dslighting 1.7.1__py3-none-any.whl → 1.7.6__py3-none-any.whl

mlebench/competitions/alaska2-image-steganalysis/prepare.py

@@ -0,0 +1,88 @@
+import random
+import shutil
+from pathlib import Path
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from tqdm import tqdm
+
+
+def prepare(raw: Path, public: Path, private: Path):
+    """
+    Splits the data in raw into public and private datasets with appropriate test/train splits.
+    """
+    # List of all train image IDs
+    cover_images_dir = raw / "Cover"
+    cover_images = sorted(list(cover_images_dir.glob("*.jpg")))
+
+    # Create train, test from train split
+    test_size = 5000
+    new_train, new_test = train_test_split(cover_images, test_size=test_size, random_state=42)
+
+    # Prepare dirs
+    steganography_algs = ["JMiPOD", "JUNIWARD", "UERD"]
+    for subdir in ["Cover", "Test"] + steganography_algs:
+        (public / subdir).mkdir(parents=True, exist_ok=True)
+
+    # Copy over new train set, giving them new ids
+    for idx, fp in tqdm(enumerate(new_train), total=len(new_train), desc="Copying train images"):
+        image_id = idx + 1  # 1-indexed
+        shutil.copyfile(src=fp, dst=public / "Cover" / f"{image_id:05d}.jpg")
+        for alg in steganography_algs:
+            shutil.copyfile(src=raw / alg / fp.name, dst=public / alg / f"{image_id:05d}.jpg")
+
+    # Populate test set
+    answers_rows = []
+    random.seed(0)
+    random.shuffle(new_test)
+    for idx, fp in tqdm(enumerate(new_test), total=len(new_test), desc="Copying test images"):
+        image_id = idx + 1  # 1-indexed
+        test_id = f"{image_id:04d}.jpg"
+        dest = public / "Test" / test_id
+
+        # For the test set, we randomly select between the "Cover" (unedited image, negative class)
+        # and one of the 3 steganography algorithms (positive class)
+        # 1:1 ratio of positive:negative examples, and even distribution of steganography algorithms
+        if random.choice([True, False]):
+            # Negative class
+            shutil.copyfile(
+                src=fp,
+                dst=dest,
+            )
+            answers_rows.append({"Id": test_id, "Label": 0})
+        else:
+            # Positive class
+            alg = random.choice(steganography_algs)
+            shutil.copyfile(src=raw / alg / fp.name, dst=dest)
+            answers_rows.append({"Id": test_id, "Label": 1})
+
+    # Write answers to file
+    answers_df = pd.DataFrame(answers_rows)
+    answers_df.to_csv(private / "test.csv", index=False)
+
+    # Create sample submission
+    sample_submission = answers_df.copy()
+    sample_submission["Label"] = 0
+    sample_submission.to_csv(public / "sample_submission.csv", index=False)
+
+    # Checks
+    assert "Id" in answers_df.columns, "Answers must have 'Id' column"
+    assert "Label" in answers_df.columns, "Answers must have 'Label' column"
+    assert "Id" in sample_submission.columns, "Sample submission must have 'Id' column"
+    assert "Label" in sample_submission.columns, "Sample submission must have 'Label' column"
+    assert (
+        len(answers_df) == test_size
+    ), f"Expected {test_size} test images, but got {len(answers_df)}"
+    assert len(sample_submission) == len(
+        answers_df
+    ), f"Sample submission ({len(sample_submission)}) and answers ({len(answers_df)}) must have the same length"
+    assert (
+        len(list(public.glob("Test/*.jpg"))) == test_size
+    ), f"Expected {test_size} test images in public/Test, but got {len(list(public.glob('Test/*.jpg')))}"
+    assert len(list(public.glob("Cover/*.jpg"))) == len(
+        new_train
+    ), f"Expected {len(new_train)} train images in public/Cover, but got {len(list(public.glob('Cover/*.jpg')))}"
+    for alg in steganography_algs:
+        assert len(list(public.glob(f"{alg}/*.jpg"))) == len(
+            new_train
+        ), f"Expected {len(new_train)} train images in public/{alg}, but got {len(list(public.glob(f'{alg}/*.jpg')))}"

