How do i speed up a python nested loop? - python

I'm trying to calculate the gravity effect of a buried object by calculating the effect on each side of the body then summing up the contributions to get one measurement at one station, an repeating for a number of stations. the code is as follows( the body is a square and the code calculates clockwise around it, that's why it goes from -x back to -x coordinates)
grav = []
x=si.arange(-30.0,30.0,0.5)
#-9.79742526 9.78716693 22.32153704 27.07382349 2138.27146193
xcorn = (-9.79742526,9.78716693 ,9.78716693 ,-9.79742526,-9.79742526)
zcorn = (22.32153704,22.32153704,27.07382349,27.07382349,22.32153704)
gamma = (6.672*(10**-11))#'N m^2 / Kg^2'
rho = 2138.27146193#'Kg / m^3'
grav = []
iter_time=[]
def procedure():
for i in si.arange(len(x)):# cycles position
t0=time.clock()
sum_lines = 0.0
for n in si.arange(len(xcorn)-1):#cycles corners
x1 = xcorn[n]-x[i]
x2 = xcorn[n+1]-x[i]
z1 = zcorn[n]-0.0 #just depth to corner since all observations are on the surface.
z2 = zcorn[n+1]-0.0
r1 = ((z1**2) + (x1**2))**0.5
r2 = ((z2**2) + (x2**2))**0.5
O1 = si.arctan2(z1,x1)
O2 = si.arctan2(z2,x2)
denom = z2-z1
if denom == 0.0:
denom = 1.0e-6
alpha = (x2-x1)/denom
beta = ((x1*z2)-(x2*z1))/denom
factor = (beta/(1.0+(alpha**2)))
term1 = si.log(r2/r1)#log base 10
term2 = alpha*(O2-O1)
sum_lines = sum_lines + (factor*(term1-term2))
sum_lines = sum_lines*2*gamma*rho
grav.append(sum_lines)
t1 = time.clock()
dt = t1-t0
iter_time.append(dt)
Any help in speeding this loop up would be appreciated Thanks.

Your xcorn and zcorn values repeat, so consider caching the result of some of the computations.
Take a look at the timeit and profile modules to get more information about what is taking the most computational time.

It is very inefficient to access individual elements of a numpy array in a Python loop. For example, this Python loop:
for i in xrange(0, len(a), 2):
a[i] = i
would be much slower than:
a[::2] = np.arange(0, len(a), 2)
You could use a better algorithm (less time complexity) or use vector operations on numpy arrays as in the example above. But the quicker way might be just to compile the code using Cython:
#cython: boundscheck=False, wraparound=False
#procedure_module.pyx
import numpy as np
cimport numpy as np
ctypedef np.float64_t dtype_t
def procedure(np.ndarray[dtype_t,ndim=1] x,
np.ndarray[dtype_t,ndim=1] xcorn):
cdef:
Py_ssize_t i, j
dtype_t x1, x2, z1, z2, r1, r2, O1, O2
np.ndarray[dtype_t,ndim=1] grav = np.empty_like(x)
for i in range(x.shape[0]):
for j in range(xcorn.shape[0]-1):
x1 = xcorn[j]-x[i]
x2 = xcorn[j+1]-x[i]
...
grav[i] = ...
return grav
It is not necessary to define all types but if you need a significant speed up compared to Python you should define at least types of arrays and loop indexes.
You could use cProfile (Cython supports it) instead of manual calls to time.clock().
To call procedure():
#!/usr/bin/env python
import pyximport; pyximport.install() # pip install cython
import numpy as np
from procedure_module import procedure
x = np.arange(-30.0,30.0,0.5)
xcorn = np.array((-9.79742526,9.78716693 ,9.78716693 ,-9.79742526,-9.79742526))
grav = procedure(x, xcorn)

