pointblank 0.19.0__py3-none-any.whl → 0.20.0__py3-none-any.whl

pointblank/locales/data/US/text.json

@@ -0,0 +1,56 @@
+{
+  "words": [
+    "lorem", "ipsum", "dolor", "sit", "amet", "consectetur", "adipiscing", "elit",
+    "sed", "do", "eiusmod", "tempor", "incididunt", "ut", "labore", "et", "dolore",
+    "magna", "aliqua", "enim", "ad", "minim", "veniam", "quis", "nostrud",
+    "exercitation", "ullamco", "laboris", "nisi", "aliquip", "ex", "ea", "commodo",
+    "consequat", "duis", "aute", "irure", "in", "reprehenderit", "voluptate",
+    "velit", "esse", "cillum", "fugiat", "nulla", "pariatur", "excepteur", "sint",
+    "occaecat", "cupidatat", "non", "proident", "sunt", "culpa", "qui", "officia",
+    "deserunt", "mollit", "anim", "id", "est", "laborum", "the", "and", "for",
+    "are", "but", "not", "you", "all", "can", "had", "her", "was", "one", "our",
+    "out", "day", "get", "has", "him", "his", "how", "its", "may", "new", "now",
+    "old", "see", "two", "way", "who", "boy", "did", "own", "say", "she", "too",
+    "use", "time", "very", "when", "come", "could", "make", "like", "back", "only",
+    "over", "such", "year", "into", "just", "most", "also", "been", "call", "from",
+    "have", "more", "made", "find", "long", "down", "look", "many", "then", "them",
+    "well", "would", "about", "after", "being", "could", "first", "great", "little",
+    "might", "never", "other", "right", "still", "their", "there", "these", "thing",
+    "think", "those", "three", "today", "under", "water", "where", "which", "while",
+    "world", "write", "years"
+  ],
+  "sentence_patterns": [
+    "The {adjective} {noun} {verb} the {adjective} {noun}.",
+    "A {noun} {verb} {adverb} in the {noun}.",
+    "{proper_noun} {verb} the {adjective} {noun} {adverb}."
+  ],
+  "adjectives": [
+    "quick", "brown", "lazy", "fast", "slow", "big", "small", "old", "new", "young",
+    "bright", "dark", "loud", "quiet", "hot", "cold", "warm", "cool", "soft", "hard",
+    "smooth", "rough", "clean", "dirty", "happy", "sad", "angry", "calm", "brave",
+    "shy", "clever", "foolish", "kind", "mean", "rich", "poor", "strong", "weak",
+    "tall", "short", "wide", "narrow", "deep", "shallow", "thick", "thin", "heavy",
+    "light", "full", "empty", "open", "closed", "wet", "dry", "fresh", "stale"
+  ],
+  "nouns": [
+    "dog", "cat", "bird", "fish", "tree", "house", "car", "book", "table", "chair",
+    "door", "window", "road", "river", "mountain", "ocean", "sky", "sun", "moon",
+    "star", "cloud", "rain", "snow", "wind", "fire", "water", "earth", "air",
+    "stone", "wood", "metal", "glass", "paper", "cloth", "food", "drink", "money",
+    "time", "place", "person", "child", "man", "woman", "boy", "girl", "friend",
+    "family", "school", "work", "city", "country", "world", "life", "day", "night",
+    "morning", "evening", "week", "month", "year", "story", "song", "game", "sport"
+  ],
+  "verbs": [
+    "runs", "jumps", "walks", "talks", "sees", "hears", "feels", "thinks", "knows",
+    "wants", "needs", "likes", "loves", "hates", "finds", "gives", "takes", "makes",
+    "says", "tells", "asks", "answers", "helps", "works", "plays", "reads", "writes",
+    "draws", "sings", "dances", "cooks", "eats", "drinks", "sleeps", "wakes", "opens",
+    "closes", "starts", "stops", "begins", "ends", "moves", "stays", "comes", "goes"
+  ],
+  "adverbs": [
+    "quickly", "slowly", "carefully", "happily", "sadly", "loudly", "quietly",
+    "easily", "hardly", "always", "never", "often", "sometimes", "usually",
+    "really", "very", "quite", "almost", "already", "still", "just", "only"
+  ]
+}

