additory 0.1.0a3__py3-none-any.whl → 0.1.1a1__py3-none-any.whl

additory/synthetic/strategies.py

@@ -1,850 +0,0 @@
-"""
-Strategy handlers for synthetic data generation
-
-Provides different strategies for generating synthetic data:
-- auto: Random sampling from existing values
-- increment: Increment numeric or pattern-based values
-- choice:[...]: Random selection from inline list
-"""
-
-import re
-import random
-from typing import Any, Dict, List, Optional, Tuple
-
-from additory.common.exceptions import ValidationError, AugmentError
-
-
-def parse_strategy_params(strategy_spec: str) -> Tuple[str, Dict[str, Any]]:
-    """
-    Parse strategy specification with inline parameters.
-    
-    Supports two formats:
-    1. key=value format: "increment:start=100:pattern=EMP_[001]"
-    2. range format: "range:18-65"
-    
-    Args:
-        strategy_spec: Strategy string with optional parameters
-    
-    Returns:
-        Tuple of (strategy_name, params_dict)
-        - strategy_name: Base strategy name (e.g., "increment", "range")
-        - params_dict: Dictionary of parsed parameters
-    
-    Raises:
-        ValidationError: If parameter format is invalid
-    
-    Examples:
-        >>> parse_strategy_params("increment")
-        ("increment", {})
-        
-        >>> parse_strategy_params("increment:start=100")
-        ("increment", {"start": 100})
-        
-        >>> parse_strategy_params("increment:start=100:pattern=EMP_[001]")
-        ("increment", {"start": 100, "pattern": "EMP_[001]"})
-        
-        >>> parse_strategy_params("range:18-65")
-        ("range", {"min": 18, "max": 65})
-    """
-    if not strategy_spec or not strategy_spec.strip():
-        raise ValidationError("Empty strategy specification")
-    
-    parts = strategy_spec.split(":")
-    
-    strategy_name = parts[0].strip()
-    
-    if not strategy_name:
-        raise ValidationError("Empty strategy name")
-    
-    if len(parts) == 1:
-        # No parameters
-        return strategy_name, {}
-    
-    # Special case: range format "range:18-65"
-    if strategy_name == "range" and len(parts) == 2:
-        range_part = parts[1].strip()
-        
-        # Check if it's the min-max format (no = sign)
-        if "=" not in range_part:
-            if "-" not in range_part:
-                raise ValidationError(
-                    f"Invalid range format: {range_part}. "
-                    "Expected format: range:min-max (e.g., range:18-65)"
-                )
-            
-            # Split by dash, handling negative numbers
-            # Use regex to properly split on dash
-            match = re.match(r'^(-?\d+)-(-?\d+)$', range_part)
-            if match:
-                try:
-                    min_val = int(match.group(1))
-                    max_val = int(match.group(2))
-                    return strategy_name, {"min": min_val, "max": max_val}
-                except ValueError:
-                    raise ValidationError(
-                        f"Invalid range format: {range_part}. "
-                        "Expected format: range:min-max (e.g., range:18-65)"
-                    )
-            else:
-                raise ValidationError(
-                    f"Invalid range format: {range_part}. "
-                    "Expected format: range:min-max (e.g., range:18-65)"
-                )
-    
-    # Parse key=value parameters
-    params = {}
-    
-    for i in range(1, len(parts)):
-        param_part = parts[i].strip()
-        
-        if "=" not in param_part:
-            raise ValidationError(
-                f"Invalid parameter format: '{param_part}'. "
-                "Expected format: key=value (e.g., start=100)"
-            )
-        
-        key, value = param_part.split("=", 1)
-        key = key.strip()
-        value = value.strip()
-        
-        if not key:
-            raise ValidationError(
-                f"Empty parameter key in: '{param_part}'"
-            )
-        
-        if not value:
-            raise ValidationError(
-                f"Empty parameter value for key '{key}'"
-            )
-        
-        # Try to convert numeric strings to integers
-        try:
-            # Check if it's a valid integer
-            if value.lstrip('-').isdigit():
-                params[key] = int(value)
-            else:
-                # Keep as string
-                params[key] = value
-        except ValueError:
-            # Keep as string if conversion fails
-            params[key] = value
-    
-    return strategy_name, params
-
-
-def parse_increment_strategy(strategy_spec: str) -> Tuple[Optional[str], Optional[str]]:
-    """
-    Parse increment strategy specification.
