def scale_data(self, scaler='Robust'):
print('Scale featurized data been called\n')
print('-------------------------------\n')
from msmbuilder.preprocessing import RobustScaler
if scaler == 'Robust':
scaler = RobustScaler()
self.scaled_data = scaler.fit_transform(self.sim_seqs)
print('scaled ', self.scaled_data[0].shape)
# #
print("Scaling feautirized data successfully")
print('-----------------------------------\n')
def calculate_fitness(population_dihedral, diheds, score_global, i, lock):
import pandas as pd
import numpy as np
pop_index = i
new_diheds = []
for i in range(0, len(diheds)):
X = diheds[i]
selected_features = X[:, population_dihedral]
new_diheds.append(selected_features)
from msmbuilder.preprocessing import RobustScaler
scaler = RobustScaler()
scaled_diheds = scaler.fit_transform(new_diheds)
scaled_diheds = new_diheds
from msmbuilder.decomposition import tICA
tica_model = tICA(lag_time=2, n_components=5)
tica_model.fit(scaled_diheds)
tica_trajs = tica_model.transform(scaled_diheds)
from msmbuilder.cluster import MiniBatchKMeans
clusterer = MiniBatchKMeans(n_clusters=200, random_state=42)
clustered_trajs = clusterer.fit_transform(tica_trajs)
from msmbuilder.msm import MarkovStateModel
msm = MarkovStateModel(lag_time=50, n_timescales=5)
#msm.fit_transform(clustered_trajs)
from sklearn.cross_validation import KFold
n_states = [4]
cv = KFold(len(clustered_trajs), n_folds=5)
results = []
for n in n_states:
msm.n_states_ = n
for fold, (train_index, test_index) in enumerate(cv):
train_data = [clustered_trajs[i] for i in train_index]
test_data = [clustered_trajs[i] for i in test_index]
msm.fit(train_data)
train_score = msm.score(train_data)
test_score = msm.score(test_data)
time_score = msm.timescales_[0]
time_test_score = time_score + test_score
print(time_score)
print(test_score)
av_score = time_test_score / 2
results.append({
'train_score': train_score,
'test_score': test_score,
'time_score': time_score,
'av_score': av_score,
'n_states': n,
'fold': fold
})
print(msm.timescales_)
results = pd.DataFrame(results)
avgs = (results.groupby('n_states').aggregate(np.median).drop('fold',
axis=1))
best_nt = avgs['test_score'].idxmax()
best_n = avgs['av_score'].idxmax()
best_score = avgs.loc[best_n, 'av_score']
best_scorent = avgs.loc[best_nt, 'test_score']
print(best_scorent)
lock.acquire()
score_global.update({pop_index: best_scorent})
lock.release()
def main():
cli = argparse.ArgumentParser()
cli.add_argument('-e', '--eps', help='eps', default=1, type=float)
cli.add_argument('-m',
'--min_samples',
help='min_samples',
default=5,
type=int)
cli.add_argument('-l', '--nlist', help='nlist', default=1000, type=int)
cli.add_argument('-p', '--nprobe', help='nprob', default=10, type=int)
# Download example dataset
from msmbuilder.example_datasets import AlanineDipeptide
ala2 = AlanineDipeptide(verbose=False)
xyz = ala2.get().trajectories
print(ala2.description())
#xyz = [t[::10] for t in xyz]
print("{} trajectories".format(len(xyz)))
# msmbuilder does not keep track of units! You must keep track of your
# data's timestep
to_ns = 0.5
print("with length {} ns".format(set(len(x) * to_ns for x in xyz)))
from msmbuilder.featurizer import DihedralFeaturizer
featurizer = DihedralFeaturizer(types=['phi', 'psi'])
diheds = featurizer.fit_transform(xyz)
print(xyz[0].xyz.shape)
print(diheds[0].shape)
from msmbuilder.preprocessing import RobustScaler
scaler = RobustScaler()
scaled_diheds = scaler.fit_transform(diheds)
print(diheds[0].shape)
print(scaled_diheds[0].shape)
from msmbuilder.decomposition import tICA
tica_model = tICA(lag_time=2, n_components=2)
