def get_apogee(dr='16',use_astroNN=True):
"""
dr: dr to select.
astronn: boolean flag for whether to use astroNN abundances, defaults
to ASPCAP abundances or not.
Returns APOGEE allStar file without duplicates.
"""
dr = str(dr)
# Change to relevant data release
change_dr(dr)
# Only use astroNN values if they are available for this data release.
if use_astroNN:
if int(dr)<14:
use_astroNN=False
elif int(dr)>=14:
allStar=apread.allStar(rmcommissioning=True,
rmdups=False,
use_astroNN=True)
if not use_astroNN:
allStar=apread.allStar(rmcommissioning=True,
rmdups=False,
use_astroNN=False)
# Manually remove duplicates
apids,inds=np.unique(allStar['APOGEE_ID'],return_index=True)
return allStar[inds]
def fit_func(elem,
name,
spectra,
spectra_errs,
T,
dat_type,
run_number,
location,
sigma_val=None): ###Fitting function
"""Return fit residuals from quadratic fit, spectral errors for desired element, fluxes for desired element,
an appropriately-sized array of effective temperatures, the quadratic fitting parameters, the residuals,
errors, temperatures, and fluxes with NaNs removed, and the normalized elemental weights.
Functions:
Reads in the DR14 windows.
Obtains the indices of pixels of the absorption lines and saves the flux value and uncertainty for
each star in these pixels.
Performs the quadratic fit on each pixel using weight_lsq() and computes the residuals using residuals().
Obtains the flux values, uncertainties, fits, residuals, and temperatures with NaNs removed.
Writes the residuals and fit parameters to .hdf5 files.
Parameters
----------
elem : str
Element name (i.e. 'AL')
name : str
Name of desired cluster (i.e. 'NGC 2682')
spectra : tuple
Array of floats representing the spectra of the desired cluster
spectra_errs : tuple
Array of floats representing the spectral uncertainties of the desired cluster
T : tuple
Array of floats representing the effective temperature of each star in the cluster
dat_type : str
Indicates whether the data being examined is the data or a simulation
run_number : int
Number of the run by which to label files
location : str
If running locally, set to 'personal'. If running on the server, set to 'server'.
sigma_val : float, optional
Indicates the value of sigma being used for the simulation in question, if applicable (default is None)
Returns
-------
elem_res : tuple
Array of floats representing the fit residuals, with original positioning of points maintained
final_err : tuple
Array of floats representing the spectral uncertainties from the lines of the desired element,
with original positioning of points maintained
final_points : tuple
Array of floats representing the fluxes from the lines of the desired element, with original
positioning of points maintained
temp_array : tuple
Array of floats representing the effective temperature of each star in the cluster, with a row for
each pixel of the desired element
elem_a : tuple
Array of floats representing the fitting parameters for the quadratic terms in the fits for each pixel of
the desired element
elem_b : tuple
Array of floats representing the fitting parameters for the linear terms in the fits for each pixel of
the desired element
elem_c : tuple
Array of floats representing the fitting parameters for the constant terms in the fits for each pixel of
the desired element
nanless_res : tuple
Array of floats representing the fit residuals, with NaNs removed
nanless_T : tuple
Array of floats representing the effective temperature of each star in the cluster, with a row for
each pixel of the desired element, with NaNs removed
nanless_points : tuple
Array of floats representing the fluxes from the lines of the desired element, with NaNs removed
normed_weights : tuple
Array of floats representing the weight of each elemental window, normalized to 1
"""
change_dr('12') ###Switch data-release to 12
#Find the DR14 windows from the DR12 windows
dr12_elem_windows = window.read(
elem) ###Read in the DR12 windows for the element in question
change_dr('14') ###Switch back to DR14
dr14_elem_windows_12 = np.concatenate(
