AttributeError: module 'collections' has no attribute 'Sequence'
i get this error everything i try to run my code but there isn't any information about how to use Mothur except for the the documentation.
`# python3
import sys
import queue
import itertools
from collections import deque
from mothur_py import Mothur
import collections.abc as collections
class KmerIdMgmt:
def __init__(self):
self.id = 0
self.ids_map = {}
self.kmers = {}
def insert(self, kmer):
if kmer not in self.ids_map:
self.ids_map[kmer] = self.id
self.kmers[self.id] = kmer
self.id += 1
return self.ids_map[kmer]
class DeBruijnGraph(object):
def __init__(self, k, reads):
self.k = k
self.threshold = self.k + 1
self.kmer_ids = KmerIdMgmt()
self.coverage = {}
self.graph = {}
self.outgoing_num = lambda k: len(self.graph[k][0])
self.incoming_num = lambda k: self.graph[k][1]
self.make_deBruijn_graph(self.break_reads_into_kmers(reads))
def break_reads_into_kmers(self, reads):
break_read = lambda read: [ read[j:j + self.k] for j in range(len(read) - self.k + 1) ]
return [ kmer for read in reads for kmer in break_read(read) ]
def make_deBruijn_graph(self, kmers):
def add_edge(graph, coverage, left, right):
graph.setdefault(left, [set(), 0])
graph.setdefault(right, [set(), 0])
coverage.setdefault((left, right), 0)
coverage[(left, right)] += 1
if right not in graph[left][0]:
graph[left][0].add(right)
graph[right][1] += 1
for kmer in kmers:
left = self.kmer_ids.insert(kmer[:-1])
right = self.kmer_ids.insert(kmer[1:])
if left != right:
add_edge(self.graph, self.coverage, left, right)
def remove_leaves(self):
removable = [ k for k, v in self.graph.items() if len(v[0]) == 0 ]
for k in removable:
del self.graph[k]
def print_graph(self):
for k, v in self.graph.items():
print(k, v)
class TipRemoval(DeBruijnGraph):
def __init__(self, k, reads):
DeBruijnGraph.__init__(self, k, reads)
def remove_tips(self):
for k, v in self.graph.items():
find_and_remove = None
if self.outgoing_num(k) == 1 and self.incoming_num(k) == 0:
find_and_remove = self.find_and_remove_incoming
elif self.outgoing_num(k) > 1:
find_and_remove = self.find_and_remove_outgoing
else: continue
condition = True
while condition:
condition = False
for edge in v[0]:
if find_and_remove(edge, 0):
v[0].remove(edge)
condition = True
break
def find_and_remove_outgoing(self, current, depth):
if self.outgoing_num(current) > 1 or self.incoming_num(current) > 1:
return False
if depth == self.threshold:
return False
if self.outgoing_num(current) == 0:
return True
if self.find_and_remove_outgoing(next(iter(self.graph[current][0])), depth + 1):
to = next(iter(self.graph[current][0]))
self.graph[current][0].pop()
self.graph[to][1] -= 1
return True
return False
def find_and_remove_incoming(self, current, depth):
if self.outgoing_num(current) == 0 or self.incoming_num(current) > 1:
return True
if depth == self.threshold:
return False
if self.find_and_remove_incoming(next(iter(self.graph[current][0])), depth + 1):
to = next(iter(self.graph[current][0]))
self.graph[current][0].pop()
self.graph[to][1] -= 1
return True
return False
class BubbleRemoval(TipRemoval):
def __init__(self, k, reads):
TipRemoval.__init__(self, k, reads)
self.paths = {}
def remove_bubbles(self):
for k, v in self.graph.items():
if self.outgoing_num(k) > 1:
self.dfs(path=[k], current=k, depth=0)
for pair, candidates_list in self.paths.items():
source, target = pair[0], pair[1]
best_path = max(candidates_list, key=lambda item: item[1])[0]
for path, _ in candidates_list:
