def test_hyper():
for x in sorted(exparg):
test("erf", x, N(sp.erf(x)))
for x in sorted(exparg):
test("erfc", x, N(sp.erfc(x)))
gamarg = FiniteSet(*(x+S(1)/12 for x in exparg))
betarg = ProductSet(gamarg, gamarg)
for x in sorted(gamarg):
test("lgamma", x, N(sp.log(abs(sp.gamma(x)))))
for x in sorted(gamarg):
test("gamma", x, N(sp.gamma(x)))
for x, y in sorted(betarg, key=lambda (x, y): (y, x)):
test("beta", x, y, N(sp.beta(x, y)))
pgamarg = FiniteSet(S(1)/12, S(1)/3, S(3)/2, 5)
pgamargp = ProductSet(gamarg & Interval(0, oo, True), pgamarg)
for a, x in sorted(pgamargp):
test("pgamma", a, x, N(sp.lowergamma(a, x)))
for a, x in sorted(pgamargp):
test("pgammac", a, x, N(sp.uppergamma(a, x)))
for a, x in sorted(pgamargp):
test("pgammar", a, x, N(sp.lowergamma(a, x)/sp.gamma(a)))
for a, x in sorted(pgamargp):
test("pgammarc", a, x, N(sp.uppergamma(a, x)/sp.gamma(a)))
for a, x in sorted(pgamargp):
test("ipgammarc", a, N(sp.uppergamma(a, x)/sp.gamma(a)), x)
pbetargp = [(a, b, x) for a, b, x in ProductSet(betarg, pgamarg)
if a > 0 and b > 0 and x < 1]
pbetargp.sort(key=lambda (a, b, x): (b, a, x))
for a, b, x in pbetargp:
test("pbeta", a, b, x, mp.betainc(mpf(a), mpf(b), x2=mpf(x)))
for a, b, x in pbetargp:
test("pbetar", a, b, x, mp.betainc(mpf(a), mpf(b), x2=mpf(x),
regularized=True))
for a, b, x in pbetargp:
test("ipbetar", a, b, mp.betainc(mpf(a), mpf(b), x2=mpf(x),
regularized=True), x)
for x in sorted(posarg):
test("j0", x, N(sp.besselj(0, x)))
for x in sorted(posarg):
test("j1", x, N(sp.besselj(1, x)))
for x in sorted(posarg-FiniteSet(0)):
test("y0", x, N(sp.bessely(0, x)))
for x in sorted(posarg-FiniteSet(0)):
test("y1", x, N(sp.bessely(1, x)))
def _f_cdf(dfn, dfd, x):
if x < 0:
return mpmath.mpf(0)
dfn, dfd, x = mpmath.mpf(dfn), mpmath.mpf(dfd), mpmath.mpf(x)
ub = dfn*x/(dfn*x + dfd)
res = mpmath.betainc(dfn/2, dfd/2, x2=ub, regularized=True)
return res
def test_btdtria(self):
_assert_inverts(
sp.btdtria,
lambda a, b, x: mpmath.betainc(a, b, x2=x, regularized=True),
0, [ProbArg(), Arg(0, 1e3, inclusive_a=False),
Arg(0, 1, inclusive_a=False, inclusive_b=False)],
rtol=1e-6)
def e_ratio(a,b,e,x): # Get S bt2 = mp.beta(a,b-1.0) # Beta function bix = mp.betainc(a,b+1.0,0.0,e) # Incomplete Beta function hf = mp.hyp2f1(1.0,a,a+b-1.0,-1.0) # 2F1, Gauss' hypergeometric function hfre = mp.re(hf) Sval = bix - x*bt2*hfre # Get U c1 = mp.mpc(1.0 + a) c2 = mp.mpc(-b) c3 = mp.mpc(1.0) c4 = mp.mpc(2.0 + a) Uval = mp.appellf1(c1,c2,c3,c4,e,-e) Ure = mp.re(Uval) # Get P & Q Pval = mp.hyp2f1(a+1.0,1.0-b,a+2.0,e) # 2F1, Gauss' hypergeometric function Pre = mp.re(Pval) Qval = mp.hyp2f1(a+1.0,2.0-b,a+2.0,e) # 2F1, Gauss' hypergeometric function Qre = mp.re(Qval) # Get T Tval = ( (e**(1.0+a)) / (1.0+a) )*( 3.0*Pre + 2.0*Qre - Ure ) Tval = Tval + 4.0*Sval # Get Rval (ratio) Rval = 0.25*(1.0-e*e)*( (1.0-e)**(1.0-b) )*( e**(1.0-a) )*Tval return Rval