(dr12_elem_windows[246:3274], dr12_elem_windows[3585:6080],
dr12_elem_windows[6344:8335]
)) ###Fit the dr12 windows to dr14 ("hacked" dr14 windows)
normalized_dr14_elem_windows_12 = (
dr14_elem_windows_12 - np.nanmin(dr14_elem_windows_12)) / (
np.nanmax(dr14_elem_windows_12) - np.nanmin(dr14_elem_windows_12)
) ###Normalize the hacked dr14 windows to 1
#Get the indices of the lines
ind_12 = np.argwhere(
normalized_dr14_elem_windows_12 > 0
) ###Get the indices of all of the pixels of the absorption lines of the element in question
ind_12 = ind_12.flatten(
) ###Get rid of the extra dimension produced by np.argwhere
#Get the fluxes and errors from spectra
len_spectra = len(spectra) ###Number of stars
elem_points_12 = np.zeros(
(len(ind_12), len_spectra)
) ###Array for values of the points in the spectra that are at the indices of the elemental lines in DR12
elem_err_12 = np.zeros(
(len(ind_12), len_spectra)
) ###Array for values of the errors in the spectra that are at the indices of the elemental lines in DR12
for i in range(0,
len(ind_12)): ###Iterate through the DR12 elemental indices
for j in range(0, len_spectra): ###Iterate through the stars
elem_points_12[i][j] = spectra[j][ind_12[
i]] ###Get the values of the points in the spectra at these indices in DR12
elem_err_12[i][j] = spectra_errs[j][ind_12[
i]] #APOGEE measured errors ###Get the values of the errors in the spectra at these indices in DR12
#Use only pixels with more than 5 points
final_points_12 = [] ###Empty list for the final DR12 points
final_err_12 = [] ###Empty list for the final DR12 errors
final_inds_12 = [] ###Empty list for the final DR12 elemental line indices
for i in range(
len(elem_points_12)): ###Iterate through the DR12 flux points
if np.count_nonzero(
~np.isnan(elem_points_12[i])
) >= 5: ###If the number of points in each pixel that are not NaNs is greater than or equal to 5
final_points_12.append(elem_points_12[i]) ###Append those points
final_err_12.append(elem_err_12[i]) ###Append those errors
final_inds_12.append(ind_12[i]) ###Append those indices
final_points_12 = np.array(final_points_12) ###Make into array
final_err_12 = np.array(final_err_12) ###Make into array
final_inds_12 = np.array(final_inds_12) ###Make into array
if len(
final_inds_12
) == 0: ###If no indices are left (i.e. if there are less than 5 points in every pixel)
print('Warning: less than 5 points for every pixel, skipping ',
elem) ###Skip and don't finish this element
else: ###If there are enough points left
dr12_weights = normalized_dr14_elem_windows_12[
final_inds_12] ###Get all of the weights of the elemental pixels for DR12
sorted_dr12_weights = np.sort(
dr12_weights) ###Sort these weights from smallest to largest
#Get windows
if location == 'personal': ###If running on Mac
window_file = pd.read_hdf(
'/Users/chloecheng/Personal/dr14_windows.hdf5',
'window_df') ###Get file I made for DR14 windows
elif location == 'server': ###If running on the server
window_file = pd.read_hdf(
'/geir_data/scr/ccheng/AST425/Personal/dr14_windows.hdf5',
'window_df') ###Get file I made for DR14 windows
dr14_elem_windows_14 = window_file[
elem].values ###Get the DR14 windows for the element in question
normalized_dr14_elem_windows_14 = (
dr14_elem_windows_14 - np.min(dr14_elem_windows_14)) / (
np.max(dr14_elem_windows_14) - np.min(dr14_elem_windows_14)
) ###Normalize these windows to 1
#Get the indices of the lines
if elem == 'C' or elem == 'N' or elem == 'FE': ###If we're looking at one of the elements with order ~1000 pixels
ind = np.argwhere(
normalized_dr14_elem_windows_14 > np.min(
sorted_dr12_weights[int(len(sorted_dr12_weights) * 0.7):])
) ###Get rid of the smallest 70% of the DR12 pixels
else: ###For all of the other elements
ind = np.argwhere(
normalized_dr14_elem_windows_14 > 0) ###Get all of the pixels
ind = ind.flatten(
) ###Get rid of the extra dimension from argwhere (try to streamline this)
#Get the fluxes and errors from spectra
#Limits of DR12 detectors
dr12_d1_left = 322 ###Left limit of detector 1
dr12_d1_right = 3242 ###Right limit of detector 1