if best_path == path or not self.bubble_possible(source, target):
continue
if self.paths_disjoint(best_path, path) and self.path_exists(path):
self.remove_path(path)
def bubble_possible(self, source, target):
return len(self.graph[source][0]) > 1 and self.graph[target][1] > 1
def path_exists(self, path):
for j in range(len(path) -1):
if path[j +1] not in self.graph[path[j]][0]:
return False
return True
def remove_path(self, path):
for j in range(len(path) -1):
self.graph[path[j]][0].remove(path[j +1])
self.graph[path[j +1]][1] -= 1
del self.coverage[(path[j], path[j +1])]
def paths_disjoint(self, a, b):
return len(set(a) & set(b)) == 2
def dfs(self, path, current, depth):
if current != path[0] and self.incoming_num(current) > 1:
weight = sum(self.coverage[(path[i], path[i+1])] for i in range(len(path)-1)) / len(path)
self.paths.setdefault((path[0], current), list()).append((path[:], weight))
if depth == self.threshold:
return
for next_ in self.graph[current][0]:
if next_ not in path:
path.append(next_)
self.dfs(path, next_, depth + 1)
path.remove(next_)
class PhiX174GenomeAssembler(BubbleRemoval):
def __init__(self, k, reads):
BubbleRemoval.__init__(self, k, reads)
def make_Euler_cycle(self):
verteces = deque()
path = []
# line 191
current = next(iter(self.graph))
verteces.append(current)
while verteces:
current = verteces[0]
if len(self.graph[current][0]) != 0:
t = next(iter(self.graph[current][0]))
verteces.append(t)
self.graph[current][0].remove(t)
continue
path.append(current)
verteces.popleft()
return path
def assemble(self):
self.remove_tips()
self.remove_leaves()
self.remove_bubbles()
cycle = self.make_Euler_cycle()
circular_genome = self.kmer_ids.kmers[cycle[0]]
for i in range(1, len(cycle) - (self.k - 1)):
circular_genome += self.kmer_ids.kmers[cycle[i]][-1]
return circular_genome
if __name__ == "__main__":
n_kmers = int(input())
for _ in range(n_kmers):
reads = list(input())
reads = str(reads)
with open('reads.fasta', 'w') as read:
read.write(reads)
k = 100
m = Mothur()
contig = m.make.contigs(ffasta = read)
for x in range(n_kmers):
print(">CONTIG", x)
print(contig)
`
import operator
class Point():
def __init__(self,x,y):
self.x=x
self.y=y
def __repr__(self):
return '<{0},{1}>'.format(self.x,self.y)
def distance(a,b):
return abs((a.x-b.x)**2+(a.y-b.y)**2)**.5
def closest(points):
n = len(points)
if n<=1:
print("invalid input")
elif n==2:
return (points[0],points[1])
elif n==3:
(a,b,c)=points
ret = (a,b) if distance(a,b) < distance(b,c) else (a,c)
ret = (ret[0],ret[1]) if distance(ret[0],ret[1])<distance(b,c) else (b,c)
else:
points = sorted(points,key=operator.attrgetter('x'))
leftPoints = points[:n//2]
rightPoints = points[n//2:]
(left_a,left_b) = closest(leftPoints)
(right_a,right_b) = closest(rightPoints)
d = min(distance(left_a,left_b),distance(right_a,right_b))
mid = (points[n//2].x+points[n//2+1].x)/2
midRange = filter(lambda pt:pt.x >=mid-d and pt.x<=mid+d,points)
midRange = sorted(midRange,key=operator.attrgetter('y'))
ret = None
localMin = None
for i in range(len(midRange)):
a = midRange[i]
for j in range(i+1,len(midRange)):
b = midRange[j]
if(not ret)or (abs(a.y-b.y)<=d and distance(a,b)<localMin):
localMin= distance(a,c)
ret = (a,b)
return ret
points =[Point(1,2),Point(0,0),Point(3,6),Point(4,7),Point(5,5),Point(8,4),Point(2,9),Point(4,5),Point(8,1),Point(4,3),Point(3,3)]
print(closest(points))
. The error is mentioned in the screenshot that I have uploaded .:
The error is coming while I am trying to run it in Python 3.7.
