Geek Answers Handbook

Fastest way to convert a Numpy array to a sparse dictionary?

I am interested in converting a numpy array to a sparse dictionary as quickly as possible. Let me clarify:

Given an array:

numpy.array([12,0,0,0,3,0,0,1])

I want to create a dictionary:

{0:12, 4:3, 7:1}

As you can see, we simply convert the type of the sequence to an explicit mapping of indices other than their values.

To make this a little more interesting, I suggest the following test harness for testing alternatives:

from timeit import Timer

if __name__ == "__main__":
  s = "import numpy; from itertools import izip; from numpy import nonzero, flatnonzero; vector =         numpy.random.poisson(0.1, size=10000);"

  ms = [ "f = flatnonzero(vector); dict( zip( f, vector[f] ) )"
             , "f = flatnonzero(vector); dict( izip( f, vector[f] ) )"
             , "f = nonzero(vector); dict( izip( f[0], vector[f] ) )"
             , "n = vector > 0; i = numpy.arange(len(vector))[n]; v = vector[n]; dict(izip(i,v))"
             , "i = flatnonzero(vector); v = vector[vector > 0]; dict(izip(i,v))"
             , "dict( zip( flatnonzero(vector), vector[flatnonzero(vector)] ) )"
             , "dict( zip( flatnonzero(vector), vector[nonzero(vector)] ) )"
             , "dict( (i, x) for i,x in enumerate(vector) if x > 0);"
             ]
  for m in ms:
    print "  %.2fs" % Timer(m, s).timeit(1000), m

I use Poisson distribution to simulate the types of arrays that interest me.

Here are my results:

   0.78s f = flatnonzero(vector); dict( zip( f, vector[f] ) )
   0.73s f = flatnonzero(vector); dict( izip( f, vector[f] ) )
   0.71s f = nonzero(vector); dict( izip( f[0], vector[f] ) )
   0.67s n = vector > 0; i = numpy.arange(len(vector))[n]; v = vector[n]; dict(izip(i,v))
   0.81s i = flatnonzero(vector); v = vector[vector > 0]; dict(izip(i,v))
   1.01s dict( zip( flatnonzero(vector), vector[flatnonzero(vector)] ) )
   1.03s dict( zip( flatnonzero(vector), vector[nonzero(vector)] ) )
   4.90s dict( (i, x) for i,x in enumerate(vector) if x > 0);

As you can see, the fastest solution I have found is

n = vector > 0;
i = numpy.arange(len(vector))[n]
v = vector[n]
dict(izip(i,v))

Any faster way?

Edit: Step

i = numpy.arange(len(vector))[n]

, , , , 1/10 , . , .

+5
6

, .

, dict ( ), ; , , , python mem- , , , .

+2
>>> a=np.array([12,0,0,0,3,0,0,1])
>>> {i:a[i] for i in np.nonzero(a)[0]}
{0: 12, 4: 3, 7: 1}
+2

scipy :

from scipy.sparse import *
import numpy
a=numpy.array([12,0,0,0,3,0,0,1])
m=csr_matrix(a)

d={}
for i in m.nonzero()[1]:
  d[i]=m[0,i]
print d
0

, -, :

i = np.flatnonzero(vector)
dict.fromkeys(i.tolist(), vector[i].tolist())

Timing:

import numpy as np
from itertools import izip

vector = np.random.poisson(0.1, size=10000)

%timeit f = np.flatnonzero(vector); dict( izip( f, vector[f] ) )
# 1000 loops, best of 3: 951 µs per loop

%timeit f = np.flatnonzero(vector); dict.fromkeys(f.tolist(), vector[f].tolist())
# 1000 loops, best of 3: 419 µs per loop

scipy.sparse.dok_matrix pandas.DataFrame.to_dict, .

0

np.unique return_index=True:

>>> import numpy as np

>>> arr = np.array([12,0,0,0,3,0,0,1])

>>> val, idx = np.unique(arr, return_index=True)
>>> mask = val != 0                                # exclude zero
>>> dict(zip(idx[mask], val[mask]))                # create the dictionary
{0: 12, 4: 3, 7: 1}

, list, numpy.array, tolist:

>>> dict(zip(idx[mask].tolist(), val[mask].tolist()))

Timing

, , :

import numpy as np
from scipy.sparse import csr_matrix

arr = np.random.randint(0, 10, size=10000)  # 10k items
arr[arr < 7] = 0                            # make it sparse

# ----------

%timeit {i:arr[i] for i in np.nonzero(arr)[0]}
# 3.7 ms ± 51 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

# ----------

%%timeit

val, idx = np.unique(arr, return_index=True)
mask = val != 0
dict(zip(idx[mask].tolist(), val[mask].tolist()))

# 844 µs ± 42.7 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

# ----------

%%timeit

m=csr_matrix(a)

d={}
for i in m.nonzero()[1]:
    d[i]=m[0,i]

# 1.52 s ± 57.4 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
0

?

numpy,

i = (p > 0) [0]

-1

More articles:


All Articles