Skip to content

Class swarmauri_standard.metrics.LevenshteinMetric.LevenshteinMetric

swarmauri_standard.metrics.LevenshteinMetric.LevenshteinMetric

Bases: MetricBase

Implementation of Levenshtein distance metric.

Levenshtein distance is a string metric for measuring the difference between two sequences. It represents the minimum number of single-character edits (insertions, deletions, or substitutions) required to change one string into another.

This metric is widely used in natural language processing and bioinformatics for measuring the similarity between strings.

type class-attribute instance-attribute

type = 'LevenshteinMetric'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

name class-attribute instance-attribute

name = None

resource class-attribute instance-attribute

resource = METRIC.value

version class-attribute instance-attribute

version = '0.1.0'

distance

distance(x, y)

Calculate the Levenshtein distance between two strings.

Parameters

x : MetricInput First string y : MetricInput Second string

Returns

float The Levenshtein distance between x and y

Raises

TypeError If inputs are not strings

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
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
def distance(self, x: MetricInput, y: MetricInput) -> float:
    """
    Calculate the Levenshtein distance between two strings.

    Parameters
    ----------
    x : MetricInput
        First string
    y : MetricInput
        Second string

    Returns
    -------
    float
        The Levenshtein distance between x and y

    Raises
    ------
    TypeError
        If inputs are not strings
    """
    if not isinstance(x, str) or not isinstance(y, str):
        logger.error(f"Inputs must be strings, got {type(x)} and {type(y)}")
        raise TypeError(f"Inputs must be strings, got {type(x)} and {type(y)}")

    logger.debug(f"Calculating Levenshtein distance between '{x}' and '{y}'")

    # If either string is empty, the distance is the length of the other string
    if len(x) == 0:
        return len(y)
    if len(y) == 0:
        return len(x)

    # Initialize the matrix
    # The matrix has len(x)+1 rows and len(y)+1 columns
    matrix = [[0 for _ in range(len(y) + 1)] for _ in range(len(x) + 1)]

    # Initialize the first row and column
    for i in range(len(x) + 1):
        matrix[i][0] = i
    for j in range(len(y) + 1):
        matrix[0][j] = j

    # Fill the matrix using dynamic programming
    for i in range(1, len(x) + 1):
        for j in range(1, len(y) + 1):
            # If characters match, no additional cost
            if x[i - 1] == y[j - 1]:
                cost = 0
            else:
                cost = 1

            # Calculate the minimum of the three possible operations:
            # deletion, insertion, or substitution
            matrix[i][j] = min(
                matrix[i - 1][j] + 1,  # deletion
                matrix[i][j - 1] + 1,  # insertion
                matrix[i - 1][j - 1] + cost,  # substitution
            )

    # The bottom-right cell contains the Levenshtein distance
    return matrix[len(x)][len(y)]

distances

distances(x, y)

Calculate Levenshtein distances between collections of strings.

Parameters

x : Union[MetricInput, MetricInputCollection] First collection of strings y : Union[MetricInput, MetricInputCollection] Second collection of strings

Returns

Union[List[float], IVector, IMatrix] Matrix of distances between strings in x and y

Raises

TypeError If inputs are not collections of strings

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
 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
def distances(
    self,
    x: Union[MetricInput, MetricInputCollection],
    y: Union[MetricInput, MetricInputCollection],
) -> Union[List[float], IVector, IMatrix]:
    """
    Calculate Levenshtein distances between collections of strings.

    Parameters
    ----------
    x : Union[MetricInput, MetricInputCollection]
        First collection of strings
    y : Union[MetricInput, MetricInputCollection]
        Second collection of strings

    Returns
    -------
    Union[List[float], IVector, IMatrix]
        Matrix of distances between strings in x and y

    Raises
    ------
    TypeError
        If inputs are not collections of strings
    """
    logger.debug("Calculating Levenshtein distances between collections")

    # Convert numpy arrays to lists if necessary
    if isinstance(x, np.ndarray):
        x = x.tolist()
    if isinstance(y, np.ndarray):
        y = y.tolist()

    # Validate input types
    if not isinstance(x, list) or not isinstance(y, list):
        logger.error(
            f"Inputs must be lists or numpy arrays, got {type(x)} and {type(y)}"
        )
        raise TypeError(
            f"Inputs must be lists or numpy arrays, got {type(x)} and {type(y)}"
        )

    # Validate that all elements are strings
    for i, item in enumerate(x):
        if not isinstance(item, str):
            logger.error(
                f"All elements must be strings, found {type(item)} at index {i} in x"
            )
            raise TypeError(
                f"All elements must be strings, found {type(item)} at index {i} in x"
            )

    for i, item in enumerate(y):
        if not isinstance(item, str):
            logger.error(
                f"All elements must be strings, found {type(item)} at index {i} in y"
            )
            raise TypeError(
                f"All elements must be strings, found {type(item)} at index {i} in y"
            )

    # Create a matrix of distances
    result = [[self.distance(xi, yi) for yi in y] for xi in x]

    # If only one string in x, return a vector
    if len(x) == 1:
        return result[0]

    return result

check_non_negativity

check_non_negativity(x, y)

Check if the Levenshtein metric satisfies the non-negativity axiom: d(x,y) ≥ 0.

