Extend linting with ruff (#1642)

asreview/__init__.py

@@ -12,27 +12,31 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+# deprecated in __init__.py, use asreview.models.feature_extraction instead
+from asreview._deprecated import _deprecated_func
 from asreview.data.base import ASReviewData
 from asreview.data.base import load_data
 from asreview.io.utils import list_readers
 from asreview.io.utils import list_writers
-from asreview.project import ASReviewProject
-from asreview.project import open_state
-from asreview.utils import asreview_path
-from asreview.utils import get_data_home
-
-# deprecated in __init__.py, use asreview.models.feature_extraction instead
-from asreview._deprecated import _deprecated_func
 from asreview.models.feature_extraction.embedding_lstm import (
     load_embedding as _load_embedding,
-)  # NOQA
+)
+
+# NOQA
 from asreview.models.feature_extraction.embedding_lstm import (
     sample_embedding as _sample_embedding,
-)  # NOQA
+)
+
+# NOQA
 from asreview.models.feature_extraction.embedding_lstm import (
     text_to_features as _text_to_features,
-)  # NOQA
+)
+from asreview.project import ASReviewProject
+from asreview.project import open_state
+from asreview.utils import asreview_path
+from asreview.utils import get_data_home
 
+# NOQA
 from ._version import get_versions
 
 __version__ = get_versions()["version"]

asreview/__main__.py

@@ -83,7 +83,7 @@ def main():
             "-V",
             "--version",
             action="version",
-            version="%(prog)s {version}".format(version=__version__),
+            version=f"%(prog)s {__version__}",
         )
 
         args, _ = parser.parse_known_args()

asreview/_deprecated.py

@@ -22,7 +22,7 @@ def _deprecated_func(msg):
     def dec(func):
         @functools.wraps(func)
         def wrapper(*args, **kwargs):
-            warnings.warn(msg)
+            warnings.warn(msg, stacklevel=2)
             return func(*args, **kwargs)
 
         return wrapper
@@ -32,7 +32,10 @@ def wrapper(*args, **kwargs):
 
 class DeprecateAction(argparse.Action):
     def __call__(self, parser, namespace, values, option_string=None):
-        logging.warning(f"Argument {self.option_strings} is deprecated and is ignored.")
+        logging.warning(
+            f"Argument {self.option_strings} is deprecated and is ignored.",
+            stacklevel=2,
+        )
         delattr(namespace, self.dest)
 
 

asreview/_version.py

@@ -124,7 +124,7 @@ def run_command(
             return None, None
     else:
         if verbose:
-            print("unable to find command, tried %s" % (commands,))
+            print(f"unable to find command, tried {commands}")
         return None, None
     stdout = process.communicate()[0].strip().decode()
     if process.returncode != 0:
@@ -163,8 +163,7 @@ def versions_from_parentdir(
 
     if verbose:
         print(
-            "Tried directories %s but none started with prefix %s"
-            % (str(rootdirs), parentdir_prefix)
+            f"Tried directories {str(rootdirs)} but none started with prefix {parentdir_prefix}"
         )
     raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
 
@@ -178,7 +177,7 @@ def git_get_keywords(versionfile_abs: str) -> Dict[str, str]:
     # _version.py.
     keywords: Dict[str, str] = {}
     try:
-        with open(versionfile_abs, "r") as fobj:
+        with open(versionfile_abs) as fobj:
             for line in fobj:
                 if line.strip().startswith("git_refnames ="):
                     mo = re.search(r'=\s*"(.*)"', line)
@@ -386,7 +385,7 @@ def git_pieces_from_vcs(
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
-            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (
+            pieces["error"] = "tag '{}' doesn't start with prefix '{}'".format(
                 full_tag,
                 tag_prefix,
             )

asreview/datasets.py

@@ -82,7 +82,7 @@ def __init__(
         img_url=None,
         license=None,
         year=None,
-        aliases=[],
+        aliases=None,
         **kwargs,
     ):
         """Base class for metadata of dataset.
@@ -136,6 +136,8 @@ def __init__(
 
         """
 
+        if aliases is None:
+            aliases = []
         self.dataset_id = dataset_id
         self.filepath = filepath
         self.title = title
@@ -406,7 +408,7 @@ def __init__(self):
         meta_file = "https://raw.githubusercontent.com/asreview/paper-asreview/master/index_v1.json"  # noqa
         datasets = _download_from_metadata(meta_file)
 
-        super(NaturePublicationDataGroup, self).__init__(*datasets)
+        super().__init__(*datasets)
 
 
 class SynergyDataSet(BaseDataSet):
@@ -744,7 +746,7 @@ def __init__(self):
 
         datasets = [SynergyDataSet(k, **v) for k, v in synergy_metadata.items()]
 
-        super(SynergyDataGroup, self).__init__(*datasets)
+        super().__init__(*datasets)
 
 
 class BenchmarkDataGroup(BaseDataGroup):
@@ -761,9 +763,10 @@ def __init__(self):
             "use SYNERGY dataset instead. For more information, see "
             "https://github.com/asreview/synergy-dataset.",
             category=UserWarning,
+            stacklevel=2,
         )
 
         meta_file = "https://raw.githubusercontent.com/asreview/systematic-review-datasets/master/index_v1.json"  # noqa
         datasets = _download_from_metadata(meta_file)
 
