Related
I'm trying to write a function to evaluate the probability mass function for the bivariate poisson distribution.
This is easy when all of the parameters (x, y, theta1, theta2, theta0) are scalars, but tricky to scale up without loops to allow these parameters to be vectors. I need it to scale such that, for:
theta0 being a scalar - the "correlation parameter" in the equation
theta1 and theta2 having length l
x, y both having length n
the output array would have shape (l, n, n). For example, a slice [j, :, :] from the output array would look like:
The first part (the constant, before the summation) I think i've figured out:
import numpy as np
from scipy.special import factorial
def constant(theta1, theta2, theta0, x, y):
exponential_part = np.exp(-(theta1 + theta2 + theta0)).reshape(-1, 1, 1)
x = np.tile(x, (len(x), 1)).transpose()
y = np.tile(y, (len(y), 1))
double_factorial = (np.power(np.array(theta1).reshape(-1, 1, 1), x)/factorial(x)) * \
(np.power(np.array(theta2).reshape(-1, 1, 1), y)/factorial(y))
return exponential_part * double_factorial
But I'm struggling with the summation part. How can I vectorize a summation where the limits depend on variable arrays?
I think I have this figured out, based on the approach that #w-m suggests: calculate every possible summation term which could appear, based on the maximum x or y value which appears, and use a mask to get rid of the ones you don't want. Assuming you have your x and y terms go from 0 to N, in consecutive order, this is calculating up to three times more terms than are actually required, but this is offset by getting to use vectorization.
Reference implementation
I wrote this by first writing a pure-Python reference implementation, which just implements your problem using loops. With 4 nested loops, it's not exactly fast, but it's handy to have while testing the numpy version.
import numpy as np
from scipy.special import factorial, comb
import operator as op
from functools import reduce
def choose(n, r):
# https://stackoverflow.com/a/4941932/530160
r = min(r, n-r)
numer = reduce(op.mul, range(n, n-r, -1), 1)
denom = reduce(op.mul, range(1, r+1), 1)
return numer // denom # or / in Python 2
def reference_impl_constant(s_theta1, s_theta2, s_theta0, s_x, s_y):
# Cast to float to prevent overflow
s_theta1 = float(s_theta1)
s_theta2 = float(s_theta2)
s_theta0 = float(s_theta0)
s_x = float(s_x)
s_y = float(s_y)
term1 = np.exp(-(s_theta1 + s_theta2 + s_theta0))
term2 = (s_theta1 ** s_x / factorial(s_x))
term3 = (s_theta2 ** s_y / factorial(s_y))
assert term1 >= 0
assert term2 >= 0
assert term3 >= 0
return term1 * term2 * term3
def reference_impl_constant_loop(theta1, theta2, theta0, x, y):
theta_len = theta1.shape[0]
xy_len = x.shape[0]
constant_array = np.zeros((theta_len, xy_len, xy_len))
for i in range(theta_len):
for j in range(xy_len):
for k in range(xy_len):
s_theta1 = theta1[i]
s_theta2 = theta2[i]
s_theta0 = theta0
s_x = x[j]
s_y = y[k]
constant_term = reference_impl_constant(s_theta1, s_theta2, s_theta0, s_x, s_y)
assert constant_term >= 0
constant_array[i, j, k] = constant_term
return constant_array
def reference_impl_summation(s_theta1, s_theta2, s_theta0, s_x, s_y):
sum_ = 0
for i in range(min(s_x, s_y) + 1):
sum_ += choose(s_x, i) * choose(s_y, i) * factorial(i) * ((s_theta0/s_theta1/s_theta2) ** i)
assert sum_ >= 0
return sum_
def reference_impl_summation_loop(theta1, theta2, theta0, x, y):
theta_len = theta1.shape[0]
xy_len = x.shape[0]
summation_array = np.zeros((theta_len, xy_len, xy_len))
for i in range(theta_len):
for j in range(xy_len):
for k in range(xy_len):
s_theta1 = theta1[i]
s_theta2 = theta2[i]
s_theta0 = theta0
s_x = x[j]
s_y = y[k]
summation_term = reference_impl_summation(s_theta1, s_theta2, s_theta0, s_x, s_y)
assert summation_term >= 0
summation_array[i, j, k] = summation_term
return summation_array
def reference_impl(theta1, theta2, theta0, x, y):
# all array inputs must be 1D
assert len(theta1.shape) == 1
assert len(theta2.shape) == 1
assert len(x.shape) == 1
assert len(y.shape) == 1
# theta vectors must have same length
theta_len = theta1.shape[0]
assert theta2.shape[0] == theta_len
# x and y must have same length
xy_len = x.shape[0]
assert y.shape[0] == xy_len
# theta0 is scalar
assert isinstance(theta0, (int, float))
constant_array = np.zeros((theta_len, xy_len, xy_len))
output = np.zeros((theta_len, xy_len, xy_len))
constant_array = reference_impl_constant_loop(theta1, theta2, theta0, x, y)
summation_array = reference_impl_summation_loop(theta1, theta2, theta0, x, y)
output = constant_array * summation_array
return output
Numpy implementation
I split the implementation of this across two functions.
The fast_constant() function calculates everything to the left of the summation symbol. The fast_summation() function calculates everything inside the summation symbol.
import numpy as np
from scipy.special import factorial, comb
def fast_summation(theta1, theta2, theta0, x, y):
x = np.tile(x, (len(x), 1)).transpose()
y = np.tile(y, (len(y), 1))
sum_limit = np.minimum(x, y)
max_sum_limit = np.max(sum_limit)
i = np.arange(max_sum_limit + 1).reshape(-1, 1, 1)
summation_mask = (i <= sum_limit)
theta_ratio = (theta0 / (theta1 * theta2)).reshape(-1, 1, 1, 1)
theta_to_power = np.power(theta_ratio, i)
terms = comb(x, i) * comb(y, i) * factorial(i) * theta_to_power
# mask out terms which aren't part of sum
terms *= summation_mask
# axis 0 is theta
# axis 1 is i
# axis 2 & 3 are x and y
# so sum across axis 1
terms = terms.sum(axis=1)
return terms
def fast_constant(theta1, theta2, theta0, x, y):
theta1 = theta1.astype('float64')
theta2 = theta2.astype('float64')
exponential_part = np.exp(-(theta1 + theta2 + theta0)).reshape(-1, 1, 1)
# x and y must be 1D
assert len(x.shape) == 1
assert len(y.shape) == 1
# x and y must have same shape
assert x.shape == y.shape
x_len, y_len = x.shape[0], y.shape[0]
x = x.reshape((x_len, 1))
y = y.reshape((1, y_len))
double_factorial = (np.power(np.array(theta1).reshape(-1, 1, 1), x)/factorial(x)) * \
(np.power(np.array(theta2).reshape(-1, 1, 1), y)/factorial(y))
return exponential_part * double_factorial
def fast_impl(theta1, theta2, theta0, x, y):
return fast_summation(theta1, theta2, theta0, x, y) * fast_constant(theta1, theta2, theta0, x, y)
Benchmarking
Assuming that X and Y range from 0 to 20, and that theta is centered somewhere inside that range, I get the result that the numpy version is roughly 280 times faster than the pure python reference.
Numerical stability
I'm unsure how numerically stable this is. For example, when I center theta at 100, I get a floating-point overflow. Typically, when computing an expression which has lots of choose and factorial expressions inside it, you'll use some mathematical equivalent which results in smaller intermediate sums. In this case I have so little understanding of the math that I don't know how you'd do that.
I set a function like that:
def triangular(x, a, b, c):
if x <= a:
return 0
if a < x <= b:
return (x - a)/(b - a)
if b < x <= c:
return (c - x)/(c - b)
if c < x:
return 0
I want to draw the image of this function so I use:
x = range(-10, 10, 0.1)
y = triangular(x,1,2,3)
plt.figure()
plt.plot(x,y)
plt.show()
However, it shows error:'float' object cannot be interpreted as an integer, why? need I correct my function or input?
I tried to change to
x = np.arange(-10, 10, 0.1)
y = triangular(x,1,2,3)
plt.figure()
plt.plot(x,y)
plt.show()
it shows
The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
Instead of
x = range(-10, 10, 0.1)
y = triangular(x,1,2,3)
use
import numpy as np
...
