def train_digits(PERCENT=1, EPOCHS=1):
digits = read_data.read_file(fdata='digitdata/trainingimages',
flabel='digitdata/traininglabels',
WIDTH=28,
HEIGHT=28,
type='digits')
num_data = len(digits[0]) #amount of training data
neurons = []
hits = 0
for x in range(10): #create 10 neuron classes
neurons.append(neuron(size=28 * 28))
for epochs in range(EPOCHS):
digits = read_data.read_file(fdata='digitdata/trainingimages',
flabel='digitdata/traininglabels',
WIDTH=28,
HEIGHT=28,
type='digits')
for k in range(int(num_data * PERCENT)):
x = rand.randint(0, len(digits[0]) - 1) #get x as random
features = get_features.features_from_image(
digits[0][x]) #get vector of features
scores = []
for y in neurons: #get score for each class
scores.append(y.score(features))
winnerIndex = scores.index(max(scores))
if winnerIndex != digits[1][x]:
neurons[winnerIndex].weights -= features
neurons[digits[1][x]].weights += features
digits[0].pop(x)
digits[1].pop(x)
return neurons
def train_faces(PERCENT=1, EPOCHS=1):
faces = read_data.read_file(fdata='facedata/facedatatrain',
flabel='facedata/facedatatrainlabels',
WIDTH=60,
HEIGHT=70,
type='faces')
num_data = len(faces[0]) #amount of training
neurons = []
hits = 0
neurons.append(neuron(size=60 * 70))
for epochs in range(EPOCHS):
faces = read_data.read_file(fdata='facedata/facedatatrain',
flabel='facedata/facedatatrainlabels',
WIDTH=60,
HEIGHT=70,
type='faces')
for k in range(int(num_data * PERCENT)):
x = rand.randint(0, len(faces[0]) - 1) #get x as random
features = get_features.features_from_image(
faces[0][x]) #get vector of features
if neurons[0].score(features) < 0 and faces[1][x] == 1:
neurons[0].weights += features
elif neurons[0].score(features) >= 0 and faces[1][x] == 0:
neurons[0].weights -= features
faces[0].pop(x)
faces[1].pop(x)
return neurons
def train_digits(PERCENTAGE=1):
digits = read_data.read_file(fdata='digitdata/trainingimages',
flabel='digitdata/traininglabels',
WIDTH=28,
HEIGHT=28,
type='digits')
num_data = len(digits[0]) #amount of training data
label_obj = []
features = get_features.features_from_image(digits[0][0])
for x in range(10): #create 10 label objects for each class
lbl = label()
lbl.v0 = np.ones(len(features))
lbl.v1 = np.ones(len(features))
lbl.v2 = np.ones(len(features))
label_obj.append(lbl)
'''
get frequency of feature values for each feature in training set
'''
for k in range(int(num_data *
PERCENTAGE)): # for each training data number
x = rand.randint(0, len(digits[0]) - 1) #get x as random index
features = get_features.features_from_image(
digits[0][x]) #get vector of features
label_obj[digits[1][x]].frequency += 1
for y in range(len(features)):
if features[y] == 0:
label_obj[digits[1][x]].v0[y] += 1
elif features[y] == 1:
label_obj[digits[1][x]].v1[y] += 1
elif features[y] == 2:
label_obj[digits[1][x]].v2[y] += 1
digits[0].pop(x)
digits[1].pop(x)
return label_obj, num_data
def perceptron_deploy(digit=1, PERCENTAGE=1, digits=True):
if digits:
data = read_data.read_file(fdata='digitdata/testimages',
flabel='digitdata/testlabels',
WIDTH=28,
HEIGHT=28,
type='digits')
else:
data = read_data.read_file(fdata='facedata/facedatatest',
flabel='facedata/facedatatestlabels',
WIDTH=60,
HEIGHT=70,
type='faces')
num_data = len(data[1]) #amount of training data
neurons = []
if digits:
neurons = perceptron.train_digits(PERCENT=PERCENTAGE, EPOCHS=1)
else:
neurons = perceptron.train_faces(PERCENT=PERCENTAGE, EPOCHS=1)
print("Trained Model!")
hits = 0
num = 0
if digits:
while True:
num = rand.randint(0, len(data[0]) - 1)
if digit == data[1][num]:
print("Found Digit to Guess!")