-        super(BenchmarkDataGroup, self).__init__(*datasets)
+        super().__init__(*datasets)

asreview/entry_points/lab.py

@@ -30,7 +30,7 @@ def _deprecated_dev_mode():
         exit(1)
 
 
-class LABEntryPoint(object):
+class LABEntryPoint:
     """Entry point to start the ASReview LAB webapp."""
 
     def execute(self, argv):

asreview/entry_points/simulate.py

@@ -200,7 +200,7 @@ def execute(self, argv):  # noqa
                 prior_df = s.get_priors()
 
                 print("The following records are prior knowledge:\n")
-                for i, row in prior_df.iterrows():
+                for _i, row in prior_df.iterrows():
                     preview = as_data.record(row["record_id"])
                     print(preview)
 

asreview/io/excel_reader.py

@@ -48,7 +48,7 @@ def read_data(cls, fp):
         best_sheet = None
         sheet_obj_val = -1
         wanted_columns = []
-        for type_name, type_list in COLUMN_DEFINITIONS.items():
+        for _type_name, type_list in COLUMN_DEFINITIONS.items():
             wanted_columns.extend(type_list)
 
         for sheet_name in dfs:

asreview/io/paper_record.py

@@ -139,7 +139,9 @@ class PaperRecord:
         Any extra keyword arguments will be put in self.extra_fields.
     """
 
-    def __init__(self, record_id, column_spec={}, **kwargs):
+    def __init__(self, record_id, column_spec=None, **kwargs):
+        if column_spec is None:
+            column_spec = {}
         for attr in [
             "title",
             "abstract",

asreview/io/ris.py

@@ -132,7 +132,7 @@ def _strip_zotero_p_tags(note_list):
 
     @classmethod
     def _read_from_file(cls, fp, encoding="utf8"):
-        with open(fp, "r", encoding=encoding) as bibliography_file:
+        with open(fp, encoding=encoding) as bibliography_file:
             return list(rispy.load(bibliography_file, skip_unknown_tags=True))
 
     @classmethod

asreview/io/utils.py

@@ -78,7 +78,7 @@ def _is_record_id_int(s):
         raise ValueError("Column 'record_id' should contain integer values.")
 
 
-def _standardize_dataframe(df, column_def={}):
+def _standardize_dataframe(df, column_def=None):
     """Create a ASReview readable dataframe.
 
     The main purpose is to rename columns with slightly different names;
@@ -95,6 +95,8 @@ def _standardize_dataframe(df, column_def={}):
     pd.DataFrame:
         Cleaned dataframe with proper column names.
     """
+    if column_def is None:
+        column_def = {}
     all_column_spec = {}
 
     # remove whitespace from colnames

asreview/models/balance/double.py

@@ -55,7 +55,7 @@ class DoubleBalance(BaseBalance):
     label = "Dynamic resampling (Double)"
 
     def __init__(self, a=2.155, alpha=0.94, b=0.789, beta=1.0, random_state=None):
-        super(DoubleBalance, self).__init__()
+        super().__init__()
         self.a = a
         self.alpha = alpha
         self.b = b

asreview/models/balance/triple.py

@@ -81,7 +81,7 @@ def __init__(
     ):
         """Initialize the triple balance strategy."""
 
-        super(TripleBalance, self).__init__()
+        super().__init__()
         self.a = a
         self.alpha = alpha
         self.b = b

asreview/models/balance/undersample.py

@@ -40,7 +40,7 @@ class UndersampleBalance(BaseBalance):
 
     def __init__(self, ratio=1.0, random_state=None):
         """Initialize the undersampling balance strategy."""
-        super(UndersampleBalance, self).__init__()
+        super().__init__()
         self.ratio = ratio
         self._random_state = get_random_state(random_state)
 

asreview/models/classifiers/logistic.py

@@ -45,7 +45,7 @@ class LogisticClassifier(BaseTrainClassifier):
     label = "Logistic regression"
 
     def __init__(self, C=1.0, class_weight=1.0, random_state=None, n_jobs=1):
-        super(LogisticClassifier, self).__init__()
+        super().__init__()
         self.C = C
         self.class_weight = class_weight
         self.n_jobs = n_jobs

asreview/models/classifiers/lstm_base.py

@@ -106,7 +106,7 @@ def __init__(
         class_weight=30.0,
     ):
         """Initialize the LSTM base model"""
-        super(LSTMBaseClassifier, self).__init__()
+        super().__init__()
         self.embedding_matrix = embedding_matrix
         self.backwards = backwards
         self.dropout = dropout
@@ -175,7 +175,7 @@ def full_hyper_space(self):
 
