comparison correlation_matrix.py @ 3:89009e9b7eb0 draft

Uploaded

2:f0c8cdd78e28

import scipy.stats

def main():
    parser = generate_parser()
    args = parser.parse_args()
    data, names = load_data(args)
    corr = find_correlations(data, args)
    save_data(corr, names, args)

def load_data(args):
    infile = open(args.input)
    names = []
    data = []
    if args.column:
        temp = infile.readline()
    temp = infile.readline()
    if args.int:
        dtype = int
    else:
        dtype = float

    if len(names) == 0:
        names = None
    data = numpy.array(data)
    if args.features:
        data = data.T
    return data, names

def find_correlations(data, args):
    corr = numpy.ones((data.shape[0], data.shape[0]), dtype=numpy.float32)
    if args.test == 'pearson':
        findcorr = scipy.stats.pearsonr

3:89009e9b7eb0

import scipy.stats

def main():
    parser = generate_parser()
    args = parser.parse_args()
    data, rnames = load_data(args)
    corr = find_correlations(data, args)
    save_data(corr, names, args)

def load_data(args):
    infile = open(args.input)
    names = []
    cnames = None
    data = []
    if args.column:
        cnames = infile.readline().split()
        if args.rows:
            cnames = cnames[1:]
    temp = infile.readline()
    if args.int:
        dtype = int
    else:
        dtype = float

    if len(names) == 0:
        names = None
    data = numpy.array(data)
    if args.features:
        data = data.T
        names = cnames
    return data, names, cnames

def find_correlations(data, args):
    corr = numpy.ones((data.shape[0], data.shape[0]), dtype=numpy.float32)
    if args.test == 'pearson':
        findcorr = scipy.stats.pearsonr