dr12_d2_left = 3648 ###Left limit of detector 2
dr12_d2_right = 6048 ###Right limit of detector 2
dr12_d3_left = 6412 ###Left limit of detector 3
dr12_d3_right = 8306 ###Right limit of detector 3
elem_points = np.zeros(
(len(ind), len_spectra)
) ###Make an empty array to hold the values of the spectra at the elemental indices
elem_err = np.zeros(
(len(ind), len_spectra)
) ###Make an empty array to hold the values of the spectral errors at the elemental indices
for i in range(0, len(ind)): ###Iterate through the elemental indices
for j in range(
0, len_spectra): ###Iterate through the number of stars
###If the indices are outside of the bounds of the DR12 detectors (these bounds should be right)
if ind[i] < dr12_d1_left or (
dr12_d1_right < ind[i] < dr12_d2_left) or (
dr12_d2_right < ind[i] <
dr12_d3_left) or ind[i] > dr12_d3_right:
elem_points[i][
j] = np.nan ###Set the point to NaN and ignore
elem_err[i][j] = np.nan ###Set the error to NaN and ignore
else: ###If the indices are within the bounds of the DR12 detectors
elem_points[i][j] = spectra[j][
ind[i]] ###Get the corresponding point in the spectra
elem_err[i][j] = spectra_errs[j][ind[
i]] #APOGEE measured errors ###Get the corresponding point in the spectral errors
#Use only pixels with more than 5 points
final_points = [
] ###Make an array for the final set of spectral points
final_err = [
] ###Make an array for the final set of spectral error points
final_inds = [
] ###Make an array for the final set of elemental indices
for i in range(len(
elem_points)): ###Iterate through the points we just obtained
if np.count_nonzero(
~np.isnan(elem_points[i])
) >= 5: ###If the number of non-NaNs in the pixel is greater than or equal to 5
final_points.append(elem_points[i]) ###Append the points
final_err.append(elem_err[i]) ###Append the errors
final_inds.append(ind[i]) ###Append the indices
final_points = np.array(final_points) ###Make into array
final_err = np.array(final_err) ###Make into array
final_inds = np.array(final_inds) ###Make into array
if len(final_points) == 0: ###If all pixels have less than 5 points
print('Warning: less than 5 points for every pixel, skipping ',
elem) ###Skip the element and end here
else: ###If there are some pixels remaining
#Create an appropriately-sized array of temperatures to mask as well
temp_array = np.full(
(final_points.shape), T
) ###Create an array of the temperatures that is the same size as the spectral points, but each row is the same set of temperatures
for i in range(
0,
len(final_points)): ###Iterate through the spectral points
for j in range(0, len_spectra): ###Iterate through the stars
if np.isnan(final_points[i][j]): ###If the point is a NaN
temp_array[i][
j] = np.nan ###Mask the corresponding point in the temperature array
#Do fits with non-nan numbers
nanless_inds = np.isfinite(
final_points) ###Get the indices of the non-NaN points
fits = [] ###Create an empty list for the fit parameters
for i in range(
len(final_points)): ###Iterate through the spectral points
fits.append(
weight_lsq(final_points[i][nanless_inds[i]],
temp_array[i][nanless_inds[i]],
final_err[i][nanless_inds[i]])
) ###Fit using weight_lsq function and all points that are not NaNs
for i in range(len(fits)): ###Iterate through the fits
fits[i] = np.array(
fits[i]) ###Make each sub-list into an array
fits = np.array(fits) ###Make the whole list into an array
###Check the order of these as well - I think it should be fine if you just change the order in weight_lsq bc still return a, b, c in the order 0, 1, 2
elem_a = fits[:, 0] ###Get the a-parameter
elem_b = fits[:, 1] ###Get the b-parameter
elem_c = fits[:, 2] ###Get the c-parameter
elem_fits = np.zeros_like(
final_points) ###Create an array to save the actual fits
for i in range(0,
len(final_points)): ###Iterate through the points
elem_fits[i] = elem_a[i] * temp_array[i]**2 + elem_b[
i] * temp_array[i] + elem_c[i] ###Fit quadratically
#Calculate residuals
elem_res = residuals(final_points,
elem_fits) ###Calculate the fit residuals
