def make_grid_for_file(results_dir, list_file, grid_file):
POOL_DIRECTIONS = ['H', 'V']
POOL_RANGE = range(1, 13)
logger.info('%s => %s', list_file, grid_file)
df = DataFrame(filename=os.path.join(results_dir, list_file))
(pair, id) = df.get_columns('pair', 'id')
logger.info('%d hits', len(pair))
col_names = [ 'V' + str(i) for i in POOL_RANGE ]
row_names = [ 'H' + str(i) for i in POOL_RANGE ]
data_dict = dict() # will hold a list of the hits for each row, column pair
for r in row_names:
for c in col_names:
data_dict[(r,c)] = [ ]
for (mypair, myid) in zip(pair, id):
(horiz, vert) = mypair.split(' x ')
data_dict[(horiz, vert)] = data_dict[(horiz, vert)] + [ myid ]
# now build a new data frame as a list of tuples, column name and column list
data_by_column = [ ]
# first column is the row names
data_by_column += [(grid_file, row_names)]
# subsequent columns are by vertical pool
for c in col_names:
col_data = [ ]
for r in row_names:
col_data.append(' '.join(sorted(data_dict[(r,c)])))
data_by_column += [ (c, col_data)]
grid_dataframe = DataFrame(data=data_by_column)
grid_dataframe.write(os.path.join(results_dir, grid_file))
def get_control_from_file(filename, simple=True):
"""
read the file as a data frame
for each id, check how many times it occurs as control or experimental
make a dict with (id, name) as key where pair is often as controls, or name is nd
"""
logger.info('reading controls from %s', filename)
control = DataFrame(filename=filename)
control_dict = dict()
if (simple):
(ids, names) = control.get_columns('id','name')
for (id, name) in zip(ids, names):
control_dict[(id,name)] = True
else:
(id, name, control, exptl) = control.get_columns('id', 'name', 'control', 'exptl')
id_to_name = dict()
for (i, n, c, e) in zip(id, name, control, exptl):
isND = n in [ 'ND', 'nd', 'N.D.' ]
isControl = (i == 'CONTROL')
isIgg = (n == 'IgG')
if ((c >= e) or isND or isControl or isIgg):
control_dict[(i, n)] = True
# insert some special cases
control_dict[('CONTROL', 'IgG')] = True
for (i, n) in zip(id, name):
if i not in id_to_name:
id_to_name[i] = dict()
id_to_name[i][n] = True
id_to_names = dict()
for i in id_to_name:
names = sorted(id_to_name[i].keys())
cnt = len(names)
name_str = ','.join(names)
id_to_names[i] = dict()
id_to_names[i]['cnt'] = cnt
id_to_names[i]['names'] = name_str
ids = sorted(id_to_names.keys())
cnts = [ id_to_names[x]['cnt'] for x in ids ]
names = [ id_to_names[x]['names'] for x in ids ]
df = DataFrame(data=[ ('id', ids), ('cnt', cnts), ('names', names)])
df.write('id_to_names.txt')
return(control_dict)
