def build_bayes_graph(img, labels, sigma=1e2, kappa=2):
""" Build a graph from 4-neighborhood of pixels.
Foreground and background is determined from
labels (1 for foreground, 0 for background)
and is modeled with naive Bayes classifiers."""
m, n = img.shape[:2]
# RGB vector version (one pixel per row)
vim = img.reshape((-1, 3))
# RGB for foreground and background
foreground = img[labels == 1].reshape((-1, 3))
background = img[labels == 0].reshape((-1, 3))
train_data = [foreground, background]
# train naive Bayes classifier
bc = BayesClassifier()
bc.train(train_data)
# get probabilities for all pixels
bc_lables, prob = bc.classify(vim)
prob_fg, prob_bg = prob[0], prob[1]
print(np.amax(prob_fg), np.max(prob_bg))
# create graph with m*n+2 nodes
gr = Graph()
gr.add_node(range(m * n + 2))
source = m * n # second to last is source
sink = m * n + 1 # last node is sink
# normalize
for i in range(vim.shape[0]):
vim[i] = vim[i] / np.linalg.norm(vim[i])
# go through all nodes and add edges
for i in range(m * n):
print(i)
# add edge from source
gr.add_edge((source, i), (prob_fg[i] / (prob_fg[i] + prob_bg[i])))
# add edge to sink
gr.add_edge((i, sink), (prob_bg[i] / (prob_fg[i] + prob_bg[i])))
# add edges to neighbors
if i % n != 0: # left exists
edge_wt = kappa * \
np.exp(-1.0 * sum((vim[i] - vim[i - 1])**2) / sigma)
gr.add_edge((i, i - 1), edge_wt)
if (i + 1) % n != 0: # right exists
edge_wt = kappa * \
np.exp(-1.0 * sum((vim[i] - vim[i + 1])**2) / sigma)
gr.add_edge((i, i + 1), edge_wt)
if i // n != 0: # up exists
edge_wt = kappa * \
np.exp(-1.0 * sum((vim[i] - vim[i - n])**2) / sigma)
gr.add_edge((i, i - n), edge_wt)
if i // n != m - 1: # down exists
edge_wt = kappa * \
np.exp(-1.0 * sum((vim[i] - vim[i + n])**2) / sigma)
gr.add_edge((i, i + n), edge_wt)
gr.build_flow(source, sink)
return gr
words = re.findall("[a-z0-9']+", " ".join(line_split[1:]))
return msg_type, set(words)
if __name__ == '__main__':
with open('data/data.txt', 'r') as f:
messages = []
for line in f:
msg_type, words = tokenize(line)
messages.append({'msg_type': msg_type, 'words': words})
training_set = messages[:int(len(messages) * 0.75)]
testing_set = messages[int(len(messages) * 0.75):]
bayes = BayesClassifier()
bayes.train(training_set)
classified = bayes.classify(testing_set)
true_positive = len([
1 for message in classified
if message['msg_type'] == 'spam' and message['prob_spam'] > 0.5
])
false_positive = len([
1 for message in classified
if message['msg_type'] == 'ham' and message['prob_spam'] > 0.5
])
true_negative = len([
1 for message in classified
if message['msg_type'] == 'ham' and message['prob_spam'] <= 0.5
])
false_negative = len([
#!/usr/bin/env python
#-*- encoding:utf-8 -*-
import sys, os
from preprocess import Preprocessor
from features import FeatureSelector
from bayes import BayesClassifier
if __name__ == '__main__':
train_file = sys.argv[1]
test_file = sys.argv[2]
pr = Preprocessor()
pr.build_vocabulary_and_categories(train_file)
fs = FeatureSelector(train_file, ck = 500)
fs.select_features()
bc = BayesClassifier(train_file, test_file, model = 'bernoulli')
bc.train()
bc.test()