#Remove nans from fits, residuals, errors, and temperatures for plotting and cumulative distribution
#calculation purposes
nanless_fits = [] ###Create an empty list for the nanless fits
nanless_res = [
] ###Create an empty list for the nanless fit residuals
nanless_err = [] ###Create an empty list for the nanless errors
nanless_T = [
] ###Create an empty list for the nanless temperatures
nanless_points = [
] ###Create an empty list for the nanless spectral points
for i in range(
len(final_points)): ###Iterate through the spectral points
nanless_fits.append(
elem_fits[i][nanless_inds[i]]) ###Append the nanless fits
nanless_res.append(elem_res[i][
nanless_inds[i]]) ###Append the nanless residuals
nanless_err.append(final_err[i][
nanless_inds[i]]) ###Append the nanless errors
nanless_T.append(temp_array[i][
nanless_inds[i]]) ###Append the nanless temperatures
nanless_points.append(final_points[i][
nanless_inds[i]]) ###Append the nanless points
for i in range(
len(final_points)): ###Turn all sub lists into arrays
nanless_fits[i] = np.array(nanless_fits[i])
nanless_res[i] = np.array(nanless_res[i])
nanless_err[i] = np.array(nanless_err[i])
nanless_T[i] = np.array(nanless_T[i])
nanless_points[i] = np.array(nanless_points[i])
nanless_fits = np.array(
nanless_fits) ###Turn all lists into arrays
nanless_res = np.array(nanless_res)
nanless_err = np.array(nanless_err)
nanless_T = np.array(nanless_T)
nanless_points = np.array(nanless_points)
#Get the weights for later
weights = normalized_dr14_elem_windows_14[
final_inds] ###Get the weights fo the DR14 lines that we're using
normed_weights = weights / np.sum(
weights) ###Normalize the weights
#File-saving
#If we are looking at the data
timestr = time.strftime("%Y%m%d_%H%M%S") ###date_time string
name_string = str(name).replace(' ',
'') ###cluster name, remove space
pid = str(os.getpid()) ###PID string
if sigma_val == None: ###IF we are looking at the data
if location == 'personal': ###If running on Mac
path_dat = '/Users/chloecheng/Personal/run_files/' + name_string + '/' + name_string + '_' + str(
elem) + '_' + 'fit_res' + '_' + str(
dat_type) + '_' + timestr + '_' + pid + '_' + str(
run_number) + '.hdf5' ###Use this path
elif location == 'server': ###If running on server
path_dat = '/geir_data/scr/ccheng/AST425/Personal/run_files/' + name_string + '/' + name_string + '_' + str(
elem) + '_' + 'fit_res' + '_' + str(
dat_type) + '_' + timestr + '_' + pid + '_' + str(
run_number) + '.hdf5' ###Use this path
#If the file exists, output the desired variables
if glob.glob(
path_dat
): ###If the file already exists, don't write anything
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
#If the file does not exist, create file and output the desired variables
else: ###If the file does not exist, write all fitting information
file = h5py.File(path_dat, 'w')
file['points'] = final_points
file['residuals'] = elem_res
file['err_200'] = final_err
file['a_param'] = elem_a
file['b_param'] = elem_b
file['c_param'] = elem_c
file.close()
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
#If we are looking at simulations
else: ###If we are looking at a simulation
if location == 'personal': ###If running from Mac
path_sim = '/Users/chloecheng/Personal/run_files/' + name_string + '/' + name_string + '_' + str(
elem) + '_' + 'fit_res' + '_' + str(
dat_type) + '_' + timestr + '_' + pid + '_' + str(
run_number) + '.hdf5' ###Use this path
elif location == 'server': ###If running on server
path_sim = '/geir_data/scr/ccheng/AST425/Personal/run_files/' + name_string + '/' + name_string + '_' + str(
elem) + '_' + 'fit_res' + '_' + str(
dat_type) + '_' + timestr + '_' + pid + '_' + str(
run_number) + '.hdf5' ###Use this path
#If the file exists, append to the file
if glob.glob(path_sim): ###If the file exists
file = h5py.File(path_sim, 'a') ###Append to the file
#If the group for the particular value of sigma exists, don't do anything
if glob.glob(
str(sigma_val)
): ###If this value of sigma has already been tested, don't write anything
file.close()