mlebench/competitions/alaska2-image-steganalysis/prepare_val.py

@@ -0,0 +1,148 @@
+import random
+import shutil
+from pathlib import Path
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from tqdm import tqdm
+
+
+def _create_dataset_split(
+    train_image_paths: list,
+    test_image_paths: list,
+    raw_dir: Path,
+    public_dir: Path,
+    private_dir: Path,
+    steganography_algs: list,
+):
+    """
+    Helper function to create a dataset split (e.g., train/test or train_val/test_val).
+
+    This function populates the public and private directories with the respective
+    training images, test images, and test set ground-truth labels.
+    """
+    # Prepare dirs
+    public_dir.mkdir(parents=True, exist_ok=True)
+    private_dir.mkdir(parents=True, exist_ok=True)
+    for subdir in ["Cover", "Test"] + steganography_algs:
+        (public_dir / subdir).mkdir(exist_ok=True)
+
+    # Copy over the train set for this split, giving them new ids
+    for idx, fp in tqdm(
+        enumerate(train_image_paths), total=len(train_image_paths), desc=f"Copying train images to {public_dir.name}"
+    ):
+        image_id = idx + 1  # 1-indexed
+        shutil.copyfile(src=fp, dst=public_dir / "Cover" / f"{image_id:05d}.jpg")
+        for alg in steganography_algs:
+            shutil.copyfile(src=raw_dir / alg / fp.name, dst=public_dir / alg / f"{image_id:05d}.jpg")
+
+    # Populate the test set for this split
+    answers_rows = []
+    random.seed(0)  # Reset seed for deterministic test set creation
+    random.shuffle(test_image_paths)
+    for idx, fp in tqdm(
+        enumerate(test_image_paths), total=len(test_image_paths), desc=f"Copying test images to {public_dir.name}"
+    ):
+        image_id = idx + 1  # 1-indexed
+        test_id = f"{image_id:04d}.jpg"
+        dest = public_dir / "Test" / test_id
+
+        # For the test set, we randomly select between the "Cover" (unedited image, negative class)
+        # and one of the 3 steganography algorithms (positive class)
+        # 1:1 ratio of positive:negative examples, and even distribution of steganography algorithms
+        if random.choice([True, False]):
+            # Negative class
+            shutil.copyfile(
+                src=fp,
+                dst=dest,
+            )
+            answers_rows.append({"Id": test_id, "Label": 0})
+        else:
+            # Positive class
+            alg = random.choice(steganography_algs)
+            shutil.copyfile(src=raw_dir / alg / fp.name, dst=dest)
+            answers_rows.append({"Id": test_id, "Label": 1})
+
+    # Write answers to file
+    answers_df = pd.DataFrame(answers_rows)
+    answers_df.to_csv(private_dir / "test.csv", index=False)
+
+    # Create sample submission
+    sample_submission = answers_df.copy()
+    sample_submission["Label"] = 0
+    sample_submission.to_csv(public_dir / "sample_submission.csv", index=False)
+
+    # Checks
+    test_size = len(test_image_paths)
+    assert "Id" in answers_df.columns, "Answers must have 'Id' column"
+    assert "Label" in answers_df.columns, "Answers must have 'Label' column"
+    assert "Id" in sample_submission.columns, "Sample submission must have 'Id' column"
+    assert "Label" in sample_submission.columns, "Sample submission must have 'Label' column"
+    assert (
+        len(answers_df) == test_size
+    ), f"Expected {test_size} test images, but got {len(answers_df)}"
+    assert len(sample_submission) == len(
+        answers_df
+    ), f"Sample submission ({len(sample_submission)}) and answers ({len(answers_df)}) must have the same length"
+    assert (
+        len(list(public_dir.glob("Test/*.jpg"))) == test_size
+    ), f"Expected {test_size} test images in {public_dir.name}/Test, but got {len(list(public_dir.glob('Test/*.jpg')))}"
+    assert len(list(public_dir.glob("Cover/*.jpg"))) == len(
+        train_image_paths
+    ), f"Expected {len(train_image_paths)} train images in {public_dir.name}/Cover, but got {len(list(public_dir.glob('Cover/*.jpg')))}"
+    for alg in steganography_algs:
+        assert len(list(public_dir.glob(f"{alg}/*.jpg"))) == len(
+            train_image_paths
+        ), f"Expected {len(train_image_paths)} train images in {public_dir.name}/{alg}, but got {len(list(public_dir.glob(f'{alg}/*.jpg')))}"
+
+
+def prepare(raw: Path, public: Path, private: Path):
+    """
+    Splits the data in raw into public and private datasets with appropriate test/train splits.
+    Also creates a secondary validation split (train_val/test_val) in parallel directories.
+    """
+    # List of all train image IDs
+    cover_images_dir = raw / "Cover"
+    cover_images = sorted(list(cover_images_dir.glob("*.jpg")))
+    steganography_algs = ["JMiPOD", "JUNIWARD", "UERD"]
+    test_size = 5000
+
+    # --- Stage 1: Create the main competition train/test split ---
+    # This split creates the final test set used for scoring.
+    # The outputs in `public` and `private` are left untouched by subsequent steps.
+    train_main, test_main = train_test_split(
+        cover_images, test_size=test_size, random_state=42
+    )
+
+    _create_dataset_split(
+        train_image_paths=train_main,
+        test_image_paths=test_main,
+        raw_dir=raw,
+        public_dir=public,
+        private_dir=private,
+        steganography_algs=steganography_algs,
+    )
+
+    # --- Stage 2: Create the validation train/test split ---
+    # This performs a second split on the main training data (`train_main`)
+    # to create a new, smaller training set and a validation set.
+    # Outputs are saved to `public_val` and `private_val` to avoid conflicts.
+    public_val = public.parent / "public_val"
+    private_val = private.parent / "private_val"
+
+    # Split `train_main` again, using the same logic as the first split
+    # to create a validation set of the same size as the main test set.
+    train_val, test_val = train_test_split(
+        train_main, test_size=test_size, random_state=42
+    )
+
+    # The new split is processed using the same helper function to ensure
+    # identical directory structure, filenames, and creation logic.
+    _create_dataset_split(
+        train_image_paths=train_val,
+        test_image_paths=test_val,
+        raw_dir=raw,
+        public_dir=public_val,
+        private_dir=private_val,
+        steganography_algs=steganography_algs,
+    )