def e_ratio(a, b, e, x):
# Get S
bt2 = mp.beta(a, b - 1.0) # Beta function
bix = mp.betainc(a, b + 1.0, 0.0, e) # Incomplete Beta function
hf = mp.hyp2f1(1.0, a, a + b - 1.0,
-1.0) # 2F1, Gauss' hypergeometric function
hfre = mp.re(hf)
Sval = bix - x * bt2 * hfre
# Get U
c1 = mp.mpc(1.0 + a)
c2 = mp.mpc(-b)
c3 = mp.mpc(1.0)
c4 = mp.mpc(2.0 + a)
Uval = mp.appellf1(c1, c2, c3, c4, e, -e)
Ure = mp.re(Uval)
# Get P & Q
Pval = mp.hyp2f1(a + 1.0, 1.0 - b, a + 2.0,
e) # 2F1, Gauss' hypergeometric function
Pre = mp.re(Pval)
Qval = mp.hyp2f1(a + 1.0, 2.0 - b, a + 2.0,
e) # 2F1, Gauss' hypergeometric function
Qre = mp.re(Qval)
# Get T
Tval = ((e**(1.0 + a)) / (1.0 + a)) * (3.0 * Pre + 2.0 * Qre - Ure)
Tval = Tval + 4.0 * Sval
# Get Rval (ratio)
Rval = 0.25 * (1.0 - e * e) * (
(1.0 - e)**(1.0 - b)) * (e**(1.0 - a)) * Tval
return Rval
def beta_cdf(x, a, b):
if x <= S(0):
return Float('0.0')
if x >= S(1):
return Float('1.0')
mpmath.mp.dps = 500
result = mpmath.betainc(to_mpmath(a), to_mpmath(b), 0, to_mpmath(x), regularized=True)
return Float(result)
def multi_winner_ode(c, y, n, k):
w = y[0] #input comes in as an array
c = mp.mpf(c)
w = mp.mpf(w)
num = -2**(-n) * (2-c)**(n-k-1) * c**(k-1) * (2*c - w - 2) * (w-2)
denom = (c-w) * mp.beta(k, n-k) * mp.betainc(k, n-k, 0, c/2, regularized=True)
return num/denom
def test_btdtrib(self):
# Use small values of a or mpmath doesn't converge
_assert_inverts(
sp.btdtrib,
lambda a, b, x: mpmath.betainc(a, b, x2=x, regularized=True),
1, [Arg(0, 1e2, inclusive_a=False), ProbArg(),
Arg(0, 1, inclusive_a=False, inclusive_b=False)],
rtol=1e-7, endpt_atol=[None, 1e-20, 1e-20])
def cdf(k, p):
"""
CDF of the log-series distribution.
"""
p = _validate_p(p)
if k < 1:
return _mpm.mp.zero
with _mpm.extradps(5):
return 1 + _mpm.betainc(k + 1, 0, 0, p) / _mpm.log1p(-p)
def _binomial_cdf(k, n, p):
k, n, p = mpmath.mpf(k), mpmath.mpf(n), mpmath.mpf(p)
if k <= 0:
return mpmath.mpf(0)
elif k >= n:
return mpmath.mpf(1)
onemp = mpmath.fsub(1, p, exact=True)
return mpmath.betainc(n - k, k + 1, x2=onemp, regularized=True)
def sf(k, p):
"""
Survival function of the log-series distribution.
"""
p = _validate_p(p)
if k < 1:
return _mpm.mp.one
with _mpm.extradps(5):
return -_mpm.betainc(k + 1, 0, 0, p) / _mpm.log1p(-p)
def sf(x, dfn, dfd):
"""
Survival function of the F distribution.
`dfn` and `dfd` are the numerator and denominator degrees of freedom, resp.
"""
if x <= 0:
return mpmath.mp.one
with mpmath.mp.extradps(5):
x = mpmath.mp.mpf(x)
dfn = mpmath.mp.mpf(dfn)
dfd = mpmath.mp.mpf(dfd)
dfnx = dfn * x
return mpmath.betainc(dfn/2, dfd/2, x1=dfnx/(dfnx + dfd),
regularized=True)
def sf(a, b=np.inf, dps=15):
dps_temp = mp.mp.dps
mp.mp.dps = dps
tmp_a = d1*a/d2
tmp_b = d1*b/d2
beta_a = tmp_a / (1. + tmp_a)
beta_b = tmp_b / (1. + tmp_b)
if b == np.inf:
beta_b = 1.
