为什么这个 python class 不适用于 numba jitclass？
Why this python class is not working with numba jitclass?
我在 numpy 的帮助下编写了以下代码，我想用 numba 提高性能。我不确定为什么它不起作用，因为我已经按照 numba 系统设置了所有变量。我正在尝试加快此代码的速度，因为我将来会处理大型数据集。
import numpy as np
import math
from numba import jitclass
from numba import float64,int64
spec =[
('spacing',float64),
('n_iterations',int64),
('np_emptyhouses',float64[:,:]),
('np_agenthouses',float64[:,:]),
('similarity_threshhold',float64),
('n_changes',int64)
]
@jitclass(spec)
class geo_schelling_update:
def __init__(self,n_iterations,spacing,np_agenthouses,np_emptyhouses,similarity_threshhold):
self.spacing=spacing
self.n_iterations=n_iterations
self.np_emptyhouses=np_emptyhouses
self.np_agenthouses=np_agenthouses
self.similarity_threshhold=similarity_threshhold
def distance_vectorize(self,pointA1, pointA2,agent):
x_square=np.square(pointA1-agent[0])
y_square=np.square(pointA2-agent[1])
dist=np.sqrt(np.array(x_square,dtype=np.float32)+np.array(y_square,dtype=np.float32))
return np.round(dist,4)
def is_unsatisfied_vectorize(self,x,y):
race = np.extract(np.logical_and(np.equal(self.np_agenthouses[:,0],x),np.equal(self.np_agenthouses[:,1],y)),self.np_agenthouses[:,2])[0]
euclid_distance1=round(math.hypot(self.spacing,self.spacing),4)
euclid_distance2=self.spacing
total_agents=np.extract(np.logical_or(np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance1),np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance2)),self.np_agenthouses[:,2])
if total_agents.size ==0:
return False
else:
return total_agents[total_agents==race].size/total_agents.size<self.similarity_threshhold
def move_to_empty(self,x,y):
race = np.extract(np.logical_and(np.equal(self.np_agenthouses[:,0],x),np.equal(self.np_agenthouses[:,1],y)),self.np_agenthouses[:,2])[0]
x_new,y_new=self.np_emptyhouses[np.random.choice(self.np_emptyhouses.shape[0],1),:][0]
self.np_agenthouses=self.np_agenthouses[~(np.logical_and(self.np_agenthouses[:,0]==x, self.np_agenthouses[:,1]==y))]
self.np_agenthouses=np.vstack([self.np_agenthouses,[x_new,y_new,race]])
self.np_emptyhouses=self.np_emptyhouses[~(np.logical_and(self.np_emptyhouses[:,0]==x_new, self.np_emptyhouses[:,1]==y_new))]
self.np_emptyhouses=np.vstack([self.np_emptyhouses,[x,y]])
def update_helper(self,agent):
if self.is_unsatisfied_vectorize(agent[0],agent[1]):
self.move_to_empty(agent[0],agent[1])
return 1
else:
return 0
def update(self):
for i in np.arange(self.n_iterations):
np_oldagenthouses=self.np_agenthouses.copy()
n_changes=0
for row in np_oldagenthouses:
n=self.update_helper(row)
n_changes+=n
print(n_changes)
print(i)
if n_changes == 0:
break
np_agenthouses=np.array([[-71.8, 41.4, 2.0],
[-71.6, 41.4, 2.0],
[-71.6, 41.6, 2.0],
[-71.4, 41.6, 1.0],
[-71.6, 41.8, 1.0],
[-71.4, 41.8, 2.0],
[-71.6, 42.0, 2.0],
[-71.4, 42.0, 1.0],
[-71.4, 41.4, 2.0],
[-71.2, 41.4, 1.0]])
np_emptyhouses=np.array([[-71.8, 41.3],[-71.8, 41.4],[-71.5, 41.5],
[-71.5, 41.6],[-71.7, 41.8],[-71.7, 41.9],
[-71.5, 41.9],[-71.2, 41.4],[-71.6, 41.7]])
spacing=0.1
similarity_threshhold=0.65
n_iterations=100
schelling= geo_schelling_update(n_iterations,
spacing,
np_agenthouses,
np_emptyhouses,similarity_threshhold)
schelling.update()
这是我收到的错误：
TypingError: Failed in nopython mode pipeline (step: nopython frontend)
Failed in nopython mode pipeline (step: nopython frontend)
Failed in nopython mode pipeline (step: nopython frontend)
Invalid use of Function(<function round_ at 0x000001909ED270D0>) with argument(s) of type(s): (array(float64, 1d, C), Literal[int](4))
* parameterized
In definition 0:
All templates rejected with literals.
