T. K. Daisy Leung astro313

Machine learning and deep learning in astronomy:

Machine learning has a long history in astronomy, but deep learning (DL) only got traction since arount 2016. Here I will list current DL effords:

The main field of ML applications in astrophysics is object classification. With source counts now ranging into the 10⁷-10⁸ for most surveys, machine learning is put to use to allow the classification of a large number of sources which would otherwise need an infeasible amount of manpower:

Classifying galaxies according to their HI content - SVM perform best in specisifity and is hence used over a DNN
Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks *05/2019 - CNN show better performance than Capsule Networks, dropout provides more robusteness against image noise. Trained with LoTTs images.
[Optical Transient Object Classification in Wide Field Smal


	gridfile = '/mnt/home/daisyleung/Downloads/SIGAME_dev/sigame/temp/z6_data_files/cloud_models/GMC/grids/GMCgrid_abun_z6_em.models'

	import glob
	import pandas as pd
	import numpy as np
	gridsDF = pd.read_pickle(gridfile)
	nHmw = gridsDF['nHmw']
	nHmin = gridsDF['nHmin']
	#

	import numpy as np
	import matplotlib.pyplot as pl
	import scipy.stats as st

	data = np.random.multivariate_normal((0, 0), [[0.8, 0.05], [0.05, 0.7]], 100)
	x = data[:, 0]
	y = data[:, 1]
	xmin, xmax = -3, 3
	ymin, ymax = -3, 3

	"""

	DL and AP's edit to yt clump_finder to fix bugs and make it work, in order to do science with the Kavli project.

	Last mod: July 17th 2018

	PATH: blah blah (ipython installation path)/lib/python2.7/site-packages/yt/analysis_modules/level_sets/

	Clump finding helper classes


	import matplotlib.cm as cm

	max_color = 15.0 #Set maximum color index
	color_gradient = cm.jet(arange(max_color)/max_color) #Set up color list from a canned color bar found in python
	color_list = ['black','gray','darkorange','blue','red','green','orange','magenta','darkgoldenrod','purple','deeppink','darkolivegreen', 'cyan','yellow','beige']
	symbol_list = ['o','v','8','x','s','*','h','D','^','8','1','o','o','o','o','o','o','o'] #Symbol list for rotation ladders on black and white Boltzmann plot
	#for c in matplotlib.colors.cnames:
	#color_list.append(c)


	# --- Cloud mass distribution, of clouds ID across all snapshots -----

	fig = plt.figure()
	ax = fig.add_subplot(111)

	allmasses = []
	for snap in ss.iterkeys():
	for snapleafs in ss[snap].iterkeys():
	allmasses.append(ss[snap][snapleafs].mass_Msun)

	def mass_function(data, logged=False,
	nbins=35, verbose=True):
	"""
	Calculates a mass function from data, using 3 methods.

	Parameters
	----------
	data: array

	logged: boolean


	'''

	from https://gist.github.com/IndianGuru/1192249


	Working, as of 21 Oct 2017


	'''

	if [ -f ~/.bash_profile ]; then
	. ~/.bash_profile
	fi