pointblank/locales/data/_shared/misc.json

@@ -0,0 +1,42 @@
+{
+  "file_extensions": [
+    "txt", "pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", "csv", "json",
+    "xml", "html", "css", "js", "py", "java", "cpp", "h", "md", "rst",
+    "png", "jpg", "jpeg", "gif", "svg", "bmp", "ico", "webp", "tiff",
+    "mp3", "wav", "ogg", "flac", "aac", "wma",
+    "mp4", "avi", "mkv", "mov", "wmv", "flv", "webm",
+    "zip", "tar", "gz", "rar", "7z", "bz2",
+    "sql", "db", "sqlite", "tsv", "yaml", "yml",
+    "c", "cs", "rb", "php", "go", "rs", "ts", "tsx", "jsx"
+  ],
+  "mime_types": [
+    "text/plain", "text/html", "text/css", "text/javascript", "text/csv",
+    "application/json", "application/xml", "application/pdf",
+    "application/zip", "application/gzip", "application/x-tar",
+    "application/msword", "application/vnd.ms-excel", "application/vnd.ms-powerpoint",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+    "image/png", "image/jpeg", "image/gif", "image/svg+xml", "image/webp", "image/bmp",
+    "audio/mpeg", "audio/wav", "audio/ogg", "audio/flac", "audio/aac",
+    "video/mp4", "video/webm", "video/x-msvideo", "video/quicktime", "video/x-matroska",
+    "application/octet-stream", "multipart/form-data"
+  ],
+  "currency_codes": [
+    "AED", "AFN", "ALL", "AMD", "ANG", "AOA", "ARS", "AUD", "AWG", "AZN",
+    "BAM", "BBD", "BDT", "BGN", "BHD", "BIF", "BMD", "BND", "BOB", "BRL",
+    "BSD", "BTN", "BWP", "BYN", "BZD", "CAD", "CDF", "CHF", "CLP", "CNY",
+    "COP", "CRC", "CUP", "CVE", "CZK", "DJF", "DKK", "DOP", "DZD", "EGP",
+    "ERN", "ETB", "EUR", "FJD", "FKP", "GBP", "GEL", "GHS", "GIP", "GMD",
+    "GNF", "GTQ", "GYD", "HKD", "HNL", "HTG", "HUF", "IDR", "ILS", "INR",
+    "IQD", "IRR", "ISK", "JMD", "JOD", "JPY", "KES", "KGS", "KHR", "KMF",
+    "KPW", "KRW", "KWD", "KYD", "KZT", "LAK", "LBP", "LKR", "LRD", "LSL",
+    "LYD", "MAD", "MDL", "MGA", "MKD", "MMK", "MNT", "MOP", "MRU", "MUR",
+    "MVR", "MWK", "MXN", "MYR", "MZN", "NAD", "NGN", "NIO", "NOK", "NPR",
+    "NZD", "OMR", "PAB", "PEN", "PGK", "PHP", "PKR", "PLN", "PYG", "QAR",
+    "RON", "RSD", "RUB", "RWF", "SAR", "SBD", "SCR", "SDG", "SEK", "SGD",
+    "SHP", "SLE", "SOS", "SRD", "SSP", "STN", "SVC", "SYP", "SZL", "THB",
+    "TJS", "TMT", "TND", "TOP", "TRY", "TTD", "TWD", "TZS", "UAH", "UGX",
+    "USD", "UYU", "UZS", "VES", "VND", "VUV", "WST", "YER", "ZAR", "ZMW", "ZWL"
+  ]
+}

pointblank/schema.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import copy
 from dataclasses import dataclass
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Literal
 
 import narwhals as nw
 
@@ -12,7 +12,9 @@ from pointblank._utils import _get_tbl_type, _is_lazy_frame, _is_lib_present, _i
 if TYPE_CHECKING:
     from typing import Any
 
-__all__ = ["Schema", "_check_schema_match"]
+    from pointblank.field import Field
+
+__all__ = ["Schema", "generate_dataset", "_check_schema_match"]
 
 
 @dataclass
@@ -789,6 +791,230 @@ class Schema:
     def __repr__(self):
         return f"Schema(columns={self.columns})"
 
