def test_csv_load_data():
fp = Path("test", "demo_data", "csv_example_with_labels.csv")
_, x, y = asr.read_data(fp)
assert x.shape[0] == 6
assert y.shape[0] == 6
fp = Path("test", "demo_data", "csv_example_without_labels.csv")
_, x, y = asr.read_data(fp)
assert x.shape[0] == 2 and y is None
def check_lstm(lstm_model):
# load data
_, texts, y = asr.read_data(data_fp)
# create features and labels
X, word_index = asr.text_to_features(texts)
# Load embedding layer.
embedding = asr.load_embedding(embedding_fp, word_index=word_index)
embedding_matrix = asr.sample_embedding(embedding, word_index)
# create the model
model = KerasClassifier(
lstm_model(embedding_matrix=embedding_matrix),
verbose=1,
)
fit_kwargs = {"epochs": 2, "batch_size": 2, "class_weight": 20.0}
# start the review process.
reviewer = asr.ReviewSimulate(
X,
y=y,
model=model,
n_instances=1,
n_queries=1,
fit_kwargs=fit_kwargs,
prior_included=[1, 3], # List of some included papers
prior_excluded=[2, 4], # List of some excluded papers
)
reviewer.review()
check_log(reviewer._logger._log_dict)
def check_nb_svm(sk_model):
# load data
_, texts, y = asr.read_data(data_fp)
# create features and labels
X, _ = asr.text_to_features(texts)
# create the model
model = sk_model()
# start the review process.
reviewer = asr.ReviewSimulate(
X,
y=y,
model=model,
n_instances=1,
n_queries=1,
prior_included=[1, 3], # List of some included papers
prior_excluded=[2, 4], # List of some excluded papers
)
reviewer.review()
check_log(reviewer._logger._log_dict)
#!/usr/bin/env python
'''
Created on 23 Apr 2019
@author: qubix
'''
import sys
import asreview
filename = sys.argv[1]
file_out = sys.argv[2]
print(filename)
_, text, labels = asreview.read_data(filename)
X, word_index = asreview.text_to_features(text)
with open(file_out, "w") as f:
for key in word_index:
f.write(f"{key}\n")