fauxdata-cli 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

fauxdata/__init__.py

@@ -1,3 +1,3 @@
 """fauxdata - CLI for generating and validating fake datasets."""
 
-__version__ = "0.2.0"
+__version__ = "0.2.2"

fauxdata/commands/agent.py

@@ -139,7 +139,7 @@ Notes:
 
 {presets}
 
-Presets are locale-aware and coherent within a row (the email matches the name, the city matches the country). Known limit: `unique: true` is not enforced on person and address presets such as `name`, `email`, `user_name`, `city` (pointblank issue #441). Validate with `rows_distinct` if uniqueness matters.
+Presets are locale-aware and coherent within a row (the email matches the name, the city matches the country).
 
 ## Validation rules
 

fauxdata/commands/infer.py

@@ -31,6 +31,11 @@ _DTYPE_MAP = {
     "Date": "date",
 }
 
+# Presets pointblank matches on the column name alone, skipping categorical detection.
+# Personal presets (name, phone, address...) are left out on purpose: restoring their
+# source values would copy real people's data into the schema.
+_CATEGORICAL_PRESETS = {"state", "city", "country", "country_code_2", "currency_code", "company", "job"}
+
 
 def _col_type_from_dtype(dtype: str) -> str:
     """Map a pointblank/polars dtype name to a fauxdata col_type."""
@@ -83,6 +88,19 @@ def _field_to_spec(field) -> dict:
     return spec
 
 
+def _restore_categorical(spec: dict, series: pl.Series, threshold: int | float) -> dict:
+    """Replace a name-matched preset with the source values on a low-cardinality column."""
+    if spec.get("preset") not in _CATEGORICAL_PRESETS or spec.get("unique"):
+        return spec
+    limit = threshold if isinstance(threshold, int) else int(threshold * series.len())
+    values = series.drop_nulls().unique().sort().to_list()
+    if len(values) > limit:
+        return spec
+    del spec["preset"]
+    spec["values"] = values
+    return spec
+
+
 def _build_validation(columns: list[tuple[str, dict]]) -> list[dict]:
     """Derive validation rules from the inferred column specs."""
     rules: list[dict] = []
@@ -160,14 +178,18 @@ def run(
     if not json_out:
         rprint(f"  Loaded [bold]{len(df)}[/bold] rows, [bold]{len(df.columns)}[/bold] columns")
 
+    threshold = _threshold(categorical_threshold)
     pb_schema = pb.schema_from_tbl(
         df,
-        categorical_threshold=_threshold(categorical_threshold),
+        categorical_threshold=threshold,
         detect_presets=detect_presets,
         sample_size=sample_size,
     )
 
-    columns = [(col_name, _field_to_spec(field)) for col_name, field in pb_schema.columns]
+    columns = [
+        (col_name, _restore_categorical(_field_to_spec(field), df[col_name], threshold))
+        for col_name, field in pb_schema.columns
+    ]
 
     schema_name = name or Path(dataset_path).stem
     out_rows = rows if rows is not None else len(df)

fauxdata/validator.py

@@ -80,8 +80,7 @@ def _add_rule(v: pb.Validate, rule: ValidationRule) -> None:
 
 def _extract_results(v: pb.Validate, rules: list[ValidationRule]) -> list[dict]:
     """Extract per-step results as a list of dicts."""
-    # validation_info, not get_dataframe_report(): the report fails on list-valued
-    # columns (rows_distinct) in pointblank 1.0.1
+    # validation_info carries active and eval_error, used to flag steps that could not run
     steps = {s.i: s for s in v.validation_info}
     results = []
     # Build a flat list of steps (one per column for multi-column rules)

{fauxdata_cli-0.2.0.dist-info → fauxdata_cli-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: fauxdata-cli
-Version: 0.2.0
+Version: 0.2.2
 Summary: CLI for generating and validating fake datasets
 Project-URL: Homepage, https://aborruso.github.io/fauxdata/
 Project-URL: Repository, https://github.com/aborruso/fauxdata
@@ -13,7 +13,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.11
-Requires-Dist: pointblank>=1.0.1
+Requires-Dist: pointblank>=1.2.0
 Requires-Dist: polars>=1.0
 Requires-Dist: pyfiglet>=1.0
 Requires-Dist: pyyaml>=6.0
@@ -93,7 +93,7 @@ fauxdata init --name orders
 
