def GSLR(pathway_id_and_filepath_and_nodes_and_edges_and_costs):
pathway_id, filepath, nodes, edges, costs = pathway_id_and_filepath_and_nodes_and_edges_and_costs
# we had done dataset.to_csv(filename, index=True, header=True)
dataset = pd.read_csv(filepath, index_col=0)
y = LabelEncoder().fit_transform(dataset.index.tolist())
dataset = dataset.transpose().reindex(index=nodes).transpose()
X = dataset.values
d = len(nodes)
c = 2
graph_opts = gslr.GraphOptions(edges=edges,
root=-1,
num_clusters=1,
pruning='strong')
sparsity_low = 50
sparsity_high = 100
verbosity_level = 0
num_steps = 35
possible_steps = np.array([0.03, 0.1, 0.3])
steps = np.tile(possible_steps, (num_steps, 1))
features = []
accuracies = []
for train, test in StratifiedKFold(n_splits=10).split(X, y):
W0 = np.zeros((c, d))
W_hat, losses = gslr.gslr(X[train],
y[train],
W0,
sparsity_low,
sparsity_high,
graph_opts,
steps,
verbosity_level,
edge_costs=costs,
edge_costs_multiplier=2)
yhat = gslr.predict(X[test], W_hat)
num_cor = gslr.num_correct(y[test], yhat)
accuracy = num_cor / float(len(test))
features.append(W_hat[0])
accuracies.append(accuracy)
features = pd.DataFrame(features, columns=dataset.columns)
features = features.columns[(features != 0).any()].tolist()
return pathway_id, accuracies, features
def GSLR(pathway_id_and_filepath_and_nodes_and_edges_and_costs_and_low_and_high):
pathway_id, filepath, nodes, edges, costs, sparsity_low, sparsity_high = pathway_id_and_filepath_and_nodes_and_edges_and_costs_and_low_and_high
print()
print('-----------------')
print(pathway_id)
print(str(sparsity_low)+'-'+str(sparsity_high))
print()
# we had done dataset.to_csv(filename, index=True, header=True)
dataset = pd.read_csv(filepath, index_col=0)
y = LabelEncoder().fit_transform(dataset.index.tolist())
dataset = dataset.transpose().reindex(index=nodes).transpose()
X = dataset.values
d = len(nodes)
c = 2
graph_opts = gslr.GraphOptions(edges=edges, root=-1, num_clusters=1, pruning='strong')
verbosity_level = 1
num_steps = 35
possible_steps = np.array([0.03,0.1,0.3])
steps = np.tile(possible_steps, (num_steps, 1))
featuresets = []
accuracies = []
for train, test in StratifiedKFold(n_splits=10).split(X, y):
print()
print('fold')
print()
W0 = np.zeros((c, d))
W_hat, losses = gslr.gslr(X[train], y[train], W0, sparsity_low, sparsity_high, graph_opts, steps, verbosity_level, edge_costs=costs, edge_costs_multiplier=2)
yhat = gslr.predict(X[test], W_hat)
num_cor = gslr.num_correct(y[test], yhat)
accuracy = num_cor / float(len(test))
accuracies.append(accuracy)
features = pd.DataFrame(W_hat, columns=dataset.columns)
features = features.columns[(features != 0).any()].tolist()
featuresets.append(features)
return pathway_id, (sparsity_low, sparsity_high), accuracies, featuresets
def GSLR(filepath_and_pathway_ids_and_nodes_and_edges): filepath, pathway_id_1, pathway_id_2, nodes, edges = filepath_and_pathway_ids_and_nodes_and_edges # we had done dataset.to_csv(filename, index=True, header=True) dataset = pd.read_csv(filepath, index_col=0) y = LabelEncoder().fit_transform(dataset.index.tolist()) dataset = dataset.transpose().reindex(index=nodes).transpose() X = dataset.values d = len(nodes) c = 2 graph_opts = gslr.GraphOptions(edges=edges, root=-1, num_clusters=1, pruning='strong') sparsity_low = 30 sparsity_high = 70 verbosity_level = 0 num_steps = 50 possible_steps = np.array([0.1,0.2]) steps = np.tile(possible_steps, (num_steps, 1)) features = [] accuracies = [] for train, test in StratifiedKFold(n_splits=10).split(X, y): W0 = np.zeros((c, d)) W_hat, losses = gslr.gslr(X[train], y[train], W0, sparsity_low, sparsity_high, graph_opts, steps, verbosity_level) yhat = gslr.predict(X[test], W_hat) num_cor = gslr.num_correct(y[test], yhat) accuracy = num_cor / float(len(test)) features.append(W_hat[0]) accuracies.append(accuracy) features = pd.DataFrame(features, columns=dataset.columns) features = features.columns[(features != 0).any()].tolist() return pathway_id_1, pathway_id_2, accuracies, features
sparsity_low = 150
sparsity_high = 400
verbosity_level = 1
num_steps = 100
possible_steps = np.array([0.03, 0.1, 0.3])
steps = np.tile(possible_steps, (num_steps, 1))
W0 = np.zeros((c, d))
W_hat, losses = gslr.gslr(X, y, W0, sparsity_low, sparsity_high, graph_opts, steps, verbosity_level, edge_costs=inbiomap_experimentally.cost.values, edge_costs_multiplier=6)
yhat = gslr.predict(X, W_hat)
num_cor = gslr.num_correct(y, yhat)
return num_cor, W_hat, losses
if __name__ == "__main__":
### I. Load Ovarian Cancer Proteomics Dataset
# medullo = pd.read_csv('/Users/alex/Documents/proteomics/data_preparation/proteomics_data/medullo_inbiomap_exp.tsv', index_col=0)
dataset = pd.read_csv('/Users/alex/Documents/proteomics/data_preparation/proteomics_data/ovarian_inbiomap_exp.tsv', index_col=0)
# brca = pd.read_csv('/Users/alex/Documents/proteomics/data_preparation/proteomics_data/brca_inbiomap_exp.tsv', index_col=0)
# medullo_labels = pd.read_csv('/Users/alex/Documents/proteomics/data_preparation/proteomics_data/raw/medullo_labels.csv', index_col=0)
labels = pd.read_csv('/Users/alex/Documents/proteomics/data_preparation/proteomics_data/raw/ovarian_labels.csv', index_col=0)