Levenshtein distance is always non-negative by definition.

Parameters

x : MetricInput First string y : MetricInput Second string

Returns

bool True, as Levenshtein distance is always non-negative

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
def check_non_negativity(self, x: MetricInput, y: MetricInput) -> bool:
    """
    Check if the Levenshtein metric satisfies the non-negativity axiom: d(x,y) ≥ 0.

    Levenshtein distance is always non-negative by definition.

    Parameters
    ----------
    x : MetricInput
        First string
    y : MetricInput
        Second string

    Returns
    -------
    bool
        True, as Levenshtein distance is always non-negative
    """
    logger.debug(f"Checking non-negativity axiom for '{x}' and '{y}'")

    # Levenshtein distance is always non-negative as it counts the number of operations
    # which cannot be negative
    return True

check_identity_of_indiscernibles

check_identity_of_indiscernibles(x, y)

Check if the Levenshtein metric satisfies the identity of indiscernibles axiom: d(x,y) = 0 if and only if x = y.

Parameters

x : MetricInput First string y : MetricInput Second string

Returns

bool True if d(x,y) = 0 iff x = y, False otherwise

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
def check_identity_of_indiscernibles(self, x: MetricInput, y: MetricInput) -> bool:
    """
    Check if the Levenshtein metric satisfies the identity of indiscernibles axiom:
    d(x,y) = 0 if and only if x = y.

    Parameters
    ----------
    x : MetricInput
        First string
    y : MetricInput
        Second string

    Returns
    -------
    bool
        True if d(x,y) = 0 iff x = y, False otherwise
    """
    logger.debug(f"Checking identity of indiscernibles axiom for '{x}' and '{y}'")

    # The distance is 0 if and only if the strings are identical
    return (self.distance(x, y) == 0) == (x == y)

check_symmetry

check_symmetry(x, y)

Check if the Levenshtein metric satisfies the symmetry axiom: d(x,y) = d(y,x).

Parameters

x : MetricInput First string y : MetricInput Second string

Returns

bool True if d(x,y) = d(y,x), False otherwise

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
def check_symmetry(self, x: MetricInput, y: MetricInput) -> bool:
    """
    Check if the Levenshtein metric satisfies the symmetry axiom: d(x,y) = d(y,x).

    Parameters
    ----------
    x : MetricInput
        First string
    y : MetricInput
        Second string

    Returns
    -------
    bool
        True if d(x,y) = d(y,x), False otherwise
    """
    logger.debug(f"Checking symmetry axiom for '{x}' and '{y}'")

    # Calculate distances in both directions and check if they're equal
    d_xy = self.distance(x, y)
    d_yx = self.distance(y, x)

    return d_xy == d_yx

check_triangle_inequality

check_triangle_inequality(x, y, z)

Check if the Levenshtein metric satisfies the triangle inequality axiom: d(x,z) ≤ d(x,y) + d(y,z).

Parameters

x : MetricInput First string y : MetricInput Second string z : MetricInput Third string

Returns

bool True if d(x,z) ≤ d(x,y) + d(y,z), False otherwise

Source code in swarmauri_standard/metrics/LevenshteinMetric.py
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
def check_triangle_inequality(
    self, x: MetricInput, y: MetricInput, z: MetricInput
) -> bool:
    """
    Check if the Levenshtein metric satisfies the triangle inequality axiom:
    d(x,z) ≤ d(x,y) + d(y,z).

    Parameters
    ----------
    x : MetricInput
        First string
    y : MetricInput
        Second string
    z : MetricInput
        Third string

    Returns
    -------
    bool
        True if d(x,z) ≤ d(x,y) + d(y,z), False otherwise
    """
    logger.debug(f"Checking triangle inequality axiom for '{x}', '{y}', and '{z}'")

    # Calculate the three distances
    d_xy = self.distance(x, y)
    d_yz = self.distance(y, z)
    d_xz = self.distance(x, z)

    # Check if the triangle inequality holds
    return d_xz <= d_xy + d_yz

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
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
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
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
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger