parse_csv.py

import numpy as np

def parse_csv(fname):
    lines = []
    with open(fname, 'r') as fd:
        for line in fd.readlines():
            if not line.startswith('#'):
                lines.append(line.strip().split(','))
    names = [field.split('.') for field in lines[0]]
    data = np.array([[float(f) for f in line] for line in lines[1:]])

    namemap = {}
    maxdims = {}
    for i, name in enumerate(names):
        if name[0] not in namemap:
            namemap[name[0]] = []
        namemap[name[0]].append(i)
        if len(name) > 1:
            maxdims[name[0]] = name[1:]

    for name in maxdims.keys():
        dims = []
        for dim in maxdims[name]:
            dims.append(int(dim))
        maxdims[name] = tuple(reversed(dims))

    # data in linear order per Stan, e.g. mat is col maj
    data_ = {}
    for name, idx in namemap.items():
        new_shape = (-1, ) + maxdims.get(name, ())
        data_[name] = data[:, idx].reshape(new_shape)

    return data_


def parse_csv2(dir, fname):
    lines = []
    with open(dir+fname, 'r') as fd:
        for line in fd.readlines():
            if not line.startswith('#'):
                lines.append(line.strip().split(','))
    names = [field.split('.') for field in lines[0]]
    data = np.array([[float(f) for f in line] for line in lines[1:]])

    namemap = {}
    maxdims = {}
    for i, name in enumerate(names):
        if name[0] not in namemap:
            namemap[name[0]] = []
        namemap[name[0]].append(i)
        if len(name) > 1:
            maxdims[name[0]] = name[1:]

    for name in maxdims.keys():
        dims = []
        for dim in maxdims[name]:
            dims.append(int(dim))
        maxdims[name] = tuple(reversed(dims))

    # data in linear order per Stan, e.g. mat is col maj
    data_ = {}
    for name, idx in namemap.items():
        new_shape = (-1, ) + maxdims.get(name, ())
        data_[name] = data[:, idx].reshape(new_shape)

    return data_