Related

Numba parallel code slower than its sequential counterpart

I'm new to Numba and I'm trying to implement an old Fortran code in Python using Numba (version 0.54.1), but when I add parallel = True the program actually slows down. My program is very simple: I change the positions x and y in a L x L grid and for each position in the grid I perform a summation
import numpy as np
import numba as nb
#nb.njit(parallel=True)
def lyapunov_grid(x_grid, y_grid, k, N):
L = len(x_grid)
lypnv = np.zeros((L, L))
for ii in nb.prange(L):
for jj in range(L):
x = x_grid[ii]
y = y_grid[jj]
beta0 = 0
sumT11 = 0
for j in range(N):
y = (y - k*np.sin(x)) % (2*np.pi)
x = (x + y) % (2*np.pi)
J = np.array([[1.0, -k*np.cos(x)], [1.0, 1.0 - k*np.cos(x)]])
beta = np.arctan((-J[1,0]*np.cos(beta0) + J[1,1]*np.sin(beta0))/(J[0,0]*np.cos(beta0) - J[0,1]*np.sin(beta0)))
T11 = np.cos(beta0)*(J[0,0]*np.cos(beta) - J[1,0]*np.sin(beta)) - np.sin(beta0)*(J[0,1]*np.cos(beta) - J[1,1]*np.sin(beta))
sumT11 += np.log(abs(T11))/np.log(2)
beta0 = beta
lypnv[ii, jj] = sumT11/N
return lypnv
# Compile
_ = lyapunov_grid(np.linspace(0, 1, 10), np.linspace(0, 1, 10), 1, 10)
# Parameters
N = int(1e3)
L = 128
pi = np.pi
k = 1.5
# Limits of the phase space
x0 = -pi
xf = pi
y0 = -pi
yf = pi
# Grid positions
x = np.linspace(x0, xf, L, endpoint=True)
y = np.linspace(y0, yf, L, endpoint=True)
lypnv = lyapunov_grid(x, y, k, N)
With parallel=False it takes about 8s to run, however with parallel=True it takes about 14s. I also tested with another code from https://github.com/animator/mandelbrot-numba and in this case the parallelization works.
import math
import numpy as np
import numba as nb
WIDTH = 1000
MAX_ITER = 1000
#nb.njit(parallel=True)
def mandelbrot(width, max_iter):
pixels = np.zeros((width, width, 3), dtype=np.uint8)
for y in nb.prange(width):
for x in range(width):
c0 = complex(3.0*x/width - 2, 3.0*y/width - 1.5)
c = 0
for i in range(1, max_iter):
if abs(c) > 2:
log_iter = math.log(i)
pixels[y, x, :] = np.array([int(255*(1+math.cos(3.32*log_iter))/2),
int(255*(1+math.cos(0.774*log_iter))/2),
int(255*(1+math.cos(0.412*log_iter))/2)],
dtype=np.uint8)
break
c = c * c + c0
return pixels
# compile
_ = mandelbrot(WIDTH, 10)
calcpixels = mandelbrot(WIDTH, MAX_ITER)
One main issue is that the second function call compile the function again. Indeed, the types of the provided arguments change: in the first call the third argument is an integer (int transformed to a np.int_) while in the second call the third argument (k) is a floating point number (float transformed to a np.float64). Numba recompiles the function for different parameter types because they are deduced from the type of the arguments and it does not know you want to use a np.float64 type for the third argument (since the first time the function is compiled with for a np.int_ type). One simple solution to fix the problem is to change the first call to:
_ = lyapunov_grid(np.linspace(0, 1, 10), np.linspace(0, 1, 10), 1.0, 10)
However, this is not a robust way to fix the problem. You can specify the parameter types to Numba so it will compile the function at declaration time. This also remove the need to artificially call the function (with useless parameters).
#nb.njit('float64[:,:](float64[::1], float64[::1], float64, float64)', parallel=True)
Note that (J[0,0]*np.cos(beta0) - J[0,1]*np.sin(beta0)) is zero the first time resulting in a division by 0.
Another main issue comes from the allocations of many small arrays in the loop causing a contention of the standard allocator (see this post for more information). While Numba could theoretically optimize it (ie. replace the array with local variables), it actually does not, resulting in a huge slowdown and a contention. Hopefully, in your case, you do not need to actually create the array. At last, you can create it only in the encompassing loop and modify it in the innermost loop. Here is the optimized code:
#nb.njit('float64[:,:](float64[::1], float64[::1], float64, float64)', parallel=True)
def lyapunov_grid(x_grid, y_grid, k, N):
L = len(x_grid)
lypnv = np.zeros((L, L))
for ii in nb.prange(L):
J = np.ones((2, 2), dtype=np.float64)
for jj in range(L):
x = x_grid[ii]
y = y_grid[jj]
beta0 = 0
sumT11 = 0
for j in range(N):
y = (y - k*np.sin(x)) % (2*np.pi)
x = (x + y) % (2*np.pi)
J[0, 1] = -k*np.cos(x)
J[1, 1] = 1.0 - k*np.cos(x)
beta = np.arctan((-J[1,0]*np.cos(beta0) + J[1,1]*np.sin(beta0))/(J[0,0]*np.cos(beta0) - J[0,1]*np.sin(beta0)))
T11 = np.cos(beta0)*(J[0,0]*np.cos(beta) - J[1,0]*np.sin(beta)) - np.sin(beta0)*(J[0,1]*np.cos(beta) - J[1,1]*np.sin(beta))
sumT11 += np.log(abs(T11))/np.log(2)
beta0 = beta
lypnv[ii, jj] = sumT11/N
return lypnv
Here is the results on a old 2-core machine (with 4 hardware threads):
Original sequential: 15.9 s
Original parallel: 11.9 s
Fix-build sequential: 15.7 s
Fix-build parallel: 10.1 s
Optimized sequential: 2.73 s
Optimized parallel: 0.94 s
The optimized implementation is much faster than the others. The parallel optimized version scale very well compared than the original one (2.9 times faster than the sequential one). Finally, the best version is about 12 times faster than the original parallel version. I expect a much faster computation on a recent machine with many more cores.

