Python text_to_features示例

示例#1

def check_nb_svm(sk_model, monkeypatch):
    # load data
    as_data = asr.ASReviewData.from_file(data_fp)
    _, texts, _ = as_data.get_data()

    # create features and labels
    X, _ = asr.text_to_features(texts)

    # create the model
    model = sk_model()

    monkeypatch.setattr('builtins.input', lambda _: "0")

    # start the review process.
    reviewer = asr.ReviewOracle(
        X,
        as_data=as_data,
        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)

示例#2

def check_lstm(lstm_model, monkeypatch):
    # load data
    as_data = asr.ASReviewData.from_file(data_fp)
    _, texts, _ = as_data.get_data()

    # 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}

    monkeypatch.setattr('builtins.input', lambda _: "0")
    # start the review process.
    reviewer = asr.ReviewOracle(
        X,
        as_data=as_data,
        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)

示例#3

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)

示例#4

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)

示例#5

文件： token_gen.py 项目： GerbrichFerdinands/automated-systematic-review-simulations

#!/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")