def SDSS_PCA():
#Based on Figure 7.4
#Download SDSS Data:
data = sdss_corrected_spectra.fetch_sdss_corrected_spectra()
spectra = sdss_corrected_spectra.reconstruct_spectra(data)
wavelengths = sdss_corrected_spectra.compute_wavelengths(data)
print spectra.shape,wavelengths.shape
def compute_PCA(n_components=5):
spec_mean = spectra.mean(axis=0)
print spec_mean.shape
#Randomized PCA is faster (according to astroML):
pca = RandomizedPCA(n_components-1)
pca.fit(spectra)
pca_components = np.vstack([spec_mean,pca.components_])
return pca_components
n_components = 5
pca_components = compute_PCA(n_components)
fig,axs = plt.subplots(n_components,sharex=True)
for i in range(len(axs)):
axs[i].plot(wavelengths,pca_components[i],ls='-',color='black')
axs[i].yaxis.set_major_locator(MaxNLocator(nbins=4,steps=[1,2,4,5,10]))
axs[i].set_ylabel(i+1)
#axs[i].set_yscale('log')
axs[-1].set_xlabel(r'Wavelength ($\AA$)')
fig.subplots_adjust(hspace=0)
fig.text(0.02, 0.5, 'Component', ha='center', va='center', rotation='vertical')
fig.savefig('SDSS_PCA.png',dpi=300)
def SDSS_PCA():
#Based on Figure 7.4
#Download SDSS Data:
data = sdss_corrected_spectra.fetch_sdss_corrected_spectra()
spectra = sdss_corrected_spectra.reconstruct_spectra(data)
wavelengths = sdss_corrected_spectra.compute_wavelengths(data)
print spectra.shape, wavelengths.shape
def compute_PCA(n_components=5):
spec_mean = spectra.mean(axis=0)
print spec_mean.shape
#Randomized PCA is faster (according to astroML):
pca = RandomizedPCA(n_components - 1)
pca.fit(spectra)
pca_components = np.vstack([spec_mean, pca.components_])
return pca_components
n_components = 5
pca_components = compute_PCA(n_components)
fig, axs = plt.subplots(n_components, sharex=True)
for i in range(len(axs)):
axs[i].plot(wavelengths, pca_components[i], ls='-', color='black')
axs[i].yaxis.set_major_locator(
MaxNLocator(nbins=4, steps=[1, 2, 4, 5, 10]))
axs[i].set_ylabel(i + 1)
#axs[i].set_yscale('log')
axs[-1].set_xlabel(r'Wavelength ($\AA$)')
fig.subplots_adjust(hspace=0)
fig.text(0.02,
0.5,
'Component',
ha='center',
va='center',
rotation='vertical')
fig.savefig('SDSS_PCA.png', dpi=300)
import os
import numpy as np
from matplotlib import pyplot as plt
from sklearn.decomposition import NMF
from sklearn.decomposition import FastICA
from sklearn.decomposition import RandomizedPCA
from astroML.datasets import sdss_corrected_spectra
from astroML.utils.decorators import pickle_results
#------------------------------------------------------------
# Download data
data = sdss_corrected_spectra.fetch_sdss_corrected_spectra()
spectra = sdss_corrected_spectra.reconstruct_spectra(data)
wavelengths = sdss_corrected_spectra.compute_wavelengths(data)
#----------------------------------------------------------------------
# Compute PCA, ICA, and NMF components
# we'll save the results so that they can be re-used
@pickle_results('spec_decompositions.pkl')
def compute_PCA_ICA_NMF(n_components=5):
spec_mean = spectra.mean(0)
# PCA: use randomized PCA for speed
pca = RandomizedPCA(n_components - 1)
pca.fit(spectra)
pca_comp = np.vstack([spec_mean,
pca.components_])
# The figure produced by this code is published in the textbook
# "Statistics, Data Mining, and Machine Learning in Astronomy" (2013)
# For more information, see http://astroML.github.com
import numpy as np
from matplotlib import pyplot as plt
from sklearn import manifold, neighbors
from astroML.datasets import sdss_corrected_spectra
from astroML.datasets import fetch_sdss_corrected_spectra
from astroML.decorators import pickle_results
from astroML.plotting.tools import discretize_cmap
#------------------------------------------------------------
# Fetch the data
data = fetch_sdss_corrected_spectra()
spec = sdss_corrected_spectra.reconstruct_spectra(data)
color = data['lineindex_cln']
#------------------------------------------------------------
# Compute the LLE projection; save the results
@pickle_results("spec_LLE.pkl")
def compute_spec_LLE(n_neighbors=10, out_dim=3):
# Compute the LLE projection
LLE = manifold.LocallyLinearEmbedding(n_neighbors, out_dim,
method='modified',
eigen_solver='dense')
Y_LLE = LLE.fit_transform(spec)
print " - finished LLE projection"
# remove outliers for the plot
