所以我正在尝试使用
在我的脚本顶部加上
有没有办法使用
我可以对非Cython化的函数进行分析，但其速度远慢于Cython化的函数，因此我无法使用从分析中得出的信息。纯Python函数的缓慢将使我无法改进Cython函数。
以下是我想要进行分析的函数代码：
line_profiler在自己的Python脚本中对一个函数进行性能剖析，因为我想获取每行代码的时间。唯一的问题是这个函数是Cython类型的，而line_profiler无法正常工作。在最初的运行中，它只是崩溃并出现错误。然后我添加了!python
cython: profile=True
cython: linetrace=True
cython: binding=True
在我的脚本顶部加上
line_profiler，现在它可以正常运行，但是时间和统计信息都是空的！有没有办法使用
line_profiler来分析Cython函数？我可以对非Cython化的函数进行分析，但其速度远慢于Cython化的函数，因此我无法使用从分析中得出的信息。纯Python函数的缓慢将使我无法改进Cython函数。
以下是我想要进行分析的函数代码：
class motif_hit(object):
__slots__ = ['position', 'strand']
def __init__(self, int position=0, int strand=0):
self.position = position
self.strand = strand
#the decorator for line_profiler
@profile
def find_motifs_cython(list bed_list, list matrices=None, int limit=0, int mut=0):
cdef int q = 3
cdef list bg = [0.25, 0.25, 0.25, 0.25]
cdef int matrices_length = len(matrices)
cdef int results_length = 0
cdef int results_length_shuffled = 0
cdef np.ndarray upper_adjust_list = np.zeros(matrices_length, np.int)
cdef np.ndarray lower_adjust_list = np.zeros(matrices_length, np.int)
#this one need to be a list for MOODS
cdef list threshold_list = [None for _ in xrange(matrices_length)]
cdef list matrix_list = [None for _ in xrange(matrices_length)]
cdef np.ndarray results_list = np.zeros(matrices_length, np.object)
cdef int count_seq = len(bed_list)
cdef int mat
cdef int i, j, k
cdef int position, strand
cdef list result, results, results_shuffled
cdef dict result_temp
cdef int length
if count_seq > 0:
for mat in xrange(matrices_length):
matrix_list[mat] = matrices[mat]['matrix'].tolist()
#change that for a class
results_list[mat] = {'kmer': matrices[mat]['kmer'],
'motif_count': 0,
'pos_seq_count': 0,
'motif_count_shuffled': 0,
'pos_seq_count_shuffled': 0,
'ratio': 0,
'sequence_positions': np.empty(count_seq, np.object)}
length = len(matrices[mat]['kmer'])
#wrong with imbalanced matrices
upper_adjust_list[mat] = int(ceil(length / 2.0))
lower_adjust_list[mat] = int(floor(length / 2.0))
#upper_adjust_list[mat] = 0
#lower_adjust_list[mat] = 0
#-0.1 to adjust for a division floating point bug (4.99999 !< 5, but is < 4.9!)
threshold_list[mat] = MOODS.max_score(matrix_list[mat]) - float(mut) - 0.1
#for each sequence
for i in xrange(count_seq):
item = bed_list[i]
#TODO: remove the Ns, but it might unbalance
results = MOODS.search(str(item.sequence[limit:item.total_length - limit]), matrix_list, threshold_list, q=q, bg=bg, absolute_threshold=True, both_strands=True)
results_shuffled = MOODS.search(str(item.sequence_shuffled[limit:item.total_length - limit]), matrix_list, threshold_list, q=q, bg=bg, absolute_threshold=True, both_strands=True)
results = results[0:len(matrix_list)]
results_shuffled = results_shuffled[0:len(matrix_list)]
results_length = len(results)
#for each matrix
for j in xrange(results_length):
result = results[j]
result_shuffled = results_shuffled[j]
upper_adjust = upper_adjust_list[j]
lower_adjust = lower_adjust_list[j]
result_length = len(result)
result_length_shuffled = len(result_shuffled)
if result_length > 0:
results_list[j]['pos_seq_count'] += 1
results_list[j]['sequence_positions'][i] = np.empty(result_length, np.object)
#for each motif
for k in xrange(result_length):
position = result[k][0]
strand = result[k][1]
if position >= 0:
strand = 0
adjust = upper_adjust
else:
position = -position
strand = 1
adjust = lower_adjust
results_list[j]['motif_count'] += 1
results_list[j]['sequence_positions'][i][k] = motif_hit(position + adjust + limit, strand)
if result_length_shuffled > 0:
results_list[j]['pos_seq_count_shuffled'] += 1
#for each motif
for k in xrange(result_length_shuffled):
results_list[j]['motif_count_shuffled'] += 1
#j = j + 1
#i = i + 1
for i in xrange(results_length):
result_temp = results_list[i]
result_temp['ratio'] = float(result_temp['pos_seq_count']) / float(count_seq)
return results_list
我相信三重嵌套循环是主要的缓慢部分-它的任务仅仅是重新排列来自MOODS的结果，而MOODS是执行主要工作的C模块。
motif_hit和MOODS。 - Padraic Cunningham%prun命令来运行该文件。 - Padraic Cunningham