import numpy
import networkx as nx
if __name__ == "__main__":
# Method variables
# n (path length) should be either 1 or 2
# note: tried 3, but didn't give good results, so now code is limited to 1 or 2
n = 1
input_file = "test-full-new.txt"
output_file = "test-local-path-1.txt"
# Generate graph from edges file
G = ex.read_graph(c.output_dir + "edges-directed-6.txt")
# Get feature space and target words
features_index = u.read_features_file(c.output_dir + "feat-space.txt")
target_words = u.get_target_words()
# Get sentences/vectors of data to expand
sentences, data = ex.get_expansion_data(input_file, features_index)
# Get matrix of weight vectors
print "generating weight matrix..."
W, b_arr = u.get_weight_matrix(target_words)
# Iterate over instances and expand them
print "expanding feature vectors..."
i = 0
for vect in data:
#if i == 3:
# break
print "Accuracy:", (
(pos_correct + neg_correct + neut_correct) / float(total)) * 100
print "Pos accuracy:", (pos_correct / float(pos_total)) * 100
print "Neg accuracy:", (neg_correct / float(neg_total)) * 100
print "Neut accuracy:", (neut_correct / float(neut_total)) * 100
print ""
if __name__ == "__main__":
train_data_file = "train-output1.txt"
#test_data_file = "wordnet-expanded-test.txt"
#test_data_file = "output-700/expanded-data/test-expand-short-path1.txt"
test_data_file = "test-output1.txt"
# Get feature space
features_index = u.read_features_file("feat-space-sent-prefix.txt")
feature_size = len(features_index)
# Get idf values for features
term_idf = {}
with open("term-idf.txt") as file:
for line in file:
line = line.strip().split()
term_idf[line[0]] = float(line[1])
# Get train data
print "Getting train data..."
train_data = []
train_labels = []
f = 0.2 # factor to weight feature values
threshold = 0.65
print "# Results for:", title
print "Accuracy:", ((pos_correct + neg_correct) / float(total))*100
print "Pos accuracy:", (pos_correct / float(pos_total))*100
print "Neg accuracy:", (neg_correct / float(neg_total))*100
print ""
return incorrect
if __name__ == "__main__":
train_data_file = "train-6000.txt"
#test_data_file = "wordnet-expanded-test.txt"
test_data_file = "output-700/expanded-data/test-threshold.txt"
# Get feature space
features_index = u.read_features_file("feat-space-sent-prefix.txt")
feature_size = len(features_index)
# Get idf values for features
term_idf = {}
with open("term-idf.txt") as file:
for line in file:
line = line.strip().split()
term_idf[line[0]] = float(line[1])
# Get train data
print "Getting train data..."
train_data = []
train_labels = []
f = 0.2 # factor to weight feature values
threshold = 0.65
import numpy
import networkx as nx
if __name__ == "__main__":
# Method variables
#predict_threshold = 0.9 # prediction threshold
input_file = "test-full.txt"
output_file = "test-expanded-all-neighb.txt"
# Generate graph from edges file
G = ex.read_graph(c.output_dir + "edges-directed-6.txt")
# Get feature space and target words
features_index = u.read_features_file(c.output_dir + "feat-space.txt")
target_words = u.get_target_words()
# Get sentences/vectors of data to expand
sentences, data = ex.get_expansion_data(input_file, features_index)
# Get matrix of weight vectors
print "generating weight matrix..."
W, b_arr = u.get_weight_matrix(target_words)
print "expanding feature vectors..."
i = 0
for vect in data:
#if i == 5:
# break
value = i[1]
#print word, value
try:
vect[features_index[word]] = float(value)
except:
pass
l.append(line[0])
d.append(vect)
return d, l
if __name__ == "__main__":
# Get feature vectors
print "generating feature vectors..."
features_index = u.read_features_file("output-700/feat-space.txt")
feature_size = len(features_index)
target_words = u.get_target_words()
# Now let's do SCL
print "getting targets..."
targets = u.get_target_words()
# Load target word weight vectors as rows into matrix W
print "creating W..."
W, _ = u.get_weight_matrix(targets)
# Perform SVD on W
print "performing SVD(W)..."
WT = W.T
# SVD returns U, S, V.T