-    
-    Args:
-        strategy_spec: Strategy string like:
-            - "increment"
-            - "increment:EMP_[001]_ID"
-            - r"increment:A(\\d+)"
-    
-    Returns:
-        Tuple of (pattern, regex_pattern)
-        - pattern: Original pattern string (for bracket notation)
-        - regex_pattern: Compiled regex pattern (for extraction)
-    
-    Examples:
-        >>> parse_increment_strategy("increment")
-        (None, None)
-        
-        >>> parse_increment_strategy("increment:EMP_[001]_ID")
-        ("EMP_[001]_ID", r"EMP_(\\d{3})_ID")
-        
-        >>> parse_increment_strategy(r"increment:A(\\d+)")
-        (None, r"A(\\d+)")
-    """
-    parts = strategy_spec.split(":", 1)
-    
-    if len(parts) == 1:
-        # Simple "increment" with no pattern
-        return None, None
-    
-    pattern_str = parts[1].strip()
-    
-    # Check if it's bracket notation: EMP_[001]_ID
-    if "[" in pattern_str and "]" in pattern_str:
-        # Extract the bracketed part
-        bracket_match = re.search(r'\[(\d+)\]', pattern_str)
-        if not bracket_match:
-            raise ValidationError(
-                f"Invalid bracket pattern: {pattern_str}. "
-                "Brackets must contain digits, e.g., [001] or [123]"
-            )
-        
-        # Get the number inside brackets to determine padding
-        number_str = bracket_match.group(1)
-        padding = len(number_str)
-        
-        # Convert bracket notation to regex
-        # EMP_[001]_ID -> EMP_(\d{3})_ID
-        regex_pattern = pattern_str.replace(f"[{number_str}]", f"(\\d{{{padding}}})")
-        
-        return pattern_str, regex_pattern
-    
-    # Otherwise, assume it's already a regex pattern
-    # Validate that it has a capture group
-    if "(" not in pattern_str or ")" not in pattern_str:
-        raise ValidationError(
-            f"Invalid pattern: {pattern_str}. "
-            "Pattern must either use bracket notation [001] or regex with capture group (\\d+)"
-        )
-    
-    return None, pattern_str
-
-
-def validate_increment_column(
-    last_value: Any,
-    pattern: Optional[str],
-    regex_pattern: Optional[str]
-) -> Tuple[int, Optional[str], Optional[int]]:
-    """
-    Validate that a column can be incremented and extract current value.
-    
-    Args:
-        last_value: Last value in the column
-        pattern: Pattern string (if using bracket notation)
-        regex_pattern: Regex pattern (if provided)
-    
-    Returns:
-        Tuple of (current_number, prefix_suffix_template, padding)
-        - current_number: The numeric value to increment from
-        - prefix_suffix_template: Template for reconstruction (e.g., "EMP_{}_ID")
-        - padding: Number of digits for zero-padding (or None)
-    
-    Raises:
-        ValidationError: If column cannot be incremented
-    """
-    last_value_str = str(last_value)
-    
-    # Case 1: Pure numeric value
-    if regex_pattern is None and pattern is None:
-        try:
-            current_number = int(last_value)
-            return current_number, None, None
-        except (ValueError, TypeError):
-            raise ValidationError(
-                f"Column has non-numeric last value '{last_value}'. "
-                "For non-numeric columns, you must provide a pattern. "
-                "Examples: 'increment:EMP_[001]_ID' or 'increment:A(\\d+)'"
-            )
-    
-    # Case 2: Pattern-based value
-    if regex_pattern is None:
-        raise ValidationError("Pattern parsing failed - this should not happen")
-    
-    # Try to match the pattern
-    match = re.search(regex_pattern, last_value_str)
-    if not match:
-        raise ValidationError(
-            f"Pattern '{pattern or regex_pattern}' does not match last value '{last_value}'. "
-            "Please verify the pattern matches your data."
-        )
-    
-    # Extract the numeric part
-    try:
-        number_str = match.group(1)
-        current_number = int(number_str)
-        padding = len(number_str) if number_str.startswith('0') else None
-    except (ValueError, IndexError):
-        raise ValidationError(
-            f"Could not extract numeric value from '{last_value}' using pattern '{pattern or regex_pattern}'"
-        )
-    
-    # Create template for reconstruction
-    # Replace the captured group with {} placeholder
-    template = re.sub(r'\([^)]+\)', '{}', regex_pattern)
-    # Remove regex special characters for simple replacement
-    template = template.replace('\\d', '').replace('{', '').replace('}', '')
-    
-    # Better approach: use the actual matched string positions
-    start, end = match.span(1)
-    template = last_value_str[:start] + '{}' + last_value_str[end:]
-    
-    return current_number, template, padding
-
-
-def generate_increment_values(
-    start_number: int,
-    count: int,
-    template: Optional[str],
-    padding: Optional[int]
-) -> List[Any]:
-    """
-    Generate incremented values.
-    
-    Args:
-        start_number: Starting number (last value + 1)
-        count: Number of values to generate
-        template: Template for reconstruction (e.g., "EMP_{}_ID")
-        padding: Number of digits for zero-padding
-    
-    Returns:
-        List of generated values
-    """
-    values = []
-    
-    for i in range(count):
-        new_number = start_number + i
-        
-        if template is None:
-            # Pure numeric
-            values.append(new_number)
-        else:
-            # Pattern-based
-            if padding:
-                number_str = str(new_number).zfill(padding)
-            else:
-                number_str = str(new_number)
-            
-            new_value = template.format(number_str)
-            values.append(new_value)
-    
-    return values
-
-
-def apply_increment_strategy(
-    df_polars: Any,
-    column: str,
-    strategy_spec: str,
-    n_rows: int,
-    params: Optional[Dict[str, Any]] = None
-) -> List[Any]:
-    """
-    Apply increment strategy to a column (Polars-only).
-    
-    Supports two modes:
-    1. Extend mode: Increment from last value in df_polars
-    2. Create mode: Start from specified value (requires params with 'start')
-    
-    Args:
-        df_polars: Input Polars DataFrame (None in create mode)
-        column: Column name to increment
-        strategy_spec: Strategy specification (e.g., "increment:EMP_[001]_ID")
-        n_rows: Number of new values to generate
-        params: Optional parameters dict with 'start' and/or 'pattern' keys
-    
-    Returns:
-        List of new values for the column
-    
-    Raises:
-        ValidationError: If strategy cannot be applied
-    
-    Examples:
-        # Extend mode (with DataFrame)
-        >>> apply_increment_strategy(df, "id", "increment", 5)
-        [11, 12, 13, 14, 15]  # if last value was 10
-        
-        # Create mode (no DataFrame, with start parameter)
-        >>> apply_increment_strategy(None, "id", "increment", 5, {"start": 100})
-        [100, 101, 102, 103, 104]
-        
-        # Create mode with pattern
-        >>> apply_increment_strategy(None, "emp_id", "increment", 3, 
-        ...                          {"start": 1, "pattern": "EMP_[001]"})
-        ["EMP_001", "EMP_002", "EMP_003"]
-    """
-    # Determine mode: extend (has df) or create (no df)
-    is_create_mode = df_polars is None
-    
-    if is_create_mode:
-        # Create mode: use start parameter
-        if params is None or "start" not in params:
-            raise ValidationError(
-                f"Increment strategy in create mode requires 'start' parameter. "
-                f"Use format: 'increment:start=N' or 'increment:start=N:pattern=P'"
-            )
-        
-        start_number = params["start"]
-        
-        # Check if pattern is provided in params
-        if "pattern" in params:
-            pattern_str = params["pattern"]
-            
-            # Parse the pattern to get template and padding
-            if "[" in pattern_str and "]" in pattern_str:
-                # Bracket notation: EMP_[001]
-                bracket_match = re.search(r'\[(\d+)\]', pattern_str)
-                if not bracket_match:
-                    raise ValidationError(
-                        f"Invalid bracket pattern: {pattern_str}. "
-                        "Brackets must contain digits, e.g., [001] or [123]"
-                    )
-                
-                number_str = bracket_match.group(1)
-                padding = len(number_str)
-                
-                # Create template by replacing [NNN] with {}
-                template = pattern_str.replace(f"[{number_str}]", "{}")
-            else:
-                raise ValidationError(
-                    f"Invalid pattern: {pattern_str}. "
-                    "Pattern must use bracket notation [001]"
-                )
-        else:
-            # No pattern, pure numeric
-            template = None
-            padding = None
-        
-        # Generate values starting from start_number
-        new_values = generate_increment_values(
-            start_number=start_number,
-            count=n_rows,
-            template=template,
-            padding=padding
-        )
-        
-        return new_values
-    
-    else:
-        # Extend mode: use existing logic
-        # Parse the strategy
-        pattern, regex_pattern = parse_increment_strategy(strategy_spec)
-        
-        # Get last value from the Polars column
-        last_value = df_polars[column][-1]
-        
-        # Validate and extract current value
-        current_number, template, padding = validate_increment_column(
-            last_value, pattern, regex_pattern
-        )
-        
-        # Generate new values starting from current + 1
-        new_values = generate_increment_values(
-            start_number=current_number + 1,
-            count=n_rows,
-            template=template,
-            padding=padding
-        )
-        
-        return new_values
-
-
-def parse_strategy_dict(strategy: Any) -> Dict[str, str]:
-    """
-    Parse and validate strategy parameter.