# fit and transform can be done in seperate steps:
tica_model.fit(diheds)
tica_trajs = tica_model.transform(diheds)
featurizer = DihedralFeaturizer(types=['phi', 'psi'], sincos=False)
diheds = featurizer.fit_transform(xyz)
print(diheds[0].shape)
print(tica_trajs[0].shape)
# ===========================================================================
#if os.path.isfile("./phi_angles.txt") and os.path.isfile("./psi_angles.txt") is True:
# phi_angles = np.loadtxt("./phi_angles.txt", dtype=np.float32)
# psi_angles = np.loadtxt("./psi_angles.txt", dtype=np.float32)
#X = np.column_stack((phi_angles, psi_angles))
#print(X.shape)
phi_angles = np.degrees(diheds[0][:, 0])
psi_angles = np.degrees(diheds[0][:, 1])
print(phi_angles)
X = tica_trajs[0].astype(np.float32)
#rint(X)
n_size = X.shape[0]
dimension = X.shape[1]
#print(X.shape)
# ===========================================================================
args = cli.parse_args()
eps = args.eps # eps
min_samples = args.min_samples # min_samples
nlist = args.nlist
nprobe = args.nprobe
IVFFlat = True
print('n_size = %d,\t dimension = %d,\t eps = %f, min_samples = %d' %
(n_size, dimension, eps, min_samples))
n_samples = 1000
percent = 0.9
import random
whole_samples = random.sample(list(X), n_samples)
#print whole_samples
from metrics.pairwise import pairwise_distances
sample_dist_metric = pairwise_distances(whole_samples,
whole_samples,
metric='l2')
print(sample_dist_metric.shape)
sample_dist = []
for i in range(0, n_samples):
for j in range(i + 1, n_samples):
sample_dist.append(sample_dist_metric[i, j])
sorted_sample_dist = np.sort(sample_dist)
print("Len of samples:", len(sorted_sample_dist),
np.max(sorted_sample_dist), np.min(sorted_sample_dist))
eps_list = []
len_samples = len(sorted_sample_dist)
for percent in [0.30, 0.20, 0.10]: #,0.005, 0.003,
# 0.002, 0.001, 0.0008, 0.0005, 0.0003, 0.0002, 0.0001, 0.00005]:
#percent /= 10.0
index = int(round(len_samples * percent))
if index == len_samples:
index -= 1
dc = sorted_sample_dist[index]
#print index, sorted_sample_dist[index]
eps_list.append(dc)
print(eps_list)
#print X
# ===========================================================================
# do Clustering using MR -DBSCAN method
clustering_name = "mr-dbscan_iter_"
#potential = True
remove_outliers = False
potential = False
eps = eps_list[0]
min_samples = 1
len_frames = len(X)
print("Total frames:", len_frames)
print("Running first calculation")
db = Faiss_DBSCAN(eps=eps,
min_samples=min_samples,
nlist=nlist,
nprobe=nprobe,
metric="l2",
GPU=False,
IVFFlat=IVFFlat)
db.fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
old_assignments = db.labels_
n_microstates = len(
set(old_assignments)) - (1 if -1 in old_assignments else 0)
print('Estimated number of clusters: %d' % n_microstates)
# Calculating percentage of each states
frame_bincount = np.bincount(
old_assignments[old_assignments >= 0]) #remove outliers
frame_freq_index_sorted = np.argsort(
frame_bincount)[::-1] # descending arg sort
frame_freq_percent_sorted = frame_bincount[
frame_freq_index_sorted] / np.float32(len_frames)
print(frame_freq_percent_sorted[0:10])
print(frame_freq_index_sorted[0:10])
old_frame_freq_percent_sorted = frame_freq_percent_sorted
old_frame_freq_index_sorted = frame_freq_index_sorted
n_microstates = len(
set(old_assignments)) - (1 if -1 in old_assignments else 0)
print('Estimated number of clusters: %d' % n_microstates)
iter_name = clustering_name + '0' + '_eps_' + str(
eps) + '_min_samples_' + str(min_samples) + '_n_states_' + str(
n_microstates)
plot_cluster(labels=old_assignments,
phi_angles=phi_angles,
psi_angles=psi_angles,
name=iter_name,
