def map_process(obj, reduce_dict, axes, map_name):
"""
process the dimensionality reduction command
"""
# project
if 'type' in reduce_dict.keys() and reduce_dict['type'] == 'RAW':
proj = obj['design_matrix']
if obj['map_options']['peratom']:
proj_atomic = obj['design_matrix_atomic']
else:
proj_atomic = None
else:
from asaplib.reducedim import Dimension_Reducers
dreducer = Dimension_Reducers(reduce_dict)
proj = dreducer.fit_transform(obj['design_matrix'])
if obj['map_options']['peratom']:
print("Project atomic design matrix with No. of samples:",
len(obj['design_matrix_atomic']))
proj_atomic = dreducer.transform(obj['design_matrix_atomic'])
else:
proj_atomic = None
# plot
fig_spec = obj['fig_options']
plotcolor = obj['map_options']['color']
plotcolor_atomic = obj['map_options']['color_atomic']
annotate = obj['map_options']['annotate']
if 'cluster_labels' in obj.keys():
labels = obj['cluster_labels']
else:
labels = []
map_plot(fig_spec, proj, proj_atomic, plotcolor, plotcolor_atomic, labels,
annotate, axes)
# output
outfilename = obj['fig_options']['outfile']
outmode = obj['map_options']['outmode']
species_name = obj['map_options']['only_use_species']
if obj['map_options']['project_atomic']:
map_save(outfilename, outmode, obj['asapxyz'], None, proj, map_name,
species_name)
else:
map_save(outfilename, outmode, obj['asapxyz'], proj, proj_atomic,
map_name, species_name)
def main():
"""
Test if dimensionality reduction is working.
Parameters
----------
fxyz: string giving location of xyz file
prefix: string giving the filename prefix
"""
fxyz = os.path.join(os.path.split(__file__)[0], 'small_molecules-SOAP.xyz')
fmat = ['SOAP-n4-l3-c1.9-g0.23']
fcolor = 'dft_formation_energy_per_atom_in_eV'
pca_d = 10
prefix = "test-dimensionality-reduction"
foutput = prefix + "-pca-d" + str(pca_d)
# try to read the xyz file
asapxyz = ASAPXYZ(fxyz)
desc, _ = asapxyz.get_descriptors(fmat, False)
print(desc)
"""
reduce_dict = { "pca":
{"type": 'PCA', 'parameter':{"n_components": pca_d, "scalecenter": scale}}
}
reduce_dict = {
"preprocessing": {"type": 'SCALE', 'parameter': None},
"umap":
{"type": 'UMAP', 'parameter':{"n_components": pca_d, "n_neighbors": 10}}
}
reduce_dict = {
"reduce1_pca": {"type": 'PCA', 'parameter':{"n_components": 20, "scalecenter":True}},
"reduce2_tsne": {"type": 'TSNE', 'parameter': {"n_components": 2, "perplexity":20}}
}
"""
reduce_dict = {
"preprocessing": {"type": 'SCALE', 'parameter': None},
"skpca":
{"type": 'SPARSE_KPCA',
'parameter':{"n_components": pca_d,
"kernel": {"first_kernel": {"type": 'linear', "normalize": True}}
}
}
}
dreducer = Dimension_Reducers(reduce_dict)
proj = dreducer.fit_transform(desc)
# save
asapxyz.set_descriptors(proj, 'pca_coord')
asapxyz.write(foutput)
# color scheme
plotcolor, plotcolor_peratom, colorlabel, colorscale = set_color_function(fcolor, asapxyz)
outfile = 'PCA_4_' + prefix + '-c-' + fcolor + '.png'
fig_spec_dict = {
'outfile': outfile,
'show': False,
'title': None,
'xlabel': 'Principal Axis 1',
'ylabel': 'Principal Axis 2',
'xaxis': True, 'yaxis': True,
'remove_tick': False,
'rasterized': True,
'fontsize': 16,
'components':{
"first_p": {"type": 'scatter', 'clabel': colorlabel},
"second_p": {"type": 'annotate', 'adtext': False}
}
}
asap_plot = Plotters(fig_spec_dict)
asap_plot.plot(proj[::-1, [0, 1]], plotcolor[::-1], [], [])
plt.show()
def main(fmat, fxyz, ftags, fcolor, colorscol, prefix, output, peratom, keepraw, scale, pca_d, pc1, pc2, projectatomic, plotatomic,
adtext):
"""
Parameters
----------
fmat: Location of descriptor matrix file or name of the tags in ase xyz file. You can use gen_descriptors.py to compute it.
fxyz: Location of xyz file for reading the properties.
ftags: Location of tags for the first M samples. Plot the tags on the PCA map.
fcolor: Location of a file or name of the tags in ase xyz file. It should contain properties for all samples (N floats) used to color the scatterplot'
colorscol: The column number of the properties used for the coloring. Starts from 0.
prefix: Filename prefix, default is ASAP
output: The format for output files ([xyz], [matrix]). Default is xyz.