-    
-    Args:
-        strategy: Strategy specification, can be:
-            - str: "auto" (default for all columns)
-            - dict: {"col1": "increment", "col2": "auto", ...}
-    
-    Returns:
-        Dictionary mapping column names to strategy specs
-    
-    Raises:
-        ValidationError: If strategy format is invalid
-    """
-    if isinstance(strategy, str):
-        # Simple string strategy applies to all columns
-        return {"__default__": strategy}
-    
-    if isinstance(strategy, dict):
-        # Validate all strategy values are strings
-        for col, strat in strategy.items():
-            if not isinstance(strat, str):
-                raise ValidationError(
-                    f"Strategy for column '{col}' must be a string, got {type(strat)}"
-                )
-        return strategy
-    
-    raise ValidationError(
-        f"Strategy must be str or dict, got {type(strategy)}"
-    )
-
-
-def get_column_strategy(column: str, strategy_dict: Dict[str, str]) -> str:
-    """
-    Get strategy for a specific column.
-    
-    Args:
-        column: Column name
-        strategy_dict: Parsed strategy dictionary
-    
-    Returns:
-        Strategy string for the column (defaults to "auto")
-    """
-    if column in strategy_dict:
-        return strategy_dict[column]
-    
-    # Return default strategy
-    return strategy_dict.get("__default__", "auto")
-
-
-def parse_choice_strategy(strategy_spec: str) -> Tuple[str, Optional[List[Any]]]:
-    """
-    Parse choice strategy specification.
-    
-    Args:
-        strategy_spec: Strategy string like:
-            - "choice:[value1,value2,value3]"
-    
-    Returns:
-        Tuple of (strategy_type, values)
-        - strategy_type: "choice"
-        - values: List of values
-    
-    Raises:
-        ValidationError: If strategy format is invalid
-    
-    Examples:
-        >>> parse_choice_strategy("choice:[Active,Inactive,Pending]")
-        ("choice", ["Active", "Inactive", "Pending"])
-    """
-    if strategy_spec.startswith("choice:["):
-        # Inline list: choice:[value1,value2,value3]
-        if not strategy_spec.endswith("]"):
-            raise ValidationError(
-                f"Invalid choice strategy: {strategy_spec}. "
-                "Must be in format: choice:[value1,value2,value3]"
-            )
-        
-        # Extract values between [ and ]
-        values_str = strategy_spec[len("choice:["):-1]
-        
-        if not values_str.strip():
-            raise ValidationError(
-                f"Choice list cannot be empty: {strategy_spec}"
-            )
-        
-        # Split by comma and strip whitespace
-        values = [v.strip() for v in values_str.split(",")]
-        
-        if len(values) == 0:
-            raise ValidationError(
-                f"Choice list must contain at least one value: {strategy_spec}"
-            )
-        
-        return "choice", values
-    
-    else:
-        raise ValidationError(
-            f"Invalid choice strategy: {strategy_spec}. "
-            "Must start with 'choice:['"
-        )
-
-
-def apply_range_strategy(
-    min_val: int,
-    max_val: int,
-    n_rows: int,
-    seed: Optional[int]
-) -> List[int]:
-    """
-    Apply range strategy to generate random integers within a range.
