def evaluate_svm():
argparser = argparse.ArgumentParser()
argparser.add_argument("shared_file_path", help="<path to shared file>")
argparser.add_argument("design_file_path", help="<path to design file>")
args = argparser.parse_args()
print("shared file path: {0.shared_file_path}".format(args))
print("design file path: {0.design_file_path}".format(args))
shared_data = mothur_files.load_shared_file(args.shared_file_path)
design_data = mothur_files.load_design_file(args.design_file_path)
scaler = sklearn.preprocessing.StandardScaler()
# the scaler returns a copy by default
X = scaler.fit_transform(shared_data.otu_frequency)
y = design_data.class_number_for_row[:,0]
y_labels = [design_data.class_number_to_name[n] for n in sorted(design_data.class_number_to_name.keys())]
C_range = 10.0 ** np.arange(-3, 3)
gamma_range = 10.0 ** np.arange(-5, -3)
degree_range = np.arange(1, 5)
coef0_range = np.arange(-3.0, 3.0)
support_vector_machine(X, y, y_labels, "linear", dict(C=C_range), shared_data)
support_vector_machine(X, y, y_labels, "rbf", dict(gamma=gamma_range, C=C_range), shared_data)
support_vector_machine(X, y, y_labels, "poly", dict(C=C_range, degree=degree_range, coef0=coef0_range), shared_data)
support_vector_machine(X, y, y_labels, "sigmoid", dict(C=C_range, coef0=coef0_range), shared_data)
def svm_hmp_2_feature_plot():
print('hazzah!')
shared_file_path = '/home/jlynch/gsoc2013/data/Stool.0.03.subsample.0.03.filter.shared'
design_file_path = '/home/jlynch/gsoc2013/data/Stool.0.03.subsample.0.03.filter.mix.design'
shared_data = mothur_files.load_shared_file(shared_file_path)
design_data = mothur_files.load_design_file(design_file_path)
otu1 = 'Otu29878'
otu2 = 'Otu29552'
# where are Otu29741 and Otu29678
n_otu1 = shared_data.otu_column_names.index(otu1)
n_otu2 = shared_data.otu_column_names.index(otu2)
print('{} is on column {}'.format(otu1, n_otu1))
print('{} is on column {}'.format(otu2, n_otu2))
print('shape of design_data.class_number_for_row {}'.format(
design_data.class_number_for_row.shape))
class_zero = design_data.class_number_for_row == 2.0
class_one = design_data.class_number_for_row == 1.0
print('class zero count: {}'.format(np.sum(class_zero)))
print('class one count: {}'.format(np.sum(class_one)))
two_labels = np.logical_or(class_zero, class_one)
print('shape of two_labels: {}'.format(two_labels.shape))
label_index = np.arange(design_data.class_number_for_row.shape[0])
reduced_label_index = label_index[two_labels[:, 0]]
print('reduced_label_index: {}'.format(reduced_label_index))
two_labels_otu_frequency = shared_data.otu_frequency[
reduced_label_index, :]
print('shape of two_labels_otu_frequency: {}'.format(
two_labels_otu_frequency.shape))
reduced_otu_frequency = two_labels_otu_frequency[:, [n_otu1, n_otu2]]
print('shaped of reduced_otu_frequency: {}'.format(
reduced_otu_frequency.shape))
#print('reduced_otu_frequency:\n{}'.format(reduced_otu_frequency))
scaler = sklearn.preprocessing.StandardScaler()
# the scaler returns a copy by default
#X = scaler.fit_transform(reduced_otu_frequency)
#exit()
# the next line is pretty good
# smo.smo(reduced_otu_frequency, design_data.class_number_for_row[two_labels], 0.5)
smo.smo(reduced_otu_frequency,
design_data.class_number_for_row[two_labels], 0.5)
pl.xlabel(otu1)
pl.ylabel(otu2)
pl.gca().set_xticklabels([])
pl.gca().set_yticklabels([])
pl.show()
def select_features():
shared_data_file_path = 'data/Stool.0.03.subsample.0.03.filter.shared'
design_data_file_path = 'data/Stool.0.03.subsample.0.03.filter.mix.design'
shared_label_names, shared_group_names, otu_column_names, shared_data = \
mothur_files.load_shared_file(shared_data_file_path)
design_group_names, design_partition_names = \
mothur_files.load_design_file(design_data_file_path)
elastic_net(shared_data, otu_column_names, design_partition_names)
linear_support_vector_machine(shared_data, otu_column_names, design_partition_names)
rbf_support_vector_machine(shared_data, otu_column_names, design_partition_names)
def svm_hmp_2_feature_plot():
print('hazzah!')