Crank Nicolson Method on Wave Function Python

I am trying to propagate a gaussian wave packet using the crank nicolson method in imaginary time (multiply the time step by the unit imaginary). The code that I have written in attempt to achieve this is shown here:
import matplotlib.pyplot as plt #this allows you to plot, and changes the name to plt
import numpy as np #this allows you to do math, and changes the name to np
import math
import scipy.linalg as la
def V(x):
# k = 1
# v = k*x**4
v = 0.25*(x-3)**2+0.15*(x-3)**4
return v
def Psi(x):
psi = np.exp(-2*(x-3)**2)
return psi
#Function for computing integral using trapezoid method
def TrapInt(y, h):
trap = [(float(y[ii]) + float(y[ii+1])) for ii in range(0, len(y)-1)]
return float(h)/2*sum(trap)
N = 1000
L = 3;
h = 0.01
x = np.arange(0,6,h);
t = np.linspace(0,L,300);
t = 1j*t;
dt = t[1] - t[0]
dx = x[1] - x[0]
A = 1j*dt/(2*dx**2)
pot = V(x)
Q = np.zeros([len(x),len(x)],dtype = complex)
P = np.zeros([len(x),len(x)],dtype = complex)
wave = np.zeros([len(x),len(t)],dtype = complex)
wave[:,0] = Psi(x)
B = (1- 2*A - 1j*dt*pot)
for ii in range(0,len(x)-1):
Q[ii][ii] = -(B[ii])
P[ii][ii] = (B[ii])
Q[ii][ii+1] = (2-A)
P[ii][ii+1] = A
if ii >= 1:
Q[ii][ii-1] = -A
P[ii][ii-1] = A
plt.plot(wave[:,0])
for ii in range(0,len(t)-1):
one = np.matmul(P,wave[:,ii])
wave[:,ii+1] = np.matmul(la.inv(Q),one)
I can't seem to find any mathematical errors in my implementation of the crank nicolson method; however, whenever I try to run this it gives an error saying that Q is singular (has no inverse). I'm not sure why this is occurring. Any help is appreciated. Thanks
You never assign to Q[-1]. Zero rows have been known to produce singular matrices in some cases.
Also, don’t repeatedly invert the matrix. Probably don’t invert it at all, but rather store some decomposition of it to allow efficient calculation of Q-1x.

Usage of parallel option in numba.jit decoratior makes function give wrong result

Given two opposite corners of a rectangle (x1, y1) and (x2, y2) and two radii r1 and r2, find the ratio of points that lie between the circles defined by the radii r1 and r2 to the total number of points in the rectangle.
Simple NumPy approach:
def func_1(x1,y1,x2,y2,r1,r2,n):
x11,y11 = np.meshgrid(np.linspace(x1,x2,n),np.linspace(y1,y2,n))
z1 = np.sqrt(x11**2+y11**2)
a = np.where((z1>(r1)) & (z1<(r2)))
fill_factor = len(a[0])/(n*n)
return fill_factor
Next I tried to optimize this function with the jit decorator from numba. When I use:
nopython = True
The function is faster and gives the right output. But when I also add:
parallel = True
The function is faster but gives the wrong result.
I know that this has something to do with my z matrix since that is not being updated properly.
#jit(nopython=True,parallel=True)
def func_2(x1,y1,x2,y2,r1,r2,n):
x_ = np.linspace(x1,x2,n)
y_ = np.linspace(y1,y2,n)
z1 = np.zeros((n,n))
for i in range(n):
for j in range(n):
z1[i][j] = np.sqrt((x_[i]*x_[i]+y_[j]*y_[j]))
a = np.where((z1>(r1)) & (z1<(r2)))
fill_factor = len(a[0])/(n*n)
return fill_factor
Test values :
x1 = 1.0
x2 = -1.0
y1 = 1.0
y2 = -1.0
r1 = 0.5
r2 = 0.75
n = 25000
Additional info : Python version : 3.6.1, Numba version : 0.34.0+5.g1762237, NumPy version : 1.13.1
The problem with parallel=True is that it's a black-box. Numba doesn't even guarantee that it will actually parallelize anything. It uses heuristics to find out if it's parallelizable and what could be done in parallel. These can fail and in your example they do fail, just like in my experiments with parallel and numba. That makes parallel untrustworthy and I would advise against using it!
In newer versions (0.34) prange was added an you could have more luck with that. It can't be applied in this case because prange works like range and that's different from np.linspace...
Just a note: You can avoid building z and doing the np.where in your function completely, you could just do the checks explicitly:
import numpy as np
import numba as nb
#nb.njit # equivalent to "jit(nopython=True)".
def func_2(x1,y1,x2,y2,r1,r2,n):
x_ = np.linspace(x1,x2,n)
y_ = np.linspace(y1,y2,n)
cnts = 0
for i in range(n):
for j in range(n):
z = np.sqrt(x_[i] * x_[i] + y_[j] * y_[j])
if r1 < z < r2:
cnts += 1
fill_factor = cnts/(n*n)
return fill_factor
That should also provide some speedup compared to your function, maybe even more than using parallel=True (if it would work correctly).