-    
-    Args:
-        min_val: Minimum value (inclusive)
-        max_val: Maximum value (inclusive)
-        n_rows: Number of values to generate
-        seed: Random seed for reproducibility
-    
-    Returns:
-        List of random integers within the specified range
-    
-    Raises:
-        ValidationError: If min_val >= max_val
-    
-    Examples:
-        >>> apply_range_strategy(18, 65, 5, seed=42)
-        [34, 52, 23, 61, 38]
-        
-        >>> apply_range_strategy(40000, 120000, 3, seed=42)
-        [75000, 110000, 45000]
-    """
-    # Validate range
-    if min_val >= max_val:
-        raise ValidationError(
-            f"Invalid range: min ({min_val}) must be less than max ({max_val})"
-        )
-    
-    # Set seed for reproducibility
-    if seed is not None:
-        random.seed(seed)
-    
-    # Generate random integers within range (inclusive)
-    values = [random.randint(min_val, max_val) for _ in range(n_rows)]
-    
-    return values
-
-
-def apply_choice_strategy(
-    strategy_spec: str,
-    n_rows: int,
-    seed: Optional[int]
-) -> List[Any]:
-    """
-    Apply choice strategy to generate values.
-    
-    Args:
-        strategy_spec: Strategy specification (e.g., "choice:[A,B,C]")
-        n_rows: Number of values to generate
-        seed: Random seed for reproducibility
-    
-    Returns:
-        List of randomly selected values
-    
-    Raises:
-        ValidationError: If strategy cannot be applied
-    """
-    # Parse the strategy
-    strategy_type, values = parse_choice_strategy(strategy_spec)
-    
-    # Generate random selections
-    if seed is not None:
-        # Use Python's random for consistency across backends
-        random.seed(seed)
-    
-    selected_values = random.choices(values, k=n_rows)
-    
-    return selected_values
-
-
-
-def apply_forecast_strategy(
-    df_polars: Any,
-    column: str,
-    strategy_spec: str,
-    n_rows: int,
-    seed: Optional[int] = None
-) -> List[Any]:
-    """
-    Apply forecast strategy to a column.
-    
-    Supports:
-    - forecast:linear
-    - forecast:polynomial
-    - forecast:exponential
-    - forecast:moving_average
-    - forecast:seasonal
-    - forecast:auto
-    
-    Args:
-        df_polars: Input Polars DataFrame
-        column: Column name to forecast
-        strategy_spec: Strategy specification (e.g., "forecast:seasonal:period=12")
-        n_rows: Number of values to forecast
-        seed: Random seed (not used for deterministic forecasts)
-    
-    Returns:
-        List of forecasted values
-    
-    Raises:
-        ValidationError: If strategy cannot be applied
-    
-    Examples:
-        >>> apply_forecast_strategy(df, "sales", "forecast:linear", 10)
-        [105.2, 110.4, 115.6, ...]
-        
-        >>> apply_forecast_strategy(df, "sales", "forecast:seasonal:period=12", 24)
-        [98.5, 102.3, 95.8, ...]
-    """
-    from additory.synthetic.forecast import forecast_values, ForecastMethod
-    
-    # Parse strategy: forecast:method:param1=val1:param2=val2
-    parts = strategy_spec.split(":")
-    
-    if len(parts) < 2:
-        raise ValidationError(
-            f"Invalid forecast strategy: {strategy_spec}. "
-            "Expected format: forecast:method or forecast:method:param=value"
-        )
-    
-    # parts[0] is "forecast", parts[1] is method
-    method = parts[1].strip()
-    
-    # Parse additional parameters
-    params = {}
-    for i in range(2, len(parts)):
-        param_part = parts[i].strip()
-        
-        if "=" in param_part:
-            key, value = param_part.split("=", 1)
-            key = key.strip()
-            value = value.strip()
-            
-            # Try to convert to int/float
-            try:
-                if "." in value:
-                    params[key] = float(value)
-                else:
-                    params[key] = int(value)
-            except ValueError:
-                params[key] = value
-    
-    # Call forecast function
-    try:
-        return forecast_values(
-            df_polars,
-            column,
-            n_rows,
-            method=method,
-            **params
-        )
-    except Exception as e:
-        raise ValidationError(f"Forecast strategy failed: {e}")
-
-
-def apply_distribution_strategy(
-    df_polars: Any,
-    column: str,
-    strategy_spec: str,
-    n_rows: int,
-    seed: Optional[int] = None
-) -> List[Any]:
-    """
-    Apply distribution strategy to a column.