break
else:
num = rand.randint(0, len(data[0]) - 1)
features = get_features.features_from_image(
data[0][num]) #get vector of features
scores = []
for y in neurons:
scores.append(y.score(features))
if digits:
winnerIndex = scores.index(max(scores))
print("Predicted the digit: %s" % winnerIndex)
else:
if scores[0] < 0:
print("Not Face!")
else:
print("Is Face!")
plt.imshow(data[0][num])
plt.show()
def infrence_model(PERCENTAGE=1):
SMOOTHER = 1
label_obj, num_data = train_digits(PERCENTAGE=PERCENTAGE)
digits = read_data.read_file(fdata='digitdata/testimages',
flabel='digitdata/testlabels',
WIDTH=28,
HEIGHT=28,
type='digits')
predictions = [] #outputs from bayes classifier
for x in range(len(digits[0])):
features = get_features.features_from_image(
digits[0][x]) #get array of features
maxls = []
cur_guess = None
for y in range(
10): #get prob of each label and choose highest as answer
p_y = math.log(
(label_obj[y].frequency) / int(num_data * PERCENTAGE))
likelihood = 0
for feats in range(len(features)):
if features[feats] == 0:
likelihood += math.log(
(label_obj[y].v0[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v0[feats]) *
SMOOTHER)
elif features[feats] == 1:
likelihood += math.log(
(label_obj[y].v1[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v1[feats]) *
SMOOTHER)
elif features[feats] == 2:
likelihood += math.log(
(label_obj[y].v2[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v2[feats]) *
SMOOTHER)
likelihood = likelihood + p_y
maxls.append(likelihood)
predictions.append(maxls.index(max(maxls)))
hits = 0
for x in range(len(digits[1])):
if predictions[x] == digits[1][x]:
hits += 1
accuracy = hits / len(digits[1])
return accuracy
def bayes_digit(digit=1, PERCENTAGE=1):
SMOOTHER = 1
label_obj, num_data = naive_bayes_digits.train_digits(PERCENTAGE=1)
print("Trained Model!")
digits = read_data.read_file(fdata='digitdata/testimages',
flabel='digitdata/testlabels',
WIDTH=28,
HEIGHT=28,
type='digits')
num = 0
while True:
num = rand.randint(0, len(digits[0]) - 1)
if digit == digits[1][num]:
break
print("Found Digit to Guess!")
features = get_features.features_from_image(
digits[0][num]) #get array of features
maxls = []
for y in range(10): #get prob of each label and choose highest as answer
p_y = math.log((label_obj[y].frequency) / int(num_data) * PERCENTAGE)
likelihood = 0
for feats in range(len(features)):
if features[feats] == 0:
likelihood += math.log(
(label_obj[y].v0[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v0[feats]) *
SMOOTHER)
elif features[feats] == 1:
likelihood += math.log(
(label_obj[y].v1[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v1[feats]) *
SMOOTHER)
elif features[feats] == 2:
likelihood += math.log(
(label_obj[y].v2[feats] + SMOOTHER) /
(label_obj[y].frequency + label_obj[y].v2[feats]) *
SMOOTHER)
likelihood = likelihood + p_y
maxls.append(likelihood)
prediction = maxls.index(max(maxls))
print("Predicted the digit: %s" % prediction)
plt.imshow(digits[0][num])
plt.show()
def deploy_model(PERCENT,
EPOCHS,
digits=True): #set digits to false to train faces
if digits:
data = read_data.read_file(fdata='digitdata/testimages',
flabel='digitdata/testlabels',
WIDTH=28,
HEIGHT=28,
type='digits')
else:
data = read_data.read_file(fdata='facedata/facedatatest',
flabel='facedata/facedatatestlabels',
WIDTH=60,
HEIGHT=70,
type='faces')
num_data = len(data[1]) #amount of training data
neurons = []
if digits:
neurons = train_digits(PERCENT=PERCENT, EPOCHS=EPOCHS)
else:
neurons = train_faces(PERCENT=PERCENT, EPOCHS=EPOCHS)
hits = 0
for x in range(num_data):
features = get_features.features_from_image(
data[0][x]) #get vector of features
scores = []
for y in neurons:
scores.append(y.score(features))
if digits:
winnerIndex = scores.index(max(scores))
if winnerIndex == data[1][x]:
hits += 1
else:
if scores[0] < 0 and data[1][x] == 0:
hits += 1
elif scores[0] >= 0 and data[1][x] == 1:
hits += 1
return hits / num_data