#If not, append a new group to the file for the particular value of sigma
else: ###If it has not been tested, write all fitting information to a group named after the value of sigma
grp = file.create_group(str(sigma_val))
grp['points'] = final_points
grp['residuals'] = elem_res
grp['err_200'] = final_err
grp['a_param'] = elem_a
grp['b_param'] = elem_b
grp['c_param'] = elem_c
file.close()
#If the file does not exist, create a new file
else: ###If the file does not exist, write all of the fitting information to a group named after the value of sigma
file = h5py.File(path_sim, 'w')
grp = file.create_group(str(sigma_val))
grp['points'] = final_points
grp['residuals'] = elem_res
grp['err_200'] = final_err
grp['a_param'] = elem_a
grp['b_param'] = elem_b
grp['c_param'] = elem_c
file.close()
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
-h Help file
--cluster=<arg> Cluster name
--red_clump=<arg> Whether to exclude red clump stars in rcsample or not
--element=<arg> Element name
--type=<arg> Data type
--location=<arg> Machine where the code is being run
"""
#Imports
#apogee package
import apogee.tools.read as apread ###Read in the allStar data
from apogee.tools.path import change_dr ###Change the data-release
from apogee.spec import window ###Windows in fitting function for DR12
from apogee.tools.read import rcsample ###Remove red clumps
change_dr('14') #use DR14 ###Change to DR14
#astropy helper functions
import astropy.io.fits as afits ###Read OCCAM file
#basic math and plotting
from docopt import docopt ###Run with docopt from terminal
import numpy as np ###Numpy
import pandas as pd ###Read DR14 windows file
import h5py ###Read/write files
import glob ###See whether file/directory exists or not
import matplotlib.pyplot as plt ###Plot for weighted least-squares function if matrix is singular
import os ###Make directory for cluster
import time ###Label files with date and time
fs = 16 ###Plot fontsize
plt.rc('font', family='serif', size=fs) ###Plot fonts
def pixels_cannon(*args, **kwargs):
"""
NAME:
pixels_cannon
PURPOSE:
determine continuum pixels using a Cannon-like technique (Ness et al. 2015)
INPUT:
Either:
a) Input for running the apogee.spec.cannon:
spec - spectra to fit (nspec,nlambda)
specerrs - errors on the spectra (nspec,nlambda); assume no covariances
label1, label2, ... - labels (nspec); best to subtract reference values before running this
type= ('lin') type of Cannon to run:
'lin' - linear Cannon
'quad' - quadratic Cannon
b) Output from a previous Cannon run:
coefficients - coefficients from the fit (ncoeffs,nlambda)
scatter - scatter from the fit (nlambda)
KEYWORDS:
baseline_dev= (0.015) maximum deviation from baseline
label1_max= (10.**-5.) maximum deviation in first linear coefficient
label2_max= (0.006) similar for the second
label3_max= (0.012) similar for the third
labelN_max= same with default 0.03
...
scatter_max= (0.015) maximum scatter of residuals
dr= (module-wide default) data release
OUTPUT:
Boolean index into the wavelength range with True for continuum pixels
HISTORY:
2015-02-05 - Written - Bovy (IAS@KITP)
"""
# Grab kwargs
type = kwargs.pop('type', 'lin')
dr = kwargs.pop('dr', path._default_dr())
# Parse input
if len(args) == 0: # Use default fit
from apogee.spec._train_cannon import load_fit
coeffs, scatter, baseline_labels = load_fit()
type = 'quad'
else:
spec = args[0]
specerr = args[1]
# Determine the type of input
if len(specerr.shape) == 2:
# Run the Cannon
if type.lower() == 'lin':
coeffs, scatter = cannon.linfit(*args)
elif type.lower() == 'quad':
coeffs, scatter = cannon.quadfit(*args)
else:
coeffs = spec
scatter = specerr
ncoeffs = coeffs.shape[0]
if type.lower() == 'lin':
nlabels = ncoeffs - 1
elif type.lower() == 'quad':
nlabels = int((-3 + numpy.sqrt(9 + 8 * (ncoeffs - 1)))) // 2
# Determine continuum pixels
out = numpy.ones(len(scatter), dtype='bool')
# Deviation from baseline
out[numpy.fabs(coeffs[0] - 1.) > kwargs.get('baseline_dev', 0.015)] = False
# Large dependence on labels
maxs = numpy.zeros(nlabels)
maxs[0] = kwargs.get('label1_max', 10.**-5.)
