def fqframe(fileh):
final_schema = Schema({
'id': str,
'seq': str,
'quality': str,
'qual_ints': check_np_type('int64'),
'error': check_np_type('float64'),
'description': str
})
#get_object = _id
index = ['id']
columns = ('id', 'seq', 'quality', 'description', 'qual_ints', 'error')
SANGER = True
get_id = attr('id')
get_seq = compose(str, attr('seq'))
get_qual_ints = compose_all(np.array, itemgetter('phred_quality'),
attr('_per_letter_annotations'))
get_description = attr('description')
get_quality = SeqIO.QualityIO._get_sanger_quality_str
get_error = compose(error, get_qual_ints)
#get_error = error_from_ints(get_qual_ints)
getters = [
get_id, get_seq, get_quality, get_description, get_qual_ints, get_error
]
assert len(getters) == len(columns)
metadata = {'filename': fileh.name}
iterator = get_fastq(fileh)
get_raw_record = partial(next, iterator)
# def get_row(record):
# #record = next(fileh)
## import sys
## __module__ = sys.modules[__name__]
## get_getter = compose(attr, "get_{0}".format)
## _getters = map(get_getter, columns)
## self_getters = apply_each(_getters, __module__) #fzip(_getters, repeat(__module__, clen))
# results = apply_each(self_getters, record)
# final_dict = dict(zip(columns, results))
# final_schema.validate(final_dict)
# return final_dict
# def load_fastq():
# fq = get_fastq(fileh)
# dicts = map(get_row, fq)
# return pd.DataFrame(dicts).set_index(index) #, index=index, columns=columns)
#jreturn nameddict(
return {
'obj_func': get_raw_record,
'columns': columns,
'getters': getters,
'validator': final_schema,
'dictgetters': None
}
def fqframe(fileh):
final_schema = Schema({
'id' : str,
'seq' : str,
'quality' : str,
'qual_ints' : check_np_type('int64'),
'error' : check_np_type('float64'),
'description' : str
})
#get_object = _id
index = ['id']
columns = ('id', 'seq', 'quality', 'description', 'qual_ints', 'error')
SANGER = True
get_id = attr('id')
get_seq= compose(str, attr('seq'))
get_qual_ints = compose_all(np.array, itemgetter('phred_quality'), attr('_per_letter_annotations'))
get_description = attr('description')
get_quality = SeqIO.QualityIO._get_sanger_quality_str
get_error = compose(error, get_qual_ints)
#get_error = error_from_ints(get_qual_ints)
getters = [get_id, get_seq, get_quality, get_description, get_qual_ints, get_error]
assert len(getters) == len(columns)
metadata = {'filename' : fileh.name}
iterator = get_fastq(fileh)
get_raw_record = partial(next, iterator)
# def get_row(record):
# #record = next(fileh)
## import sys
## __module__ = sys.modules[__name__]
## get_getter = compose(attr, "get_{0}".format)
## _getters = map(get_getter, columns)
## self_getters = apply_each(_getters, __module__) #fzip(_getters, repeat(__module__, clen))
# results = apply_each(self_getters, record)
# final_dict = dict(zip(columns, results))
# final_schema.validate(final_dict)
# return final_dict
# def load_fastq():
# fq = get_fastq(fileh)
# dicts = map(get_row, fq)
# return pd.DataFrame(dicts).set_index(index) #, index=index, columns=columns)
#jreturn nameddict(
return { 'obj_func' : get_raw_record,
'columns' : columns,
'getters' : getters,
'validator' : final_schema,
'dictgetters' : None
}
def fqframe(fileh):
final_schema = Schema({
'id': str,
'seq': str,
'quality': str,
'qual_ints': check_np_type('int64'),
'error': check_np_type('float64'),
'description': str
})
#get_object = _id
