Apply ruff flake8-comprehensions (#21694)

examples/tensorflow/benchmarking/plot_csv_file.py

@@ -83,7 +83,7 @@ def can_convert_to_float(string):
 class Plot:
     def __init__(self, args):
         self.args = args
-        self.result_dict = defaultdict(lambda: dict(bsz=[], seq_len=[], result={}))
+        self.result_dict = defaultdict(lambda: {"bsz": [], "seq_len": [], "result": {}})
 
         with open(self.args.csv_file, newline="") as csv_file:
             reader = csv.DictReader(csv_file)
@@ -116,8 +116,8 @@ class Plot:
             axis.set_major_formatter(ScalarFormatter())
 
         for model_name_idx, model_name in enumerate(self.result_dict.keys()):
-            batch_sizes = sorted(list(set(self.result_dict[model_name]["bsz"])))
-            sequence_lengths = sorted(list(set(self.result_dict[model_name]["seq_len"])))
+            batch_sizes = sorted(set(self.result_dict[model_name]["bsz"]))
+            sequence_lengths = sorted(set(self.result_dict[model_name]["seq_len"]))
             results = self.result_dict[model_name]["result"]
 
             (x_axis_array, inner_loop_array) = (

examples/tensorflow/image-classification/run_image_classification.py

@@ -300,7 +300,7 @@ def main():
     # Prepare label mappings.
     # We'll include these in the model's config to get human readable labels in the Inference API.
     labels = dataset["train"].features["labels"].names
-    label2id, id2label = dict(), dict()
+    label2id, id2label = {}, {}
     for i, label in enumerate(labels):
         label2id[label] = str(i)
         id2label[str(i)] = label

examples/tensorflow/language-modeling/run_clm.py

@@ -600,7 +600,7 @@ def main():
 
         if training_args.output_dir is not None:
             output_eval_file = os.path.join(training_args.output_dir, "all_results.json")
-            results_dict = dict()
+            results_dict = {}
             results_dict["train_loss"] = train_loss
             results_dict["train_perplexity"] = train_perplexity
             results_dict["eval_loss"] = validation_loss

examples/tensorflow/language-modeling/run_mlm.py

@@ -623,7 +623,7 @@ def main():
 
     if training_args.output_dir is not None:
         output_eval_file = os.path.join(training_args.output_dir, "all_results.json")
-        results_dict = dict()
+        results_dict = {}
         results_dict["train_loss"] = train_loss
         results_dict["train_perplexity"] = train_perplexity
         results_dict["eval_loss"] = validation_loss

examples/tensorflow/question-answering/run_qa.py

@@ -464,7 +464,7 @@ def main():
 
         return tokenized_examples
 
-    processed_datasets = dict()
+    processed_datasets = {}
     if training_args.do_train:
         if "train" not in datasets:
             raise ValueError("--do_train requires a train dataset")

examples/tensorflow/text-classification/run_glue.py

@@ -310,12 +310,12 @@ def main():
     if config.label2id != PretrainedConfig(num_labels=num_labels).label2id and not is_regression:
         # Some have all caps in their config, some don't.
         label_name_to_id = {k.lower(): v for k, v in config.label2id.items()}
-        if list(sorted(label_name_to_id.keys())) == list(sorted(label_list)):
+        if sorted(label_name_to_id.keys()) == sorted(label_list):
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
             logger.warning(
                 "Your model seems to have been trained with labels, but they don't match the dataset: ",
-                f"model labels: {list(sorted(label_name_to_id.keys()))}, dataset labels: {list(sorted(label_list))}."
+                f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )
             label_to_id = {label: i for i, label in enumerate(label_list)}
@@ -383,7 +383,7 @@ def main():
         dataset_options.experimental_distribute.auto_shard_policy = tf.data.experimental.AutoShardPolicy.OFF
         num_replicas = training_args.strategy.num_replicas_in_sync
 
-        tf_data = dict()
+        tf_data = {}
         max_samples = {
             "train": data_args.max_train_samples,
             "validation": data_args.max_eval_samples,

examples/tensorflow/text-classification/run_text_classification.py

@@ -343,13 +343,13 @@ def main():
     if "train" in datasets:
         if not is_regression and config.label2id != PretrainedConfig(num_labels=num_labels).label2id:
             label_name_to_id = config.label2id
-            if list(sorted(label_name_to_id.keys())) == list(sorted(label_list)):
+            if sorted(label_name_to_id.keys()) == sorted(label_list):
                 label_to_id = label_name_to_id  # Use the model's labels
             else:
                 logger.warning(
                     "Your model seems to have been trained with labels, but they don't match the dataset: ",
-                    f"model labels: {list(sorted(label_name_to_id.keys()))}, dataset labels:"
-                    f" {list(sorted(label_list))}.\nIgnoring the model labels as a result.",
+                    f"model labels: {sorted(label_name_to_id.keys())}, dataset labels:"
+                    f" {sorted(label_list)}.\nIgnoring the model labels as a result.",
                 )
                 label_to_id = {v: i for i, v in enumerate(label_list)}
         elif not is_regression:
@@ -411,7 +411,7 @@ def main():
         dataset_options.experimental_distribute.auto_shard_policy = tf.data.experimental.AutoShardPolicy.OFF
         num_replicas = training_args.strategy.num_replicas_in_sync
 
-        tf_data = dict()
+        tf_data = {}
         max_samples = {
             "train": data_args.max_train_samples,
             "validation": data_args.max_val_samples,