import pandas as pd
import numpy as np
from tqdm import tqdm
import helper
pathways, interactome = helper.setup()
interactome_e2n = helper.convert_edges_to_node(interactome,
'edge_weight',
'interactome_weight')
interactome_en = helper.keep_edge_nodes(interactome_e2n,
['head', 'interactome_weight'])
interactome_degrees = pd.read_csv(
'../output/features_interactome_no_nearest_01.txt', delimiter='\t')
interactome_features = pd.merge(interactome_degrees,
interactome_en, left_on='name',
right_on='head')
interactome_features.drop('head', axis=1, inplace=True)
num_folds = 2
create_additional_featuers = False
for pathway in tqdm(pathways):
pathway_dist_score = pd.read_csv(
'../output/features_{}_03.txt'.format(pathway), delimiter='\t',
na_values=['None'])
import pandas as pd
import numpy as np
from tqdm import tqdm
import helper
pathways, interactome = helper.setup()
interactome_e2n = helper.convert_edges_to_node(interactome, 'edge_weight',
'interactome_weight')
interactome_en = helper.keep_edge_nodes(interactome_e2n,
['head', 'interactome_weight'])
interactome_degrees = pd.read_csv(
'../output/features_interactome_no_nearest_01.txt', delimiter='\t')
interactome_features = pd.merge(interactome_degrees,
interactome_en,
left_on='name',
right_on='head')
interactome_features.drop('head', axis=1, inplace=True)
num_folds = 2
create_additional_featuers = False
for pathway in tqdm(pathways):
pathway_dist_score = pd.read_csv(
'../output/features_{}_03.txt'.format(pathway),
delimiter='\t',
format(pathway),
delimiter='\t')
pagerank_df = pd.read_csv('../data/pagerank/{}-q_0.50-edge-fluxes.txt'.
format(pathway),
delimiter='\t')
cyclinker_df = pd.read_csv('../data/cyclinker/{}-k_110000-ranked-edges.txt'.
format(pathway),
delimiter='\t')
pagerank_df_e2n = helper.convert_edges_to_node(
pagerank_df, 'edge_flux', 'pagerank_value')
cyclinker_df_e2n = helper.convert_edges_to_node(
cyclinker_df, 'KSP index', 'cyclinker_value')
pagerank_en = helper.keep_edge_nodes(
pagerank_df_e2n, ['head', 'pagerank_value'])
cyclinker_en = helper.keep_edge_nodes(
cyclinker_df_e2n, ['head', 'cyclinker_value'])
pathway_dist_ranks = pd.merge(
pathway_dist_en, pagerank_en,
left_on='name', right_on='head', how='left')
pathway_dist_ranks = pd.merge(
pathway_dist_ranks, cyclinker_en,
left_on='name', right_on='head', how='left')
pathway_dist_ranks.ix[
pd.isnull(pathway_dist_ranks['pagerank_value']),
'pagerank_value'] = pathway_dist_ranks['pagerank_value'].min()
