Python scipy.empty() Examples

def fake_mldata(columns_dict, dataname, matfile, ordering=None):
    """Create a fake mldata data set.

    .. deprecated:: 0.20
        Will be removed in version 0.22

    Parameters
    ----------
    columns_dict : dict, keys=str, values=ndarray
        Contains data as columns_dict[column_name] = array of data.

    dataname : string
        Name of data set.

    matfile : string or file object
        The file name string or the file-like object of the output file.

    ordering : list, default None
        List of column_names, determines the ordering in the data set.

    Notes
    -----
    This function transposes all arrays, while fetch_mldata only transposes
    'data', keep that into account in the tests.
    """
    datasets = dict(columns_dict)

    # transpose all variables
    for name in datasets:
        datasets[name] = datasets[name].T

    if ordering is None:
        ordering = sorted(list(datasets.keys()))
    # NOTE: setting up this array is tricky, because of the way Matlab
    # re-packages 1D arrays
    datasets['mldata_descr_ordering'] = sp.empty((1, len(ordering)),
                                                 dtype='object')
    for i, name in enumerate(ordering):
        datasets['mldata_descr_ordering'][0, i] = name

    scipy.io.savemat(matfile, datasets, oned_as='column') 

def fake_mldata(columns_dict, dataname, matfile, ordering=None):
    """Create a fake mldata data set.

    Parameters
    ----------
    columns_dict : dict, keys=str, values=ndarray
        Contains data as columns_dict[column_name] = array of data.

    dataname : string
        Name of data set.

    matfile : string or file object
        The file name string or the file-like object of the output file.

    ordering : list, default None
        List of column_names, determines the ordering in the data set.

    Notes
    -----
    This function transposes all arrays, while fetch_mldata only transposes
    'data', keep that into account in the tests.
    """
    datasets = dict(columns_dict)

    # transpose all variables
    for name in datasets:
        datasets[name] = datasets[name].T

    if ordering is None:
        ordering = sorted(list(datasets.keys()))
    # NOTE: setting up this array is tricky, because of the way Matlab
    # re-packages 1D arrays
    datasets['mldata_descr_ordering'] = sp.empty((1, len(ordering)),
                                                 dtype='object')
    for i, name in enumerate(ordering):
        datasets['mldata_descr_ordering'][0, i] = name

    scipy.io.savemat(matfile, datasets, oned_as='column') 

def parse_plink_snps(genotype_file, snp_indices):
    plinkf = plinkfile.PlinkFile(genotype_file)
    samples = plinkf.get_samples()
    num_individs = len(samples)
    num_snps = len(snp_indices)
    raw_snps = sp.empty((num_snps, num_individs), dtype='int8')
    # If these indices are not in order then we place them in the right place while parsing SNPs.
    snp_order = sp.argsort(snp_indices)
    ordered_snp_indices = list(snp_indices[snp_order])
    ordered_snp_indices.reverse()
    # Iterating over file to load SNPs
    snp_i = 0
    next_i = ordered_snp_indices.pop()
    line_i = 0
    max_i = ordered_snp_indices[0]
    while line_i <= max_i: 
        if line_i < next_i:
            next(plinkf)
        elif line_i == next_i:
            line = next(plinkf)
            snp = sp.array(line, dtype='int8')
            bin_counts = line.allele_counts()
            if bin_counts[-1] > 0:
                mode_v = sp.argmax(bin_counts[:2])
                snp[snp == 3] = mode_v
            s_i = snp_order[snp_i]
            raw_snps[s_i] = snp
            if line_i < max_i:
                next_i = ordered_snp_indices.pop()
            snp_i += 1
        line_i += 1
    plinkf.close()
    assert snp_i == len(raw_snps), 'Parsing SNPs from plink file failed.'
    num_indivs = len(raw_snps[0])
    freqs = sp.sum(raw_snps, 1, dtype='float32') / (2 * float(num_indivs))
    return raw_snps, freqs 

def csr_to_problem(x, prob):
	# Extra space for termination node and (possibly) bias term
	x_space = prob.x_space = scipy.empty((x.nnz+x.shape[0]*2), dtype=feature_node)
	prob.rowptr = x.indptr.copy()
	prob.rowptr[1:] += 2*scipy.arange(1,x.shape[0]+1)
	prob_ind = x_space["index"]
	prob_val = x_space["value"]
	prob_ind[:] = -1
	if jit_enabled:
		csr_to_problem_jit(x.shape[0], x.data, x.indices, x.indptr, prob_val, prob_ind, prob.rowptr)
	else:
		csr_to_problem_nojit(x.shape[0], x.data, x.indices, x.indptr, prob_val, prob_ind, prob.rowptr) 

def fake_mldata(columns_dict, dataname, matfile, ordering=None):
    """Create a fake mldata data set.

    Parameters
    ----------
    columns_dict : dict, keys=str, values=ndarray
        Contains data as columns_dict[column_name] = array of data.

    dataname : string
        Name of data set.

    matfile : string or file object
        The file name string or the file-like object of the output file.

    ordering : list, default None
        List of column_names, determines the ordering in the data set.

    Notes
    -----
    This function transposes all arrays, while fetch_mldata only transposes
    'data', keep that into account in the tests.
    """
    datasets = dict(columns_dict)

    # transpose all variables
    for name in datasets:
        datasets[name] = datasets[name].T

    if ordering is None:
        ordering = sorted(list(datasets.keys()))
    # NOTE: setting up this array is tricky, because of the way Matlab
    # re-packages 1D arrays
    datasets['mldata_descr_ordering'] = sp.empty((1, len(ordering)),
                                                 dtype='object')
    for i, name in enumerate(ordering):
        datasets['mldata_descr_ordering'][0, i] = name

    scipy.io.savemat(matfile, datasets, oned_as='column') 

def ldpred_inf(beta_hats, h2=0.1, n=1000, inf_shrink_matrices=None, 
               reference_ld_mats=None, genotypes=None, ld_window_size=100, verbose=False):
    """
    Apply the infinitesimal shrink w LD (which requires LD information).
    
    If reference_ld_mats are supplied, it uses those, otherwise it uses the LD in the genotype data.
    
    If genotypes are supplied, then it assumes that beta_hats and the genotypes are synchronized.

    """
    n = float(n)
    if verbose:
        print('Doing LD correction')
    t0 = time.time()
    m = len(beta_hats)
    updated_betas = sp.empty(m)

    for i, wi in enumerate(range(0, m, ld_window_size)):
        start_i = wi
        stop_i = min(m, wi + ld_window_size)
        curr_window_size = stop_i - start_i
        if inf_shrink_matrices!=None:
            A_inv = inf_shrink_matrices[i]
        else:
            if reference_ld_mats != None:
                D = reference_ld_mats[i]
            else:
                if genotypes != None:
                    X = genotypes[start_i: stop_i]
                    num_indivs = X.shape[1]
                    D = sp.dot(X, X.T) / num_indivs
                else:
                    raise NotImplementedError
            A = ((m / h2) * sp.eye(curr_window_size) + (n / (1.0)) * D)
            A_inv = linalg.pinv(A)
        updated_betas[start_i: stop_i] = sp.dot(A_inv * n , beta_hats[start_i: stop_i])  # Adjust the beta_hats

        if verbose:
            sys.stdout.write('\r%0.2f%%' % (100.0 * (min(1, float(wi + ld_window_size) / m))))
            sys.stdout.flush()

    t1 = time.time()
    t = (t1 - t0)
    if verbose:
        print('\nIt took %d minutes and %0.2f seconds to perform the Infinitesimal LD shrink' % (t / 60, t % 60))
    return updated_betas