In definition 1:
All templates rejected without literals.
This error is usually caused by passing an argument of a type that is unsupported by the named function.
[1] During: resolving callee type: Function(<function round_ at 0x000001909ED270D0>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (42)
File "test2.py", line 42:
def is_unsatisfied_vectorize(self,x,y):
<source elided>
euclid_distance2=self.spacing
total_agents=np.extract(np.logical_or(np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance1),np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance2)),self.np_agenthouses[:,2])
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'is_unsatisfied_vectorize') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (57)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'is_unsatisfied_vectorize') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (57)
File "test2.py", line 57:
def update_helper(self,agent):
if self.is_unsatisfied_vectorize(agent[0],agent[1]):
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update_helper') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (68)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update_helper') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (68)
File "test2.py", line 68:
def update(self):
<source elided>
for row in np_oldagenthouses:
n=self.update_helper(row)
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at <string> (3)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at <string> (3)
我也是运行这个代码在IDE。如果上面的代码不适用于 numba 那么使这段代码工作以获得相同结果的最佳方法是什么。
问题出在 np.round。从文档中看并不完全清楚，但您可以从 source 中看出，如果您在数组输入上使用该函数，则需要提供所有 3 个参数。所以以下不起作用：
nb.jit(nopython=True)
def func(x):
return np.round(x)
但以下内容按预期工作：
nb.jit(nopython=True)
def func(x):
out = np.empty_like(x)
np.round(x, 0, out)
return out
有关完整说明，请参阅 docs for np.around。我将在 numba 问题跟踪器上提出一个问题，因为从文档中看这并不明显。
我在 numpy 的帮助下编写了以下代码，我想用 numba 提高性能。我不确定为什么它不起作用，因为我已经按照 numba 系统设置了所有变量。我正在尝试加快此代码的速度，因为我将来会处理大型数据集。
import numpy as np
import math
from numba import jitclass
from numba import float64,int64
spec =[
('spacing',float64),
('n_iterations',int64),
('np_emptyhouses',float64[:,:]),
('np_agenthouses',float64[:,:]),
('similarity_threshhold',float64),
('n_changes',int64)
]
@jitclass(spec)
class geo_schelling_update:
def __init__(self,n_iterations,spacing,np_agenthouses,np_emptyhouses,similarity_threshhold):
self.spacing=spacing
self.n_iterations=n_iterations
self.np_emptyhouses=np_emptyhouses
self.np_agenthouses=np_agenthouses
self.similarity_threshhold=similarity_threshhold
def distance_vectorize(self,pointA1, pointA2,agent):
x_square=np.square(pointA1-agent[0])
y_square=np.square(pointA2-agent[1])
dist=np.sqrt(np.array(x_square,dtype=np.float32)+np.array(y_square,dtype=np.float32))
return np.round(dist,4)
def is_unsatisfied_vectorize(self,x,y):
race = np.extract(np.logical_and(np.equal(self.np_agenthouses[:,0],x),np.equal(self.np_agenthouses[:,1],y)),self.np_agenthouses[:,2])[0]
euclid_distance1=round(math.hypot(self.spacing,self.spacing),4)
euclid_distance2=self.spacing
total_agents=np.extract(np.logical_or(np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance1),np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance2)),self.np_agenthouses[:,2])
if total_agents.size ==0:
return False
else:
return total_agents[total_agents==race].size/total_agents.size<self.similarity_threshhold
def move_to_empty(self,x,y):
race = np.extract(np.logical_and(np.equal(self.np_agenthouses[:,0],x),np.equal(self.np_agenthouses[:,1],y)),self.np_agenthouses[:,2])[0]
x_new,y_new=self.np_emptyhouses[np.random.choice(self.np_emptyhouses.shape[0],1),:][0]
self.np_agenthouses=self.np_agenthouses[~(np.logical_and(self.np_agenthouses[:,0]==x, self.np_agenthouses[:,1]==y))]
self.np_agenthouses=np.vstack([self.np_agenthouses,[x_new,y_new,race]])