+    def generate(
+        self,
+        n: int = 100,
+        seed: int | None = None,
+        output: Literal["polars", "pandas", "dict"] = "polars",
+        country: str = "US",
+    ) -> Any:
+        """
+        Generate synthetic test data conforming to this schema.
+
+        This method generates random data that matches the schema's column definitions. When the
+        schema is defined using `Field` objects with constraints (e.g., `min_val`, `max_val`,
+        `pattern`, `preset`), the generated data will respect those constraints.
+
+        Parameters
+        ----------
+        n
+            Number of rows to generate. Default is `100`.
+        seed
+            Random seed for reproducibility. If provided, the same seed will produce
+            the same data. Default is `None` (non-deterministic).
+        output
+            Output format for the generated data. Options are: (1) `"polars"` (default) returns a
+            Polars DataFrame, (2) `"pandas"` returns a Pandas DataFrame, and (3) `"dict"` returns
+            a dictionary of lists.
+        country
+            Country code for realistic data generation when using presets (e.g., `preset="email"`,
+            `preset="address"`). Accepts ISO 3166-1 alpha-2 codes (e.g., `"US"`, `"DE"`, `"FR"`)
+            or alpha-3 codes (e.g., `"USA"`, `"DEU"`, `"FRA"`). Default is `"US"`.
+
+        Returns
+        -------
+        DataFrame or dict
+            Generated data in the requested format.
+
+        Raises
+        ------
+        ValueError
+            If the schema has no columns or if constraints cannot be satisfied.
+        ImportError
+            If required optional dependencies are not installed.
+
+        Supported Countries
+        -------------------
+        The `country=` parameter controls the country used for generating realistic data with
+        presets (e.g., `preset="email"`, `preset="address"`). This affects location-specific
+        formats like addresses, phone numbers, and postal codes. Currently, **50 countries** are
+        supported with full locale data:
+
+        **Europe (32 countries):** Austria (`"AT"`), Belgium (`"BE"`), Bulgaria (`"BG"`),
+        Croatia (`"HR"`), Cyprus (`"CY"`), Czech Republic (`"CZ"`), Denmark (`"DK"`),
+        Estonia (`"EE"`), Finland (`"FI"`), France (`"FR"`), Germany (`"DE"`), Greece (`"GR"`),
+        Hungary (`"HU"`), Iceland (`"IS"`), Ireland (`"IE"`), Italy (`"IT"`), Latvia (`"LV"`),
+        Lithuania (`"LT"`), Luxembourg (`"LU"`), Malta (`"MT"`), Netherlands (`"NL"`),
+        Norway (`"NO"`), Poland (`"PL"`), Portugal (`"PT"`), Romania (`"RO"`), Russia (`"RU"`),
+        Slovakia (`"SK"`), Slovenia (`"SI"`), Spain (`"ES"`), Sweden (`"SE"`),
+        Switzerland (`"CH"`), United Kingdom (`"GB"`)
+
+        **Americas (7 countries):** Argentina (`"AR"`), Brazil (`"BR"`), Canada (`"CA"`),
+        Chile (`"CL"`), Colombia (`"CO"`), Mexico (`"MX"`), United States (`"US"`)
+
+        **Asia-Pacific (10 countries):** Australia (`"AU"`), China (`"CN"`), Hong Kong (`"HK"`),
+        India (`"IN"`), Indonesia (`"ID"`), Japan (`"JP"`), New Zealand (`"NZ"`),
+        Philippines (`"PH"`), South Korea (`"KR"`), Taiwan (`"TW"`)
+
+        **Middle East (1 country):** Turkey (`"TR"`)
+
+        Examples
+        --------
+        Using `pb.Schema` we first put together a schema with field constraints:
+
+        ```{python}
+        import pointblank as pb
+
+        schema = pb.Schema(
+            user_id=pb.int_field(min_val=1, unique=True),
+            email=pb.string_field(preset="email"),
+            age=pb.int_field(min_val=18, max_val=100),
+            status=pb.string_field(allowed=["active", "pending", "inactive"]),
+        )
+        ```
+
+        With the `generate()` method, we can obtain a set number of rows of generated data:
+
+        ```{python}
+        # Generate 100 rows of test data
+        pb.preview(schema.generate(n=100, seed=23))
+        ```
+
+        It's possible to generate data from a simple dtype-only schema:
+
+        ```{python}
+        schema = pb.Schema(name="String", age="Int64", active="Boolean")
+        pb.preview(schema.generate(n=50, seed=123, output="pandas"))
+        ```
+