-    
-    Supports:
-    - normal (or normal:auto)
-    - normal:mean=X:std=Y
-    - uniform:min=X:max=Y
-    - skewed_left:skewness=X
-    - skewed_right:skewness=X
-    
-    Args:
-        df_polars: Input Polars DataFrame (for parameter estimation)
-        column: Column name to generate from
-        strategy_spec: Strategy specification (e.g., "normal:auto")
-        n_rows: Number of values to generate
-        seed: Random seed for reproducibility
-    
-    Returns:
-        List of generated values
-    
-    Raises:
-        ValidationError: If strategy cannot be applied
-    
-    Examples:
-        >>> apply_distribution_strategy(df, "age", "normal:auto", 100, seed=42)
-        [34.5, 28.9, 41.2, ...]
-        
-        >>> apply_distribution_strategy(df, "score", "uniform:min=0:max=100", 50)
-        [45.2, 78.9, 12.3, ...]
-    """
-    from additory.common.distributions import generate_distribution_values
-    
-    # Parse strategy: distribution:param1=val1:param2=val2
-    parts = strategy_spec.split(":")
-    
-    if len(parts) < 1:
-        raise ValidationError(f"Invalid distribution strategy: {strategy_spec}")
-    
-    distribution = parts[0].strip()
-    
-    # Parse additional parameters
-    params = {}
-    auto_mode = False
-    
-    for i in range(1, len(parts)):
-        param_part = parts[i].strip()
-        
-        if param_part == "auto":
-            # Special case: normal:auto
-            auto_mode = True
-            continue
-        
-        if "=" in param_part:
-            key, value = param_part.split("=", 1)
-            key = key.strip()
-            value = value.strip()
-            
-            # Try to convert to int/float
-            try:
-                if "." in value:
-                    params[key] = float(value)
-                else:
-                    params[key] = int(value)
-            except ValueError:
-                params[key] = value
-    
-    # Get existing data for parameter estimation
-    data = df_polars[column].to_numpy()
-    
-    # Determine distribution type
-    if auto_mode:
-        dist_type = 'auto'
-    else:
-        dist_type = distribution
-    
-    # Call distribution function
-    try:
-        return generate_distribution_values(
-            n_rows,
-            distribution=dist_type,
-            data=data,
-            seed=seed,
-            **params
-        )
-    except Exception as e:
-        raise ValidationError(f"Distribution strategy failed: {e}")
-
-
-def apply_smote_strategy(
-    df_polars: Any,
-    columns: List[str],
-    strategy_spec: str,
-    n_rows: int,
-    seed: Optional[int] = None
-) -> Dict[str, List[Any]]:
-    """
-    Apply SMOTE strategy to multiple columns.
-    
-    SMOTE generates synthetic samples using k-nearest neighbors.
-    
-    Args:
-        df_polars: Input Polars DataFrame
-        columns: List of column names to use for SMOTE
-        strategy_spec: Strategy specification (e.g., "smote:k=5")
-        n_rows: Number of synthetic samples to generate
-        seed: Random seed for reproducibility
-    
-    Returns:
-        Dictionary mapping column names to generated values
-    
-    Raises:
-        ValidationError: If strategy cannot be applied
-    
-    Examples:
-        >>> apply_smote_strategy(df, ["feature1", "feature2"], "smote:k=5", 100)
-        {"feature1": [1.2, 3.4, ...], "feature2": [5.6, 7.8, ...]}
-    """
-    from additory.synthetic.smote import generate_smote_values
-    
-    # Parse strategy: smote:k=5
-    parts = strategy_spec.split(":")
-    
-    # Parse parameters
-    params = {}
-    for i in range(1, len(parts)):
-        param_part = parts[i].strip()
-        
-        if "=" in param_part:
-            key, value = param_part.split("=", 1)
-            key = key.strip()
-            value = value.strip()
-            
-            # Convert k to k_neighbors
-            if key == "k":
-                key = "k_neighbors"
-            
-            # Try to convert to int
-            try:
-                params[key] = int(value)
-            except ValueError:
-                params[key] = value
-    
-    # Call SMOTE function
-    try:
-        return generate_smote_values(
-            df_polars,
-            columns,
-            n_rows,
-            seed=seed,
-            **params
-        )
-    except Exception as e:
-        raise ValidationError(f"SMOTE strategy failed: {e}")