Skip to content

transform_rule

Transform rule model for reusable feature transformations.

Defines TransformRule - a reusable transformation that can be created from natural language descriptions and applied across different datasets.

TransformRule

Bases: BaseModel

A reusable feature transformation rule.

Transform rules capture feature engineering logic that can be generated from natural language descriptions and reused across different datasets.

Parameters:

Name Type Description Default
id str

Unique identifier for the rule

 required
name str

Human-readable name for the rule

 required
description str

Natural language description of what the rule does

 required
code str

Python code that implements the transformation

 required
input_columns list[str]

Column names or patterns this rule expects as input

 required
output_name str

Name for the output feature (default: derived from rule name)

 required
output_type str

Expected output data type ('numeric', 'categorical', 'boolean')

 required
tags list[str]

Tags for categorization and search

 required
column_patterns list[str]

Regex patterns for matching columns (e.g., 'price.', '._amount')

 required
usage_count int

Number of times this rule has been applied

 required
created_at str

ISO timestamp of rule creation

 required
metadata dict

Additional metadata

 required

Examples:

>>> rule = TransformRule(
...     name="ratio_calculation",
...     description="Calculate ratio of two numeric columns",
...     code="result = df['{col1}'] / (df['{col2}'] + 1e-8)",
...     input_columns=["col1", "col2"],
...     tags=["ratio", "numeric"]
... )
>>> result = rule.apply(df, column_mapping={"col1": "price", "col2": "quantity"})
Source code in featcopilot/core/transform_rule.py 
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
class TransformRule(BaseModel):
    """
    A reusable feature transformation rule.

    Transform rules capture feature engineering logic that can be generated
    from natural language descriptions and reused across different datasets.

    Parameters
    ----------
    id : str, optional
        Unique identifier for the rule
    name : str
        Human-readable name for the rule
    description : str
        Natural language description of what the rule does
    code : str
        Python code that implements the transformation
    input_columns : list[str]
        Column names or patterns this rule expects as input
    output_name : str, optional
        Name for the output feature (default: derived from rule name)
    output_type : str
        Expected output data type ('numeric', 'categorical', 'boolean')
    tags : list[str]
        Tags for categorization and search
    column_patterns : list[str]
        Regex patterns for matching columns (e.g., 'price.*', '.*_amount')
    usage_count : int
        Number of times this rule has been applied
    created_at : str
        ISO timestamp of rule creation
    metadata : dict
        Additional metadata

    Examples
    --------
    >>> rule = TransformRule(
    ...     name="ratio_calculation",
    ...     description="Calculate ratio of two numeric columns",
    ...     code="result = df['{col1}'] / (df['{col2}'] + 1e-8)",
    ...     input_columns=["col1", "col2"],
    ...     tags=["ratio", "numeric"]
    ... )
    >>> result = rule.apply(df, column_mapping={"col1": "price", "col2": "quantity"})
    """

    id: str = Field(default_factory=lambda: str(uuid.uuid4())[:8], description="Unique rule identifier")
    name: str = Field(description="Human-readable rule name")
    description: str = Field(description="Natural language description of the transformation")
    code: str = Field(description="Python code implementing the transformation")
    input_columns: list[str] = Field(default_factory=list, description="Expected input column names or placeholders")
    output_name: Optional[str] = Field(default=None, description="Output feature name")
    output_type: str = Field(default="numeric", description="Output data type")
    tags: list[str] = Field(default_factory=list, description="Tags for categorization")
    column_patterns: list[str] = Field(default_factory=list, description="Regex patterns for column matching")
    usage_count: int = Field(default=0, description="Number of times applied")
    created_at: str = Field(
        default_factory=lambda: datetime.now(timezone.utc).isoformat(), description="Creation timestamp"
    )
    metadata: dict[str, Any] = Field(default_factory=dict, description="Additional metadata")

    def get_output_name(self, column_mapping: Optional[dict[str, str]] = None) -> str:
        """
        Get the output feature name.

        Parameters
        ----------
        column_mapping : dict, optional
            Mapping from placeholder columns to actual column names

        Returns
        -------
        str
            Output feature name
        """
        if self.output_name:
            return self.output_name

        # Generate name from input columns
        if column_mapping and self.input_columns:
            cols = [column_mapping.get(c, c) for c in self.input_columns[:2]]
            return f"{'_'.join(cols)}_{self.name}"

        return f"rule_{self.name}"

    def matches_columns(self, columns: list[str]) -> tuple[bool, dict[str, str]]:
        """
        Check if this rule can be applied to the given columns.