mlebench/competitions/aptos2019-blindness-detection/grade.py

@@ -0,0 +1,35 @@
+from pandas import DataFrame
+from sklearn.metrics import cohen_kappa_score
+
+from mlebench.grade_helpers import InvalidSubmissionError
+
+
+def prepare_for_grading(submission: DataFrame, answers: DataFrame, target_column: str) -> tuple:
+
+    if target_column not in submission.columns:
+        raise InvalidSubmissionError(f"Submission must contain the target column '{target_column}'")
+    assert (
+        target_column in answers.columns
+    ), f"Answers must contain the target column '{target_column}'"
+    if submission.empty:
+        raise InvalidSubmissionError("Submission DataFrame should not be empty")
+    assert not answers.empty, "Answers DataFrame should not be empty"
+    if set(submission["id_code"]) != set(answers["id_code"]):
+        raise InvalidSubmissionError("Submission must have the same id_codes as answers")
+
+    # Ensure the submissions and answers are sorted by id_code
+    submission_sorted = submission.sort_values(by="id_code")
+    answers_sorted = answers.sort_values(by="id_code")
+
+    # Extract the target columns
+    y_pred = submission_sorted[target_column].values
+    y_true = answers_sorted[target_column].values
+
+    return y_pred, y_true
+
+
+def grade(submission: DataFrame, answers: DataFrame) -> float:
+    y_pred, y_true = prepare_for_grading(
+        submission=submission, answers=answers, target_column="diagnosis"
+    )
+    return cohen_kappa_score(y_pred, y_true, weights="quadratic")