+        We can obtain synthetic data with German addresses using presets for person name and city of
+        residence. Note the use of `country="DE"` in the `generate()` call:
+
+        ```{python}
+        schema = pb.Schema(
+            name=pb.string_field(preset="name"),
+            city=pb.string_field(preset="city"),
+        )
+        pb.preview(schema.generate(n=20, seed=23, country="DE"))
+        ```
+        """
+        from pointblank.field import Field
+        from pointblank.generate import GeneratorConfig, generate_dataframe
+
+        if self.columns is None or len(self.columns) == 0:
+            raise ValueError("Cannot generate data from an empty schema.")
+
+        # Convert schema columns to Field objects
+        fields: dict[str, Field] = {}
+
+        for col_tuple in self.columns:
+            col_name = col_tuple[0]
+
+            # Check if the value is already a Field object
+            if len(col_tuple) > 1 and isinstance(col_tuple[1], Field):
+                fields[col_name] = col_tuple[1]
+            elif len(col_tuple) > 1:
+                # Simple dtype string - convert to basic Field
+                dtype_str = col_tuple[1]
+                fields[col_name] = _dtype_string_to_field(dtype_str)
+            else:
+                # No dtype specified - default to String
+                fields[col_name] = Field(dtype="String")
+
+        # Create generator config
+        config = GeneratorConfig(
+            n=n,
+            seed=seed,
+            output=output,
+            country=country,
+        )
+
+        return generate_dataframe(fields, config)
+
+
+def _dtype_string_to_field(dtype_str: str) -> "Field":
+    """
+    Convert a dtype string to a basic Field object.
+
+    This handles the mapping from various dtype string formats to
+    standardized Field dtypes.
+    """
+    from pointblank.field import (
+        BoolField,
+        DateField,
+        DatetimeField,
+        DurationField,
+        FloatField,
+        IntField,
+        StringField,
+        TimeField,
+    )
+
+    # Normalize dtype string
+    dtype_lower = dtype_str.lower()
+
+    # Map common dtype strings to Field classes and dtypes
+    dtype_mapping = {
+        # Integer types
+        "int8": ("int", "Int8"),
+        "int16": ("int", "Int16"),
+        "int32": ("int", "Int32"),
+        "int64": ("int", "Int64"),
+        "int": ("int", "Int64"),
+        "integer": ("int", "Int64"),
+        "uint8": ("int", "UInt8"),
+        "uint16": ("int", "UInt16"),
+        "uint32": ("int", "UInt32"),
+        "uint64": ("int", "UInt64"),
+        # Float types
+        "float32": ("float", "Float32"),
+        "float64": ("float", "Float64"),
+        "float": ("float", "Float64"),
+        "double": ("float", "Float64"),
+        # String types
+        "string": ("string", "String"),
+        "str": ("string", "String"),
+        "utf8": ("string", "String"),
+        "object": ("string", "String"),
+        # Boolean
+        "bool": ("bool", "Boolean"),
+        "boolean": ("bool", "Boolean"),
+        # Date/time types
+        "date": ("date", "Date"),
+        "datetime": ("datetime", "Datetime"),
+        "timestamp": ("datetime", "Datetime"),
+        "time": ("time", "Time"),
+        "duration": ("duration", "Duration"),
+        "timedelta": ("duration", "Duration"),
+    }
+
+    # Field class mapping
+    field_classes = {
+        "int": IntField,
+        "float": FloatField,
+        "string": StringField,
+        "bool": BoolField,
+        "date": DateField,
+        "datetime": DatetimeField,
+        "time": TimeField,
+        "duration": DurationField,
+    }
+
+    # Try direct mapping first
+    if dtype_lower in dtype_mapping:
+        field_type, dtype = dtype_mapping[dtype_lower]
+        field_class = field_classes[field_type]
+        return field_class(dtype=dtype)
+
+    # Try to match partial strings (e.g., "datetime64[ns]" -> "Datetime")
+    for key, (field_type, dtype) in dtype_mapping.items():
+        if key in dtype_lower:
+            field_class = field_classes[field_type]
+            return field_class(dtype=dtype)
+
+    # Default to StringField for unknown types
+    return StringField()
+
 
