def predict():
req_json = request.get_json(silent=True)
text = req_json["text"]
vector = util.get_vectors(text, wordvectors, stop_words)
vc = np.array([vector]).reshape(1, -1)
proba = model.predict_proba(vc)[0]
cat = model.predict(vc)[0]
code, label = util.get_result(proba, cat)
response = {"code": code, "label": label}
return response
import annoy
import random
import PIL.Image, PIL.ImageOps
import numpy
import util
annoy_fn = 'mnist.annoy'
data_fn = 'mnist.pkl.gz'
if not os.path.exists(annoy_fn):
if not os.path.exists(data_fn):
print 'downloading'
urlretrieve('http://deeplearning.net/data/mnist/mnist.pkl.gz', data_fn)
a = annoy.AnnoyIndex(784, 'euclidean')
for i, pic in util.get_vectors(data_fn):
a.add_item(i, pic)
print 'building'
a.build(10)
a.save(annoy_fn)
a = annoy.AnnoyIndex(784, 'euclidean')
a.load(annoy_fn)
pics = 5
nns = 10
img_size = 100
margin = 16
main_image = PIL.Image.new('RGB', (img_size * nns + margin, img_size * pics), 'white')
from util import get_vectors
if len(sys.argv) < 2:
print __doc__
raise
fn = sys.argv[1]
search_k = 100000
if len(sys.argv) > 2:
search_k = int(sys.argv[2])
fn_annoy = fn + '.annoy'
fn_lmdb = fn + '.lmdb' # stores word <-> id mapping
word, vec = get_vectors(fn).next()
size = len(vec)
env = lmdb.open(fn_lmdb, map_size=int(1e9))
if not os.path.exists(fn_annoy) or not os.path.exists(fn_lmdb):
i = 0
a = annoy.AnnoyIndex(size)
with env.begin(write=True) as txn:
for word, vec in get_vectors(sys.argv[1]):
a.add_item(i, vec)
id = 'i%d' % i
word = 'w' + word
txn.put(id, word)
txn.put(word, id)
i += 1
if i % 1000 == 0:
from util import get_vectors
if len(sys.argv) < 2:
print __doc__
raise
fn = sys.argv[1]
search_k = 100000
if len(sys.argv) > 2:
search_k = int(sys.argv[2])
fn_annoy = fn + '.annoy'
fn_lmdb = fn + '.lmdb' # stores word <-> id mapping
word, vec = get_vectors(fn).next()
size = len(vec)
env = lmdb.open(fn_lmdb, map_size=int(1e9))
if not os.path.exists(fn_annoy) or not os.path.exists(fn_lmdb):
i = 0
a = annoy.AnnoyIndex(size)
with env.begin(write=True) as txn:
for word, vec in get_vectors(sys.argv[1]):
a.add_item(i, vec)
id = 'i%d' % i
word = 'w' + word
txn.put(id, word)
txn.put(word, id)
i += 1
if i % 1000 == 0:
fs_synt = [2, 4, 8, 16, 32, 64, 128, 256, 512, 1024]
ts_synt = []
for f in fs_synt:
print f, '...'
dataset = get_gaussian(n, f)
avgs = get_avgs(dataset)
ts_synt.append(avgs)
fs_real = []
ts_real = []
es_real = []
for fn in sys.argv[1:]:
print fn, '...'
es_real.append(fn.split('/')[-1])
dataset = [numpy.array(x) for item, x in get_vectors(fn, n)]
f = len(dataset[0])
avgs = get_avgs(dataset, d=distance.cosine)
fs_real.append(f)
ts_real.append(avgs)
print fs_real, ts_real, es_real
def configure_ax():
fig, ax = plt.subplots()
ax.set_xscale('log')
ax.set_yscale('log')
ax.grid(True, 'both')
ax.set_xlabel('Number of dimensions')
ax.set_ylabel('Euclidean/cosine distance')
return fig, ax