potential=potential)
n_iterations = len(eps_list)
print("n_iterations:", n_iterations)
min_samples_list = [50, 30, 10]
#min_samples_list = [50, 30, 20, 15, 10, 8, 5, 2]
n_min_samples = len(min_samples_list)
#eps_list = [3.0, 2.0, 1.0, 0.8, 0.5]
#min_samples_list = [3, 3, 3, 3, 3, 2, 2]
results = np.zeros((n_min_samples, n_iterations, len_frames),
dtype=np.int32)
for i in range(1, n_iterations):
eps = eps_list[i]
min_samples = min_samples_list[i]
db = Faiss_DBSCAN(eps=eps,
min_samples=min_samples,
nlist=nlist,
nprobe=nprobe,
metric="l2",
GPU=False,
IVFFlat=IVFFlat).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
new_assignments = db.labels_
if i is n_iterations - 1:
remove_outliers = True
#else:
# remove_outliers = False
assignments = merge_assignments(new_assignments,
old_assignments,
remove_outliers=remove_outliers)
n_microstates = len(set(assignments)) - (1 if -1 in assignments else 0)
#results[j,i, :]= np.array(assignments)
print("Iter:", i, "Running MR-DBSCAN at eps:", eps, 'min_sampes:',
min_samples, 'Estimated number of clusters:', n_microstates)
#print('Estimated number of clusters: %d' % n_microstates)
iter_name = clustering_name + str(i) + '_eps_' + str(
eps) + '_min_samples_' + str(min_samples) + '_n_states_' + str(
n_microstates)
plot_cluster(labels=assignments,
phi_angles=phi_angles,
psi_angles=psi_angles,
name=iter_name,
potential=potential)
#old_assignments = assignments
#print(results)
#np.save("results.npy", results)
#np.savetxt("results.csv", results, fmt="%d", delimiter=",")
np.savetxt("eps_list.txt", eps_list, fmt="%f", delimiter=",")
np.savetxt("min_samples_list.txt",
min_samples_list,
fmt="%d",
delimiter=",")
if __name__ == "__main__":
trajectory_dir = '/Volumes/REA_Data/AADH/traj_5_rxts'
topology_file = '/Users/robert_arbon/Code/AADH/Analysis/MSM_Reactants_Only/2agy_rxt.psf'
reference_file = '/Users/robert_arbon/Code/AADH/Analysis/MSM_Reactants_Only/2agy_rxt.pdb'
reference_traj = md.load(reference_file)
# Load the meta data
meta = load_metadata(traj_dir=trajectory_dir, top=topology_file)
# Featurize
feature = RawPositionsFeaturizer(ref_traj=reference_traj)
ftrajs = featurize(featurizer=feature, meta_data=meta)
# Summarize
variance = np.var(combine(ftrajs), axis=0)
plot_features(variance,
name='Variance.png',
feature_name='Variance',
ordered=False)
# Normalize
scaler = RobustScaler()
strajs = scaler.fit_transform(ftrajs)
# perform tICA
tica_obj = tICA(n_components=10, lag_time=10, kinetic_mapping=True)
tica_traj = tica_obj.fit_transform(strajs)
#featurizer = DihedralFeaturizer(types=['chi1', 'chi2'], resids= 73,74,75,76,77,78,79,80,81,82,83) diheds = featurizer.fit_transform(ds) dump(diheds, "features.pkl") #print(ds[0].shape) print(diheds[0].shape) # this basically maps every feature to atom indices. df1 = pd.DataFrame(featurizer.describe_features(ds)) dump(df1, "feature_descriptor.pkl") #Robust scaling from msmbuilder.preprocessing import RobustScaler scaler = RobustScaler() scaled_diheds = scaler.fit_transform(diheds) print(diheds[0].shape) print(scaled_diheds[0].shape) #Reducing dimension tica_model = tICA(lag_time=1, n_components=10) # fit and transform can be done in seperate steps: tica_model.fit(diheds) tica_trajs = tica_model.transform(diheds) print(diheds[0].shape) print(tica_trajs[0].shape) #lets dump the tica mdl for future use verbosedump(tica_model, "tica_mdl_flapchi1angle.pkl")
def main_modified(generations):
import numpy as np
from msmbuilder.preprocessing import RobustScaler
import time
import pickle
import os
import multiprocessing
os.environ["OMP_NUM_THREADS"] = "1"
import operator
from multiprocessing import Pool
