Sign upLogin

IlyaGusev/rulm

View on GitHub
Star

Showing 260 of 260 total issues

Avoid too many return statements within this function.
Open

    return text
Severity: Major
Found in data_processing/create_librusec.py - About 30 mins to fix

    Avoid too many return statements within this function.
    Open

            return text
    Severity: Major
    Found in data_processing/util.py - About 30 mins to fix

      Avoid too many return statements within this function.
      Open

              return
      Severity: Major
      Found in data_processing/save_mc4.py - About 30 mins to fix

        Identical blocks of code found in 2 locations. Consider refactoring.
        Open

            with open(os.path.expanduser(token), "r") as r:
        toloka_token = r.read().strip()
        Severity: Minor
        Found in self_instruct/crowd/aggregate.py and 1 other location - About 30 mins to fix
        self_instruct/crowd/upload.py on lines 76..77

        Duplicated Code

        Duplicated code can lead to software that is hard to understand and difficult to change. The Don't Repeat Yourself (DRY) principle states:

        Every piece of knowledge must have a single, unambiguous, authoritative representation within a system.

        When you violate DRY, bugs and maintenance problems are sure to follow. Duplicated code has a tendency to both continue to replicate and also to diverge (leaving bugs as two similar implementations differ in subtle ways).

        Tuning

        This issue has a mass of 32.

        We set useful threshold defaults for the languages we support but you may want to adjust these settings based on your project guidelines.

        The threshold configuration represents the minimum mass a code block must have to be analyzed for duplication. The lower the threshold, the more fine-grained the comparison.

        If the engine is too easily reporting duplication, try raising the threshold. If you suspect that the engine isn't catching enough duplication, try lowering the threshold. The best setting tends to differ from language to language.

        See codeclimate-duplication's documentation for more information about tuning the mass threshold in your .codeclimate.yml.

        Refactorings

        Further Reading

        Avoid too many return statements within this function.
        Open

                        return
        Severity: Major
        Found in data_processing/save_mc4.py - About 30 mins to fix

          Avoid too many return statements within this function.
          Open

                          return
          Severity: Major
          Found in data_processing/save_mc4.py - About 30 mins to fix

            Avoid too many return statements within this function.
            Open

                return processed_comments
            Severity: Major
            Found in data_processing/create_habr.py - About 30 mins to fix

              Similar blocks of code found in 2 locations. Consider refactoring.
              Open

                          elif line.startswith("assistant:"):
                line = line.replace("assistant:", "").lstrip()
                prompt_messages.append({"role": "assistant", "content": line})
              Severity: Minor
              Found in self_instruct/src/data_processing/to_reward_dataset.py and 1 other location - About 30 mins to fix
              self_instruct/src/data_processing/to_reward_dataset.py on lines 46..48

              Duplicated Code

              Duplicated code can lead to software that is hard to understand and difficult to change. The Don't Repeat Yourself (DRY) principle states:

              Every piece of knowledge must have a single, unambiguous, authoritative representation within a system.

              When you violate DRY, bugs and maintenance problems are sure to follow. Duplicated code has a tendency to both continue to replicate and also to diverge (leaving bugs as two similar implementations differ in subtle ways).

              Tuning

              This issue has a mass of 32.

              We set useful threshold defaults for the languages we support but you may want to adjust these settings based on your project guidelines.

              The threshold configuration represents the minimum mass a code block must have to be analyzed for duplication. The lower the threshold, the more fine-grained the comparison.

              If the engine is too easily reporting duplication, try raising the threshold. If you suspect that the engine isn't catching enough duplication, try lowering the threshold. The best setting tends to differ from language to language.

              See codeclimate-duplication's documentation for more information about tuning the mass threshold in your .codeclimate.yml.

              Refactorings

              Further Reading

              Function get_muserc has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def get_muserc(split):
    dataset = load_dataset(HF_DATASET, "muserc", split=split)
    for row in dataset:
        record = {
            "task": "muserc",
              Severity: Minor
              Found in self_instruct/src/data_processing/convert_rsg.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function get_terra has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def get_terra(split):
    dataset = load_dataset(HF_DATASET, "terra", split=split)
    for row in dataset:
        record = {
            "task": "terra",
              Severity: Minor
              Found in self_instruct/src/data_processing/convert_rsg.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function get_lidirus has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def get_lidirus():
    dataset = load_dataset(HF_DATASET, "lidirus", split="test")
    for row in dataset:
        record = {
            "task": "terra",
              Severity: Minor
              Found in self_instruct/src/data_processing/convert_rsg.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function __init__ has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

                  def __init__(
        self,
        original_records: List[Dict],
        tokenizer: AutoTokenizer,
        max_tokens_count: int,
              Severity: Minor
              Found in self_instruct/src/train_reward.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function aggregate has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def aggregate(records, overlap=5, min_agreement=0.0):
    results = defaultdict(list)
    records.sort(key=lambda x: x["assignment_id"])
    for r in records:
        results[get_key(r)].append(r["result"])
              Severity: Minor
              Found in self_instruct/crowd/aggregate.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function get_rucos has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def get_rucos(split, sample_rate: float = 0.05):
    dataset = load_dataset(HF_DATASET, "rucos", split=split)
    for row in dataset:
        if split != "test" and random.random() > sample_rate:
            continue
              Severity: Minor
              Found in self_instruct/src/data_processing/convert_rsg.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function get_danetqa has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def get_danetqa(split):
    dataset = load_dataset(HF_DATASET, "danetqa", split=split)
    for row in dataset:
        record = {
            "task": "parus",
              Severity: Minor
              Found in self_instruct/src/data_processing/convert_rsg.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function sample_record has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

                  def sample_record(self, username, retries=300, max_overlap=3):
        found_new = False
        for _ in range(retries):
            record = sysrand.choice(self.records)
            instruction = record["instruction"]
              Severity: Minor
              Found in self_instruct/src/bot/run_sbs.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function interact has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def interact(
    model_path,
    n_ctx=2000,
    top_k=30,
    top_p=0.9,
              Severity: Minor
              Found in self_instruct/src/interact_mistral_llamacpp.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function interact has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def interact(
    model_path,
    n_ctx=2000,
    top_k=30,
    top_p=0.9,
              Severity: Minor
              Found in self_instruct/src/interact_llamacpp.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function interact has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def interact(
    model_path,
    n_ctx=8192,
    top_k=30,
    top_p=0.9,
              Severity: Minor
              Found in self_instruct/src/interact_llama3_llamacpp.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Function main has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.
              Open

              def main(
    input_path,
    output_path
):
    with open(output_path, "w") as w:
              Severity: Minor
              Found in data_processing/convert_yandex_q.py - About 25 mins to fix

              Cognitive Complexity

              Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.

              A method's cognitive complexity is based on a few simple rules:

              • Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
              • Code is considered more complex for each "break in the linear flow of the code"
              • Code is considered more complex when "flow breaking structures are nested"

              Further reading

              Severity
              Category
              Status
              Source
              Language