peratom: Whether to output per atom pca coordinates (True/False)
keepraw: Whether to keep the high dimensional descriptor when output is an xyz file (True/False)
scale: Scale the coordinates (True/False). Scaling highly recommanded.
pca_d: Number of the principle components to keep
pc1: Plot the projection along which principle axes
pc2: Plot the projection along which principle axes
projectatomic: build the projection using the (big) atomic descriptor matrix
plotatomic: Plot the PCA coordinates of all atomic environments (True/False)
adtext: Whether to adjust the texts (True/False)
Returns
-------
"""
foutput = prefix + "-pca-d" + str(pca_d)
use_atomic_desc = (peratom or plotatomic or projectatomic)
# try to read the xyz file
if fxyz != 'none':
asapxyz = ASAPXYZ(fxyz)
desc, desc_atomic = asapxyz.get_descriptors(fmat, use_atomic_desc)
if projectatomic: desc = desc_atomic.copy()
else:
asapxyz = None
print("Did not provide the xyz file. We can only output descriptor matrix.")
output = 'matrix'
# we can also load the descriptor matrix from a standalone file
if os.path.isfile(fmat[0]):
try:
desc = np.genfromtxt(fmat[0], dtype=float)
print("loaded the descriptor matrix from file: ", fmat)
except:
raise ValueError('Cannot load the descriptor matrix from file')
# sanity check
if len(desc) == 0:
raise ValueError('Please supply descriptor in a xyz file or a standlone descriptor matrix')
print("shape of the descriptor matrix: ", np.shape(desc), "number of descriptors: ", np.shape(desc[0]))
if ftags != 'none':
tags = np.loadtxt(ftags, dtype="str")[:]
ndict = len(tags)
else:
tags = []
reduce_dict = { "pca":
{"type": 'PCA', 'parameter':{"n_components": pca_d, "scalecenter": scale}}
}
"""
reduce_dict = { "umap":
{"type": 'UMAP', 'parameter':{"n_components": pca_d, "n_neighbors": 10}}
}
reduce_dict = {
"reduce1_pca": {"type": 'PCA', 'parameter':{"n_components": 20, "scalecenter":True}},
"reduce2_tsne": {"type": 'TSNE', 'parameter': {"n_components": 2, "perplexity":20}}
}
"""
dreducer = Dimension_Reducers(reduce_dict)
proj = dreducer.fit_transform(desc)
if peratom or plotatomic and not projectatomic:
proj_atomic_all = dreducer.transform(desc_atomic)
# save
if output == 'matrix':
np.savetxt(foutput + ".coord", proj, fmt='%4.8f', header='low D coordinates of samples')
if peratom:
np.savetxt(foutput + "-atomic.coord", proj_atomic_all, fmt='%4.8f', header='low D coordinates of samples')
if output == 'xyz':
asapxyz.set_descriptors(proj, 'pca_coord')
if peratom:
asapxyz.set_atomic_descriptors(proj_atomic_all, 'pca_coord')
# remove the raw descriptors
if not keepraw:
asapxyz.remove_descriptors(fmat)
asapxyz.remove_atomic_descriptors(fmat)
asapxyz.write(foutput)
# color scheme
plotcolor, plotcolor_peratom, colorlabel, colorscale = set_color_function(fcolor, asapxyz, colorscol, 0, (peratom or plotatomic), projectatomic)
if plotatomic:
outfile = 'PCA_4_' + prefix + '-c-' + fcolor + '-plotatomic.png'
else:
outfile = 'PCA_4_' + prefix + '-c-' + fcolor + '.png'
fig_spec_dict = {
'outfile': outfile,
'show': False,
'title': None,
'xlabel': 'Principal Axis 1',
'ylabel': 'Principal Axis 2',
'xaxis': True, 'yaxis': True,
'remove_tick': False,
'rasterized': True,
'fontsize': 16,
'components':{
"first_p": {"type": 'scatter', 'clabel': colorlabel},
"second_p": {"type": 'annotate', 'adtext': adtext}
}
}
asap_plot = Plotters(fig_spec_dict)
asap_plot.plot(proj[::-1, [pc1, pc2]], plotcolor[::-1], [], tags)
if peratom or plotatomic and not projectatomic:
asap_plot.plot(proj_atomic_all[::-1, [pc1, pc2]], plotcolor_peratom[::-1],[],[])
plt.show()
"n_sparse": -1, # no sparsification
# "scale":True,
"kernel": {
"first_kernel": {
"type": 'linear'
}
}
}
}
#reduce_dict['skpca'] = {"type": 'PCA',
# 'parameter':{"n_components": 10,
# }}
from asaplib.reducedim import Dimension_Reducers
dreducer = Dimension_Reducers(reduce_dict)
dm = asapxyz.get_atomic_descriptors(['SOAP-n6-l6-c6.0-g0.44'], 14)
proj = dreducer.fit_transform(dm)
from asaplib.plot import Plotters
fig_spec = {
'outfile': 'test.png',
'show': False,
'title': None,
'size': [8 * 1.1, 8],
'cmap': 'gnuplot',
'components': {
'first_p': {
'type': 'scatter',