Correctly annotate a numba function using jit

I started with this code to calculate a simple matrix multiplication. It runs with %timeit in around 7.85s on my machine.
To try to speed this up I tried cython which reduced the time to 0.4s. I want to also try to use numba jit compiler to see if I can get similar speed ups (with less effort). But adding the #jit annotation appears to give exactly the same timings (~7.8s). I know it can't figure out the types of the calculate_z_numpy() call but I'm not sure what I can do to coerce it. Any ideas?
from numba import jit
import numpy as np
#jit('f8(c8[:],c8[:],uint)')
def calculate_z_numpy(q, z, maxiter):
"""use vector operations to update all zs and qs to create new output array"""
output = np.resize(np.array(0, dtype=np.int32), q.shape)
for iteration in range(maxiter):
z = z*z + q
done = np.greater(abs(z), 2.0)
q = np.where(done, 0+0j, q)
z = np.where(done, 0+0j, z)
output = np.where(done, iteration, output)
return output
def calc_test():
w = h = 1000
maxiter = 1000
# make a list of x and y values which will represent q
# xx and yy are the co-ordinates, for the default configuration they'll look like:
# if we have a 1000x1000 plot
# xx = [-2.13, -2.1242,-2.1184000000000003, ..., 0.7526000000000064, 0.7584000000000064, 0.7642000000000064]
# yy = [1.3, 1.2948, 1.2895999999999999, ..., -1.2844000000000058, -1.2896000000000059, -1.294800000000006]
x1, x2, y1, y2 = -2.13, 0.77, -1.3, 1.3
x_step = (float(x2 - x1) / float(w)) * 2
y_step = (float(y1 - y2) / float(h)) * 2
y = np.arange(y2,y1-y_step,y_step,dtype=np.complex)
x = np.arange(x1,x2,x_step)
q1 = np.empty(y.shape[0],dtype=np.complex)
q1.real = x
q1.imag = y
# Transpose y
x_y_square_matrix = x+y[:, np.newaxis] # it is np.complex128
# convert square matrix to a flatted vector using ravel
q2 = np.ravel(x_y_square_matrix)
# create z as a 0+0j array of the same length as q
# note that it defaults to reals (float64) unless told otherwise
z = np.zeros(q2.shape, np.complex128)
output = calculate_z_numpy(q2, z, maxiter)
print(output)
calc_test()
I figured out how to do this with some help from someone else.
#jit('i4[:](c16[:],c16[:],i4,i4[:])',nopython=True)
def calculate_z_numpy(q, z, maxiter,output):
"""use vector operations to update all zs and qs to create new output array"""
for iteration in range(maxiter):
for i in range(len(z)):
z[i] = z[i] + q[i]
if z[i] > 2:
output[i] = iteration
z[i] = 0+0j
q[i] = 0+0j
return output
What I learnt is that use numpy datastructures as inputs (for typing), but within use c like paradigms for looping.
This runs in 402ms which is a touch faster than cython code 0.45s so for fairly minimal work in rewriting the loop explicitly we have a python version faster than C(just).