sf = mp.betainc(d1/2., d2/2.,
x1=beta_a, x2=beta_b,
regularized=True)
mp.mp.dps = dps_temp
return sf
def flex(c,y,n,k):
j = n-1
# n here is other number of players aka N-1
# k is # number of winners
w = y[0]
# print(c,w,n,k)
# num = (1-c)**j * c**k * (-1+w) * (1-2*c+w) * gamma(1+j) * gamma(1-k+j)**2
# denom = -2 * (1 - c)**k * c * (c - w) * gamma(k) * gamma(1 - k + j) + 2 * (1 - c)**j * c**(1 + k) * (c - w) * gamma(k) * gamma(1+j) * hyp2f1(1, k - j, 1 + k, c/(-1 + c))
# print(c**(k-1))
# print(k,j+1-k)
# print(betainc(c, k, j+1-k))
# print(betainc(np.float64(.999),2.0,1.0))
c = mp.mpf(c)
w = mp.mpf(w)
num = -(1-c)**(j-k) * c**(k-1) * (w-1) * (1-2*c + w)
# print(num)
denom = 2 * beta(k, j+1-k) * (1 - mp.betainc(k, j+1-k, 0, c, regularized=True)) * (c-w)
# print(num)
# print(denom)
return num/denom
def F_int_func(i, a, b, c, A, x, verbose=False): beta_inc = special.betainc(A, i+1, x) if not(beta_inc ): alt = F_int_func2(i, a, b, c, A, x, verbose=False) if verbose: print 'rounding error 1', i, beta_inc, special.betaln(A, i+1), mpmath.betainc(A, i+1, x), alt return alt beta_inc = 10e-320 liter = math.lgamma(a+i) - math.lgamma(a) \ + math.lgamma(b+i) - math.lgamma(b) \ + math.lgamma(c) - math.lgamma(c+i) \ - math.lgamma(i+1) \ + math.log( beta_inc ) \ + special.betaln(A, i+1) if liter > 709.: # if verbose: print 'rounding error 2', i, liter = 709. return math.exp(liter)
def test_betainc(self):
assert_mpmath_equal(sc.betainc,
_exception_to_nan(lambda a, b, x: mpmath.betainc(a, b, 0, x, regularized=True)),
[Arg(), Arg(), Arg()])
#!/usr/bin/python
"""
"""
import mpmath as mp
import numpy as np
import sys
mp.mp.dps = 30
a = float(sys.argv[1])
b = float(sys.argv[2])
x_lo = float(sys.argv[3])
n = int (sys.argv[4])
for x in np.logspace(x_lo, 0, n) :
x = mp.mpf(x)
with mp.extradps(300) :
y = mp.betainc(a, b, 0, x, regularized=True)
print x, y
def cdf(d1, d2, x):
d1, d2, x = map(mpf, (d1, d2, x))
return mp.betainc(d1/2, d2/2, x2=x/(x+d2/d1), regularized=True)
def cdf(k, x):
k, x = map(mpf, (k, x))
return .5 + .5*mp.sign(x)*mp.betainc(k/2, .5, x1=1/(1+x**2/k),
regularized=True)
plt.plot(
x,
y,
label=
f"{name} sample, conversion rate: {y_mode:0.1E} $\pm$ {y_var:0.1E}"
)
plt.yticks([])
plt.legend()
plt.show()
plot([beta_C, beta_T], names=["Control", "Test"])
from mpmath import betainc
p = betainc(a_T, b_T, 0.003, 1, regularized=True) #result: 0.48112566853812544
import seaborn as sns
import pandas as pd
import numpy as np
imps_ctrl, convs_ctrl = 16500, 30
imps_test, convs_test = 17000, 50
#here we create the Beta functions for the two sets
a_C, b_C = convs_ctrl + 1, imps_ctrl - convs_ctrl + 1
a_T, b_T = convs_test + 1, imps_test - convs_test + 1
val_C = np.random.beta(a_C, b_C, 1000000)
val_T = np.random.beta(a_T, b_T, 1000000)
vals = np.vstack([val_C, val_T]).T
mp.dps = 1000
mp.pretty = True
n = 4
j = n-1
# n here is other number of players aka N-1
# k is # number of winners
k = 2
H = lambda c, w: (-(1-c)**(j-k) * c**(k-1) * (w-1) * (1-2*c + w))/(2 * mp.beta(k, j+1-k) * (1 - mp.betainc(k, j+1-k, 0, c, regularized=True)))
G = lambda c, w: (-(1-c)**(j-k) * c**(k-1) * (w-1) * (1-2*c + w))/(2 * beta(k, j+1-k) * (1 - mp.betainc(k, j+1-k, 0, c, regularized=True)))
num = lambda c, w: -(1-c)**(j-k) * c**(k-1) * (w-1) * (1-2*c + w)
denom = lambda c,w: 2 * mp.beta(k, j+1-k) * (1 - mp.betainc(k, j+1-k, 0, c, regularized=True))
func = lambda c, w: (2**(-1 - n) * (2 - c)**(-k + n) * c**(-1 + k) * (-4 + 4 * c - 2 * c * w + w**2)) \
/ (mp.beta(k, 1 - k + n)* (-1 + mp.betainc( k, 1 - k + n,0, c/2) * (c - w)))
print(H(.2,.5))
print(G(.2,.5))
c_end = mp.mpf('0')
c_0 = mp.mpf('1.995')
w_0 = mp.mpf('1.99')
w_c = [w_0]
cs = [c_0]
def _h(self, c):
c = np.complex(c)
f1 = -(-c) ** self.alpha * c ** self.alpha
f2 = mpmath.betainc(-c, 3 - self.alpha, self.alpha - 2)
return (f1 * f2).real
