def node_presence(graphs, path):
if __name__ == '__main__':
if len(sys.argv) != 3:
print 'usage: make_paths <filename> <npaths>'
sys.exit(-1)
filename = sys.argv[1]
npaths = int(sys.argv[2])
print 'loading clean training files'
edge_lists = loader.load_train_files(train_format, file_low, file_high)
graphs = loader.get_graphs_from_edge_lists(edge_lists)
print 'making paths file %s' % filename
with open(filename, 'w') as outfile:
for i in range(npaths):
outfile.write(delim.join(random_shortest_path(graphs)))
outfile.write('\n')
import numpy as np
import loader
from collections import defaultdict
train_file_format = 'train/train%d.txt'
train_file_low = 1
train_file_high = 15
test_times = 5
paths_file = 'paths.txt'
submission_file = 'submission.csv'
if __name__ == '__main__':
print 'loading data'
paths = loader.load_paths_file(paths_file)
graphs = loader.load_train_files(train_file_format,
train_file_low, train_file_high)
m = len(paths)
n = test_times
# pred = np.zeros((m,n))
pred = np.random.rand(m,n)
print 'training node name decoder model'
print 'get all nodes'
names = loader.get_all_nodes_dict(graphs, paths)
print 'make word lookup'
word_lookup = loader.make_word_lookup(names)
print 'get name found'
name_found, edits = loader.get_name_found(names, word_lookup)
actual = defaultdict(int)
corrected = defaultdict(int)
def write_analysis_matrix(data, pred, filename):
m, nd = data.shape
m, np = pred.shape
with open(filename, 'w') as f:
for i in range(m):
for j in range(nd):
f.write('%d,' % data[i,j])
for j in range(np):
f.write('%f,' % pred[i,j])
f.write('\n')
if __name__ == '__main__':
print 'loading clean training files'
edge_lists = loader.load_train_files(train_format, file_low, file_high)
graphs = loader.get_graphs_from_edge_lists(edge_lists)
print 'loading paths file'
paths = loader.load_paths_file(paths_file)
print 'loading shortest path files'
scosts = loader.load_shortest_path_costs(costs_format, file_low, file_high)
print 'computing path costs'
pcosts = loader.compute_path_costs(graphs, paths)
print 'getting shortest path matrix'
data = loader.get_shortest_path_matrix(graphs, paths, scosts, pcosts)
print 'running logistic regression'