maxs[1] = kwargs.get('label2_max', 0.006)
maxs[2] = kwargs.get('label3_max', 0.012)
for ii in range(nlabels - 3):
maxs[ii + 3] = kwargs.get('label%i_max' % (ii + 4), 0.03)
for ii in range(1, nlabels + 1):
out[numpy.fabs(coeffs[ii]) > maxs[ii - 1]] = False
# Large residuals
out[scatter > kwargs.get('scatter_max', 0.015)] = False
_, _, _, aspcapDR12length = _aspcapPixelLimits(dr='12')
if int(dr) > 12 and coeffs.shape[1] == aspcapDR12length:
# Want continuum pixels on >DR12 ASPCAP grid, but using coefficients
# from <= DR12 grid
dr_module = path._default_dr()
path.change_dr(12)
out = toApStarGrid(out)
path.change_dr(dr)
out = toAspcapGrid(out)
path.change_dr(dr_module)
return out
def fit_func(elem, name, spectra, spectra_errs, T, dat_type, run_number, location, sigma_val=None):
"""Return fit residuals from quadratic fit, spectral errors for desired element, fluxes for desired element,
an appropriately-sized array of effective temperatures, the quadratic fitting parameters, the residuals,
errors, temperatures, and fluxes with NaNs removed, and the normalized elemental weights.
Functions:
Reads in the DR14 windows.
Obtains the indices of pixels of the absorption lines and saves the flux value and uncertainty for
each star in these pixels.
Performs the quadratic fit on each pixel using weight_lsq() and computes the residuals using residuals().
Obtains the flux values, uncertainties, fits, residuals, and temperatures with NaNs removed.
Writes the residuals and fit parameters to .hdf5 files.
Parameters
----------
elem : str
Element name (i.e. 'AL')
name : str
Name of desired cluster (i.e. 'NGC 2682')
spectra : tuple
Array of floats representing the spectra of the desired cluster
spectra_errs : tuple
Array of floats representing the spectral uncertainties of the desired cluster
T : tuple
Array of floats representing the effective temperature of each star in the cluster
dat_type : str
Indicates whether the data being examined is the data or a simulation
run_number : int
Number of the run by which to label files
location : str
If running locally, set to 'personal'. If running on the server, set to 'server'.
sigma_val : float, optional
Indicates the value of sigma being used for the simulation in question, if applicable (default is None)
Returns
-------
elem_res : tuple
Array of floats representing the fit residuals, with original positioning of points maintained
final_err : tuple
Array of floats representing the spectral uncertainties from the lines of the desired element,
with original positioning of points maintained
final_points : tuple
Array of floats representing the fluxes from the lines of the desired element, with original
positioning of points maintained
temp_array : tuple
Array of floats representing the effective temperature of each star in the cluster, with a row for
each pixel of the desired element
elem_a : tuple
Array of floats representing the fitting parameters for the quadratic terms in the fits for each pixel of
the desired element
elem_b : tuple
Array of floats representing the fitting parameters for the linear terms in the fits for each pixel of
the desired element
elem_c : tuple
Array of floats representing the fitting parameters for the constant terms in the fits for each pixel of
the desired element
nanless_res : tuple
Array of floats representing the fit residuals, with NaNs removed
nanless_T : tuple
Array of floats representing the effective temperature of each star in the cluster, with a row for
each pixel of the desired element, with NaNs removed
nanless_points : tuple
Array of floats representing the fluxes from the lines of the desired element, with NaNs removed
normed_weights : tuple
Array of floats representing the weight of each elemental window, normalized to 1
"""
change_dr('12')
#Find the DR14 windows from the DR12 windows
dr12_elem_windows = window.read(elem)
change_dr('14')
dr14_elem_windows_12 = np.concatenate((dr12_elem_windows[246:3274], dr12_elem_windows[3585:6080], dr12_elem_windows[6344:8335]))