 def _process_columns(
     *,
@@ -1302,3 +1528,114 @@ def _check_schema_match(
         )
 
     return res
+
+
+def generate_dataset(
+    schema: Schema,
+    n: int = 100,
+    seed: int | None = None,
+    output: Literal["polars", "pandas", "dict"] = "polars",
+    country: str = "US",
+) -> Any:
+    """
+    Generate synthetic test data from a schema.
+
+    This function generates random data that conforms to a schema's column definitions. When the
+    schema is defined using `Field` objects with constraints (e.g., `min_val`, `max_val`,
+    `pattern`, `preset`), the generated data will respect those constraints.
+
+    This is a convenience function that wraps `Schema.generate()` for a more functional style
+    of usage, similar to how `load_dataset()` loads built-in datasets.
+
+    Parameters
+    ----------
+    schema
+        The schema object defining the structure and constraints of the data to generate.
+    n
+        Number of rows to generate. Default is `100`.
+    seed
+        Random seed for reproducibility. If provided, the same seed will produce
+        the same data. Default is `None` (non-deterministic).
+    output
+        Output format for the generated data. Options are: (1) `"polars"` (default) returns a
+        Polars DataFrame, (2) `"pandas"` returns a Pandas DataFrame, and (3) `"dict"` returns
+        a dictionary of lists.
+    country
+        Country code for realistic data generation when using presets (e.g., `preset="email"`,
+        `preset="address"`). Accepts ISO 3166-1 alpha-2 codes (e.g., `"US"`, `"DE"`, `"FR"`)
+        or alpha-3 codes (e.g., `"USA"`, `"DEU"`, `"FRA"`). Default is `"US"`.
+
+    Returns
+    -------
+    DataFrame or dict
+        Generated data in the requested format.
+
+    Raises
+    ------
+    ValueError
+        If the schema has no columns or if constraints cannot be satisfied.
+    ImportError
+        If required optional dependencies are not installed.
+
+    Supported Countries
+    -------------------
+    The `country=` parameter controls the country used for generating realistic data with
+    presets (e.g., `preset="email"`, `preset="address"`). This affects location-specific
+    formats like addresses, phone numbers, and postal codes. Currently, **50 countries** are
+    supported with full locale data:
+
+    **Europe (32 countries):** Austria (`"AT"`), Belgium (`"BE"`), Bulgaria (`"BG"`),
+    Croatia (`"HR"`), Cyprus (`"CY"`), Czech Republic (`"CZ"`), Denmark (`"DK"`),
+    Estonia (`"EE"`), Finland (`"FI"`), France (`"FR"`), Germany (`"DE"`), Greece (`"GR"`),
+    Hungary (`"HU"`), Iceland (`"IS"`), Ireland (`"IE"`), Italy (`"IT"`), Latvia (`"LV"`),
+    Lithuania (`"LT"`), Luxembourg (`"LU"`), Malta (`"MT"`), Netherlands (`"NL"`),
+    Norway (`"NO"`), Poland (`"PL"`), Portugal (`"PT"`), Romania (`"RO"`), Russia (`"RU"`),
+    Slovakia (`"SK"`), Slovenia (`"SI"`), Spain (`"ES"`), Sweden (`"SE"`),
+    Switzerland (`"CH"`), United Kingdom (`"GB"`)
+
+    **Americas (7 countries):** Argentina (`"AR"`), Brazil (`"BR"`), Canada (`"CA"`),
+    Chile (`"CL"`), Colombia (`"CO"`), Mexico (`"MX"`), United States (`"US"`)
+
+    **Asia-Pacific (10 countries):** Australia (`"AU"`), China (`"CN"`), Hong Kong (`"HK"`),
+    India (`"IN"`), Indonesia (`"ID"`), Japan (`"JP"`), New Zealand (`"NZ"`),
+    Philippines (`"PH"`), South Korea (`"KR"`), Taiwan (`"TW"`)
+
+    **Middle East (1 country):** Turkey (`"TR"`)
+
+    Examples
+    --------
+    Generate test data from a schema with field constraints:
+
+    ```{python}
+    import pointblank as pb
+
+    schema = pb.Schema(
+        user_id=pb.int_field(min_val=1, unique=True),
+        email=pb.string_field(preset="email"),
+        age=pb.int_field(min_val=18, max_val=100),
+        status=pb.string_field(allowed=["active", "pending", "inactive"]),
+    )
+
+    # Generate 100 rows of test data
+    pb.preview(pb.generate_dataset(schema, n=100, seed=23))
+    ```
+
+    Generate data from a simple dtype-only schema as a Pandas DataFrame:
+
+    ```{python}
+    schema = pb.Schema(name="String", age="Int64", active="Boolean")
+    pb.preview(pb.generate_dataset(schema, n=50, seed=23, output="pandas"))
+    ```
+
+    Generate data with German addresses by using `country="DE"`:
+
+    ```{python}
+    schema = pb.Schema(
+        name=pb.string_field(preset="name"),
+        address=pb.string_field(preset="address"),
+        city=pb.string_field(preset="city"),
+    )
+    pb.preview(pb.generate_dataset(schema, n=20, seed=23, country="DE"))
+    ```
+    """
+    return schema.generate(n=n, seed=seed, output=output, country=country)

{pointblank-0.19.0.dist-info → pointblank-0.20.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.19.0
+Version: 0.20.0
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License
@@ -451,6 +451,50 @@ Click the following headings to see some video demonstrations of the CLI:
 
 </details>
 
+## Generate Realistic Test Data
+
+Need test data for your validation workflows? The `generate_dataset()` function creates realistic, locale-aware synthetic data based on schema definitions. It's very useful for developing pipelines without production data, running CI/CD tests with reproducible scenarios, or prototyping workflows before production data is available.
+
+```python
+import pointblank as pb
+
+# Define a schema with field constraints
+schema = pb.Schema(
+    user_id=pb.int_field(min_val=1, unique=True),
+    name=pb.string_field(preset="name"),
+    email=pb.string_field(preset="email"),
+    age=pb.int_field(min_val=18, max_val=100),
+    status=pb.string_field(allowed=["active", "pending", "inactive"]),
+)
+
+# Generate 10 rows of realistic test data
+data = pb.generate_dataset(schema, n=10, seed=23)
+
+data
+```
+
+| user_id             | name             | email                      | age | status   |
+|---------------------|------------------|----------------------------|-----|----------|
+| 7188536481533917197 | Vivienne Rios    | vrios27@hotmail.com        | 55  | pending  |
+| 2674009078779859984 | William Schaefer | wschaefer28@yandex.com     | 28  | active   |
+| 7652102777077138151 | Lily Hansen      | lily779@aol.com            | 20  | active   |
+| 157503859921753049  | Shirley Mays     | shirley_mays@protonmail.com| 93  | inactive |
+| 2829213282471975080 | Sean Dawson      | sean_dawson@hotmail.com    | 57  | pending  |
+| 3497364383162086858 | Zachary Marsh    | zmarsh23@zoho.com          | 72  | pending  |
+| 3302703640991750415 | Gemma Gonzalez   | gemmagonzalez@yahoo.com    | 66  | pending  |
+| 6695746877064448147 | Brian Haley      | brian437@yandex.com        | 85  | inactive |
+| 2466163118311913924 | Nora Hernandez   | norahernandez@aol.com      | 63  | pending  |
+| 129827878195925732  | Diana Novak      | diana922@protonmail.com    | 34  | active   |
+
+The generator supports sophisticated data generation with these capabilities:
+
+- **Realistic data with presets**: Use built-in presets like `"name"`, `"email"`, `"address"`, `"phone"`, etc.
+- **50+ country support**: Generate locale-specific data (e.g., `country="DE"` for German addresses)
+- **Field constraints**: Control ranges, patterns, uniqueness, and allowed values
+- **Multiple output formats**: Returns Polars DataFrames by default, but also supports Pandas (`output="pandas"`) or dictionaries (`output="dict"`)
+
+This makes it easy to generate test data that matches your validation rules, helping you develop and test data quality workflows without relying on real data.
+
 ## Features That Set Pointblank Apart
 
 - **Complete validation workflow**: From data access to validation to reporting in a single pipeline