from sklearn.neighbors import KNeighborsClassifier import numpy as np import util def knnClassify(trainData, trainLabel, testData): knnClf = KNeighborsClassifier() knnClf.fit(trainData, np.ravel(trainLabel)) testLabel = knnClf.predict(testData) util.saveResult(testLabel, './result/sklearn_knn_result.csv') return testLabel if __name__ == "__main__": trainData, trainLabel = util.loadTrainData() testData = util.loadTestData() knnClassify(trainData, trainLabel, testData) print 'knnClassify is finished!'
from sklearn.ensemble import RandomForestClassifier
# Visualisation
import matplotlib.pyplot as plt # plot the data
import seaborn as sns # data visualisation
sns.set(color_codes=True)
#% matplotlib inline
import util
# In[54]:
x_raw, y_raw = util.loadTrainData()
x_test = util.loadTestData()
# In[55]:
table = {
"Class_1": 1,
"Class_2": 2,
"Class_3": 3,
"Class_4": 4,
"Class_5": 5,
"Class_6": 6,
"Class_7": 7,
"Class_8": 8,
"Class_9": 9
}
y_temp = []
userNDCGs = []
for user in users:
recommendations = rec.makeRecomendations(user, k)
recItems = recommendations['items'].tolist()
actualItems = data[data['visitorid'] == user].itemid.tolist()
hits = set(recItems) & set(actualItems)
positions = []
for hit in hits:
positions.append(recItems.index(hit))
userNDCG = 0
for pos in positions:
userNDCG += 1/(log(pos+2))
userNDCGs.append(userNDCG)
return statistics.mean(userNDCGs)
# "Main"
if __name__ == "__main__":
recomender = Recomender('model-450.meta') #TODO: insert model path
data = loadTestData()
while True:
k = input("Please enter k value (or quit to exit): ")
if str(k).lower() == "quit":
break
try:
k = int(k)
except:
print("Please enter an integer")
continue
print('Top-k Hit Ratio:', hitRatio(recomender, data[0], int(k)))
print('nDCG:', nDCG(recomender, data[0], int(k)))
def evaluate_lenet5(learning_rate=0.1, n_epoches=200,
nkerns=[20, 50], batch_size=500):
# load data from dataset
logging.info('... loading data')
trainData, trainLabel = util.load_total_data()
testData = util.loadTestData()
trainData = util.upToInt(trainData)
train_set_x = theano.shared(np.asarray(trainData,
dtype = theano.config.floatX),
borrow = True)
train_set_y = theano.shared(np.asarray(trainLabel,
dtype = theano.config.floatX),
borrow = True)
test_set_x = theano.shared(np.asarray(testData,
dtype = theano.config.floatX),
borrow = True)
train_set_y = T.cast(train_set_y, 'int32')
n_train_batches = train_set_x.get_value(borrow=True).shape[0]
n_valid_batches = train_set_x.get_value(borrow=True).shape[0]
n_test_batches = test_set_x.get_value(borrow=True).shape[0]
n_train_batches /= batch_size
n_valid_batches /= batch_size
n_test_batches /= batch_size
rng = np.random.RandomState(23455)
# allocate symbolic variables for the data
index = T.lscalar() # index to a [mini]batch
# start-snippet-1
x = T.matrix('x')
y = T.ivector('y')
logging.info('... building the model')
layer0_input = x.reshape((batch_size, 1, 28, 28))
# Construct the first convolutional pooling layer:
# filtering reduces the image size to (28-5+1 , 28-5+1) = (24, 24)
# maxpooling reduces this further to (24/2, 24/2) = (12, 12)
# 4D output tensor is thus of shape (batch_size, nkerns[0], 12, 12)
layer0 = LeNetConvPoolLayer(
rng,
input=layer0_input,
image_shape=(batch_size, 1, 28, 28),
filter_shape=(nkerns[0], 1, 5, 5),
poolsize=(2, 2)
)
# Construct the second convolutional pooling layer
# filtering reduces the image size to (12-5+1, 12-5+1) = (8, 8)
# maxpooling reduces this further to (8/2, 8/2) = (4, 4)
# 4D output tensor is thus of shape (batch_size, nkerns[1], 4, 4)
layer1 = LeNetConvPoolLayer(
rng,
input=layer0.output,
image_shape=(batch_size, nkerns[0], 12, 12),
filter_shape=(nkerns[1], nkerns[0], 5, 5),
poolsize=(2, 2)
)