        Parameters
        ----------
        columns : list[str]
            Available column names

        Returns
        -------
        matches : bool
            Whether the rule can be applied
        mapping : dict
            Suggested mapping from rule's input_columns to actual columns
        """
        if not self.input_columns:
            return True, {}

        mapping = {}

        for input_col in self.input_columns:
            # Try exact match first
            if input_col in columns:
                mapping[input_col] = input_col
                continue

            # Try pattern matching
            matched = False
            for pattern in self.column_patterns:
                regex = re.compile(pattern, re.IGNORECASE)
                for col in columns:
                    if regex.match(col) and col not in mapping.values():
                        mapping[input_col] = col
                        matched = True
                        break
                if matched:
                    break

            # Try fuzzy matching by checking if input_col is substring
            if not matched:
                for col in columns:
                    if input_col.lower() in col.lower() and col not in mapping.values():
                        mapping[input_col] = col
                        matched = True
                        break

            if not matched:
                return False, {}

        return len(mapping) == len(self.input_columns), mapping

    def apply(
        self,
        df: pd.DataFrame,
        column_mapping: Optional[dict[str, str]] = None,
        validate: bool = True,
    ) -> pd.Series:
        """
        Apply the transformation rule to a DataFrame.

        Parameters
        ----------
        df : DataFrame
            Input data
        column_mapping : dict, optional
            Mapping from rule's input_columns to actual column names
        validate : bool, default=True
            Whether to validate before execution

        Returns
        -------
        Series
            Transformed feature values

        Raises
        ------
        ValueError
            If required columns are missing or code execution fails
        """
        column_mapping = column_mapping or {}

        # Prepare the code with actual column names
        code = self._prepare_code(column_mapping)

        if validate:
            # Check required columns exist
            for input_col in self.input_columns:
                actual_col = column_mapping.get(input_col, input_col)
                if actual_col not in df.columns:
                    raise ValueError(f"Required column '{actual_col}' not found in DataFrame")

        # Execute the code in a restricted environment
        local_vars: dict[str, Any] = {"df": df, "np": np, "pd": pd}
        try:
            exec(self._get_safe_code(code), {"__builtins__": self._get_safe_builtins()}, local_vars)

            if "result" not in local_vars:
                raise ValueError("Code did not produce a 'result' variable")

            result = local_vars["result"]

            # Increment usage count
            self.usage_count += 1

            return result

        except Exception as e:
            logger.error(f"Failed to apply rule '{self.name}': {e}")
            raise ValueError(f"Rule execution failed: {e}") from e

    def _prepare_code(self, column_mapping: dict[str, str]) -> str:
        """Substitute column placeholders with actual column names."""
        code = self.code

        # Replace {col} style placeholders
        for placeholder, actual in column_mapping.items():
            code = code.replace(f"{{{{ '{placeholder}' }}}}", f"'{actual}'")
            code = code.replace(f"{{{placeholder}}}", actual)
            code = code.replace(f"df['{placeholder}']", f"df['{actual}']")
            code = code.replace(f'df["{placeholder}"]', f'df["{actual}"]')

        return code

    def _get_safe_code(self, code: str) -> str:
        """Wrap code for safe execution."""
        return code

    def _get_safe_builtins(self) -> dict[str, Any]:
        """Get restricted builtins for safe code execution."""
        return {
            "len": len,
            "sum": sum,
            "max": max,
            "min": min,
            "int": int,
            "float": float,
            "str": str,
            "bool": bool,
            "abs": abs,
            "round": round,
            "pow": pow,
            "range": range,
            "list": list,
            "dict": dict,
            "set": set,
            "tuple": tuple,
            "sorted": sorted,
            "reversed": reversed,
            "enumerate": enumerate,
            "zip": zip,
            "any": any,
            "all": all,
            "map": map,
            "filter": filter,
            "isinstance": isinstance,
            "hasattr": hasattr,
            "getattr": getattr,
        }

    def to_dict(self) -> dict[str, Any]:
        """Convert rule to dictionary for serialization."""
        return self.model_dump()

    @classmethod
    def from_dict(cls, data: dict[str, Any]) -> "TransformRule":
        """Create rule from dictionary."""
        return cls(**data)

    def __repr__(self) -> str:
        return f"TransformRule(name='{self.name}', description='{self.description[:50]}...')"

apply(df, column_mapping=None, validate=True)

Apply the transformation rule to a DataFrame.