Find all point pairs closer than a given maximum distance

I want to find (efficiently) all pairs of points that are closer than some distance max_d. My current method, using cdist, is:
import numpy as np
from scipy.spatial.distance import cdist
def close_pairs(X,max_d):
d = cdist(X,X)
I,J = (d<max_d).nonzero()
IJ = np.sort(np.vstack((I,J)), axis=0)
# remove diagonal element
IJ = IJ[:,np.diff(IJ,axis=0).ravel()<>0]
# remove duplicate
dt = np.dtype([('i',int),('j',int)])
pairs = np.unique(IJ.T.view(dtype=dt)).view(int).reshape(-1,2)
return pairs
def test():
X = np.random.rand(100,2)*20
p = close_pairs(X,2)
from matplotlib import pyplot as plt
plt.clf()
plt.plot(X[:,0],X[:,1],'.r')
plt.plot(X[p,0].T,X[p,1].T,'-b')
But I think this is overkill (and not very readable), because most of the work is done only to remove distance-to-self and duplicates.
My main question is: is there a better way to do it?
(Note: the type of outputs (array, set, ...) is not important at this point)
My current thinking is on using pdist which returns a condensed distance array which contains only the right pairs. However, once I found the suitable coordinates k's from the condensed distance array, how do I compute which i,j pairs it is equivalent to?
So the alternative question is: is there an easy way to get the list of coordinate pairs relative to the entries of pdist outputs:
a function f(k)->i,j
such that cdist(X,X)[i,j] = pdist(X)[k]
In my experience, there are two fastest ways to find neighbor lists in 3D. One is to use a most naive double-for-loop code written in C++ or Cython (in my case, both). It runs in N^2, but is very fast for small systems. The other way is to use a linear time algorithm. Scipy ckdtree is a good choice, but has limitations. Neighbor list finders from molecular dynamics software are most powerful, but are very hard to wrap, and likely have slow initialization time.
Below I compare four methods:
Naive cython code
Wrapper around OpenMM (is very hard to install, see below)
Scipy.spatial.ckdtree
scipy.spatial.distance.pdist
Test setup: n points scattered in a rectangular box at volume density 0.2. System size ranging from 10 to a 1000000 (a million) particles. Contact radius is taken from 0.5, 1, 2, 4, 7, 10. Note that because density is 0.2, at contact radius 0.5 we'll have on average about 0.1 contacts per particle, at 1 = 0.8, at 2 = 6.4, and at 10 - about 800! Contact finding was repeated several times for small systems, done once for systems >30k particles. If time per call exceeded 5 seconds, the run was aborted.
Setup: dual xeon 2687Wv3, 128GB RAM, Ubuntu 14.04, python 2.7.11, scipy 0.16.0, numpy 1.10.1. None of the code was using parallel optimizations (except for OpenMM, though parallel part went so quick that it was not even noticeable on a CPU graph, most of the time was spend piping data to-from OpenMM).
Results: Note that plots below are logscale, and spread over 6 orders of magnitude. Even small visual difference may be actually 10-fold.
For systems less than 1000 particles, Cython code was always faster. However, after 1000 particles results are dependent on the contact radius. pdist implementation was always slower than cython, and takes much more memory, because it explicitly creates a distance matrix, which is slow because of sqrt.
At small contact radius (<1 contact per particle), ckdtree is a good choice for all system sizes.
At medium contact radius, (5-50 contacts per particle) naive cython implementation is the best up to 10000 particles, then OpenMM starts to win by about several orders of magnitude, but ckdtree performs just 3-10 times worse
At high contact radius (>200 contacts per particle) naive methods work up to 100k or 1M particles, then OpenMM may win.
Installing OpenMM is very tricky; you can read more in http://bitbucket.org/mirnylab/openmm-polymer file "contactmaps.py" or in the readme. However, the results below show that it is only advantageous for 5-50 contacts per particle, for N>100k particles.
Cython code below:
import numpy as np
cimport numpy as np
cimport cython
cdef extern from "<vector>" namespace "std":
cdef cppclass vector[T]:
cppclass iterator:
T operator*()
iterator operator++()
bint operator==(iterator)
bint operator!=(iterator)
vector()
void push_back(T&)
T& operator[](int)
T& at(int)
iterator begin()
iterator end()
np.import_array() # initialize C API to call PyArray_SimpleNewFromData
cdef public api tonumpyarray(int* data, long long size) with gil:
if not (data and size >= 0): raise ValueError
cdef np.npy_intp dims = size
#NOTE: it doesn't take ownership of `data`. You must free `data` yourself
return np.PyArray_SimpleNewFromData(1, &dims, np.NPY_INT, <void*>data)
#cython.boundscheck(False)
#cython.wraparound(False)
def contactsCython(inArray, cutoff):
inArray = np.asarray(inArray, dtype = np.float64, order = "C")
cdef int N = len(inArray)
cdef np.ndarray[np.double_t, ndim = 2] data = inArray
cdef int j,i
cdef double curdist
cdef double cutoff2 = cutoff * cutoff # IMPORTANT to avoid slow sqrt calculation
cdef vector[int] contacts1
cdef vector[int] contacts2
for i in range(N):
for j in range(i+1, N):
curdist = (data[i,0] - data[j,0]) **2 +(data[i,1] - data[j,1]) **2 + (data[i,2] - data[j,2]) **2
if curdist < cutoff2:
contacts1.push_back(i)
contacts2.push_back(j)
cdef int M = len(contacts1)
cdef np.ndarray[np.int32_t, ndim = 2] contacts = np.zeros((M,2), dtype = np.int32)
for i in range(M):
contacts[i,0] = contacts1[i]
contacts[i,1] = contacts2[i]
return contacts
Compilation (or makefile) for Cython code:
cython --cplus fastContacts.pyx
g++ -g -march=native -Ofast -fpic -c fastContacts.cpp -o fastContacts.o `python-config --includes`
g++ -g -march=native -Ofast -shared -o fastContacts.so fastContacts.o `python-config --libs`
Testing code:
from __future__ import print_function, division
import signal
import time
from contextlib import contextmanager
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
from scipy.spatial import ckdtree
from scipy.spatial.distance import pdist
from contactmaps import giveContactsOpenMM # remove this unless you have OpenMM and openmm-polymer libraries installed
from fastContacts import contactsCython
class TimeoutException(Exception): pass
#contextmanager
def time_limit(seconds):
def signal_handler(signum, frame):
raise TimeoutException("Timed out!")
signal.signal(signal.SIGALRM, signal_handler)
signal.alarm(seconds)
try:
yield
finally:
signal.alarm(0)
matplotlib.rcParams.update({'font.size': 8})
def close_pairs_ckdtree(X, max_d):
tree = ckdtree.cKDTree(X)
pairs = tree.query_pairs(max_d)
return np.array(list(pairs))
def condensed_to_pair_indices(n, k):
x = n - (4. * n ** 2 - 4 * n - 8 * k + 1) ** .5 / 2 - .5
i = x.astype(int)
j = k + i * (i + 3 - 2 * n) / 2 + 1
return np.array([i, j]).T
def close_pairs_pdist(X, max_d):
d = pdist(X)
k = (d < max_d).nonzero()[0]
return condensed_to_pair_indices(X.shape[0], k)
a = np.random.random((100, 3)) * 3 # test set
methods = {"cython": contactsCython, "ckdtree": close_pairs_ckdtree, "OpenMM": giveContactsOpenMM,
"pdist": close_pairs_pdist}
# checking that each method gives the same value
allUniqueInds = []
for ind, method in methods.items():
contacts = method(a, 1)
uniqueInds = contacts[:, 0] + 100 * contacts[:, 1] # unique index of each contacts
allUniqueInds.append(np.sort(uniqueInds)) # adding sorted unique conatcts
for j in allUniqueInds:
assert np.allclose(j, allUniqueInds[0])
# now actually doing testing
repeats = [30,30,30, 30, 30, 20, 20, 10, 5, 3, 2 , 1, 1, 1]
sizes = [10,30,100, 200, 300, 500, 1000, 2000, 3000, 10000, 30000, 100000, 300000, 1000000]
systems = [[np.random.random((n, 3)) * ((n / 0.2) ** 0.333333) for k in range(repeat)] for n, repeat in
zip(sizes, repeats)]
for j, radius in enumerate([0.5, 1, 2, 4, 7, 10]):
plt.subplot(2, 3, j + 1)
plt.title("Radius = {0}; {1:.2f} cont per particle".format(radius, 0.2 * (4 / 3 * np.pi * radius ** 3)))
times = {i: [] for i in methods}
for name, method in methods.items():
for n, system, repeat in zip(sizes, systems, repeats):
if name == "pdist" and n > 30000:
break # memory issues
st = time.time()
try:
with time_limit(5 * repeat):
for ind in range(repeat):
k = len(method(system[ind], radius))
except:
print("Run aborted")
break
end = time.time()
mytime = (end - st) / repeat
times[name].append((n, mytime))
print("{0} radius={1} n={2} time={3} repeat={4} contPerParticle={5}".format(name, radius, n, mytime,repeat, 2 * k / n))
for name in sorted(times.keys()):
plt.plot(*zip(*times[name]), label=name)
plt.xscale("log")
plt.yscale("log")
plt.xlabel("System size")
plt.ylabel("Time (seconds)")
plt.legend(loc=0)
plt.show()
Here's how to do it with the cKDTree module. See query_pairs
import numpy as np
from scipy.spatial.distance import cdist
from scipy.spatial import ckdtree
def close_pairs(X,max_d):
d = cdist(X,X)
I,J = (d<max_d).nonzero()
IJ = np.sort(np.vstack((I,J)), axis=0)
# remove diagonal element
IJ = IJ[:,np.diff(IJ,axis=0).ravel()<>0]
