def run(self):
S = loader.get_S()
scorer = Scorer()
for _ in xrange(10000):
keys = self.weights_dict.keys()
shuffle(keys)
for k in keys:
sc = -float("inf")
best_dev = .02
base = self.weights_dict[k]
for dev in [.02, 0, -.02]:
self.weights_dict[k] = base + dev
w = self.weights_dict.values()
S_prime = [Si * wi for Si, wi in zip(S, w)]
S_prime = reduce(lambda x, y: x + y, S_prime)
classifications = []
for i in xrange(10000):
argmax = np.argmax(S_prime[i, :])
ide = column_to_code[argmax]
classifications.append((row_to_bizid[i], ide))
loader.write_rows_algo_classified_set(classifications)
pred, total, _ = scorer.scoreClassifications()
score = pred / total
if score > sc:
sc = score
best_dev = dev
print sc
self.weights_dict[k] = base + best_dev
w = self.weights_dict.values()
S_prime = [Si * wi for Si, wi in zip(S, w)]
S_prime = reduce(lambda x, y: x + y, S)
classifications = []
for i in xrange(10000):
ide = column_to_code[np.argmax(S_prime[i, :])]
classifications.append((row_to_bizid[i], ide))
loader.write_rows_algo_classified_set(classifications)
pred, total, _ = scorer.scoreClassifications()
score = pred / total
if score > sc:
sc = score
best_dev = dev
print sc
print self.weights_dict
def run(self):
S = loader.get_S()
scorer = Scorer()
for _ in xrange(10000):
keys = self.weights_dict.keys()
shuffle(keys)
for k in keys:
sc = -float("inf")
best_dev = .02
base = self.weights_dict[k]
for dev in [.02, 0, -.02]:
self.weights_dict[k] = base + dev
w = self.weights_dict.values()
S_prime = [Si * wi for Si, wi in zip(S, w)]
S_prime = reduce(lambda x, y: x + y, S_prime)
classifications = []
for i in xrange(10000):
argmax = np.argmax(S_prime[i, :])
ide = column_to_code[argmax]
classifications.append( (row_to_bizid[i], ide) )
loader.write_rows_algo_classified_set(classifications)
pred , total , _ = scorer.scoreClassifications()
score = pred / total
if score > sc:
sc = score
best_dev = dev
print sc
self.weights_dict[k] = base + best_dev
w = self.weights_dict.values()
S_prime = [Si * wi for Si, wi in zip(S, w)]
S_prime = reduce(lambda x, y: x + y, S)
classifications = []
for i in xrange(10000):
ide = column_to_code[np.argmax(S_prime[i, :])]
classifications.append( (row_to_bizid[i], ide) )
loader.write_rows_algo_classified_set(classifications)
pred , total , _ = scorer.scoreClassifications()
score = pred / total
if score > sc:
sc = score
best_dev = dev
print sc
print self.weights_dict
def classify(self, implement_rules=True, use_training_data=True):
classifications = []
S = loader.get_S()
S = [Si * wi for Si, wi in zip(S, self.weights_dict.values())]
S = reduce(lambda x, y: x + y, S)
for i in xrange(10000):
bizid = row_to_bizid[i]
code = self.ruleBasedClassification(bizid)
if use_training_data:
code = self.hand_classified_set.get(bizid)
if code is None or not implement_rules:
score = np.max(S[i, :])
if score > self.threshhold:
code = column_to_code[np.argmax(S[i, :])]
else:
code = 'None' # no guess
classifications.append((row_to_bizid[i], code))
return classifications
def classify(self, implement_rules = True, use_training_data=True):
classifications = []
S = loader.get_S()
S = [Si * wi for Si, wi in zip(S, self.weights_dict.values())]
S = reduce(lambda x, y: x + y, S)
for i in xrange(10000):
bizid = row_to_bizid[i]
code = self.ruleBasedClassification(bizid)
if use_training_data:
code = self.hand_classified_set.get(bizid)
if code is None or not implement_rules:
score = np.max(S[i, :])
if score > self.threshhold:
code = column_to_code[np.argmax(S[i, :])]
else:
code = 'None' # no guess
classifications.append( (row_to_bizid[i], code) )
return classifications