mlebench/competitions/aptos2019-blindness-detection/prepare.py

@@ -0,0 +1,75 @@
+import shutil
+from pathlib import Path
+
+from sklearn.model_selection import train_test_split
+
+from mlebench.utils import read_csv
+
+
+def prepare(raw: Path, public: Path, private: Path):
+    """
+    Splits the data in raw into public and private datasets with appropriate test/train splits.
+    """
+
+    # Create train, test from train split
+    old_train = read_csv(raw / "train.csv")
+    new_train, new_test = train_test_split(old_train, test_size=0.1, random_state=0)
+    new_test_without_labels = new_test.drop(columns=["diagnosis"])
+
+    (public / "test_images").mkdir(exist_ok=True)
+    (public / "train_images").mkdir(exist_ok=True)
+
+    # Copy data
+    for file_id in new_train["id_code"]:
+        shutil.copyfile(
+            src=raw / "train_images" / f"{file_id}.png",
+            dst=public / "train_images" / f"{file_id}.png",
+        )
+
+    for file_id in new_test_without_labels["id_code"]:
+        shutil.copyfile(
+            src=raw / "train_images" / f"{file_id}.png",
+            dst=public / "test_images" / f"{file_id}.png",
+        )
+
+    # Check integrity of the files copied
+    assert set(new_train["id_code"]).isdisjoint(
+        set(new_test["id_code"])
+    ), "Train and test sets should have no shared ids"
+
+    assert len(new_test_without_labels) == len(
+        new_test
+    ), "Public and Private tests should have equal length"
+
+    assert len(list(public.glob("train_images/*.png"))) == len(
+        new_train
+    ), "Public train images should have the same number of images as the length of train set"
+
+    assert len(list(public.glob("test_images/*.png"))) == len(
+        new_test_without_labels
+    ), "Public test images should have the same number of images as the length of test set"
+
+    train_image_files = set(public.glob("train_images/*.png"))
+    test_image_files = set(public.glob("test_images/*.png"))
+    common_files = train_image_files.intersection(test_image_files)
+    assert not common_files, f"Images found in both train_images and test_images: {common_files}"
+
+    for file_id in new_test["id_code"]:
+        assert (
+            public / "test_images" / f"{file_id}.png"
+        ).exists(), f"Image file for {file_id} not found in test_images"
+
+    for file_id in new_train["id_code"]:
+        assert (
+            public / "train_images" / f"{file_id}.png"
+        ).exists(), f"Image file for {file_id} not found in train_images"
+
+    # Create a sample submission file
+    submission_df = new_test.copy()
+    submission_df["diagnosis"] = 0
+
+    # Write CSVs
+    new_train.to_csv(public / "train.csv", index=False)
+    new_test.to_csv(private / "test.csv", index=False)
+    new_test_without_labels.to_csv(public / "test.csv", index=False)
+    submission_df.to_csv(public / "sample_submission.csv", index=False)