# remove duplicate
dt = np.dtype([('i',int),('j',int)])
pairs = np.unique(IJ.T.view(dtype=dt)).view(int).reshape(-1,2)
return pairs
def close_pairs_ckdtree(X, max_d):
tree = ckdtree.cKDTree(X)
pairs = tree.query_pairs(max_d)
return np.array(list(pairs))
def test():
np.random.seed(0)
X = np.random.rand(100,2)*20
p = close_pairs(X,2)
q = close_pairs_ckdtree(X, 2)
from matplotlib import pyplot as plt
plt.plot(X[:,0],X[:,1],'.r')
plt.plot(X[p,0].T,X[p,1].T,'-b')
plt.figure()
plt.plot(X[:,0],X[:,1],'.r')
plt.plot(X[q,0].T,X[q,1].T,'-b')
plt.show()
t
I finally found it myself. The function converting indices k in condensed distance array to equivalent i,j in square distance array is:
def condensed_to_pair_indices(n,k):
x = n-(4.*n**2-4*n-8*k+1)**.5/2-.5
i = x.astype(int)
j = k+i*(i+3-2*n)/2+1
return i,j
I had to play a little with sympy to find it. Now, to compute all point pairs than are less than a given distance apart:
def close_pairs_pdist(X,max_d):
d = pdist(X)
k = (d<max_d).nonzero()[0]
return condensed_to_pair_indices(X.shape[0],k)
As expected, it is more efficient than the other methods (but I did not test ckdtree). I will update the timeit answer.
slightly faster, didnt test the time difference thoroughly, but if i ran it a few times, it gave a time of about 0.0755529403687 for my method, and 0.0928771495819 for yours. I use the triu method to get rid of upper triangle of the array (where duplicates are) including diagonal (which is where the self-distances are), and i dont sort either, since if you plot it, it does not matter if i plot them in order or not. So i guess it speeds up about 15% or so
import numpy as np
from scipy.spatial.distance import cdist
from scipy.misc import comb
def close_pairs(X,max_d):
d = cdist(X,X)
I,J = (d<max_d).nonzero()
IJ = np.sort(np.vstack((I,J)), axis=0)
# remove diagonal element
IJ = IJ[:,np.diff(IJ,axis=0).ravel()<>0]
# remove duplicate
dt = np.dtype([('i',int),('j',int)])
pairs = np.unique(IJ.T.view(dtype=dt)).view(int).reshape(-1,2)
return pairs
def close_pairs1(X,max_d):
d = cdist(X,X)
d1 = np.triu_indices(len(X)) # indices of the upper triangle including the diagonal
d[d1] = max_d+1 # value that will not get selected when doing d<max_d in the next line
I,J = (d<max_d).nonzero()
pairs = np.vstack((I,J)).T
return pairs
def close_pairs3(X, max_d):
d = pdist(X)
n = len(X)
pairs = np.zeros((0,2))
for i in range(n):
for j in range(i+1,n):
# formula from http://docs.scipy.org/doc/scipy/reference/generated/scipy.spatial.distance.squareform.html
a=d[int(comb(n,2)-comb(n-i,2)+j-i-1+0.1)] # the +0.1 is because otherwise i get floating point trouble
if(a<max_d):
pairs = np.r_[pairs, np.array([i,j])[None,:]]
return pairs
def close_pairs4(X, max_d):
d = pdist(X)
n = len(X)
a = np.where(d<max_d)[0]
i = np.arange(n)[:,None]
j = np.arange(n)[None,:]
b = np.array(comb(n,2)-comb(n-i,2)+j-i-1+0.1, dtype=int)
d1 = np.tril_indices(n)
b[d1] = -1
pairs = np.zeros((0,2), dtype=int)
# next part is the bottleneck: the np.where each time,
for v in a:
i, j = np.where(v==b)
pairs = np.r_[pairs, np.array([i[0],j[0]])[None,:]]
return pairs
def close_pairs5(X, max_d):
t0=time.time()
d = pdist(X)
n = len(X)
a = np.where(d<max_d)[0]
i = np.arange(n)[:,None]
j = np.arange(n)[None,:]
t1 = time.time()
b = np.array(comb(n,2)-comb(n-i,2)+j-i-1+0.1, dtype=int)
d1 = np.tril_indices(n)
b[d1] = -1
t2 = time.time()
V = b[:,:,None]-a[None,None,:] # takes a little time
t3 = time.time()
p = np.where(V==0) # takes most of the time, thought that removing the for-loop from the previous method might improve it, but it does not do that much. This method contains the formula you wanted though, but apparently it is still faster if you use the cdist methods
t4 = time.time()
pairs = np.vstack((p[0],p[1])).T
print t4-t3,t3-t2, t2-t1, t1-t0
return pairs
def test():
X = np.random.rand(1000,2)*20
import time
t0 = time.time()
p = close_pairs(X,2)
t1 = time.time()
p2 = close_pairs1(X,2)
t2 = time.time()
print t2-t1, t1-t0
from matplotlib import pyplot as plt
plt.figure()
plt.clf()
plt.plot(X[:,0],X[:,1],'.r')
plt.plot(X[p,0].T,X[p,1].T,'-b')
plt.figure()
plt.clf()
plt.plot(X[:,0],X[:,1],'.r')
plt.plot(X[p2,0].T,X[p2,1].T,'-b')
plt.show()
test()
NOTE: plotting laggs if you do it for 1K points, but it needs 1K points to compare speeds, but i checked that it works correctly when plotting it if doing it with 100 points
The speed difference is something like ten to twenty percent, and i think it will not get much better than this, since i got rid of all the sorting and unique elements things, so the part that takes most of the time probably is the d = cdist(X, X) line
Edit: some more testing shows that in those times, that cdist line takes up about 0.065 sec, while the rest for your method is about 0.02 and for me about 0.015 sec or so. Conclusion: the main bottleneck of your code is the d = cdist(X, X) line, and the stuff i changed speeds up the rest of the code you got, but the main bottleneck stays
Edit: added the method close_pairs3, which gives you the formula, but speed blows, (still need to figure out how to invert that formula, and than it will be superfast, will do that tomorrow - will use np.where(pdist(X)
Edit: added method close_pairs4, which is slightly better than 3, and explains what happens, but is veeery slow, and same with method 5, does not have that for-loop, but is still very slow
I made some code to compare the proposed solutions.
Note: I use scipy 0.11 and cannot use the ckdtree solution (only kdtree) which I expect to be slower. Could anyone with scipy v0.12+ run this code?
import numpy as np
from scipy.spatial.distance import cdist, pdist
from scipy.spatial import ckdtree
from scipy.spatial import kdtree
def close_pairs(X,max_d):
d = cdist(X,X)
I,J = (d<max_d).nonzero()
IJ = np.sort(np.vstack((I,J)), axis=0)
# remove diagonal element
IJ = IJ[:,np.diff(IJ,axis=0).ravel()<>0]
# remove duplicate
dt = np.dtype([('i',int),('j',int)])
pairs = np.unique(IJ.T.view(dtype=dt)).view(int).reshape(-1,2)
return pairs
def condensed_to_pair_indices(n,k):
x = n-(4.*n**2-4*n-8*k+1)**.5/2-.5
i = x.astype(int)
j = k+i*(i+3-2*n)/2+1
return i,j
def close_pairs_pdist(X,max_d):
d = pdist(X)
k = (d<max_d).nonzero()[0]
return condensed_to_pair_indices(X.shape[0],k)
def close_pairs_triu(X,max_d):
d = cdist(X,X)
d1 = np.triu_indices(len(X)) # indices of the upper triangle including the diagonal
d[d1] = max_d+1 # value that will not get selected when doing d<max_d in the next line
I,J = (d<max_d).nonzero()
pairs = np.vstack((I,J)).T
return pairs
def close_pairs_ckdtree(X, max_d):
tree = ckdtree.cKDTree(X)
pairs = tree.query_pairs(max_d)
return pairs # remove the conversion as it is not required
def close_pairs_kdtree(X, max_d):
tree = kdtree.KDTree(X)
pairs = tree.query_pairs(max_d)
return pairs # remove the conversion as it is not required
methods = [close_pairs, close_pairs_pdist, close_pairs_triu, close_pairs_kdtree] #, close_pairs_ckdtree]
def time_test(n=[10,50,100], max_d=[5,10,50], iter_num=100):
import timeit
for method in methods:
print '-- time using ' + method.__name__ + ' ---'
for ni in n:
for d in max_d:
setup = '\n'.join(['import numpy as np','import %s' % __name__,'np.random.seed(0)','X = np.random.rand(%d,2)*100'%ni])
stmt = 'close_pairs.%s(X,%f)' % (method.__name__,d)
time = timeit.timeit(stmt=stmt, setup=setup, number=iter_num)/iter_num
print 'n=%3d, max_d=%2d: \t%.2fms' % (ni, d,time*1000)
Output of time_test(iter_num=10,n=[20,100,500],max_d=[1,5,10]) are:
-- time using close_pairs ---
n= 20, max_d= 1: 0.22ms
n= 20, max_d= 5: 0.16ms
n= 20, max_d=10: 0.21ms
n=100, max_d= 1: 0.41ms
n=100, max_d= 5: 0.53ms
n=100, max_d=10: 0.97ms
n=500, max_d= 1: 7.12ms
n=500, max_d= 5: 12.28ms
n=500, max_d=10: 33.41ms
-- time using close_pairs_pdist ---
n= 20, max_d= 1: 0.11ms
n= 20, max_d= 5: 0.10ms
n= 20, max_d=10: 0.11ms
n=100, max_d= 1: 0.19ms
n=100, max_d= 5: 0.19ms
n=100, max_d=10: 0.19ms
n=500, max_d= 1: 2.31ms
n=500, max_d= 5: 2.82ms
n=500, max_d=10: 2.49ms
-- time using close_pairs_triu ---
n= 20, max_d= 1: 0.17ms
n= 20, max_d= 5: 0.16ms
n= 20, max_d=10: 0.16ms
n=100, max_d= 1: 0.83ms
n=100, max_d= 5: 0.80ms
n=100, max_d=10: 0.80ms
n=500, max_d= 1: 23.64ms
n=500, max_d= 5: 22.87ms
n=500, max_d=10: 22.96ms
-- time using close_pairs_kdtree ---
n= 20, max_d= 1: 1.71ms
n= 20, max_d= 5: 1.69ms
n= 20, max_d=10: 1.96ms
n=100, max_d= 1: 34.99ms
n=100, max_d= 5: 35.47ms
n=100, max_d=10: 34.91ms
n=500, max_d= 1: 253.87ms
n=500, max_d= 5: 255.05ms
n=500, max_d=10: 256.66ms
Conclusion:
The overall fastest method is close_pairs_pdist
The initial method is relatively fast, but sensitive to both the number of samples and the percentage of pairs to return
both the close_pairs_triu and close_pairs_kdtree are sensitive to the number of samples but relatively insensitive to the number of outputs.
the close_pairs_triu method is much faster than close_pairs_kdtree
However, the ckdtree method needs to be tested.

Categories