normalized_dr14_elem_windows_12 = (dr14_elem_windows_12 - np.nanmin(dr14_elem_windows_12))/(np.nanmax(dr14_elem_windows_12) - np.nanmin(dr14_elem_windows_12))
#Get the indices of the lines
ind_12 = np.argwhere(normalized_dr14_elem_windows_12 > 0)
ind_12 = ind_12.flatten()
#Get the fluxes and errors from spectra
len_spectra = len(spectra)
elem_points_12 = np.zeros((len(ind_12), len_spectra))
elem_err_12 = np.zeros((len(ind_12), len_spectra))
for i in range(0, len(ind_12)):
for j in range(0, len_spectra):
elem_points_12[i][j] = spectra[j][ind_12[i]]
elem_err_12[i][j] = spectra_errs[j][ind_12[i]] #APOGEE measured errors
#Use only pixels with more than 5 points
final_points_12 = []
final_err_12 = []
final_inds_12 = []
for i in range(len(elem_points_12)):
if np.count_nonzero(~np.isnan(elem_points_12[i])) >= 5:
final_points_12.append(elem_points_12[i])
final_err_12.append(elem_err_12[i])
final_inds_12.append(ind_12[i])
final_points_12 = np.array(final_points_12)
final_err_12 = np.array(final_err_12)
final_inds_12 = np.array(final_inds_12)
if len(final_inds_12) == 0:
print('Warning: less than 5 points for every pixel, skipping ', elem)
else:
dr12_weights = normalized_dr14_elem_windows_12[final_inds_12]
sorted_dr12_weights = np.sort(dr12_weights)
#Get windows
if location == 'personal':
window_file = pd.read_hdf('/Users/chloecheng/Personal/dr14_windows.hdf5', 'window_df')
elif location == 'server':
window_file = pd.read_hdf('/geir_data/scr/ccheng/AST425/Personal/dr14_windows.hdf5', 'window_df')
dr14_elem_windows_14 = window_file[elem].values
normalized_dr14_elem_windows_14 = (dr14_elem_windows_14 - np.min(dr14_elem_windows_14))/(np.max(dr14_elem_windows_14) - np.min(dr14_elem_windows_14))
#Get the indices of the lines
if elem == 'C' or elem == 'N' or elem == 'FE':
ind = np.argwhere(normalized_dr14_elem_windows_14 > np.min(sorted_dr12_weights[int(len(sorted_dr12_weights)*0.7):]))
else:
ind = np.argwhere(normalized_dr14_elem_windows_14 > 0)
ind = ind.flatten()
#Get the fluxes and errors from spectra
elem_points = np.zeros((len(ind), len_spectra))
elem_err = np.zeros((len(ind), len_spectra))
for i in range(0, len(ind)):
for j in range(0, len_spectra):
elem_points[i][j] = spectra[j][ind[i]]
elem_err[i][j] = spectra_errs[j][ind[i]] #APOGEE measured errors
#Use only pixels with more than 5 points
final_points = []
final_err = []
final_inds = []
for i in range(len(elem_points)):
if np.count_nonzero(~np.isnan(elem_points[i])) >= 5:
final_points.append(elem_points[i])
final_err.append(elem_err[i])
final_inds.append(ind[i])
final_points = np.array(final_points)
final_err = np.array(final_err)
final_inds = np.array(final_inds)
if len(final_points) == 0:
print('Warning: less than 5 points for every pixel, skipping ', elem)
else:
#Create an appropriately-sized array of temperatures to mask as well
temp_array = np.full((final_points.shape), T)
for i in range(0, len(final_points)):
for j in range(0, len_spectra):
if np.isnan(final_points[i][j]):
temp_array[i][j] = np.nan
#Do fits with non-nan numbers
nanless_inds = np.isfinite(final_points)
fits = []
for i in range(len(final_points)):
fits.append(weight_lsq(final_points[i][nanless_inds[i]], temp_array[i][nanless_inds[i]], final_err[i][nanless_inds[i]]))
for i in range(len(fits)):
fits[i] = np.array(fits[i])
fits = np.array(fits)
elem_a = fits[:,0]
elem_b = fits[:,1]
elem_c = fits[:,2]
elem_fits = np.zeros_like(final_points)
for i in range(0, len(final_points)):
elem_fits[i] = elem_a[i]*temp_array[i]**2 + elem_b[i]*temp_array[i] + elem_c[i]
#Calculate residuals
elem_res = residuals(final_points, elem_fits)
#Remove nans from fits, residuals, errors, and temperatures for plotting and cumulative distribution
#calculation purposes
nanless_fits = []
nanless_res = []
nanless_err = []
nanless_T = []
nanless_points = []
for i in range(len(final_points)):
nanless_fits.append(elem_fits[i][nanless_inds[i]])
nanless_res.append(elem_res[i][nanless_inds[i]])
nanless_err.append(final_err[i][nanless_inds[i]])
nanless_T.append(temp_array[i][nanless_inds[i]])
