def init_data(self, param):
if param.data is not None or isinstance(param, NumericFeatureParameters):
return
param.num = self.feature_extractor.num_features_non_numeric(param.suffix)
if isinstance(param.dim, Number): # Dimensions given as a number, not as a file to load
param.data = defaultdict(lambda d=param.dim: Config().random.normal(size=d))
param.data[UnknownDict.UNKNOWN] # Initialize unknown value
else: # Otherwise, not a number but a string with path to word vectors file
w2v = load_word2vec(param.dim)
unk = Config().random.normal(size=w2v.vector_size)
param.dim = w2v.vector_size
param.data = UnknownDict({x: w2v[x] for x in w2v.vocab}, unk)
def main():
Config().args.nowrite = True
out_file = os.environ.get("PARAMS_FILE", "params.csv")
w2v_files = [os.environ[f] for f in os.environ if f.startswith("W2V_FILE")]
num = int(os.environ.get("PARAMS_NUM", 30))
np.random.seed()
domains = (
("seed", 2147483647),
("classifier", 100 * [config.FEEDFORWARD_NN] + list(config.CLASSIFIERS)),
("wordvectors", [50, 100, 200, 300] + [load_word2vec(f) for f in w2v_files]),
("tagdim", (5, 10, 20)),
("labeldim", (5, 10, 20)),
("punctdim", (1, 2, 3)),
("gapdim", (1, 2, 3)),
("actiondim", (3, 5, 10)),
("layerdim", (50, 100, 200, 300, 500, 1000)),
("layers", [1] + 5 * [2]),
("activation", config.ACTIVATIONS),
("init", 5 * [config.INITIALIZATIONS[0]] + list(config.INITIALIZATIONS)),
("batchsize", (10, 30, 50, 100, 200, 500)),
("minibatchsize", (50, 100, 200, 300, 500, 1000)),
("nbepochs", range(10, 51)),
("optimizer", 10 * [config.OPTIMIZERS[0]] + list(config.OPTIMIZERS)),
("loss", 20 * [config.OBJECTIVES[0]] + list(config.OBJECTIVES)),
("importance", (1, 2)),
("earlyupdate", 6 * [False] + [True]),
("iterations", range(1, 21)),
("worddropout", (0, .1, .2, .25, .3)),
("normalize", (False, True)),
("regularizer", [None] + 3 * [config.REGULARIZERS[-1]] + list(config.REGULARIZERS)),
("regularization", (1e-7, 1e-6, 1e-5, 1e-4)),
("dropout", (0, .1, .2, .3, .4, .5)),
)
params = [Params(OrderedDict(p))
for p in zip(*[[(n, v) for v in np.random.choice(vs, num)] for n, vs in domains])]
print("All parameter combinations to try:")
print("\n".join(map(str, params)))
print("Saving results to '%s'" % out_file)
with open(out_file, "w") as f:
csv.writer(f).writerow(params[0].get_field_titles())
for param in params:
param.run()
with open(out_file, "a") as f:
csv.writer(f).writerow(param.get_fields())
best = max(params, key=Params.score)
print("Best parameters: %s" % best)
def init_data(self, param):
if param.data is not None or isinstance(param, NumericFeatureParameters):
return
param.num = self.feature_extractor.num_features_non_numeric(param.suffix)
if isinstance(param.dim, Number):
param.data = DropoutDict(max_size=param.size, dropout=param.dropout)
else:
w2v = load_word2vec(param.dim)
vocab = w2v.vocab
if param.size is None or param.size == 0:
param.size = len(w2v.vocab) + 1
else:
vocab = list(vocab)[:param.size - 1]
param.dim = w2v.vector_size
weights = np.array([w2v[x] for x in vocab])
unknown = weights.mean(axis=0)
param.init = (np.vstack((unknown, weights)),)
param.data = DropoutDict(max_size=param.size, keys=vocab, dropout=param.dropout)