 ## Schema format
 
-A schema is a YAML file that describes the structure of your dataset. Here is a realistic example for a people dataset:
+A schema is a YAML file that describes the structure of your dataset. Here is a realistic example for a people dataset, adapted from [`schemas/people.yml`](https://github.com/aborruso/fauxdata/blob/main/schemas/people.yml):
 
 ```yaml
 name: people
@@ -169,12 +169,12 @@ validation:
 
 | Type | Description | Options |
 |------|-------------|---------|
-| `int` | Integer | `min`, `max`, `unique` |
-| `float` | Floating point | `min`, `max`, `precision` |
+| `int` | Integer | `min`, `max`, `unique`, `values` |
+| `float` | Floating point | `min`, `max`, `precision`, `unique`, `values` |
 | `string` | Text | `preset`, `values`, `pattern`, `unique`, `min_length`, `max_length` |
 | `bool` | Boolean | — |
-| `date` | Date | `min`, `max` (ISO format) |
-| `datetime` | Datetime | `min`, `max` (ISO format) |
+| `date` | Date | `min`, `max` (ISO format), `unique` |
+| `datetime` | Datetime | `min`, `max` (ISO format), `unique` |
 
 ### Float precision
 
@@ -269,7 +269,7 @@ fauxdata generate schemas/people.yml --out - --format jsonl | wc -l
 | `--rows` | `-r` | from schema | Number of rows to generate |
 | `--out` | `-o` | from schema | Output path — use `-` for stdout |
 | `--format` | `-f` | from schema | Output format: `csv`, `parquet`, `json`, `jsonl`, `jsonlines` |
-| `--seed` | `-s` | from schema | Random seed for reproducibility |
+| `--seed` | `-s` | from schema | Random seed for reproducibility: same seed, same data, on the same pointblank version |
 | `--validate` | `-v` | off | Run validation rules after generating |
 | `--json` | | off | Print only a JSON summary to stdout (see [Using fauxdata with AI agents](#using-fauxdata-with-ai-agents)) |
 
@@ -277,7 +277,7 @@ When `--out -` is used, all output messages are suppressed and only data is writ
 
 ### `fauxdata infer DATASET`
 
-Build a YAML schema from a **real** dataset. fauxdata inspects the table (via pointblank's schema inference) and writes a schema with inferred ranges, categorical value sets, string presets (email, url…), uniqueness, null rates, and string lengths — plus matching `validation:` rules. Feed the result back to `fauxdata generate` to produce synthetic data that mirrors the real shape, without ever shipping the real values.
+Build a YAML schema from a **real** dataset. fauxdata inspects the table (via pointblank's schema inference) and writes a schema with inferred ranges, categorical value sets, string presets (email, url…), uniqueness, null rates, and string lengths — plus matching `validation:` rules. Feed the result back to `fauxdata generate` to produce synthetic data with the same columns, ranges and value sets, without copying the real rows. Each column is generated independently, so correlations between columns, rules such as `end_date > start_date`, and category frequencies are not preserved.
 
 ```
 fauxdata infer real_data.csv                                   # -> real_data.yml
@@ -296,7 +296,7 @@ fauxdata infer big.parquet --sample-size 10000 --out - | head  # stream to stdou
 | `--detect-presets` / `--no-detect-presets` | | on | Match string columns to known presets (email, url…) |
 | `--sample-size` | | all rows | Sample N rows before analysis (for very large tables) |
 
-> **Notes.** Low-cardinality columns (≤ `--categorical-threshold` distinct values) are frozen to their exact source values via `values:` — desirable for categories like `status`, but it means sensitive low-cardinality columns are reproduced verbatim. Raise the threshold or edit the schema if that's not what you want. Also, a column inferred as `unique` over a narrow integer range cannot generate many more rows than the source; widen `min`/`max` or drop `unique` to amplify.
+> **Notes.** Low-cardinality columns (≤ `--categorical-threshold` distinct values) are frozen to their exact source values via `values:` — desirable for categories like `status`, but it means sensitive low-cardinality columns are reproduced verbatim. Raise the threshold or edit the schema if that's not what you want. This also applies to columns whose name suggests a place, company or job (`region`, `city`, `company`...). Personal presets are never frozen, so a low-cardinality column such as `product_name` still gets people's names: use `--no-detect-presets` or edit the schema. Also, a column inferred as `unique` over a narrow integer range cannot generate many more rows than the source; widen `min`/`max` or drop `unique` to amplify.
 
 ### `fauxdata validate DATASET SCHEMA`
 
@@ -365,13 +365,13 @@ fauxdata validate data.csv schema.yml --json
 
 ## Example schemas
 
-Three ready-to-use schemas are included in `schemas/`:
+Three ready-to-use schemas are included in [`schemas/`](https://github.com/aborruso/fauxdata/tree/main/schemas):
 
 | Schema | Domain | Columns |
 |--------|--------|---------|
-| `people.yml` | Personal data | id, name, email, age, city, country_code, active, signup_date, score |
-| `orders.yml` | E-commerce | order_id, customer_id, product, amount, status, created_at |
-| `events.yml` | Analytics | event_id, user_id, event_type, timestamp, ip, user_agent, session_duration |
+| [`people.yml`](https://github.com/aborruso/fauxdata/blob/main/schemas/people.yml) | Personal data | id, name, email, age, city, country_code, active, signup_date, score |
+| [`orders.yml`](https://github.com/aborruso/fauxdata/blob/main/schemas/orders.yml) | E-commerce | order_id, customer_id, product, amount, status, created_at |
+| [`events.yml`](https://github.com/aborruso/fauxdata/blob/main/schemas/events.yml) | Analytics | event_id, user_id, event_type, timestamp, ip, user_agent, session_duration |
 