mlebench/competitions/aptos2019-blindness-detection/prepare_val.py

@@ -0,0 +1,123 @@
+import shutil
+from pathlib import Path
+import pandas as pd
+
+from sklearn.model_selection import train_test_split
+
+from mlebench.utils import read_csv
+
+
+def _process_and_save_split(
+    train_df: pd.DataFrame,
+    test_df: pd.DataFrame,
+    source_images_path: Path,
+    public_path: Path,
+    private_path: Path,
+):
+    """
+    A helper function to process a single split. It handles directory creation,
+    file copying, integrity checks, and writing output CSVs.
+    """
+    # Create output directories
+    public_path.mkdir(exist_ok=True, parents=True)
+    private_path.mkdir(exist_ok=True, parents=True)
+    (public_path / "test_images").mkdir(exist_ok=True)
+    (public_path / "train_images").mkdir(exist_ok=True)
+
+    test_df_without_labels = test_df.drop(columns=["diagnosis"])
+
+    # Copy data for the current split
+    for file_id in train_df["id_code"]:
+        shutil.copyfile(
+            src=source_images_path / f"{file_id}.png",
+            dst=public_path / "train_images" / f"{file_id}.png",
+        )
+
+    for file_id in test_df_without_labels["id_code"]:
+        shutil.copyfile(
+            src=source_images_path / f"{file_id}.png",
+            dst=public_path / "test_images" / f"{file_id}.png",
+        )
+
+    # Check integrity of the files copied for the current split
+    assert set(train_df["id_code"]).isdisjoint(
+        set(test_df["id_code"])
+    ), "Train and test sets should have no shared ids"
+
+    assert len(test_df_without_labels) == len(
+        test_df
+    ), "Public and Private tests should have equal length"
+
+    assert len(list(public_path.glob("train_images/*.png"))) == len(
+        train_df
+    ), "Public train images should have the same number of images as the length of train set"
+
+    assert len(list(public_path.glob("test_images/*.png"))) == len(
+        test_df_without_labels
+    ), "Public test images should have the same number of images as the length of test set"
+
+    train_image_files = set(public_path.glob("train_images/*.png"))
+    test_image_files = set(public_path.glob("test_images/*.png"))
+    common_files = train_image_files.intersection(test_image_files)
+    assert not common_files, f"Images found in both train_images and test_images: {common_files}"
+
+    for file_id in test_df["id_code"]:
+        assert (
+            public_path / "test_images" / f"{file_id}.png"
+        ).exists(), f"Image file for {file_id} not found in test_images"
+
+    for file_id in train_df["id_code"]:
+        assert (
+            public_path / "train_images" / f"{file_id}.png"
+        ).exists(), f"Image file for {file_id} not found in train_images"
+
+    # Create a sample submission file
+    submission_df = test_df.copy()
+    submission_df["diagnosis"] = 0
+
+    # Write CSVs for the current split
+    train_df.to_csv(public_path / "train.csv", index=False)
+    test_df.to_csv(private_path / "test.csv", index=False)
+    test_df_without_labels.to_csv(public_path / "test.csv", index=False)
+    submission_df.to_csv(public_path / "sample_submission.csv", index=False)
+
+
+def prepare(raw: Path, public: Path, private: Path):
+    """
+    Splits the data in raw into public and private datasets with appropriate test/train splits.
+    It also creates a secondary validation split in public_val/private_val directories.
+    """
+
+    # --- Stage 1: Create the original train/test split ---
+    # This section remains functionally identical to the original script
+    # to ensure the contents of `public` and `private` are unchanged.
+    old_train = read_csv(raw / "train.csv")
+    new_train, new_test = train_test_split(old_train, test_size=0.1, random_state=0)
+
+    # Process and save the original split using the helper function
+    _process_and_save_split(
+        train_df=new_train,
+        test_df=new_test,
+        source_images_path=raw / "train_images",
+        public_path=public,
+        private_path=private,
+    )
+
+    # --- Stage 2: Create the new train/validation split ---
+    # This split takes the training set from Stage 1 (`new_train`) and splits it again.
+    public_val = public.parent / "public_val"
+    private_val = private.parent / "private_val"
+
+    # The test size is 1/9 of the `new_train` data, which is equivalent to 10% of the
+    # original total data. This makes the new validation set (`test_val`) have the
+    # same size as the original test set (`new_test`).
+    train_val, test_val = train_test_split(new_train, test_size=1 / 9, random_state=0)
+
+    # Process and save the new validation split into the _val directories
+    _process_and_save_split(
+        train_df=train_val,
+        test_df=test_val,
+        source_images_path=raw / "train_images",
+        public_path=public_val,
+        private_path=private_val,
+    )

mlebench/competitions/bike-sharing-demand/grade.py

@@ -0,0 +1,55 @@
+import numpy as np
+import pandas as pd
+from sklearn.metrics import mean_squared_log_error
+
+from mlebench.grade_helpers import InvalidSubmissionError
+
+
+def prepare_for_metric(submission: pd.DataFrame, answers: pd.DataFrame):
+    """Prepare submission and answers for RMSLE calculation."""
+    if len(submission) != len(answers):
+        raise InvalidSubmissionError(
+            f"Submission length ({len(submission)}) != answers length ({len(answers)})"
+        )
+
+    if "datetime" not in submission.columns:
+        raise InvalidSubmissionError("Submission must have a 'datetime' column")
+
+    if "count" not in submission.columns:
+        raise InvalidSubmissionError("Submission must have a 'count' column")
+
+    # Sort by datetime
+    submission = submission.sort_values("datetime").reset_index(drop=True)
+    answers = answers.sort_values("datetime").reset_index(drop=True)
+
+    # Check datetime alignment
+    if not (submission["datetime"] == answers["datetime"]).all():
+        raise InvalidSubmissionError("Submission and answers datetime mismatch")
+
+    # Extract predictions and true values
+    y_pred = submission["count"].values
+    y_true = answers["count"].values
+
+    # Validate predictions
+    try:
+        y_pred = y_pred.astype(float)
+    except (ValueError, TypeError):
+        raise InvalidSubmissionError("Predictions must be numeric")
+
+    if np.any(np.isnan(y_pred)):
+        raise InvalidSubmissionError("Predictions cannot contain NaN values")
+
+    if np.any(y_pred < 0):
+        raise InvalidSubmissionError("Predictions cannot be negative")
+
+    return y_true, y_pred
+
+
+def grade(submission: pd.DataFrame, answers: pd.DataFrame) -> float:
+    """Calculate RMSLE score."""
+    y_true, y_pred = prepare_for_metric(submission, answers)
+
+    # RMSLE = sqrt(MSLE)
+    rmsle = np.sqrt(mean_squared_log_error(y_true, y_pred))
+
+    return rmsle

