def read_microsatellite_lines(raw_lines):
"""
How can i combine the two haploid data sources?
Maybe create each data matrix separately from the interleaved input.
@param raw_lines: raw input lines
@return: headers, diploid data
"""
lines = Util.get_stripped_lines(raw_lines)
if len(lines) % 2:
raise ValueError('expected an even number of lines')
if len(lines) < 2:
raise ValueError('expected at least two lines')
full_rows = [x.split() for x in lines]
nfullcols = len(full_rows[0])
if nfullcols < 2:
raise ValueError('expected at least two columns')
for row in full_rows:
if len(row) != nfullcols:
msg = 'each row should have the same number of elements'
raise ValueError(msg)
a_full_rows = [row for i, row in enumerate(full_rows) if i % 2 == 0]
b_full_rows = [row for i, row in enumerate(full_rows) if i % 2 == 1]
a_headers = [row[0] for row in a_full_rows]
b_headers = [row[0] for row in b_full_rows]
for h in a_headers:
if not h.endswith('a'):
msg = 'each odd row label should end with the letter a'
raise ValueError(msg)
for h in b_headers:
if not h.endswith('b'):
msg = 'each even row label should end with the letter b'
raise ValueError(msg)
headers = [h[:-1] for h in a_headers]
# get the unique elements of each column
rows = [row[1:] for row in full_rows]
cols = zip(*rows)
uniques = [list(iterutils.unique_everseen(col)) for col in cols]
# get the results for each row
a_rows = [row[1:] for row in a_full_rows]
b_rows = [row[1:] for row in b_full_rows]
a_columns = zip(*a_rows)
b_columns = zip(*b_rows)
a_binary_rows = Carbone.get_binary_rows_helper(a_columns, uniques)
b_binary_rows = Carbone.get_binary_rows_helper(b_columns, uniques)
# add the elements entrywise and return as a list of lists
bin_row_groups = [a_binary_rows, b_binary_rows]
binary_rows = np.array(bin_row_groups).sum(axis=0).tolist()
return headers, binary_rows
def read_microsatellite_lines(raw_lines):
"""
How can i combine the two haploid data sources?
Maybe create each data matrix separately from the interleaved input.
@param raw_lines: raw input lines
@return: headers, diploid data
"""
lines = Util.get_stripped_lines(raw_lines)
if len(lines) % 2:
raise ValueError('expected an even number of lines')
if len(lines) < 2:
raise ValueError('expected at least two lines')
full_rows = [x.split() for x in lines]
nfullcols = len(full_rows[0])
if nfullcols < 2:
raise ValueError('expected at least two columns')
for row in full_rows:
if len(row) != nfullcols:
msg = 'each row should have the same number of elements'
raise ValueError(msg)
a_full_rows = [row for i, row in enumerate(full_rows) if i % 2 == 0]
b_full_rows = [row for i, row in enumerate(full_rows) if i % 2 == 1]
a_headers = [row[0] for row in a_full_rows]
b_headers = [row[0] for row in b_full_rows]
for h in a_headers:
if not h.endswith('a'):
msg = 'each odd row label should end with the letter a'
raise ValueError(msg)
for h in b_headers:
if not h.endswith('b'):
msg = 'each even row label should end with the letter b'
raise ValueError(msg)
headers = [h[:-1] for h in a_headers]
# get the unique elements of each column
rows = [row[1:] for row in full_rows]
cols = zip(*rows)
uniques = [list(iterutils.unique_everseen(col)) for col in cols]
# get the results for each row
a_rows = [row[1:] for row in a_full_rows]
b_rows = [row[1:] for row in b_full_rows]
a_columns = zip(*a_rows)
b_columns = zip(*b_rows)
a_binary_rows = Carbone.get_binary_rows_helper(a_columns, uniques)
b_binary_rows = Carbone.get_binary_rows_helper(b_columns, uniques)
# add the elements entrywise and return as a list of lists
bin_row_groups = [a_binary_rows, b_binary_rows]
binary_rows = np.array(bin_row_groups).sum(axis=0).tolist()
return headers, binary_rows
def read_microsatellite_lines(raw_lines):
"""
How can i combine the two haploid data sources?
Maybe create each data matrix separately from the interleaved input.
@param raw_lines: raw input lines
@return: headers, diploid data
"""
lines = Util.get_stripped_lines(raw_lines)
full_rows = [line.split() for line in lines]
nfullcols = len(full_rows[0])
if nfullcols < 2:
raise ValueError('expected at least two columns')
if not all(len(row) == nfullcols for row in full_rows):
raise ValueError('expected the same number of elements in each row')
full_cols = zip(*full_rows)
full_names = full_cols[0]
ploidy = get_ploidy(full_names)
headers = list(gen_headers(full_names, ploidy))
# get the unique elements of each column
rows = [row[1:] for row in full_rows]
cols = zip(*rows)
uniques = [list(iterutils.unique_everseen(col)) for col in cols]
# get the rows for each offset
n = len(rows) / ploidy
groups = [[rows[j * ploidy + i] for j in range(n)] for i in range(ploidy)]
# get the column groups
col_groups = [zip(*m) for m in groups]
# get the binary row groups
bin_row_groups = [
Carbone.get_binary_rows_helper(cols, uniques) for cols in col_groups
]
# get the entrywise sum
binary_rows = np.array(bin_row_groups).sum(axis=0).tolist()
return headers, binary_rows