self.np_emptyhouses=self.np_emptyhouses[~(np.logical_and(self.np_emptyhouses[:,0]==x_new, self.np_emptyhouses[:,1]==y_new))]
self.np_emptyhouses=np.vstack([self.np_emptyhouses,[x,y]])
def update_helper(self,agent):
if self.is_unsatisfied_vectorize(agent[0],agent[1]):
self.move_to_empty(agent[0],agent[1])
return 1
else:
return 0
def update(self):
for i in np.arange(self.n_iterations):
np_oldagenthouses=self.np_agenthouses.copy()
n_changes=0
for row in np_oldagenthouses:
n=self.update_helper(row)
n_changes+=n
print(n_changes)
print(i)
if n_changes == 0:
break
np_agenthouses=np.array([[-71.8, 41.4, 2.0],
[-71.6, 41.4, 2.0],
[-71.6, 41.6, 2.0],
[-71.4, 41.6, 1.0],
[-71.6, 41.8, 1.0],
[-71.4, 41.8, 2.0],
[-71.6, 42.0, 2.0],
[-71.4, 42.0, 1.0],
[-71.4, 41.4, 2.0],
[-71.2, 41.4, 1.0]])
np_emptyhouses=np.array([[-71.8, 41.3],[-71.8, 41.4],[-71.5, 41.5],
[-71.5, 41.6],[-71.7, 41.8],[-71.7, 41.9],
[-71.5, 41.9],[-71.2, 41.4],[-71.6, 41.7]])
spacing=0.1
similarity_threshhold=0.65
n_iterations=100
schelling= geo_schelling_update(n_iterations,
spacing,
np_agenthouses,
np_emptyhouses,similarity_threshhold)
schelling.update()
这是我收到的错误：
TypingError: Failed in nopython mode pipeline (step: nopython frontend)
Failed in nopython mode pipeline (step: nopython frontend)
Failed in nopython mode pipeline (step: nopython frontend)
Invalid use of Function(<function round_ at 0x000001909ED270D0>) with argument(s) of type(s): (array(float64, 1d, C), Literal[int](4))
* parameterized
In definition 0:
All templates rejected with literals.
In definition 1:
All templates rejected without literals.
This error is usually caused by passing an argument of a type that is unsupported by the named function.
[1] During: resolving callee type: Function(<function round_ at 0x000001909ED270D0>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (42)
File "test2.py", line 42:
def is_unsatisfied_vectorize(self,x,y):
<source elided>
euclid_distance2=self.spacing
total_agents=np.extract(np.logical_or(np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance1),np.equal(np.round(np.hypot((self.np_agenthouses[:,0]-(x)),(self.np_agenthouses[:,1]-(y))),4),euclid_distance2)),self.np_agenthouses[:,2])
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'is_unsatisfied_vectorize') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (57)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'is_unsatisfied_vectorize') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (57)
File "test2.py", line 57:
def update_helper(self,agent):
if self.is_unsatisfied_vectorize(agent[0],agent[1]):
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update_helper') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (68)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update_helper') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at C:/Users/ksharma/Documents/geoschelling/test2.py (68)
File "test2.py", line 68:
def update(self):
<source elided>
for row in np_oldagenthouses:
n=self.update_helper(row)
^
[1] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[2] During: typing of call at <string> (3)
[3] During: resolving callee type: BoundFunction((<class 'numba.types.misc.ClassInstanceType'>, 'update') for instance.jitclass.geo_schelling_update#190b49eec18<spacing:float64,n_iterations:int64,np_emptyhouses:array(float64, 2d, A),np_agenthouses:array(float64, 2d, A),similarity_threshhold:float64,n_changes:int64>)
[4] During: typing of call at <string> (3)
我也是运行这个代码在IDE。如果上面的代码不适用于 numba 那么使这段代码工作以获得相同结果的最佳方法是什么。
问题出在 np.round。从文档中看并不完全清楚，但您可以从 source 中看出，如果您在数组输入上使用该函数，则需要提供所有 3 个参数。所以以下不起作用：
nb.jit(nopython=True)
def func(x):
return np.round(x)
但以下内容按预期工作：
nb.jit(nopython=True)
def func(x):
out = np.empty_like(x)
np.round(x, 0, out)
return out
有关完整说明，请参阅 docs for np.around。我将在 numba 问题跟踪器上提出一个问题，因为从文档中看这并不明显。