The error is occurring when I am trying to run the code with the parenthesis.
I was trying to run this code and encountered a run time error. I am not able to debug the code. I do believe that the error lies in functions huffman_encode and huffman_decode. The error showing is the resource warning error. Here is the code:
from linked_list import *
from huffman_bits_io import HuffmanBitsWriter as writer, HuffmanBitsReader as reader
import unittest
class Leaf:
'''class that implements Leaf'''
def __init__(self, parent, value, code, frequency):
self.parent = parent
self.frequency = frequency
self.value = value
self.code = code
def __eq__(self, other):
return type(other) == Leaf and self.parent == other.parent and self.frequency ==other.frequency and self.value==other.value and self.code==other.code
def __repr__(self):
return "[ {}, frequency = {} ]".format(self.code, self.frequency)
class Node:
'''class that implements Node'''
def __init__(self, parent, code, lchild, rchild, frequency):
self.parent = parent
self.code = code
self.frequency = frequency
self.lchild = lchild
self.rchild = rchild
def __eq__(self, other):
return type(other) == Node and self.parent==other.parent and self.code == other.code and self.frequency == other.frequency and self.lchild == other.lchild and self.rchild == other.rchild
def __repr__(self):
return "{}, freq = {}\n\left = {}\n\right = {}".format(self.code, self.frequency, self.lchild.___repr__(), self.rchild.__repr__())
def strip(string, seq):
'''this function cuts sequence from beginning of string if possible and returns result '''
if len(seq) > len(string):
return string
for i in range(len(seq)):
if seq[i] != string[i]:
return string
else:
return string[len(seq):]
def find(lst, item):
'''this function finds index of first occurrence of given element in the list and returns it or raise error if there is no such element'''
for i in range(lst.length):
if get(lst, i).value[0] == item:
return i
else:
raise ValueError
def string_traverse(node):
'''this function returns string representation of tree in pre-order traversal'''
lst = empty_list()
traverse(node, lst) #calls traverse
result_string = ''
for i in range(lst.length): #accumulate string from lst list
result_string += chr(get(lst, i).value)
return result_string
def traverse(node, code):
'''this function traverse the try and return list of leaf's value(helper for string_traverse)'''
if type(node) == Leaf:
code = add(code, node.value, code.length) #if node is Leaf than terminate recursion and return character
else:
traverse(node.lchild, code) #recursive call
traverse(node.rchild, code) #recursive call
def count_occurrences(file_name):
'''this function returns list that represent occurrence of every character of given string'''
with open(file_name) as file: #reads file
data = file.read()
lst = list()
for i in range(len(data)): #creates list of integer representation of string
lst.append(ord(data[i]))
data = lst
lst = empty_list()
for char in data: #this loop calculates occurrences of characters in the string
try:
index = find(lst, char)
lst = set(lst, index, (char, get(lst, index).value[1] + 1))
except ValueError:
lst = add(lst, (char, 1), 0)
lst = sort(lst, lambda x: x.value[1], False) #sorts occurrences
return lst
def comes_before(el1, el2):
'''this function returns True if el1 leaf should come before el2 leaf in Huffman tree meaning'''
if el1[1] < el2[1] or (el1[1] == el2[1] and type(el1[0]) is int and type(el2[0]) is int and el1[0] < el2[0]):
return True
