def _transform_cell_feats((cache_dir, images, normalization_name, output_filename, key, header)):
try:
import numpy as np
from cpa.util.cache import Cache, normalizations
cache = Cache(cache_dir)
normalization = normalizations[normalization_name]
normalizeddata, normalized_colnames = cache.load(images,
normalization=normalization)
if len(normalizeddata) == 0:
return np.empty(len(normalized_colnames)) * np.nan
normalizeddata = normalizeddata[
~np.isnan(np.sum(normalizeddata,1)),:]
if len(normalizeddata) == 0:
return np.empty(len(normalized_colnames)) * np.nan
# save the features to csv
import csv
filename = output_filename + "-" + "-".join(key) + ".csv"
f = open(filename, 'w')
w = csv.writer(f)
w.writerow(header)
for vector in normalizeddata:
w.writerow(tuple(key) + tuple(vector))
f.close()
except: # catch *all* exceptions
from traceback import print_exc
import sys
print_exc(None, sys.stderr)
return None
def _compute_ksstatistic((cache_dir, images, control_images)):
#try:
import numpy as np
import sys
from cpa.util.cache import Cache, RobustLinearNormalization
from cpa.util.ks_2samp import ks_2samp
cache = Cache(cache_dir)
normalizeddata, variables = cache.load(images, normalization=RobustLinearNormalization)
control_data, control_colnames = cache.load(control_images, normalization=RobustLinearNormalization)
assert len(control_data) >= len(normalizeddata)
assert variables == control_colnames
#downsampled = control_data[np.random.randint(0, len(control_data), len(normalizeddata)), :]
m = len(variables)
profile = np.empty(m)
for j in range(m):
profile[j] = ks_2samp(control_data[:, j], normalizeddata[:, j],
signed=True)[0]
return profile
def _compute_ksstatistic((cache_dir, images, control_images)):
import numpy as np
import sys
from cpa.util.cache import Cache, RobustLinearNormalization
from cpa.util.ks_2samp import ks_2samp
cache = Cache(cache_dir)
normalizeddata, variables = cache.load(images, normalization=RobustLinearNormalization)
control_data, control_colnames = cache.load(control_images, normalization=RobustLinearNormalization)
print normalizeddata.shape, control_data.shape
assert len(control_data) >= len(normalizeddata)
assert variables == control_colnames
#downsampled = control_data[np.random.randint(0, len(control_data), len(normalizeddata)), :]
m = len(variables)
profile = np.empty(m)
for j in range(m):
profile[j] = ks_2samp(control_data[:, j], normalizeddata[:, j],
signed=True)[0]
return profile
def _compute_svmnormalvector((cache_dir, images, control_images, rfe)):
#try:
import numpy as np
import sys
from cpa.util.cache import Cache, RobustLinearNormalization
from sklearn.svm import LinearSVC
from cpa.util.profile_svmnormalvector import _compute_rfe
cache = Cache(cache_dir)
normalizeddata, normalized_colnames = cache.load(images, normalization=RobustLinearNormalization)
control_data, control_colnames = cache.load(control_images, normalization=RobustLinearNormalization)
assert len(control_data) >= len(normalizeddata)
downsampled = control_data[np.random.randint(0, len(control_data), len(normalizeddata)), :]
x = np.vstack((normalizeddata, downsampled))
y = np.array([1] * len(normalizeddata) + [0] * len(downsampled))
clf = LinearSVC(C=1.0)
m = clf.fit(x, y)
normal_vector = m.coef_[0]
if rfe:
normal_vector[~_compute_rfe(x, y)] = 0
return normal_vector
def _compute_svmnormalvector((cache_dir, images, control_images, rfe)):
#try:
import numpy as np
import sys
from cpa.util.cache import Cache, RobustLinearNormalization
from sklearn.svm import LinearSVC
from cpa.util.profile_svmnormalvector import _compute_rfe
cache = Cache(cache_dir)
normalizeddata, normalized_colnames = cache.load(
images, normalization=RobustLinearNormalization)
control_data, control_colnames = cache.load(
control_images, normalization=RobustLinearNormalization)
assert len(control_data) >= len(normalizeddata)
downsampled = control_data[
np.random.randint(0, len(control_data), len(normalizeddata)), :]
x = np.vstack((normalizeddata, downsampled))
y = np.array([1] * len(normalizeddata) + [0] * len(downsampled))
clf = LinearSVC(C=1.0)
m = clf.fit(x, y)
normal_vector = m.coef_[0]
if rfe:
normal_vector[~_compute_rfe(x, y)] = 0
return normal_vector
def _compute_group_mean((cache_dir, images, normalization_name)):
try:
import numpy as np
from cpa.util.cache import Cache, normalizations
cache = Cache(cache_dir)
normalization = normalizations[normalization_name]
normalizeddata, normalized_colnames = cache.load(images,
normalization=normalization)
if len(normalizeddata) == 0:
return np.empty(len(normalized_colnames)) * np.nan
normalizeddata = normalizeddata[
~np.isnan(np.sum(normalizeddata,1)),:]
if len(normalizeddata) == 0:
return np.empty(len(normalized_colnames)) * np.nan
return np.mean(normalizeddata, axis = 0)
except: # catch *all* exceptions
from traceback import print_exc
import sys
print_exc(None, sys.stderr)
return None