rvs(1000, size = 1000))
# plt.hist(gamma.rvs(10000, size = 1000))
# # betaprime.rvs(12, 100000, size=1000)
#
lomax.rvs(100000, size=10000)
uniform.rvs(0.00001, 0.1, size=1000)
lomax.rvs(2, size=100)
#
#
test_data = pd.read_csv(os.path.join(
os.path.dirname(os.path.abspath("__file__")), 'amnes/data/test.csv'),
index_col="Id")
#
#
test_data_num = VariableSelector(
variable_type="numeric").fit_transform(test_data)
test_data_cat = VariableSelector(
variable_type="categorical").fit_transform(test_data)
test_data_num.shape
def samples(self, k=None, lmb=None, size = 1000, params = None):
[k, lmb] = self.determine_params(k, lmb, params)
return lomax.rvs(c=k, scale=(1 / lmb), size=size)