 ---
 

{fauxdata_cli-0.2.0.dist-info → fauxdata_cli-0.2.2.dist-info}/RECORD

@@ -1,19 +1,19 @@
-fauxdata/__init__.py,sha256=ggGU864cSergEL7CUMZS3C2czMfzK8q7xwm21VhscjI,89
+fauxdata/__init__.py,sha256=X4QgoKwTbMrq4zssag83Qa2O9IOKqphM7h0ZDJsXsIU,89
 fauxdata/generator.py,sha256=h9QGwPsZWyi12N6F_sFPcISA2JAQrSqLIzMQ1vz0fp0,5057
 fauxdata/jsonmode.py,sha256=XOVqTv1HPKyTzE9a3clSYsiFQXhuLbvgb6qCmkBzicE,498
 fauxdata/main.py,sha256=QDlYe0sDO9GatXSJUALz6bOxKewwTBwu-MANUkUAnC4,7266
 fauxdata/output.py,sha256=VS-aXquONgMxSaLBjoUBvFwQrnOSJl5X9Yzrx3XFzjY,1562
 fauxdata/schema.py,sha256=XXTUeUKiUFddHM-HfSE0vgSfj6KIBNon7sgkCxW6D6c,5943
-fauxdata/validator.py,sha256=qV5CWkpLx6BwouWG8LXnfJqjBiuT4CSVehp0SECslsA,4078
+fauxdata/validator.py,sha256=WHxZGYNKE-TxZyeMQMCLzxB26LnZIeJiNzsV3oc1e4A,4036
 fauxdata/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-fauxdata/commands/agent.py,sha256=gtkRzSK2Sx5zuisfwclTckN4EeZ47RJYXOu7OSOfP8c,5288
+fauxdata/commands/agent.py,sha256=VddV9Ws-27FmWEJlGwz_N4mpXeqvvs0ckOAy9u5Powo,5091
 fauxdata/commands/generate.py,sha256=vNaOQGJFQWiUhFfx9zOoiNR039i5JVLtD1JcNH5C-rQ,5880
-fauxdata/commands/infer.py,sha256=_2adxMD_e7fb7Vsk0FErcN4qQrPRa9kxYC-xN1_InvE,7180
+fauxdata/commands/infer.py,sha256=nw0kbBM-2hN5PHwyE_dXsSoNig1VgQPog4kRKYmgGDw,8158
 fauxdata/commands/init.py,sha256=GXJWSvndpKXI5mUe3N6IrZSK-V7JcgmKoWoh-uXljig,2964
 fauxdata/commands/preview.py,sha256=ZR7yjHHoj4QciW28ezH_9k5W2a-muX4xdxOJp5MyNjw,3063
 fauxdata/commands/validate.py,sha256=9I-8ArZnCh-QvFJ-BldtWiXDnPANuGlxBb2t2xP1aZk,2652
-fauxdata_cli-0.2.0.dist-info/METADATA,sha256=xwB8Oh19SD2xVS_VJPdZEVPhO5s47nbz0s9auyrkCB4,15261
-fauxdata_cli-0.2.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-fauxdata_cli-0.2.0.dist-info/entry_points.txt,sha256=fplnEfv4hunVCf1dWhc7fBdcAP_10PdCAqCfxIOnh1o,47
-fauxdata_cli-0.2.0.dist-info/licenses/LICENSE,sha256=NpzSNzsY_eubQrJ-zE25rLD9BTlCM3zlP-iPVNmndFk,1092
-fauxdata_cli-0.2.0.dist-info/RECORD,,
+fauxdata_cli-0.2.2.dist-info/METADATA,sha256=ApKicYUJ2vv71uc2hT_eGBkmZfVMwmAxFhjt_K5Iq7A,16165
+fauxdata_cli-0.2.2.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
+fauxdata_cli-0.2.2.dist-info/entry_points.txt,sha256=fplnEfv4hunVCf1dWhc7fBdcAP_10PdCAqCfxIOnh1o,47
+fauxdata_cli-0.2.2.dist-info/licenses/LICENSE,sha256=NpzSNzsY_eubQrJ-zE25rLD9BTlCM3zlP-iPVNmndFk,1092
+fauxdata_cli-0.2.2.dist-info/RECORD,,

{fauxdata_cli-0.2.0.dist-info → fauxdata_cli-0.2.2.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.32.4
+Generator: hatchling 1.33.0
 Root-Is-Purelib: true
 Tag: py3-none-any