shared_file_path = '/home/jlynch/gsoc2013/data/Stool.0.03.subsample.0.03.filter.shared';
design_file_path = '/home/jlynch/gsoc2013/data/Stool.0.03.subsample.0.03.filter.mix.design';
shared_data = mothur_files.load_shared_file(shared_file_path)
design_data = mothur_files.load_design_file(design_file_path)
otu1 = 'Otu29878'
otu2 = 'Otu29552'
# where are Otu29741 and Otu29678
n_otu1 = shared_data.otu_column_names.index(otu1)
n_otu2 = shared_data.otu_column_names.index(otu2)
print('{} is on column {}'.format(otu1, n_otu1))
print('{} is on column {}'.format(otu2, n_otu2))
print('shape of design_data.class_number_for_row {}'.format(design_data.class_number_for_row.shape))
class_zero = design_data.class_number_for_row == 2.0
class_one = design_data.class_number_for_row == 1.0
print('class zero count: {}'.format(np.sum(class_zero)))
print('class one count: {}'.format(np.sum(class_one)))
two_labels = np.logical_or(class_zero, class_one)
print('shape of two_labels: {}'.format(two_labels.shape));
label_index = np.arange(design_data.class_number_for_row.shape[0])
reduced_label_index = label_index[two_labels[:,0]]
print('reduced_label_index: {}'.format(reduced_label_index))
two_labels_otu_frequency = shared_data.otu_frequency[reduced_label_index,:]
print('shape of two_labels_otu_frequency: {}'.format(two_labels_otu_frequency.shape))
reduced_otu_frequency = two_labels_otu_frequency[:,[n_otu1, n_otu2]]
print('shaped of reduced_otu_frequency: {}'.format(reduced_otu_frequency.shape))
#print('reduced_otu_frequency:\n{}'.format(reduced_otu_frequency))
scaler = sklearn.preprocessing.StandardScaler()
# the scaler returns a copy by default
#X = scaler.fit_transform(reduced_otu_frequency)
#exit()
# the next line is pretty good
# smo.smo(reduced_otu_frequency, design_data.class_number_for_row[two_labels], 0.5)
smo.smo(reduced_otu_frequency, design_data.class_number_for_row[two_labels], 0.5)
pl.xlabel(otu1)
pl.ylabel(otu2)
pl.gca().set_xticklabels([])
pl.gca().set_yticklabels([])
pl.show()
def select_features():
shared_data_file_path = 'data/Stool.0.03.subsample.0.03.filter.shared'
design_data_file_path = 'data/Stool.0.03.subsample.0.03.filter.mix.design'
shared_label_names, shared_group_names, otu_column_names, shared_data = \
mothur_files.load_shared_file(shared_data_file_path)
design_group_names, design_partition_names = \
mothur_files.load_design_file(design_data_file_path)
elastic_net(shared_data, otu_column_names, design_partition_names)
linear_support_vector_machine(shared_data, otu_column_names,
design_partition_names)
rbf_support_vector_machine(shared_data, otu_column_names,
design_partition_names)
def evaluate_enet():
argparser = argparse.ArgumentParser()
argparser.add_argument("shared_file_path")
argparser.add_argument("design_file_path")
args = argparser.parse_args()
print("shared file path: {0.shared_file_path}".format(args))
print("design file path: {0.design_file_path}".format(args))
shared_data = mothur_files.load_shared_file(args.shared_file_path)
design_data = mothur_files.load_design_file(args.design_file_path)
#scaler = sklearn.preprocessing.StandardScaler()
# the scaler returns a copy by default
#X = scaler.fit_transform(shared_data.otu_frequency)
#y = design_data.class_number_for_row[:,0]
#y_labels = [design_data.class_number_to_name[n] for n in sorted(design_data.class_number_to_name.keys())]
#print(y_labels)
elastic_net_ovo(shared_data, design_data)
def evaluate_enet():
argparser = argparse.ArgumentParser()
argparser.add_argument("shared_file_path")
argparser.add_argument("design_file_path")
args = argparser.parse_args()
print("shared file path: {0.shared_file_path}".format(args))
print("design file path: {0.design_file_path}".format(args))
shared_data = mothur_files.load_shared_file(args.shared_file_path)
design_data = mothur_files.load_design_file(args.design_file_path)
# scaler = sklearn.preprocessing.StandardScaler()
# the scaler returns a copy by default
# X = scaler.fit_transform(shared_data.otu_frequency)
# y = design_data.class_number_for_row[:,0]
# y_labels = [design_data.class_number_to_name[n] for n in sorted(design_data.class_number_to_name.keys())]
# print(y_labels)
elastic_net_ovo(shared_data, design_data)