index = ['id']
columns = ('id', 'seq', 'quality', 'description', 'qual_ints', 'error')
SANGER = True
get_id = attr('id')
get_seq = compose(str, attr('seq'))
get_qual_ints = compose_all(np.array, itemgetter('phred_quality'),
attr('_per_letter_annotations'))
get_description = attr('description')
get_quality = SeqIO.QualityIO._get_sanger_quality_str
get_error = compose(error, get_qual_ints)
#get_error = error_from_ints(get_qual_ints)
def get_row(record):
#record = next(fileh)
print(get_funcs())
import sys
__module__ = sys.modules[__name__]
get_getter = compose(attr, "get_{0}".format)
_getters = map(get_getter, columns)
self_getters = apply_each(
_getters, __module__) #fzip(_getters, repeat(__module__, clen))
results = apply_each(self_getters, record)
final_dict = dict(zip(columns, results))
final_schema.validate(final_dict)
return final_dict
def load_fastq():
fq = get_fastq(fileh)
dicts = map(get_row, fq)
return pd.DataFrame(dicts).set_index(
index) #, index=index, columns=columns)
return namedtuple('FastqFrame', ['get_row', 'load_fastq'])(
get_row, load_fastq) #{'get_row' : get_row, 'load_fastq' : load_fastq}
def fqframe(fileh):
final_schema = Schema({
'id' : str,
'seq' : str,
'quality' : str,
'qual_ints' : check_np_type('int64'),
'error' : check_np_type('float64'),
'description' : str
})
#get_object = _id
index = ['id']
columns = ('id', 'seq', 'quality', 'description', 'qual_ints', 'error')
SANGER = True
get_id = attr('id')
get_seq= compose(str, attr('seq'))
get_qual_ints = compose_all(np.array, itemgetter('phred_quality'), attr('_per_letter_annotations'))
get_description = attr('description')
get_quality = SeqIO.QualityIO._get_sanger_quality_str
get_error = compose(error, get_qual_ints)
#get_error = error_from_ints(get_qual_ints)
def get_row(record):
#record = next(fileh)
print(get_funcs())
import sys
__module__ = sys.modules[__name__]
get_getter = compose(attr, "get_{0}".format)
_getters = map(get_getter, columns)
self_getters = apply_each(_getters, __module__) #fzip(_getters, repeat(__module__, clen))
results = apply_each(self_getters, record)
final_dict = dict(zip(columns, results))
final_schema.validate(final_dict)
return final_dict
def load_fastq():
fq = get_fastq(fileh)
dicts = map(get_row, fq)
return pd.DataFrame(dicts).set_index(index) #, index=index, columns=columns)
return namedtuple('FastqFrame', ['get_row', 'load_fastq'])(get_row, load_fastq)#{'get_row' : get_row, 'load_fastq' : load_fastq}
def walk(G, vstd, cycle, start, current=None, call=0):
#TODO: I think this leaves out the final step of the cycle.
if start == current: return vstd, cycle# + tuple([current])
#NOTE: checking for boolean of 0 is bad here haha
#_current = start if current else current
_current = start if current is None else current
candidates = set(G.edges(_current)) - vstd
#candidates = filterfalse(vstd.__contains__, G.neighbors(current))
edge = random.choice(tuple(candidates))
nn = edge[1]
return walk(G, vstd | set([edge]), cycle + tuple([nn]), start, nn, call+1)
filterfst = compose(next, ifilter)
def edges_of_path(G, p):
return map(X[0]['kmer'], starmap(F(G.get_edge_data), slider(p, 2)))
reconstruct_str = compose_all(''.join, pmap(''.join), edges_of_path)
def e_cycle(G, vstd=set(), cycle=(), call=0):
''' find a Eulerian path in a graph by iteratively expanding a cycle.
requires a mostly-balanced and connected graph.'''
