删除了不能运行的测试

legacy/test/api/test_pipeline.py

@@ -1,6 +0,0 @@
-import unittest
-
-
-class TestPipeline(unittest.TestCase):
-    def test_case(self):
-        pass

legacy/test/api/test_processor.py

@@ -1,101 +0,0 @@
-import random
-import unittest
-
-import numpy as np
-
-from fastNLP import Vocabulary, Instance
-from fastNLP.api.processor import FullSpaceToHalfSpaceProcessor, PreAppendProcessor, SliceProcessor, Num2TagProcessor, \
-    IndexerProcessor, VocabProcessor, SeqLenProcessor, ModelProcessor, Index2WordProcessor, SetTargetProcessor, \
-    SetInputProcessor, VocabIndexerProcessor
-from fastNLP.core.dataset import DataSet
-
-
-class TestProcessor(unittest.TestCase):
-    def test_FullSpaceToHalfSpaceProcessor(self):
-        ds = DataSet({"word": ["０0, u１, u), (u２, u2"]})
-        proc = FullSpaceToHalfSpaceProcessor("word")
-        ds = proc(ds)
-        self.assertEqual(ds.field_arrays["word"].content, ["00, u1, u), (u2, u2"])
-
-    def test_PreAppendProcessor(self):
-        ds = DataSet({"word": [["1234", "3456"], ["8789", "3464"]]})
-        proc = PreAppendProcessor(data="abc", field_name="word")
-        ds = proc(ds)
-        self.assertEqual(ds.field_arrays["word"].content, [["abc", "1234", "3456"], ["abc", "8789", "3464"]])
-
-    def test_SliceProcessor(self):
-        ds = DataSet({"xx": [[random.randint(0, 10) for _ in range(30)]] * 40})
-        proc = SliceProcessor(10, 20, 2, "xx", new_added_field_name="yy")
-        ds = proc(ds)
-        self.assertEqual(len(ds.field_arrays["yy"].content[0]), 5)
-
-    def test_Num2TagProcessor(self):
-        ds = DataSet({"num": [["99.9982", "2134.0"], ["0.002", "234"]]})
-        proc = Num2TagProcessor("<num>", "num")
-        ds = proc(ds)
-        for data in ds.field_arrays["num"].content:
-            for d in data:
-                self.assertEqual(d, "<num>")
-
-    def test_VocabProcessor_and_IndexerProcessor(self):
-        ds = DataSet({"xx": [[str(random.randint(0, 10)) for _ in range(30)]] * 40})
-        vocab_proc = VocabProcessor("xx")
-        vocab_proc(ds)
-        vocab = vocab_proc.vocab
-        self.assertTrue(isinstance(vocab, Vocabulary))
-        self.assertTrue(len(vocab) > 5)
-
-        proc = IndexerProcessor(vocab, "xx", "yy")
-        ds = proc(ds)
-        for data in ds.field_arrays["yy"].content[0]:
-            self.assertTrue(isinstance(data, int))
-
-    def test_SeqLenProcessor(self):
-        ds = DataSet({"xx": [[str(random.randint(0, 10)) for _ in range(30)]] * 10})
-        proc = SeqLenProcessor("xx", "len")
-        ds = proc(ds)
-        for data in ds.field_arrays["len"].content:
-            self.assertEqual(data, 30)
-
-    def test_ModelProcessor(self):
-        from fastNLP.models.cnn_text_classification import CNNText
-        model = CNNText((100, 100), 5)
-        ins_list = []
-        for _ in range(64):
-            seq_len = np.random.randint(5, 30)
-            ins_list.append(Instance(word_seq=[np.random.randint(0, 100) for _ in range(seq_len)], seq_lens=seq_len))
-        data_set = DataSet(ins_list)
-        data_set.set_input("word_seq", "seq_lens")
-        proc = ModelProcessor(model)
-        data_set = proc(data_set)
-        self.assertTrue("pred" in data_set)
-
-    def test_Index2WordProcessor(self):
-        vocab = Vocabulary()
-        vocab.add_word_lst(["a", "b", "c", "d", "e"])
-        proc = Index2WordProcessor(vocab, "tag_id", "tag")
-        data_set = DataSet([Instance(tag_id=[np.random.randint(0, 7) for _ in range(32)])])
-        data_set = proc(data_set)
-        self.assertTrue("tag" in data_set)
-
-    def test_SetTargetProcessor(self):
-        proc = SetTargetProcessor("a", "b", "c")
-        data_set = DataSet({"a": [1, 2, 3], "b": [1, 2, 3], "c": [1, 2, 3]})
-        data_set = proc(data_set)
-        self.assertTrue(data_set["a"].is_target)
-        self.assertTrue(data_set["b"].is_target)
-        self.assertTrue(data_set["c"].is_target)
-
-    def test_SetInputProcessor(self):
-        proc = SetInputProcessor("a", "b", "c")
-        data_set = DataSet({"a": [1, 2, 3], "b": [1, 2, 3], "c": [1, 2, 3]})
-        data_set = proc(data_set)
-        self.assertTrue(data_set["a"].is_input)
-        self.assertTrue(data_set["b"].is_input)
-        self.assertTrue(data_set["c"].is_input)
-
-    def test_VocabIndexerProcessor(self):
-        proc = VocabIndexerProcessor("word_seq", "word_ids")
-        data_set = DataSet([Instance(word_seq=["a", "b", "c", "d", "e"])])
-        data_set = proc(data_set)
-        self.assertTrue("word_ids" in data_set)

