def closest_coords(target_file):
data = read_data(target_file)
closest = (0, 0, float('inf'))
for idx1, coord1 in enumerate(data):
for idx2, coord2 in enumerate(data):
distance = euclidean_dist(coord1, coord2)
if 0 < distance < closest[2]:
closest = (idx1, idx2, distance)
print(f'{closest[0] + 1}:' + floatlist_to_string(data[closest[0]]))
print(f'{closest[1] + 1}:' + floatlist_to_string(data[closest[1]]))
__author__ = 'skao'
import data_tools as dt
from keras.models import load_model
import numpy as np
model = load_model('modelD')
images, labels = dt.read_data('data/training/training.csv')
images, labels = dt.read_data('data/test/test.csv')
#==========================================
# Analyze Model
#==========================================
test_batch, label_batch = dt.get_batch(images, labels)
results = model.predict(test_batch)
dist = [dt.distance(a, b) for a, b in zip(results, label_batch)]
#Best and Worst Performing
worst = np.argsort(dist)[-16:]
best = np.argsort(dist)[:16]
dt.create_image_display(test_batch[worst], results[worst], label_batch[worst],
False, 2, 4)
dt.create_image_display(test_batch[best], results[best], label_batch[best],
False, 2, 4)
#==========================================
# Rotations
#==========================================
rot_batch, rot_label = dt.get_batch(dt.rotate_images(images, 45, True),
def load_data( self ):
path = self.params.save_tmp % ( self.params.data_root, self.params.models_tag, self.n )
self.peptides = data_tools.read_data( self.params.data_path )
self.benchmark = ml_tools.rt_benchmark(self.peptides, 'elude', 'gp', self.n, self.params.nparts, self.params.train_ratio )
self.models, self.kernels = ml_tools.load_rt_models( path )
#!/usr/bin/python
import os
import data_tools
import feature_extraction as fe
if __name__=="__main__" :
pwd = os.path.dirname(os.path.realpath(__file__))
# Reading peptides and their retention time from file
peptides = data_tools.read_data( pwd + '/../Data/20110922_EXQ4_NaNa_SA_YeastEasy_Labelfree_01.rtimes_q_0.001.tsv')
# Building different models
mgen = fe.model_generator( peptides )
aa_list = mgen.amino_acid_list()
elude_model = mgen.get_elude_model()
bow_voc = mgen.get_bow_voc( 2 ) # K = number of letters in each word
peptide = peptides[0]
print "Elude descriptor is"
print peptide.elude_descriptor( elude_model )
print "Bow Descriptor is"
print peptide.bow_descriptor( bow_voc )
import pickle
import GPy
if __name__ == "__main__":
n = 1000
models_path = "/Users/heydar/Stuff/tmp/gprt/models_ntrain_%d.pk" % (n)
with open(models_path, "r") as ff:
models = pickle.load(ff)[0]
ff.close()
print len(models)
raw_input()
peptides = data_tools.read_data()
# duplicated_message = data_tools.checked_duplicated(peptides)
# print duplicated_message
bench = ml_tools.rt_benchmark(peptides, "elude", "gp", 100, 5)
fmat = []
mmat = []
dmat = []
for i in range(bench.parts.nfolds):
print i
model = bench.train_model(i)
f, m, d = bench.test_sorted(i, model)
fmat.append(f)
__author__ = 'skao'
import data_tools as dt
from keras.models import load_model
import numpy as np
model = load_model('modelD')
images, labels = dt.read_data('data/training/training.csv')
images, labels = dt.read_data('data/test/test.csv')
#==========================================
# Analyze Model
#==========================================
test_batch, label_batch = dt.get_batch(images, labels)
results = model.predict(test_batch)
dist = [dt.distance(a,b) for a,b in zip(results, label_batch)]
#Best and Worst Performing
worst = np.argsort(dist)[-16:]
best = np.argsort(dist)[:16]
dt.create_image_display(test_batch[worst], results[worst], label_batch[worst], False, 2, 4)
dt.create_image_display(test_batch[best], results[best], label_batch[best], False, 2, 4)
#==========================================
# Rotations
#==========================================
rot_batch, rot_label = dt.get_batch(dt.rotate_images(images, 45, True), dt.rotate_labels(labels, 45))
rot_results = model.predict(rot_batch)
__author__ = 'skao'
import data_tools as dt
from keras.layers import Dense, Convolution2D, Input, MaxPooling2D, Flatten, Dropout
from keras.models import Model
import pandas as pd
#==========================================
# Reading in data
#==========================================
images, labels = dt.read_data('data/training/training.csv')
#images, labels = dt.get_batch(images, labels, None, True)
#images, labels = dt.get_batch(images, labels, 600, False)
#for angle in [45,90,135,180,-45,-90,-135]:
# images = dt.np.vstack((images,dt.rotate_images(images, angle, reshape_bool=True)))
# labels = dt.np.vstack((labels,dt.rotate_labels(labels, angle)))
#pd.DataFrame(images).to_csv('data/training/training_images.csv')
#pd.DataFrame(labels).to_csv('data/training/training_labels.csv')
validate_data, validate_labels = dt.read_data('data/test/test.csv')
validate_data, validate_labels = dt.get_batch(validate_data, validate_labels,
validate_data.shape[0])
#==========================================
# Define Input Shape
#==========================================
input = Input(shape=(1, 96, 96), dtype='float32')
#==========================================
# Define Model Architecture
#==========================================
#!/usr/bin/python
import numpy as np
import data_tools
import ml_tools
import pickle as pk
from common import parameters
if __name__ == "__main__":
params = parameters()
peptides = data_tools.read_data( params.data_path )
for n in params.ntrain :
print n
benchmark = ml_tools.rt_benchmark( peptides, 'elude', 'gp', n , params.nparts, params.train_ratio )
models = ml_tools.single_train_gp( benchmark )
save_path = params.save_tmp % ( params.data_root, params.models_tag, n )
with open( save_path, 'w' ) as ff :
pk.dump( [ models ], ff )
ff.close()
models = None
