def run(min_wave = 4000, max_wave = 8000, category = None):
'''
run() trims all input category's deredshifted data based on
the minimum and maximum wavelength and ouputs as HDF5 file
Parameters
----------
min_wave : int indicated minimum wavelength range
max_wave : int indicated maximum wavelength range
category : list of categories to trim
'''
data_path = get.data('deredshift', category)
for data_file in data_path:
dataset = h5py.File(data_file, 'r')
data_category = data_file.split('/')[1]
data_type = data_category + '_' + 'trim'
for data_name in dataset:
spectrum = dataset[data_name][:]
wavelength = spectrum[:,0]
if (min(wavelength) > min_wave) and (max(wavelength) < max_wave):
convert_HDF5.write(data_category, str(data_name), data_type, spectrum)
continue
[num_wave,] = wavelength.shape
for i in range(num_wave):
if wavelength[i] >= min_wave:
min_range_start = i
break
for j in xrange(num_wave-1, min_range_start, -1):
if wavelength[j] <= max_wave:
max_range_start = j
break
trimmed_spectrum = spectrum[min_range_start:max_range_start+1,:]
convert_HDF5.write(data_category, str(data_name), data_type, trimmed_spectrum)
def run(min_wave = 4000, max_wave = 8000, n_rebin = 2000, category = None, rebin_type = 'log'):
'''
rebin each of the trimmed data in the category to desired number of points
Parameters
----------
min_wave : int indicating the minimum wavelength range
max_wave : int indicating the maximum wavelength range
n_rebin : int indicatinng the number of points wanted for rebin
category : list of strings of category for rebinning
rebin_type : string indicating the type of rebin wanted (log or linear)
'''
f_x = interpolation(min_wave, max_wave, category)
data_path = get.data('demean', category)
for data_file in data_path:
dataset = h5py.File(data_file, 'r')
data_category = data_file.split('/')[1]
for data_name in dataset:
if rebin_type == 'linear':
new_wavelength = np.linspace(min_wave, max_wave, num = n_rebin, endpoint = False)
else:
new_wavelength = np.logspace(np.log10(min_wave), np.log10(max_wave), num = n_rebin, endpoint = False)
f = f_x[str(data_name)]
new_flux = f(new_wavelength)
new_rebin_data = np.vstack([new_wavelength, new_flux]).T
data_filename = data_category + '_rebin_' + rebin_type
convert_HDF5.write(data_category, str(data_name), data_filename, new_rebin_data)
def demean_flux(category = None):
data_path = get.data('trim', category)
for data_file in data_path:
dataset = h5py.File(data_file, 'r')
data_category = data_file.split('/')[1]
for data_name in dataset:
name = str(data_name.split('.')[0])
spectrum = dataset[data_name][:,:]
wavelength = spectrum[:, 0]
flux = spectrum[:, 1]
demeaned_flux = demeaning(flux)
demeaned_spectrum = np.vstack([wavelength, demeaned_flux])
[nrows, ncolumns] = spectrum.shape
rest_of_spectrum = None
if ncolumns > 2:
rest_of_spectrum = spectrum[:, 2:]
[nrows, ncolumns] = rest_of_spectrum.shape
for i in range(ncolumns):
demeaned_spectrum = np.vstack([demeaned_spectrum, rest_of_spectrum[:,i]])
demeaned_spectrum = demeaned_spectrum.T
data_filename = data_category + '_' + 'demean'
convert_HDF5.write(data_category, str(data_name), data_filename, demeaned_spectrum)
def run(category = None):
'''
run() deredshifts all raw data from each category based on
z value found and outputs to HDF5 File
Parameter
---------
category : list of category to deredshift
'''
data_path = get.data('raw', category)
object_z_file = get.z_value()
object_names, z_values = extract_z_values(object_z_file)
for data_file in data_path:
filename = data_file.split('/')
data_category = filename[1]
data_name = filename[len(filename)-1]
name = data_name.split('.')[0]
spectrum = np.loadtxt(data_file)
wavelength = spectrum[:, 0]
rest_of_spectrum = spectrum[:, 1:]
z_value = None
for j in range(len(object_names)):
if (name.find(object_names[j]) != -1):
z_value = z_values[j]
break
if z_value != None:
deredshift_wavelength = wavelength/(1 + z_value)
deredshift_spectrum = deredshift_wavelength
[rows, columns] = rest_of_spectrum.shape
for i in range(columns):
deredshift_spectrum = np.vstack([deredshift_spectrum, rest_of_spectrum[:,i]])
deredshift_spectrum = deredshift_spectrum.T
data_filename = data_category + '_' + 'deredshift'
convert_HDF5.write(data_category, str(data_name), data_filename, deredshift_spectrum)
else:
print 'Cannot find z value for ' + str(data_name)
def save_pca(data_matrix):
for data_category in data_matrix:
data_filename = data_category + "_pca"
if data_category == 'all':
convert_HDF5.write(data_category, 'U', data_filename, data_matrix[data_category]['svd']['U'])
convert_HDF5.write(data_category, 'U_reduced', data_filename, data_matrix[data_category]['svd']['U_reduced'])
convert_HDF5.write(data_category, 'S', data_filename, data_matrix[data_category]['svd']['S'])
convert_HDF5.write(data_category, 'V', data_filename, data_matrix[data_category]['svd']['V'])
convert_HDF5.write(data_category, 'wavelength', data_filename, data_matrix[data_category]['wavelength'])
convert_HDF5.write(data_category, 'flux', data_filename, data_matrix[data_category]['flux'])
convert_HDF5.write(data_category, 'keys', data_filename, data_matrix[data_category]['keys'])
convert_HDF5.write(data_category, 'coefficients_normal', data_filename, data_matrix[data_category]['coefficients']['normal'])
convert_HDF5.write(data_category, 'coefficients_reduced', data_filename, data_matrix[data_category]['coefficients']['reduced'])
convert_HDF5.write(data_category, 'K_normal', data_filename, data_matrix[data_category]['K']['normal'])
convert_HDF5.write(data_category, 'K_reduced', data_filename, data_matrix[data_category]['K']['reduced'])
