def __init__(self, train_data, eta, sigma):
eta = float(eta)
sigma = float(sigma)
headers = ['base'] + util.get_headers(train_data)
self.weights = dict.fromkeys(headers, 0)
for i in range(100):
gradient = defaultdict(float)
for row in util.get_rows(train_data, shuffle=True):
target = row['spam']
del row['spam']
row['base'] = 1
w = target - cond_log_likelihood(self.weights, row)
for f, x in row.items():
gradient[f] = x*w - (self.weights[f] / (sigma**2))
if magnitude(gradient.values()) < 0.01:
break
for f in self.weights:
self.weights[f] += eta * gradient[f]
def __init__(self, train_data, eta, false=0):
eta = float(eta)
self.false = int(false)
headers = ['base'] + util.get_headers(train_data)
self.weights = dict.fromkeys(headers, 0)
for i in range(1000):
print(i+1)
error = False
for row in util.get_rows(train_data, false=self.false):
target = row['spam']
del row['spam']
output = self.classify(row)
if output != target:
error = True
delta = eta * (target - output)
row['base'] = 1
for x in row:
self.weights[x] += delta * row[x]
if not error:
break
