Merge pull request #749 from QData/format-updates

format update

docs/2notebook/0_End_to_End.ipynb

@@ -1430,7 +1430,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!textattack attack --model cnn-yelp --num-examples 3 --search-method greedy-word-wir --transformation word-swap-wordnet --constraints cola^max_diff=0.1 bert-score^min_bert_score=0.7 --enable-advance-metrics \n"
+    "!textattack attack --model cnn-yelp --num-examples 3 --search-method greedy-word-wir --transformation word-swap-wordnet --constraints cola^max_diff=0.1 bert-score^min_bert_score=0.7 --enable-advance-metrics"
    ]
   },
   {
@@ -1439,7 +1439,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!textattack attack --model lstm-mr --recipe deepwordbug --num-examples 2 --attack-n --enable-advance-metrics \n"
+    "!textattack attack --model lstm-mr --recipe deepwordbug --num-examples 2 --attack-n --enable-advance-metrics"
    ]
   },
   {
@@ -1448,7 +1448,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!textattack attack --model lstm-mr --recipe hotflip --num-examples 4 --num-examples-offset 3 --enable-advance-metrics "
+    "!textattack attack --model lstm-mr --recipe hotflip --num-examples 4 --num-examples-offset 3 --enable-advance-metrics"
    ]
   },
   {
@@ -1457,7 +1457,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!textattack attack --model-from-huggingface distilbert-base-uncased-finetuned-sst-2-english --dataset-from-huggingface glue^sst2^train --recipe deepwordbug --num-examples 3 --enable-advance-metrics\n"
+    "!textattack attack --model-from-huggingface distilbert-base-uncased-finetuned-sst-2-english --dataset-from-huggingface glue^sst2^train --recipe deepwordbug --num-examples 3 --enable-advance-metrics"
    ]
   },
   {
@@ -1466,7 +1466,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! textattack attack --model cnn-imdb --attack-from-file tests/sample_inputs/attack_from_file.py^Attack --num-examples 2  --num-examples-offset 18 --attack-n "
+    "! textattack attack --model cnn-imdb --attack-from-file tests/sample_inputs/attack_from_file.py^Attack --num-examples 2  --num-examples-offset 18 --attack-n"
    ]
   }
  ],

docs/2notebook/4_Custom_Datasets_Word_Embedding.ipynb

@@ -537,7 +537,7 @@
     "\n",
     "attack = Attack(goal_function, constraints, transformation, search_method)\n",
     "\n",
-    "# here is a legacy code piece showing how the attack runs in  details \n",
+    "# here is a legacy code piece showing how the attack runs in  details\n",
     "for example, label in custom_dataset:\n",
     "    result = attack.attack(example, label)\n",
     "    print(result.__str__(color_method=\"ansi\"))"

docs/2notebook/Example_3_Keras.ipynb

@@ -259,7 +259,6 @@
     "        self.model = model\n",
     "\n",
     "    def __call__(self, text_input_list):\n",
-    "\n",
     "        x_transform = []\n",
     "        for i, review in enumerate(text_input_list):\n",
     "            tokens = [x.strip(\",\") for x in review.split()]\n",

docs/2notebook/Example_5_Explain_BERT.ipynb

@@ -273,19 +273,9 @@
     "    list_of_text = []\n",
     "    number = input_ids.size()[0]\n",
     "    for i in range(number):\n",
-    "        ii = (\n",
-    "            input_ids[\n",
-    "                i,\n",
-    "            ]\n",
-    "            .cpu()\n",
-    "            .numpy()\n",
-    "        )\n",
-    "        tt = token_type_ids[\n",
-    "            i,\n",
-    "        ]\n",
-    "        am = attention_mask[\n",
-    "            i,\n",
-    "        ]\n",
+    "        ii = input_ids[i,].cpu().numpy()\n",
+    "        tt = token_type_ids[i,]\n",
+    "        am = attention_mask[i,]\n",
     "        txt = tokenizer.decode(ii, skip_special_tokens=True)\n",
     "        list_of_text.append(txt)\n",
     "    return list_of_text\n",

tests/test_attacked_text.py

@@ -70,7 +70,7 @@ def test_window_around_index(self, attacked_text):
 
     def test_big_window_around_index(self, attacked_text):
         assert (
-            attacked_text.text_window_around_index(0, 10 ** 5) + "."
+            attacked_text.text_window_around_index(0, 10**5) + "."
         ) == attacked_text.text
 
     def test_window_around_index_start(self, attacked_text):

tests/test_word_embedding.py

@@ -10,7 +10,7 @@ def test_embedding_paragramcf():
     word_embedding = WordEmbedding.counterfitted_GLOVE_embedding()
     assert pytest.approx(word_embedding[0][0]) == -0.022007
     assert pytest.approx(word_embedding["fawn"][0]) == -0.022007
-    assert word_embedding[10 ** 9] is None
+    assert word_embedding[10**9] is None
 
 
 def test_embedding_gensim():
@@ -37,7 +37,7 @@ def test_embedding_gensim():
     word_embedding = GensimWordEmbedding(keyed_vectors)
     assert pytest.approx(word_embedding[0][0]) == 1
     assert pytest.approx(word_embedding["bye-bye"][0]) == -1 / np.sqrt(2)
-    assert word_embedding[10 ** 9] is None
+    assert word_embedding[10**9] is None
 