from operator import itemgetter
diheds=Get_dihedral_features_villin()
scaler = RobustScaler()
scaled_feature = scaler.fit_transform(diheds)
Val=Laplacian_score(scaled_feature) # output of imp_features and col_mean of the laplacian score of each dihedral
col_mean=Val[0]
imp_features=Val[1]
current_gen = 0
for_each_gen_score =[]
population_each_gen=[]
population_dihedral=[]
population_dihedral=initial_population(imp_features)
cross_probability=0.8
num_parents=(int)(cross_probability*len(population_dihedral))
population_dihedral_duplicate=[]
numberOfThreads = multiprocessing.cpu_count()
f = open("benzamidine_diheds_ga_score"+str(generations)+".txt", "a")
while current_gen < generations:
manager = multiprocessing.Manager()
score = manager.dict()
processes = []
lock = multiprocessing.Lock()
for i in range(len(population_dihedral)):
p = multiprocessing.Process(target=calculate_fitness, args=(population_dihedral[i],scaled_feature,score,i,lock))
processes.append(p)
#starttime = time.time()
for i in chunks(processes,numberOfThreads): #chunks is a function : has to be defined
p_count=0
for process in i:
process.start()
p_count=p_count+1
print("the started process are"+str(p_count))
for process in i:
process.join()
p_count=p_count-1
print("the joined process are"+str(p_count))
for process in i:
process.terminate()
p_count=p_count+1
print("the terminated process are"+str(p_count))
scored_population={}
scored_population=dict(sorted(score.items(), key=operator.itemgetter(1)))
for_each_gen_score.append(scored_population)
population_each_gen.append(population_dihedral)
scored_population_list=list(scored_population.keys())
parents=[]
parents = select_parents_rank_based(scored_population,population_dihedral,cross_probability)
offsprings_1=[]
offsprings_1=crossover(parents,population_dihedral)
parents_binary=[]
parents_binary=parents_binarize(parents,imp_features)
offsprings_2_binary=[]
count_mutation=len(population_dihedral)-len(offsprings_1)
offsprings_2_binary=mutation_binary_offspring(parents_binary,4,count_mutation)
#,col_mean,imp_features)
offsprings_2=[]
offsprings_2=binary_to_pop_dih(offsprings_2_binary)
for i in range(len(offsprings_2)):
offsprings_2[i]=np.asarray(offsprings_2[i])
for i in range(len(offsprings_1)):
offsprings_1[i]=np.asarray(offsprings_1[i])
offsprings=[]
offsprings=offsprings_1+offsprings_2
# offsprings.append(population_dihedral[scored_population_list[len(scored_population_list)-1]])
#offsprings.append(population_dihedral[scored_population_list[len(scored_population_list)-2]])
population_dihedral=[]
population_dihedral=offsprings
current_gen = current_gen+1
print(for_each_gen_score,file=f)
f.close()
return for_each_gen_score,population_each_gen,scaled_feature,imp_features
import matplotlib
matplotlib.use('Agg')
from matplotlib.pylab import plt
from utilities import plot_box
if __name__ == '__main__':
# Load
feature_name = 'Positions'
meta, feature_trajs = load_trajs('Unscaled-{}-ftraj'.format(feature_name))
# Select scaler
featurizer = RobustScaler()
# Transform values
featurizer.fit_transform(feature_trajs.values())
scaled_trajs = {}
for k, v in feature_trajs.items():
scaled_trajs[k] = featurizer.partial_transform(v)
# Plot unscaled features
ftrajs = np.concatenate([fx[::100] for fx in scaled_trajs.values()])
fig, ax = plt.subplots(figsize=(15, 5))
plot_box(ax, fxx=ftrajs, feature_name='Scaled {}'.format(feature_name))
fig.tight_layout()
fig.savefig("Scaled-{}-box.pdf".format(feature_name))
# Save
save_trajs(scaled_trajs, 'Scaled-{}-ftraj'.format(feature_name), meta)
save_generic(featurizer, 'Scaled-{}-featurizer.pickl'.format(feature_name))