else:
return False
def build_tree(occurrences):
'''this function returns Huffman tree based on given list of occurrences'''
if occurrences.length == 1: #if we have only one character returns Leaf with this character and code '0'
return Leaf(None, get(occurrences, 0).value[0], '0', get(occurrences, 0).value[1])
while occurrences.length != 1: #algorith described in the task
el1, occurrences = remove(occurrences, 0)
el2, occurrences = remove(occurrences, 0)
el1, el2 = el1.value, el2.value
if not comes_before(el1, el2): #finds order of elements in the tree
el1, el2 = el2, el1
new = Node(None, '', None, None, el1[1] + el2[1]) #creates new node
if type(el1[0]) is Node:
el1[0].code = '0' #sets up code for node
el1[0].parent = new
new.lchild = el1[0]
else:
new.lchild = Leaf(new, el1[0], '0', el1[1]) #if el1 is character not Node we will create leaf for that character
if type(el2[0]) is Node:
el2[0].code = '1' #sets up code for node
el2[0].parent = new
new.rchild = el2[0]
else:
new.rchild = Leaf(new, el2[0], '1', el2[1]) #if el2 is character not Node we will create leaf for that character
occurrences = insert_sorted(occurrences, (new, new.frequency), comes_before) #inserts new node
return get(occurrences, 0).value[0]
def collect_code(node, code = ''):
'''this function traverse Huffman tree and collect code for each leaf and returns them as nested list(helper for create_code)'''
if type(node) == Leaf:
lst = empty_list()
return add(lst, (node.value, code + node.code), 0) #if node is Leaf terminates recursion and returns code for the leaf
else:
lst = empty_list()
lst = add(lst, collect_code(node.lchild, code + node.code), 0) #recursive call
lst = add(lst, collect_code(node.rchild, code + node.code), 0) #recursive call
return lst
def create_code(tree):
'''this function unpack result of calling collect_code and return Huffman code as a list of tuples'''
code = collect_code(tree) #calls collect code
i = 0
while i < code.length: #this loop unpacks list
if type(get(code, i).value) is not tuple:
item, code = remove(code, i)
for j in range(item.value.length):
code = add(code, get(item.value, j).value, i)
continue
i += 1
return code
def huffman_encode(input_file, output_file):
'''task describe this function'''
occurrences = count_occurrences(input_file)
tree = build_tree(occurrences)
string = empty_list()
t = traverse(tree, string)
code = create_code(tree)
with open(input_file) as file:
string = file.read()
result_string = ''
for i in range(len(string)): #this loop encodes string using code produced by create_code function
for j in range(code.length):
temp = get(code, j).value
if string[i] == chr(temp[0]):
result_string += temp[1]
break
for i in range(occurrences.length):
temp = get(occurrences, i).value
occurrences = set(occurrences, i, (chr(temp[0]), temp[1]))
occurrences = sort(occurrences, lambda x: x.value[0], False)
file = writer(output_file)
file.write_int(code.length)
for i in range(occurrences.length):
temp = get(occurrences, i).value
file.write_byte(ord(temp[0]))
file.write_int(temp[1])
file.write_code(result_string)
file.close()
return string_traverse(tree)
def huffman_decode(input_file, output_file):
'''task describe this function'''
file = reader(input_file)
number_of_codes = file.read_int()
occurrences = empty_list()
for i in range(number_of_codes):
char = file.read_byte()
number = file.read_int()
occurrences = add(occurrences, (char, number), 0)
occurrences = sort(occurrences, lambda x: x.value[1], False)
tree = build_tree(occurrences)
