def main(path):
train, test, valid = read_data(path)
data = ev_data(train["text"])
print(data)
model = build_model(ev_data(valid["text"])).fit(data)
evaluate(model, test.sample(frac=0.1), "test")
evaluate(model, valid, "valid")
evaluate(model, train, "train")
def main(path):
train, test, valid = read_data(path)
data = ev_data(train["text"])
print(data)
model = build_model(ev_data(valid["text"])).fit(data)
model[-1].set_params(batch_size=32)
evaluate(model, test, "test")
evaluate(model, valid, "valid")
evaluate(model, train, "train")
def evaluate(model, dataset, title):
data = ev_data(dataset["text"])
with timer("Predict"):
predicted = model.predict(data)
with timer("Calculate the vectorized measures"):
data["recall"] = recall(data["gold"], predicted)
data["rr"] = rr(data["gold"], predicted)
print("Evaluating on", title)
print("Recall", data["recall"].mean())
print("MRR", data["rr"].mean())
return data
def flat_oov(oov):
return ev_data(oov["text"])
def flat_data(data):
return ev_data(data["text"])
def recall_scoring(model, X, y):
dataset = ev_data(X.sample(frac=0.01)["text"])
predicted = model.predict(dataset)
return np.mean(recall(dataset["gold"], predicted))