x = np.arange(-10, 10, 0.1)
y = [triangular(elem_x,1,2,3) for elem_x in x]
You can also use NumPy indexing and masking to approach this problem avoiding for loops. Below is how you can do it. The conditions I am writing inside the function triangular in the square brackets [...] are just the boundary conditions described in your problem. It is more intuitive in the way it is written
def triangular(x, a, b, c):
x[x<=a] = 0
x[(a<x) & (x<=b)] = (x[(a<x) & (x<=b)] - a)/(b - a)
x[(b<x) & (x<=c)] = (c - x[(b<x) & (x<=c)])/(c - b)
x[x>c] = 0
return x
x = np.arange(-10, 10, 0.1)
y = triangular(x.copy(),1,2,3)
plt.figure()
plt.plot(x,y)
plt.show()
I started working on python for AI and I'm having some problems:
I have an n- Queens problem here is a detailed explanation of the problem
The fitness function receives a an array of the form:
decoded = [3, 1, 2, 5 ... n]
where the element corresponds to the X coordinate and the index corresponds to the Y coordinate
i.e. taking the coordinates from the example above:
# [X, Y]
pairCoords = [[3,0], [1, 1], [2, 2], [5, 1], ... [n, z]]
so I have the fitness function which recieves a similar array to the first example.
var record starts with the max number of collisions n(n-1)* and decreases with each collision found
def fitness(self, decodedGenes):
record = self.numeroN * (self.numeroN-1)
for y in range(len(decodedGenes)):
if self.positionIsAtacking(decodedGenes, decodedGenes[y], y):
record = record - 1
return record
so a best case world return n(n-1)* and a worst case would return 0
the auxiliar function it calls checks a given X and Y coordinates and returns if there is a collision but it's not working
def positionIsAtacking(self, coords, X, Y):
for i in range(len(coords)):
# Check Y
if (coords[i] == Y):
return True
# Check Diagonals
if (coords[i] - Y == i - X):
return True
if (coords[i] - Y == X - i):
return True
return False
I have tried changing the parameters but I do not know where to search anymore I think the second function doesn`t work or maybe y changed x and y
def fitness(self, cromosoma):
record = self.numeroN * (self.numeroN - 1)
for row in range(len(board)):
decodedGenes.append(self.decodeGene(board[row]))
for y in range(len(decodedGenes)):
x = decodedGenes[y]
record = record - self.collisions(decodedGenes, x, y)
return record
def collisions(self, coords, X, Y):
board = []
r = 0
for i in range(len(coords)):
board.append([0] * self.numeroN)
for y in range(len(coords)):
board[y][coords[y]] = 1
for y in range(len(board)):
for x in range(len(board)):
# if has Queen and is not the same
if board[y][x] == 1 and y != Y:
# check x
if x == X:
r = r + 1
# check Diagonals
if self.crash_diagonal(x, y, X, Y):
r = r + 1
return r
def crash_diagonal(self, x1, y1, x2, y2):
dx = abs(x1 - x2)
dy = abs(y1 - y2)
return dx == dy
Are there any pure-python implementations of the inverse error function?
I know that SciPy has scipy.special.erfinv(), but that relies on some C extensions. I'd like a pure python implementation.
I've tried writing my own using the Wikipedia and Wolfram references, but it always seems to diverge from the true value when the arg is > 0.9.
I've also attempted to port the underlying C code that Scipy uses (ndtri.c and the cephes polevl.c functions) but that's also not passing my unit tests.
Edit: As requested, I've added the ported code.
Docstrings (and doctests) have been removed because they're longer than the functions. I haven't yet put much effort into making the port more pythonic - I'll worry about that once I get something that passes unit tests.
Supporting functions from cephes polevl.c
def polevl(x, coefs, N):
ans = 0
power = len(coefs) - 1
for coef in coefs[:N]:
ans += coef * x**power
power -= 1
return ans
def p1evl(x, coefs, N):
return polevl(x, [1] + coefs, N)
Main Inverse Error Function
def inv_erf(z):
if z < -1 or z > 1:
raise ValueError("`z` must be between -1 and 1 inclusive")
if z == 0:
return 0
if z == 1:
return math.inf
if z == -1:
return -math.inf
# From scipy special/cephes/ndrti.c
def ndtri(y):
# approximation for 0 <= abs(z - 0.5) <= 3/8
P0 = [
-5.99633501014107895267E1,
9.80010754185999661536E1,
-5.66762857469070293439E1,
1.39312609387279679503E1,
-1.23916583867381258016E0,
]
Q0 = [
1.95448858338141759834E0,
4.67627912898881538453E0,
8.63602421390890590575E1,
-2.25462687854119370527E2,
2.00260212380060660359E2,
-8.20372256168333339912E1,
1.59056225126211695515E1,
-1.18331621121330003142E0,
]