mlebench/competitions/bike-sharing-demand/prepare.py

@@ -0,0 +1,37 @@
+from pathlib import Path
+import pandas as pd
+
+
+def prepare(raw: Path, public: Path, private: Path):
+    """
+    Prepare bike-sharing-demand dataset.
+
+    Raw data already contains:
+    - train.csv: training data with labels
+    - test.csv: test data without labels
+    - sampleSubmission.csv: sample submission format
+    - test_answer.csv: test labels (private)
+    """
+    # Read data
+    train = pd.read_csv(raw / "train.csv")
+    test = pd.read_csv(raw / "test.csv")
+    sample_submission = pd.read_csv(raw / "sampleSubmission.csv")
+    test_answer = pd.read_csv(raw / "test_answer.csv")
+
+    # Public files (visible to agents)
+    train.to_csv(public / "train.csv", index=False)
+    test.to_csv(public / "test.csv", index=False)
+    sample_submission.to_csv(public / "sampleSubmission.csv", index=False)
+
+    # Private files (for grading)
+    test_answer.to_csv(private / "test.csv", index=False)
+
+    # Validation checks
+    assert len(test_answer) == len(test), \
+        f"Test answer ({len(test_answer)}) and test ({len(test)}) must have same length"
+    assert len(sample_submission) == len(test), \
+        f"Sample submission ({len(sample_submission)}) and test ({len(test)}) must have same length"
+    assert "datetime" in test_answer.columns, "Test answer must have 'datetime' column"
+    assert "count" in test_answer.columns, "Test answer must have 'count' column"
+    assert "datetime" in sample_submission.columns, "Sample submission must have 'datetime' column"
+    assert "count" in sample_submission.columns, "Sample submission must have 'count' column"

mlebench/competitions/billion-word-imputation/grade.py

@@ -0,0 +1,37 @@
+import numpy as np
+import pandas as pd
+from Levenshtein import distance
+
+from mlebench.grade_helpers import InvalidSubmissionError
+
+
+def prepare_for_metric(submission: pd.DataFrame, answers: pd.DataFrame) -> None:
+    id_col = "id"
+    target_col = "sentence"
+
+    assert id_col in answers.columns, f"Missing {id_col} column in answers"
+    assert target_col in answers.columns, f"Missing {target_col} column in answers"
+
+    if id_col not in submission.columns:
+        raise InvalidSubmissionError(f"Missing {id_col} column in submission")
+    if target_col not in submission.columns:
+        raise InvalidSubmissionError(f"Missing {target_col} column in submission")
+
+    if len(submission) != len(answers):
+        raise InvalidSubmissionError(
+            f"Submission and answers have different lengths: {len(submission)} vs {len(answers)}"
+        )
+
+    submission = submission.sort_values(id_col).reset_index(drop=True)
+    answers = answers.sort_values(id_col).reset_index(drop=True)
+
+    if (submission[id_col].values != answers[id_col].values).any():
+        raise InvalidSubmissionError("Submission and answers should contain the same IDs")
+
+    return submission[target_col], answers[target_col]
+
+
+def grade(submission: pd.DataFrame, answers: pd.DataFrame) -> float:
+    y_pred, y_true = prepare_for_metric(submission, answers)
+    mean_levenshtein = np.mean([distance(a, b) for a, b in zip(y_true, y_pred)])
+    return mean_levenshtein