Parameters:

Name Type Description Default
df DataFrame

Input data

 required
column_mapping dict

Mapping from rule's input_columns to actual column names

 None
validate bool

Whether to validate before execution

 True

Returns:

Type Description
Series

Transformed feature values

Raises:

Type Description
ValueError

If required columns are missing or code execution fails
Source code in featcopilot/core/transform_rule.py 
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
def apply(
    self,
    df: pd.DataFrame,
    column_mapping: Optional[dict[str, str]] = None,
    validate: bool = True,
) -> pd.Series:
    """
    Apply the transformation rule to a DataFrame.

    Parameters
    ----------
    df : DataFrame
        Input data
    column_mapping : dict, optional
        Mapping from rule's input_columns to actual column names
    validate : bool, default=True
        Whether to validate before execution

    Returns
    -------
    Series
        Transformed feature values

    Raises
    ------
    ValueError
        If required columns are missing or code execution fails
    """
    column_mapping = column_mapping or {}

    # Prepare the code with actual column names
    code = self._prepare_code(column_mapping)

    if validate:
        # Check required columns exist
        for input_col in self.input_columns:
            actual_col = column_mapping.get(input_col, input_col)
            if actual_col not in df.columns:
                raise ValueError(f"Required column '{actual_col}' not found in DataFrame")

    # Execute the code in a restricted environment
    local_vars: dict[str, Any] = {"df": df, "np": np, "pd": pd}
    try:
        exec(self._get_safe_code(code), {"__builtins__": self._get_safe_builtins()}, local_vars)

        if "result" not in local_vars:
            raise ValueError("Code did not produce a 'result' variable")

        result = local_vars["result"]

        # Increment usage count
        self.usage_count += 1

        return result

    except Exception as e:
        logger.error(f"Failed to apply rule '{self.name}': {e}")
        raise ValueError(f"Rule execution failed: {e}") from e

from_dict(data) classmethod

Create rule from dictionary.

Source code in featcopilot/core/transform_rule.py 
270
271
272
273
@classmethod
def from_dict(cls, data: dict[str, Any]) -> "TransformRule":
    """Create rule from dictionary."""
    return cls(**data)

get_output_name(column_mapping=None)

Get the output feature name.

Parameters:

Name Type Description Default
column_mapping dict

Mapping from placeholder columns to actual column names

 None

Returns:

Type Description
str

Output feature name
Source code in featcopilot/core/transform_rule.py 
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
def get_output_name(self, column_mapping: Optional[dict[str, str]] = None) -> str:
    """
    Get the output feature name.

    Parameters
    ----------
    column_mapping : dict, optional
        Mapping from placeholder columns to actual column names

    Returns
    -------
    str
        Output feature name
    """
    if self.output_name:
        return self.output_name

    # Generate name from input columns
    if column_mapping and self.input_columns:
        cols = [column_mapping.get(c, c) for c in self.input_columns[:2]]
        return f"{'_'.join(cols)}_{self.name}"

    return f"rule_{self.name}"

matches_columns(columns)

Check if this rule can be applied to the given columns.

Parameters:

Name Type Description Default
columns list[str]

Available column names

 required

Returns:

Name Type Description
matches bool

Whether the rule can be applied
mapping dict

Suggested mapping from rule's input_columns to actual columns
Source code in featcopilot/core/transform_rule.py 
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
def matches_columns(self, columns: list[str]) -> tuple[bool, dict[str, str]]:
    """
    Check if this rule can be applied to the given columns.

    Parameters
    ----------
    columns : list[str]
        Available column names

    Returns
    -------
    matches : bool
        Whether the rule can be applied
    mapping : dict
        Suggested mapping from rule's input_columns to actual columns
    """
    if not self.input_columns:
        return True, {}

    mapping = {}

    for input_col in self.input_columns:
        # Try exact match first
        if input_col in columns:
            mapping[input_col] = input_col
            continue

        # Try pattern matching
        matched = False
        for pattern in self.column_patterns:
            regex = re.compile(pattern, re.IGNORECASE)
            for col in columns:
                if regex.match(col) and col not in mapping.values():
                    mapping[input_col] = col
                    matched = True
                    break
            if matched:
                break

        # Try fuzzy matching by checking if input_col is substring
        if not matched:
            for col in columns:
                if input_col.lower() in col.lower() and col not in mapping.values():
                    mapping[input_col] = col
                    matched = True
                    break

        if not matched:
            return False, {}

    return len(mapping) == len(self.input_columns), mapping

to_dict()

Convert rule to dictionary for serialization.

Source code in featcopilot/core/transform_rule.py 
266
267
268
def to_dict(self) -> dict[str, Any]:
    """Convert rule to dictionary for serialization."""
    return self.model_dump()