legacy/test/automl/test_enas.py

@@ -1,111 +0,0 @@
-import unittest
-
-from fastNLP import DataSet
-from fastNLP import Instance
-from fastNLP import Vocabulary
-from fastNLP.core.losses import CrossEntropyLoss
-from fastNLP.core.metrics import AccuracyMetric
-
-
-class TestENAS(unittest.TestCase):
-    def testENAS(self):
-        # 从csv读取数据到DataSet
-        sample_path = "tutorials/sample_data/tutorial_sample_dataset.csv"
-        dataset = DataSet.read_csv(sample_path, headers=('raw_sentence', 'label'),
-                                   sep='\t')
-        print(len(dataset))
-        print(dataset[0])
-        print(dataset[-3])
-
-        dataset.append(Instance(raw_sentence='fake data', label='0'))
-        # 将所有数字转为小写
-        dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')
-        # label转int
-        dataset.apply(lambda x: int(x['label']), new_field_name='label')
-
-        # 使用空格分割句子
-        def split_sent(ins):
-            return ins['raw_sentence'].split()
-
-        dataset.apply(split_sent, new_field_name='words')
-
-        # 增加长度信息
-        dataset.apply(lambda x: len(x['words']), new_field_name='seq_len')
-        print(len(dataset))
-        print(dataset[0])
-
-        # DataSet.drop(func)筛除数据
-        dataset.drop(lambda x: x['seq_len'] <= 3, inplace=True)
-        print(len(dataset))
-
-        # 设置DataSet中，哪些field要转为tensor
-        # set target，loss或evaluate中的golden，计算loss，模型评估时使用
-        dataset.set_target("label")
-        # set input，模型forward时使用
-        dataset.set_input("words", "seq_len")
-
-        # 分出测试集、训练集
-        test_data, train_data = dataset.split(0.5)
-        print(len(test_data))
-        print(len(train_data))
-
-        # 构建词表, Vocabulary.add(word)
-        vocab = Vocabulary(min_freq=2)
-        train_data.apply(lambda x: [vocab.add(word) for word in x['words']])
-        vocab.build_vocab()
-
-        # index句子, Vocabulary.to_index(word)
-        train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')
-        test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')
-        print(test_data[0])
-
-        # 如果你们需要做强化学习或者GAN之类的项目，你们也可以使用这些数据预处理的工具
-        from fastNLP.core.batch import Batch
-        from fastNLP.core.sampler import RandomSampler
-
-        batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler())
-        for batch_x, batch_y in batch_iterator:
-            print("batch_x has: ", batch_x)
-            print("batch_y has: ", batch_y)
-            break
-
-        from fastNLP.automl.enas_model import ENASModel
-        from fastNLP.automl.enas_controller import Controller
-        model = ENASModel(embed_num=len(vocab), num_classes=5)
-        controller = Controller()
-
-        from fastNLP.automl.enas_trainer import ENASTrainer
-
-        # 更改DataSet中对应field的名称，要以模型的forward等参数名一致
-        train_data.rename_field('words', 'word_seq')  # input field 与 forward 参数一致
-        train_data.rename_field('label', 'label_seq')
-        test_data.rename_field('words', 'word_seq')
-        test_data.rename_field('label', 'label_seq')
-
-        loss = CrossEntropyLoss(pred="output", target="label_seq")
-        metric = AccuracyMetric(pred="predict", target="label_seq")
-
-        trainer = ENASTrainer(model=model, controller=controller, train_data=train_data, dev_data=test_data,
-                          loss=CrossEntropyLoss(pred="output", target="label_seq"),
-                          metrics=AccuracyMetric(pred="predict", target="label_seq"),
-                          check_code_level=-1,
-                          save_path=None,
-                          batch_size=32,
-                          print_every=1,
-                          n_epochs=3,
-                          final_epochs=1)
-        trainer.train()
-        print('Train finished!')
-
-        # 调用Tester在test_data上评价效果
-        from fastNLP import Tester
-
-        tester = Tester(data=test_data, model=model, metrics=AccuracyMetric(pred="predict", target="label_seq"),
-                        batch_size=4)
-
-        acc = tester.test()
-        print(acc)
-
-
-if __name__ == '__main__':
-    unittest.main()