code = sort(create_code(tree), lambda x: x.value[0], False)
occurrences = sort(occurrences, lambda x: x.value[0], False)
quantity_of_bits = 0
for i in range(code.length):
quantity_of_bits += get(occurrences, i).value[1]*len(get(code, i).value[1])
occurrences = sort(occurrences, lambda x: x.value[1], False)
bit_string = ''
for i in range(quantity_of_bits):
bit_string = bit_string + ('1' if file.read_bit() else '0')
result_string = ''
while bit_string: #this loop decodes string using code produced by create_code function
for j in range(code.length):
temp = get(code, j).value
stripped = strip(bit_string, temp[1])
if len(stripped) < len(bit_string):
result_string += chr(temp[0])
bit_string = stripped
break
with open(output_file, 'w') as file:
file.write(result_string)
file.close()
class Test(unittest.TestCase):
def test_strip1(self):
self.assertEqual(strip('123456', '123'), '456')
def test_strip2(self):
self.assertEqual(strip('123', '4567'), '123')
def test_strip3(self):
self.assertEqual(strip('123', '456'), '123')
def test_find(self):
lst = empty_list()
lst = add(lst, (1, 'b'), 0)
lst = add(lst, (2, 'a'), 1)
self.assertEqual(find(lst, 2), 1)
def test_find_raise(self):
lst = empty_list()
lst = add(lst, (1, 'b'), 0)
lst = add(lst, (2, 'a'), 1)
self.assertRaises(ValueError, find, lst, 5)
def test_occurrences(self):
lst = empty_list()
lst = add(lst, (97, 5), 0)
lst = add(lst, (98, 3), 0)
lst = add(lst , (99, 7), 2)
self.assertEqual(str(count_occurrences(r'test2.txt')), str(lst))
def test_create_code_and_tree_build(self):
occurrences = count_occurrences(r'test2.txt')
tree = build_tree(occurrences)
code = create_code(tree)
code = sort(code, lambda x: x.value[0], False)
self.assertEqual(str(code), "[(97, '11'), (98, '10'), (99, '0')]")
def test_huffman_encode_decode(self):
string = huffman_encode(r'test1.txt', r'test_out.txt')
huffman_decode(r'test_out.txt', r'test_decode.txt')
self.assertEqual(string, 'a')
with open(r'test1.txt') as file1:
with open(r'test_decode.txt') as file2:
self.assertEqual(file1.read(), file2.read())
file2.close()
file1.close()
def test_huffman_encode_decode3(self):
string = huffman_encode(r'test2.txt', r'test2_out.txt')
huffman_decode(r'test2_out.txt', r'test2_decode.txt')
self.assertEqual(string, 'cba')
with open(r'test2.txt') as file1:
with open(r'test2_decode.txt') as file2:
self.assertEqual(file1.read(), file2.read())
file2.close()
file1.close()
def test_huffman_encode_decode2(self):
string = huffman_encode(r'test3.txt', r'test3_out.txt')
huffman_decode(r'test3_out.txt', r'test3_decode.txt')
self.assertEqual(string, 'edcba')
with open(r'test3.txt') as file1:
with open(r'test3_decode.txt') as file2:
self.assertEqual(file1.read(), file2.read())
file2.close()
file1.close()
if __name__ == '__main__':
unittest.main()
And following is the error:
...
Warning (from warnings module):
File "C:\Users\Vikas\Documents\fwdregardingprojectdevelopment\huffman.py", line 212
with open(output_file, 'w') as file:
ResourceWarning: unclosed file <_io.BufferedReader name='test_out.txt'>
.
Warning (from warnings module):
File "C:\Users\Vikas\Documents\fwdregardingprojectdevelopment\huffman.py", line 212
with open(output_file, 'w') as file:
ResourceWarning: unclosed file <_io.BufferedReader name='test3_out.txt'>
.
Warning (from warnings module):
File "C:\Users\Vikas\Documents\fwdregardingprojectdevelopment\huffman.py", line 212
with open(output_file, 'w') as file:
ResourceWarning: unclosed file <_io.BufferedReader name='test2_out.txt'>
.....
