import pandas as pd
import skrebate
import numpy as np
############## Her 0.1 ###################
input_file = '/home/ansohn/data/CGEMS-data/CGEMS-prostate-cancer-data-only-genes-predict-aggressive.csv'
#rel_out = '/home/ansohn/cgems/cgems_relieff.txt'
#surf_out = '/home/ansohn/cgems/cgems_surf.txt'
#surfstar_out = '/home/ansohn/cgems/cgems_surfstar.txt'
msurf_out = '/home/ansohn/cgems/cgems_msurf.txt'
data = pd.read_csv(input_file)
labels = data['class'].values
features = data.drop('class', axis=1)
#rel = skrebate.ReliefF(n_features_to_select=2, n_jobs=-1)
#surf = skrebate.SURF(n_features_to_select=2, n_jobs=-1)
#surfstar = skrebate.SURFstar(n_features_to_select=2, n_jobs=-1)
msurf = skrebate.MultiSURF(n_features_to_select=2, n_jobs=-1)
#rel1 = np.savetxt(rel_out, rel.fit(features.values, labels).top_features_.astype('int32'))
#surf1 = np.savetxt(surf_out, surf.fit(features.values, labels).top_features_.astype('int32'))
#surfstar1 = np.savetxt(surfstar_out, surfstar.fit(features.values, labels).top_features_.astype('int32'))
msurf1 = np.savetxt(
msurf_out,
msurf.fit(features.values, labels).top_features_.astype('int32'))
def _eval_search_params(params_builder):
search_params = {}
for p in params_builder['param_set']:
search_list = p['sp_list'].strip()
if search_list == '':
continue
param_name = p['sp_name']
if param_name.lower().endswith(NON_SEARCHABLE):
print("Warning: `%s` is not eligible for search and was "
"omitted!" % param_name)
continue
if not search_list.startswith(':'):
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
ev = safe_eval(search_list)
search_params[param_name] = ev
else:
# Have `:` before search list, asks for estimator evaluatio
safe_eval_es = SafeEval(load_estimators=True)
search_list = search_list[1:].strip()
# TODO maybe add regular express check
ev = safe_eval_es(search_list)
preprocessings = (
preprocessing.StandardScaler(), preprocessing.Binarizer(),
preprocessing.MaxAbsScaler(), preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(), feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(), feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS), skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0))
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessings[0:35])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessings[0:7])
elif obj == 'fs_all':
newlist.extend(preprocessings[7:14])
elif obj == 'decomp_all':
newlist.extend(preprocessings[14:25])
elif obj == 'k_appr_all':
newlist.extend(preprocessings[25:29])
elif obj == 'reb_all':
newlist.extend(preprocessings[30:35])
elif obj == 'imb_all':
newlist.extend(preprocessings[35:54])
elif type(obj) is int and -1 < obj < len(preprocessings):
newlist.append(preprocessings[obj])
elif hasattr(obj, 'get_params'): # user uploaded object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported estimator type: %r" % (obj))
search_params[param_name] = newlist
return search_params
############## Her 0.1 ###################
input_file = '/home/ansohn/Python/data/gametes-data/loc2_filtered/a5000/Her01/a_5000s_2000her_0.1__maf_0.2_EDM-1_01.txt'
rel_out = '/home/ansohn/Python/data/gametes-data/a5000_h01_relieff.txt'
surf_out = '/home/ansohn/Python/data/gametes-data/a5000_h01_surf.txt'
surfstar_out = '/home/ansohn/Python/data/gametes-data/a5000_h01_surfstar.txt'
msurf_out = '/home/ansohn/Python/data/gametes-data/a5000_h01_msurf.txt'
data = pd.read_csv(input_file, sep='\t')
labels = data['Class'].values
features = data.drop('Class', axis=1)
rel = skrebate.ReliefF(n_jobs=18)
surf = skrebate.SURF(n_jobs=18)
surfstar = skrebate.SURFstar(n_jobs=18)
msurf = skrebate.MultiSURF(n_jobs=18)
rel1 = np.savetxt(rel_out, rel.fit(features.values, labels).top_features_.astype('int32'))
surf1 = np.savetxt(surf_out, surf.fit(features.values, labels).top_features_.astype('int32'))
surfstar1 = np.savetxt(surfstar_out, surfstar.fit(features.values, labels).top_features_.astype('int32'))
msurf1 = np.savetxt(msurf_out, msurf.fit(features.values, labels).top_features_.astype('int32'))
############## Her 0.2 ###################
input_file = '/home/ansohn/Python/data/gametes-data/loc2_filtered/a5000/Her02/a_5000s_2000her_0.2__maf_0.2_EDM-1_01.txt'
rel_out = '/home/ansohn/Python/data/gametes-data/a5000_h02_relieff.txt'
surf_out = '/home/ansohn/Python/data/gametes-data/a5000_h02_surf.txt'
surfstar_out = '/home/ansohn/Python/data/gametes-data/a5000_h02_surfstar.txt'
msurf_out = '/home/ansohn/Python/data/gametes-data/a5000_h02_msurf.txt'
def get_search_params(params_builder):
search_params = {}
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
safe_eval_es = SafeEval(load_estimators=True)
for p in params_builder['param_set']:
search_p = p['search_param_selector']['search_p']
if search_p.strip() == '':
continue
param_type = p['search_param_selector']['selected_param_type']
lst = search_p.split(':')
assert (
len(lst) == 2
), "Error, make sure there is one and only one colon in search parameter input."