# the HiddenLayer being fully-connected, it operates on 2D matrices of
# shape (batch_size, num_pixels) (i.e matrix of rasterized images).
# This will generate a matrix of shape (batch_size, nkerns[1] * 4 * 4),
# or (500, 50 * 4 * 4) = (500, 800) with the default values.
layer2_input = layer1.output.flatten(2)
# construct a fully-connected sigmoidal layer
layer2 = HiddenLayer(
rng,
input=layer2_input,
n_in=nkerns[1] * 4 * 4,
n_out=500,
activation=T.tanh
)
# classify the values of the fully-connected sigmoidal layer
layer3 = LogisticRegression(input=layer2.output, n_in=500, n_out=10)
# the cost we minimize during training is the NLL of the model
cost = layer3.negative_log_likelihood(y)
# create a function to compute the mistakes that are made by the model
validate_model = theano.function(
[index],
layer3.errors(y),
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size],
y: train_set_y[index * batch_size: (index + 1) * batch_size],
}
)
# create a list of all model parameters to be fit by gradient descent
params = layer3.params + layer2.params + layer1.params + layer0.params
# create a list of gradients for all model parameters
grads = T.grad(cost, params)
# train_model is a function that updates the model parameters by
# SGD Since this model has many parameters, it would be tedious to
# manually create an update rule for each model parameter. We thus
# create the updates list by automatically looping over all
# (params[i], grads[i]) pairs.
updates = [
(param_i, param_i - learning_rate * grad_i)
for param_i, grad_i in zip(params, grads)
]
train_model = theano.function(
[index],
cost,
updates=updates,
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size],
y: train_set_y[index * batch_size: (index + 1) * batch_size]
}
)
validation_model = theano.function(
[index],
layer3.errors(y),
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size],
y: train_set_y[index * batch_size: (index + 1) * batch_size]
}
)
logging.info('... training')
patience = 10000
patience_increase = 2
improvement_threshold = 0.995
validation_frequency = min(n_train_batches, patience / 2)
best_validation_loss = np.inf
best_iter = 0
test_score = 0.
start_time = time.clock()
epoch = 0
done_looping = False
while (epoch < n_epoches) and (not done_looping):
epoch = epoch + 1
for minibatch_index in xrange(n_train_batches):
iter = (epoch - 1) * n_train_batches + minibatch_index
if iter % 100 == 0:
logging.info('training @ iter = %d' % (iter))
cost_ij = train_model(minibatch_index)
if (iter + 1) % validation_frequency == 0:
# compute zero-one loss on validation set
validation_losses = [validation_model(i) for i
in xrange(n_valid_batches)]
this_validation_loss = np.mean(validation_losses)
print('epoch %i, minibatch %i/%i, validation error %f %%' %
(epoch, minibatch_index + 1, n_train_batches,
this_validation_loss * 100.))
if (this_validation_loss * 100.) < 0.001:
done_looping = True
break
end_time = time.clock()
logging.info('The code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % ((end_time - start_time) / 60.))
# make a prediction and save file
# make a prediction
predict_model = theano.function(
inputs=[index],
outputs= layer3.predict(),
givens={
x: test_set_x[index * batch_size: (index + 1) * batch_size]
}
)
# save the result file
testLabel = np.array([])
for test_index in range(n_test_batches):
tempLabel = predict_model(test_index)
testLabel = np.hstack((testLabel, tempLabel))
util.saveResult(testLabel, './result/cnn_result.csv')