----------------------------------------------------------------------
Ran 10 tests in 0.272s
OK
it seems somewhere in your code file 'out_file' is opened and not closed
find where it is opened and close it :
out_file.close()
class block(object):
def __init__(self, N):
self.N = N; self.l, self.r, self.u, self.d = [None]*4
def move_lower(self):
res = []
for x in (self.u, self.d, self.l, self.r):
if x != None and x.N < self.N:
res.append(x)
return res
def move_lower_chain(self, res = [], history = []):
temp = self.move_lower()
if len(temp) == 0:
res.append(history + [self.N])
else:
for x in temp:
x.move_lower_chain(res, history + [x.N])
return res
I tried to change the 'move_lower_chain' function to Non-recursive function, but i couldn't and even didn't know how to solve. most difficult part was below:
for x in temp:
x.move_lower_chain(res, history + [x.N])
Is there anyone who can help me?
I'll start by a simplified explanation of what my code (function) has to do:
I get a file with words in it that I have to code to morse code, so I have another file where each character has a morse code. My problem occurs when I want to put each word in a dictionary as a key with as value that morse code.
to get the pattern of the code and assign it to that word in my dictionary I use another function but it says 'UnboundLocalError: local variable 'patroon' referenced before assignment'
while 'patroon' is actually my other function:
def patroon(woord, morse_dict, complement = False, spiegel = False):
patroon_str = ''
for letter in woord:
patroon_str += morse_dict[letter.upper()]
i=0
if complement==True:
patroon_list = list(patroon_str)
for char in patroon_str:
if char == '.':
patroon_list[i]='-'
elif char == '-': patroon_list[i]='.'
i+=1
patroon_str = ''.join(patroon_list)
if spiegel == True:
patroon_str = patroon_str[::-1]
return patroon_str
and here is the function in which it is called:
def groepen(woordenloc, morseloc):
morse_dict = morsecodes(morseloc)
woordpatroon_dict = {}
woorden = open(woordenloc, 'r')
for woord in woorden:
***woordpatroon_dict[woord] = patroon(woord, morse_dict)***
patroonwoorden_dict = {}
for woord, patroon in woordpatroon_dict.items():
if patroon in patroonwoorden_dict:
patroonwoorden_dict[patroon].add(woord)
else:
patroonwoorden_dict[patroon] = {woord}
return patroonwoorden_dict
where the stars are is where the error occurs
I'm new to python so I don't really know if this would be enough information.
this is my full code:
def morsecodes(locatie):
morse_file = open(locatie, 'r')
morse_dict = {}
for line_str in morse_file:
new_l = line_str.split()
if new_l[0].isalpha:
morse_dict[new_l[0].upper()] = new_l[1]
else: morse_dict[new_l[0]] = new_l[1]
return morse_dict
def patroon(woord, morse_dict, complement = False, spiegel = False):
patroon_str = ''
for letter in woord:
patroon_str += morse_dict[letter.upper()]
i=0
if complement==True:
patroon_list = list(patroon_str)
for char in patroon_str:
if char == '.':
patroon_list[i]='-'
elif char == '-': patroon_list[i]='.'
i+=1
patroon_str = ''.join(patroon_list)
if spiegel == True:
patroon_str = patroon_str[::-1]
return patroon_str
def isomorse(woord1, woord2, morse_dict, complement = False, spiegel = False):
patroon1 = patroon(woord1, morse_dict)
patroon2 = patroon(woord2, morse_dict, complement, spiegel)
if patroon1 == patroon2: return True
else: return False
def groepen(woordenloc, morseloc):
morse_dict = morsecodes(morseloc)
woordpatroon_dict = {}
woorden = open(woordenloc, 'r')
for woord in woorden:
woordpatroon_dict[woord] = patroon(woord, morse_dict)
patroonwoorden_dict = {}
for woord, patroon in woordpatroon_dict.items():
if patroon in patroonwoorden_dict:
patroonwoorden_dict[patroon].add(woord)
else:
patroonwoorden_dict[patroon] = {woord}
return patroonwoorden_dict
I have found my mistake, apparently python isn't (yet) smart enough to keep the name patroon as function and the 'patroon' as variable in my for loop separately (which I later use in the same function 'groepen')