if len(vstd) == len(G.edges()): return cycle
def valid(N):
edges=G.edges(N)
return not (set(edges) <= vstd)
#return bool(map(F(filterfalse, vstd.__contains__), edges))
if not cycle:
valid_start = random.choice(G.nodes()) # 6
cycle = tuple([valid_start])
else:
valid_start = filterfst(valid, cycle)
import re
import pandas as pd
from bioframes import to_np_int, sanger_qual_str_to_error
from itertools import groupby
from func import pmap, psplit, pstrip, compose, compose_all, merge_dicts, fzip, partial2, dictmap, starcompose
from operator import itemgetter
from functools import partial
import operator as op
from schema import Schema, Use
from itertools import ifilter
# Parse options
#from pyparsing import Regex
parse_array = compose_all(to_np_int, psplit(','), pstrip('[]'))
tabsplit = psplit('\t')
basic_scheme={
'QNAME' : str,
'FLAG' : int,
'RNAME' : str,
'POS' : int,
'MAPQ' : int,
'CIGAR' : str,
'RNEXT' : str,
'PNEXT' : int,
'TLEN' : int,
#'MRNM' : str,
#'MRNM' : '*='.__contains__,
#'MPOS' : int,
#'ISIZE' : int,
'SEQ' : str,
print( func.__name__)
print( args, kwargs)
#print formatAllArgs(args, kwargs)
return func(*args, **kwargs)
return wrap
def slider(seq, window, start=0):#, stop=None):
'''assert list(slider([0, 1, 2], 2)) == [ [0,1], [1,2] ]
assert list(slider('ABCDE', 4)) == [ 'ABCD', 'BCDE' ]
assert list(slider('ABCDE', 1)) == list('ABCDE')'''
N = len(seq)
for idx in xrange(N-window+1):
yield seq[idx:idx+window]
filterfst = compose(next, ifilter)
composition = compose_all(sorted, list, slider)
def fromstr(_in):
lines = filter(str.strip, _in.split('\n'))
k = int(lines[0])
s = ''.join(lines[1:])
return s, k
cfromstr = starcompose(composition, fromstr)
#assert ["AATCC", "ATCCA", "CAATC", "CCAAC", "TCCAA"] == cfromstr(r_in)
#neighobrs = filter(X[:k] == sfx, prefixg)
#NOTE: using generators over lists makes a huge difference.
def make_ovrlp_graph(kmers):
N = len(kmers)
ov = len(kmers[0]) - 1
M = np.zeros((N, N))
# return ddist(centers).argmin()
# #return min(centers, key=ddist)
def makematrices(s):
_centers, _data = splitby(_not(isin('------')), ifilter(bool, s))
#centers = map(makenp, islice(_centers, 1, None))
#data = map(makenp, islice(_data, 1, None))
centers = makenp(islice(_centers, 1, None))
data = makenp(islice(_data, 1, None))
return centers, data
isin = partial(methodcaller, '__contains__')
makearray = compose_all(np.array, pmap(np.array), pmap(float), psplit(' '))
makenp = compose(np.array, pmap(makearray))
def get_in_out(s):
raw_in, raw_out = splitby(_not(isin('Output')), ifilter(bool, s))
k = int(next(raw_in).split(' ')[0])
_in = makenp(raw_in)
_out =makenp(islice(raw_out, 1, None))
return _in, _out, k
lines = open('Lloyd.txt').readlines()
input, expected, k = get_in_out(lines)
print soft_k_means_cluster(input, k=3)
from matplotlib import pyplot
# method that gets node with matching distance
def get_match_dst(D, j, dist):
assert dist != 0
return (D[j] == dist).argmax()
#return D[i, (D[i] == dist)]
def get_match_dists(D, j, dist):
assert dist != 0
return (D[j] == dist).nonzero()
def non_diag(D, j):
return range(0, j) + range(j+1, D.shape[0])
nondiag_products = compose_all(list, get_products, non_diag)
nondiag_products3 = compose_all(list, partial(get_products, times=3), non_diag)
products3 = compose_all(list, partial(get_products, times=3))
def additive_phyloZ(D, n):
if n == 2:
return str_matrix(D)
ll = limb_len(D, n)
non_diag = range(0, n) + range(n+1, D.shape[0])
D[non_diag, j] -= ll
D[j, non_diag] -= ll
# get matching i, n, k
D.mask[n] = D.mask[:, n] = True
T = additive_phylo(D, n-1)
v_candidates_i = get_match_dst(T, i, x)
along_path = lambda c: D[k, c] + D[i, c] == x
v = filterfst(along_path, v_candidates_i)