nanless_points.append(final_points[i][nanless_inds[i]])
for i in range(len(final_points)):
nanless_fits[i] = np.array(nanless_fits[i])
nanless_res[i] = np.array(nanless_res[i])
nanless_err[i] = np.array(nanless_err[i])
nanless_T[i] = np.array(nanless_T[i])
nanless_points[i] = np.array(nanless_points[i])
nanless_fits = np.array(nanless_fits)
nanless_res = np.array(nanless_res)
nanless_err = np.array(nanless_err)
nanless_T = np.array(nanless_T)
nanless_points = np.array(nanless_points)
#Get the weights for later
weights = normalized_dr14_elem_windows_14[final_inds]
normed_weights = weights/np.sum(weights)
#File-saving
#If we are looking at the data
timestr = time.strftime("%Y%m%d_%H%M%S")
name_string = str(name).replace(' ', '')
pid = str(os.getpid())
if sigma_val == None:
if location == 'personal':
path_dat = '/Users/chloecheng/Personal/run_files_' + name_string + '_' + str(elem) + '/' + name_string + '/' + name_string + '_' + str(elem) + '_' + 'fit_res' + '_' + str(dat_type) + '_' + timestr + '_' + pid + '_' + str(run_number) + '.hdf5'
elif location == 'server':
path_dat = '/geir_data/scr/ccheng/AST425/Personal/run_files_' + name_string + '_' + str(elem) + '/' + name_string + '/' + name_string + '_' + str(elem) + '_' + 'fit_res' + '_' + str(dat_type) + '_' + timestr + '_' + pid + '_' + str(run_number) + '.hdf5'
#If the file exists, output the desired variables
if glob.glob(path_dat):
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
#If the file does not exist, create file and output the desired variables
else:
file = h5py.File(path_dat, 'w')
file['points'] = final_points
file['residuals'] = elem_res
file['err_200'] = final_err
file['a_param'] = elem_a
file['b_param'] = elem_b
file['c_param'] = elem_c
file.close()
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
#If we are looking at simulations
else:
if location == 'personal':
path_sim = '/Users/chloecheng/Personal/run_files_' + name_string + '_' + str(elem) + '/' + name_string + '/' + name_string + '_' + str(elem) + '_' + 'fit_res' + '_' + str(dat_type) + '_' + timestr + '_' + pid + '_' + str(run_number) + '.hdf5'
elif location == 'server':
path_sim = '/geir_data/scr/ccheng/AST425/Personal/run_files_' + name_string + '_' + str(elem) + '/' + name_string + '/' + name_string + '_' + str(elem) + '_' + 'fit_res' + '_' + str(dat_type) + '_' + timestr + '_' + pid + '_' + str(run_number) + '.hdf5'
#If the file exists, append to the file
if glob.glob(path_sim):
file = h5py.File(path_sim, 'a')
#If the group for the particular value of sigma exists, don't do anything
if glob.glob(str(sigma_val)):
file.close()
#If not, append a new group to the file for the particular value of sigma
else:
grp = file.create_group(str(sigma_val))
grp['points'] = final_points
grp['residuals'] = elem_res
grp['err_200'] = final_err
grp['a_param'] = elem_a
grp['b_param'] = elem_b
grp['c_param'] = elem_c
file.close()
#If the file does not exist, create a new file
else:
file = h5py.File(path_sim, 'w')
grp = file.create_group(str(sigma_val))
grp['points'] = final_points
grp['residuals'] = elem_res
grp['err_200'] = final_err
grp['a_param'] = elem_a
grp['b_param'] = elem_b
grp['c_param'] = elem_c
file.close()
return elem_res, final_err, final_points, temp_array, elem_a, elem_b, elem_c, nanless_res, nanless_err, nanless_T, nanless_points, normed_weights
-h Help file
--cluster=<arg> Cluster name
--red_clump=<arg> Whether to exclude red clump stars in rcsample or not
--element=<arg> Element name
--type=<arg> Data type
--location=<arg> Machine where the code is being run
"""
#Imports
#apogee package
import apogee.tools.read as apread
from apogee.tools.path import change_dr
from apogee.spec import window
from apogee.tools.read import rcsample
change_dr('14') #use DR14
#astropy helper functions
import astropy.io.fits as afits
#basic math and plotting
from docopt import docopt
import numpy as np
import pandas as pd
import h5py
import glob
import matplotlib.pyplot as plt
import os
import time
fs=16
plt.rc('font', family='serif',size=fs)