# Approximation for interval z = sqrt(-2 log y ) between 2 and 8
# i.e., y between exp(-2) = .135 and exp(-32) = 1.27e-14.
P1 = [
4.05544892305962419923E0,
3.15251094599893866154E1,
5.71628192246421288162E1,
4.40805073893200834700E1,
1.46849561928858024014E1,
2.18663306850790267539E0,
-1.40256079171354495875E-1,
-3.50424626827848203418E-2,
-8.57456785154685413611E-4,
]
Q1 = [
1.57799883256466749731E1,
4.53907635128879210584E1,
4.13172038254672030440E1,
1.50425385692907503408E1,
2.50464946208309415979E0,
-1.42182922854787788574E-1,
-3.80806407691578277194E-2,
-9.33259480895457427372E-4,
]
# Approximation for interval z = sqrt(-2 log y ) between 8 and 64
# i.e., y between exp(-32) = 1.27e-14 and exp(-2048) = 3.67e-890.
P2 = [
3.23774891776946035970E0,
6.91522889068984211695E0,
3.93881025292474443415E0,
1.33303460815807542389E0,
2.01485389549179081538E-1,
1.23716634817820021358E-2,
3.01581553508235416007E-4,
2.65806974686737550832E-6,
6.23974539184983293730E-9,
]
Q2 = [
6.02427039364742014255E0,
3.67983563856160859403E0,
1.37702099489081330271E0,
2.16236993594496635890E-1,
1.34204006088543189037E-2,
3.28014464682127739104E-4,
2.89247864745380683936E-6,
6.79019408009981274425E-9,
]
s2pi = 2.50662827463100050242
code = 1
if y > (1.0 - 0.13533528323661269189): # 0.135... = exp(-2)
y = 1.0 - y
code = 0
if y > 0.13533528323661269189:
y = y - 0.5
y2 = y * y
x = y + y * (y2 * polevl(y2, P0, 4) / p1evl(y2, Q0, 8))
x = x * s2pi
return x
x = math.sqrt(-2.0 * math.log(y))
x0 = x - math.log(x) / x
z = 1.0 / x
if x < 8.0: # y > exp(-32) = 1.2664165549e-14
x1 = z * polevl(z, P1, 8) / p1evl(z, Q1, 8)
else:
x1 = z * polevl(z, P2, 8) / p1evl(z, Q2, 8)
x = x0 - x1
if code != 0:
x = -x
return x
result = ndtri((z + 1) / 2.0) / math.sqrt(2)
return result
I think the error in your code is in the for loop over coefficients in the polevl function. If you replace what you have with the function below everything seems to work.
def polevl(x, coefs, N):
ans = 0
power = len(coefs) - 1
for coef in coefs:
ans += coef * x**power
power -= 1
return ans
I have tested it against scipy's implementation with the following code:
import numpy as np
from scipy.special import erfinv
N = 100000
x = np.random.rand(N) - 1.
# Calculate the inverse of the error function
y = np.zeros(N)
for i in range(N):
y[i] = inv_erf(x[i])
assert np.allclose(y, erfinv(x))
sympy? some digging may be needed to see how its implemented internally http://docs.sympy.org/latest/modules/functions/special.html#sympy.functions.special.error_functions.erfinv
from sympy import erfinv
erfinv(0.9).evalf(30)
1.16308715367667425688580351562
I am trying to calculate an integral as a summation of points. This is the important part of my code:
I define an array:
x = np.arange(-3,3,0.0223)
For this array I want to define a function shell_charge that sums the values of the bits inside of a shell that I define as r <= x
def piecew(x):
inside_shell = np.where(r <= x)
shell_charge = np.sum(dq[inside_shell])
^^ this is what I am trying to understand and fix
conds = [x == 0, (x >= -0.5) & (x <= 0.5), (x > 0.5) & (x < -0.5)]
funcs = [lambda x: 0.0, lambda x: k * shell_charge * (x)**-2,
lambda x: k * total_charge * (x+0.5)**-2.]
return np.piecewise(x, conds, funcs)
xx = np.linspace(-3, 3, 1000)
plt.plot(xx,piecew(xx))
plt.title("electric field along the x-axis")
plt.xlabel("x position [m]")
plt.ylabel("mag(E) [N/C]")
plt.show()
I am very new to working with arrays and I am not sure how to do this, I would really appreciate any help.