literal = lst[1].strip()
param_name = lst[0].strip()
if param_name:
if param_name.lower() == 'n_jobs':
sys.exit("Parameter `%s` is invalid for search." % param_name)
elif not param_name.endswith('-'):
ev = safe_eval(literal)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name] = ev
else:
# only for estimator eval, add `-` to the end of param
#TODO maybe add regular express check
ev = safe_eval_es(literal)
for obj in ev:
if 'n_jobs' in obj.get_params():
obj.set_params(n_jobs=N_JOBS)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name[:-1]] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name[:-1]] = ev
elif param_type != 'final_estimator_p':
#TODO regular express check ?
ev = safe_eval_es(literal)
preprocessors = [
preprocessing.StandardScaler(),
preprocessing.Binarizer(),
preprocessing.Imputer(),
preprocessing.MaxAbsScaler(),
preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(),
feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(),
feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS),
skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0)
]
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessors[0:36])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessors[0:8])
elif obj == 'fs_all':
newlist.extend(preprocessors[8:15])
elif obj == 'decomp_all':
newlist.extend(preprocessors[15:26])
elif obj == 'k_appr_all':
newlist.extend(preprocessors[26:30])
elif obj == 'reb_all':
newlist.extend(preprocessors[31:36])
elif obj == 'imb_all':
newlist.extend(preprocessors[36:55])
elif type(obj) is int and -1 < obj < len(preprocessors):
newlist.append(preprocessors[obj])
elif hasattr(obj, 'get_params'): # user object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported preprocessor type: %r" % (obj))
search_params['preprocessing_' + param_type[5:6]] = newlist
else:
sys.exit("Parameter name of the final estimator can't be skipped!")
return search_params
############## Her 0.1 ###################
input_file = '/home/ansohn/Python/data/gametes-data/loc2_filtered/a10/Her01/a_10s_2000her_0.1__maf_0.2_EDM-1_01.txt'
rel_out = '/home/ansohn/Python/data/gametes-data/a10_h01_relieff.txt'
surf_out = '/home/ansohn/Python/data/gametes-data/a10_h01_surf.txt'
surfstar_out = '/home/ansohn/Python/data/gametes-data/a10_h01_surfstar.txt'
msurf_out = '/home/ansohn/Python/data/gametes-data/a10_h01_msurf.txt'
data = pd.read_csv(input_file, sep='\t')
labels = data['Class'].values
features = data.drop('Class', axis=1)
rel = skrebate.ReliefF(n_jobs=5)
surf = skrebate.SURF(n_jobs=5)
surfstar = skrebate.SURFstar(n_jobs=5)
msurf = skrebate.MultiSURF(n_jobs=5)
rel1 = np.savetxt(
rel_out,
rel.fit(features.values, labels).top_features_.astype('int32'))
surf1 = np.savetxt(
surf_out,
surf.fit(features.values, labels).top_features_.astype('int32'))
surfstar1 = np.savetxt(
surfstar_out,
surfstar.fit(features.values, labels).top_features_.astype('int32'))
msurf1 = np.savetxt(
msurf_out,
msurf.fit(features.values, labels).top_features_.astype('int32'))
############## Her 0.2 ###################
############## Her 0.1 ###################
input_file = '/home/ansohn/Python/data/gametes-data/loc2_filtered/a100/Her01/a_100s_2000her_0.1__maf_0.2_EDM-1_01.txt'
rel_out = '/home/ansohn/Python/data/gametes-data/a100_h01_relieff.txt'
surf_out = '/home/ansohn/Python/data/gametes-data/a100_h01_surf.txt'
surfstar_out = '/home/ansohn/Python/data/gametes-data/a100_h01_surfstar.txt'
msurf_out = '/home/ansohn/Python/data/gametes-data/a100_h01_msurf.txt'
data = pd.read_csv(input_file, sep='\t')
labels = data['Class'].values
features = data.drop('Class', axis=1)
rel = skrebate.ReliefF()
surf = skrebate.SURF()
surfstar = skrebate.SURFstar()
msurf = skrebate.MultiSURF()
#rel1 = np.savetxt(rel_out, rel.fit(features.values, labels).top_features_.astype('int32'))
#surf1 = np.savetxt(surf_out, surf.fit(features.values, labels).top_features_.astype('int32'))
#surfstar1 = np.savetxt(surfstar_out, surfstar.fit(features.values, labels).top_features_.astype('int32'))
#msurf1 = np.savetxt(msurf_out, msurf.fit(features.values, labels).top_features_.astype('int32'))
############## Her 0.02 ###################
#input_file = '/home/ansohn/Python/data/gametes-data/loc2_filtered/a100/Her02/a_100s_2000her_0.2__maf_0.2_EDM-1_01.txt'
#rel_out = '/home/ansohn/Python/data/gametes-data/a100_h02_relieff.txt'
#surf_out = '/home/ansohn/Python/data/gametes-data/a100_h02_surf.txt'
#surfstar_out = '/home/ansohn/Python/data/gametes-data/a100_h02_surfstar.txt'
#msurf_out = '/home/ansohn/Python/data/gametes-data/a100_h02_msurf.txt'
#
#data = pd.read_csv(input_file, sep='\t')
#labels = data['Class'].values