     # test query functionality
     assert pytest.approx(word_embedding.get_cos_sim(1, 3)) == 0

textattack/attack.py

@@ -83,8 +83,8 @@ def __init__(
         constraints: List[Union[Constraint, PreTransformationConstraint]],
         transformation: Transformation,
         search_method: SearchMethod,
-        transformation_cache_size=2 ** 15,
-        constraint_cache_size=2 ** 15,
+        transformation_cache_size=2**15,
+        constraint_cache_size=2**15,
     ):
         """Initialize an attack object.
 

textattack/attack_args.py

@@ -504,8 +504,8 @@ class _CommandLineAttackArgs:
     interactive: bool = False
     parallel: bool = False
     model_batch_size: int = 32
-    model_cache_size: int = 2 ** 18
-    constraint_cache_size: int = 2 ** 18
+    model_cache_size: int = 2**18
+    constraint_cache_size: int = 2**18
 
     @classmethod
     def _add_parser_args(cls, parser):

textattack/constraints/grammaticality/cola.py

@@ -43,7 +43,7 @@ def __init__(
 
         self.max_diff = max_diff
         self.model_name = model_name
-        self._reference_score_cache = lru.LRU(2 ** 10)
+        self._reference_score_cache = lru.LRU(2**10)
         model = AutoModelForSequenceClassification.from_pretrained(model_name)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
         self.model = HuggingFaceModelWrapper(model, tokenizer)

textattack/constraints/grammaticality/language_models/google_language_model/alzantot_goog_lm.py

@@ -49,7 +49,7 @@ def __init__(self):
                 self.sess, self.graph, self.PBTXT_PATH, self.CKPT_PATH
             )
 
-        self.lm_cache = lru.LRU(2 ** 18)
+        self.lm_cache = lru.LRU(2**18)
 
     def clear_cache(self):
         self.lm_cache.clear()

textattack/constraints/grammaticality/part_of_speech.py

@@ -56,7 +56,7 @@ def __init__(
         self.language_nltk = language_nltk
         self.language_stanza = language_stanza
 
-        self._pos_tag_cache = lru.LRU(2 ** 14)
+        self._pos_tag_cache = lru.LRU(2**14)
         if tagger_type == "flair":
             if tagset == "universal":
                 self._flair_pos_tagger = SequenceTagger.load("upos-fast")

textattack/constraints/semantics/sentence_encoders/thought_vector.py

@@ -32,7 +32,7 @@ def __init__(self, embedding=None, **kwargs):
     def clear_cache(self):
         self._get_thought_vector.cache_clear()
 
-    @functools.lru_cache(maxsize=2 ** 10)
+    @functools.lru_cache(maxsize=2**10)
     def _get_thought_vector(self, text):
         """Sums the embeddings of all the words in ``text`` into a "thought
         vector"."""

textattack/goal_functions/goal_function.py

@@ -40,7 +40,7 @@ def __init__(
         use_cache=True,
         query_budget=float("inf"),
         model_batch_size=32,
-        model_cache_size=2 ** 20,
+        model_cache_size=2**20,
     ):
         validators.validate_model_goal_function_compatibility(
             self.__class__, model_wrapper.model.__class__

textattack/goal_functions/text/minimize_bleu.py

@@ -59,7 +59,7 @@ def extra_repr_keys(self):
             return ["maximizable", "target_bleu"]
 
 
-@functools.lru_cache(maxsize=2 ** 12)
+@functools.lru_cache(maxsize=2**12)
 def get_bleu(a, b):
     ref = a.words
     hyp = b.words

textattack/goal_functions/text/non_overlapping_output.py

@@ -38,12 +38,12 @@ def _get_score(self, model_output, _):
             return num_words_diff / len(get_words_cached(self.ground_truth_output))
 
 
-@functools.lru_cache(maxsize=2 ** 12)
+@functools.lru_cache(maxsize=2**12)
 def get_words_cached(s):
     return np.array(words_from_text(s))
 
 
-@functools.lru_cache(maxsize=2 ** 12)
+@functools.lru_cache(maxsize=2**12)
 def word_difference_score(s1, s2):
     """Returns the number of words that are non-overlapping between s1 and
     s2."""

textattack/metrics/attack_metrics/words_perturbed.py

@@ -31,7 +31,7 @@ def calculate(self, results):
         self.total_attacks = len(self.results)
         self.all_num_words = np.zeros(len(self.results))
         self.perturbed_word_percentages = np.zeros(len(self.results))
-        self.num_words_changed_until_success = np.zeros(2 ** 16)
+        self.num_words_changed_until_success = np.zeros(2**16)
         self.max_words_changed = 0
 
         for i, result in enumerate(self.results):

textattack/shared/validators.py

@@ -25,7 +25,10 @@
         r"^textattack.models.helpers.word_cnn_for_classification.*",
         r"^transformers.modeling_\w*\.\w*ForSequenceClassification$",
     ],
-    (NonOverlappingOutput, MinimizeBleu,): [
+    (
+        NonOverlappingOutput,
+        MinimizeBleu,
+    ): [
         r"^textattack.models.helpers.t5_for_text_to_text.*",
     ],
 }