def load_data(num_records=1750):
print('... loading data ...')
data, labels = prep.get_data(num_records)
labels += 1
train_x, test_x, train_y, test_y = train_test_split(
data, labels, test_size=0.3, random_state=28022016
)
train_x, valid_x, train_y, valid_y = train_test_split(
train_x, train_y, test_size=0.3, random_state=10032016
)
def shared_dataset(data_xy, borrow=True):
""" Function that loads the dataset into shared variables
The reason we store our dataset in shared variables is to allow
Theano to copy it into the GPU memory (when code is run on GPU).
Since copying data into the GPU is slow, copying a minibatch everytime
is needed (the default behaviour if the data is not in a shared
variable) would lead to a large decrease in performance.
"""
data_x, data_y = data_xy
shared_x = theano.shared(np.asarray(data_x,
dtype=theano.config.floatX),
borrow=borrow)
shared_y = theano.shared(np.asarray(data_y,
dtype=theano.config.floatX),
borrow=borrow)
# When storing data on the GPU it has to be stored as floats
# therefore we will store the labels as ``floatX`` as well
# (``shared_y`` does exactly that). But during our computations
# we need them as ints (we use labels as index, and if they are
# floats it doesn't make sense) therefore instead of returning
# ``shared_y`` we will have to cast it to int. This little hack
# lets ous get around this issue
return shared_x, T.cast(shared_y, 'int32')
test_x, test_y = shared_dataset((test_x, test_y))
valid_x, valid_y = shared_dataset((valid_x, valid_y))
train_x, train_y = shared_dataset((train_x, train_y))
rval = [(train_x, train_y), (valid_x, valid_y), (test_x, test_y)]
return rval
2 tests - against twitter data and against polarity list
"""
from Python_code.classifiers.preprocessing import img_preprocess as prep
from sklearn.decomposition import RandomizedPCA
from sklearn.metrics import accuracy_score, classification_report
from sklearn.cross_validation import train_test_split
import pandas as pd
import time
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC
APPLY_PCA = False
prep.SIZE = (250, 250)
data, labels = prep.get_data(1000)
# split test & train sets
train_x, test_x, train_y, test_y = train_test_split(
data, labels, test_size=0.3, random_state=28022016)
if APPLY_PCA:
pca = RandomizedPCA(n_components=100, whiten=False)
train_x = pca.fit_transform(train_x)
test_x = pca.transform(test_x)
print('starting svm')
start_time = time.time()
parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}