     @property
     def default_param(self):
-        defaults = super(LSTMBaseClassifier, self).default_param
+        defaults = super().default_param
         defaults.pop("embedding_matrix")
         return defaults
 

asreview/models/classifiers/lstm_pool.py

@@ -110,7 +110,7 @@ def __init__(
         class_weight=30.0,
     ):
         """Initialize the LSTM pool model."""
-        super(LSTMPoolClassifier, self).__init__()
+        super().__init__()
         self.embedding_matrix = embedding_matrix
         self.backwards = backwards
         self.dropout = dropout
@@ -178,7 +178,7 @@ def full_hyper_space(self):
 
     @property
     def default_param(self):
-        defaults = super(LSTMPoolClassifier, self).default_param
+        defaults = super().default_param
         defaults.pop("embedding_matrix")
         return defaults
 

asreview/models/classifiers/nb.py

@@ -43,7 +43,7 @@ class NaiveBayesClassifier(BaseTrainClassifier):
     label = "Naive Bayes"
 
     def __init__(self, alpha=3.822):
-        super(NaiveBayesClassifier, self).__init__()
+        super().__init__()
         self.alpha = alpha
         self._model = MultinomialNB(alpha=alpha)
         logging.debug(self._model)

asreview/models/classifiers/nn_2_layer.py

@@ -103,7 +103,7 @@ def __init__(
         class_weight=30.0,
     ):
         """Initialize the 2-layer neural network model."""
-        super(NN2LayerClassifier, self).__init__()
+        super().__init__()
         self.dense_width = int(dense_width)
         self.optimizer = optimizer
         self.learn_rate = learn_rate

asreview/models/classifiers/rf.py

@@ -47,7 +47,7 @@ class RandomForestClassifier(BaseTrainClassifier):
     def __init__(
         self, n_estimators=100, max_features=10, class_weight=1.0, random_state=None
     ):
-        super(RandomForestClassifier, self).__init__()
+        super().__init__()
         self.n_estimators = int(n_estimators)
         self.max_features = int(max_features)
         self.class_weight = class_weight

asreview/models/classifiers/svm.py

@@ -52,7 +52,7 @@ def __init__(
         kernel="linear",
         random_state=None,
     ):
-        super(SVMClassifier, self).__init__()
+        super().__init__()
         self.gamma = gamma
         self.class_weight = class_weight
         self.C = C

asreview/models/feature_extraction/doc2vec.py

@@ -107,7 +107,7 @@ def __init__(
         **kwargs,
     ):
         """Initialize the doc2vec model."""
-        super(Doc2Vec, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.vector_size = int(vector_size)
         self.epochs = int(epochs)
         self.min_count = int(min_count)
@@ -168,7 +168,7 @@ def full_hyper_space(self):
 
         eps = 1e-7
 
-        hyper_space, hyper_choices = super(Doc2Vec, self).full_hyper_space()
+        hyper_space, hyper_choices = super().full_hyper_space()
         hyper_space.update(
             {
                 "fex_vector_size": hp.quniform("fex_vector_size", 31.5, 127.5 - eps, 8),

asreview/models/feature_extraction/embedding_idf.py

@@ -67,7 +67,7 @@ class EmbeddingIdf(BaseFeatureExtraction):
 
     def __init__(self, *args, embedding_fp=None, random_state=None, **kwargs):
         """Initialize the Embedding-Idf model."""
-        super(EmbeddingIdf, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.embedding_fp = embedding_fp
         self.embedding = None
         self._random_state = get_random_state(random_state)

asreview/models/feature_extraction/embedding_lstm.py

@@ -88,7 +88,7 @@ def __init__(
         **kwargs,
     ):
         """Initialize the embedding matrix feature extraction."""
-        super(EmbeddingLSTM, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.embedding = None
         self.num_words = num_words
         self.max_sequence_length = max_sequence_length
@@ -132,7 +132,7 @@ def get_embedding_matrix(self, texts, embedding_fp):
     def full_hyper_space(self):
         from hyperopt import hp
 
-        hyper_space, hyper_choices = super(EmbeddingLSTM, self).full_hyper_space()
+        hyper_space, hyper_choices = super().full_hyper_space()
         hyper_space.update({"fex_loop_sequences": hp.randint("fex_loop_sequences", 2)})
         return hyper_space, hyper_choices
 
@@ -222,7 +222,7 @@ def _embedding_reader(filename, input_queue, block_size=1000):
         Number of lines for each job.
     """
 
-    with open(filename, "r", encoding="utf-8", newline="\n") as f:
+    with open(filename, encoding="utf-8", newline="\n") as f:
         # Throw away the first line, since we don't care about the dimensions.
         f.readline()
 
@@ -404,7 +404,7 @@ def load_embedding(fp, word_index=None, n_jobs=None):
     input_queue = Queue(queue_size)
     output_queue = Queue()
 
-    with open(fp, "r", encoding="utf-8", newline="\n") as f:
+    with open(fp, encoding="utf-8", newline="\n") as f:
         n_words, emb_vec_dim = list(map(int, f.readline().split(" ")))
 
     logging.debug(f"Reading {n_words} vectors with {emb_vec_dim} dimensions.")