additory 0.1.0a2__tar.gz → 0.1.0a4__tar.gz

{additory-0.1.0a2 → additory-0.1.0a4}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: additory
-Version: 0.1.0a2
-Summary: A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data support.
+Version: 0.1.0a4
+Summary: A semantic, extensible dataframe transformation engine with expressions, lookup, and synthetic data generation support.
 Author: Krishnamoorthy Sankaran
 License: MIT
 Project-URL: homepage, https://github.com/sekarkrishna/additory
@@ -13,6 +13,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pandas>=1.5
 Requires-Dist: polars>=0.20
+Requires-Dist: pyarrow>=10.0
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: requests>=2.31
 Requires-Dist: toml>=0.10
@@ -34,11 +35,11 @@ Dynamic: license-file
 
 # Additory
 
-**A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data support.**
+**A semantic, extensible dataframe transformation engine with expressions, lookup, and augmentation support.**
 
 [![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.1.0a1-orange.svg)](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/)
+[![Version](https://img.shields.io/badge/version-0.1.0a4-orange.svg)](https://github.com/sekarkrishna/additory)
 
 **Author:** Krishnamoorthy Sankaran
 
@@ -51,17 +52,17 @@ Dynamic: license-file
 ## 📦 Installation
 
 ```bash
-pip install additory==0.1.0a1
+pip install additory==0.1.0a4
 ```
 
 **Optional GPU support:**
 ```bash
-pip install additory[gpu]==0.1.0a1  # Includes cuDF for GPU acceleration
+pip install additory[gpu]==0.1.0a4  # Includes cuDF for GPU acceleration
 ```
 
 **Development installation:**
 ```bash
-pip install additory[dev]==0.1.0a1  # Includes testing and development tools
+pip install additory[dev]==0.1.0a4  # Includes testing and development tools
 ```
 
 ## 🎯 Core Functions
@@ -69,8 +70,8 @@ pip install additory[dev]==0.1.0a1  # Includes testing and development tools
 | Function | Purpose | Example |
 |----------|---------|---------|
 | `add.to()` | Lookup/join operations | `add.to(df1, from_df=df2, bring='col', against='key')` |
-| `add.augment()` | Generate additional data | `add.augment(df, n_rows=1000)` |
-| `add.synth()` | Synthetic data from schemas | `add.synth("schema.toml", rows=5000)` |
+| `add.synthetic()` | Generate additional data | `add.synthetic(df, n_rows=1000)` |
+| `add.deduce()` | Text-based label deduction | `add.deduce(df, from_column='text', to_column='label')` |
 | `add.scan()` | Data profiling & analysis | `add.scan(df, preset="full")` |
 
 ## 🧬 Available Expressions
@@ -119,7 +120,7 @@ import additory as add
 
 # Works with polars
 df_polars = pl.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
-result = add.augment(df_polars, n_rows=100)
+result = add.synthetic(df_polars, n_rows=100)
 
 # Automatic type detection and conversion
 ```
@@ -193,27 +194,42 @@ patients_with_bsa = add.bsa(patients)
 result = add.fitness_score(add.bmr(add.bmi(patients)))
 ```
 
-### 🔄 Augment and Synthetic Data
+### 🔄 Synthetic Data Generation
 
-**Augment** generates more data similar to your existing dataset, while **Synthetic** creates entirely new datasets from schema definitions.
-
-**Key Differences:**
-- **Augment**: Learns patterns from existing data to create similar rows
-- **Synthetic**: Uses predefined schemas to generate structured data
+**Synthetic** generates additional data similar to your existing dataset using inline strategies.
 
 ```python
-# Augment existing data (learns from patterns)
-more_customers = add.augment(customers, n_rows=1000)
+# Extend existing data (learns from patterns)
+more_customers = add.synthetic(customers, n_rows=1000)
 
 # Create data from scratch with strategies
-new_data = add.augment("@new", n_rows=500, strategy={
+new_data = add.synthetic("@new", n_rows=500, strategy={
     'id': 'increment:start=1',
     'name': 'choice:[John,Jane,Bob]',
     'age': 'range:18-65'
 })
+```
+
+### 🤖 Text-Based Label Deduction
 
-# Generate from schema file (structured approach)
-customers = add.synth("customer_schema.toml", rows=10000)
+**Deduce** automatically fills in missing labels by learning from your existing labeled examples. Pure Python, no LLMs, offline-first.
+
+```python
+# Deduce missing labels from text
+tickets = pd.DataFrame({
+    "ticket_text": ["Cannot log in", "Billing question", "App crashes", "Need invoice"],
+    "category": ["Technical", "Billing", None, None]
+})
+
+# Automatically fill in missing categories
+result = add.deduce(tickets, from_column="ticket_text", to_column="category")
+
+# Use multiple columns for better accuracy
+result = add.deduce(
+    df,
+    from_column=["title", "description"],
+    to_column="category"
+)
 ```
 
 ## 🧪 Examples
@@ -231,7 +247,7 @@ customers = pd.DataFrame({
 })
 
 # Generate more customers
-customers = add.augment(customers, n_rows=10000)
+customers = add.synthetic(customers, n_rows=10000)
 
 # Add customer tiers
 tiers = pd.DataFrame({
@@ -257,7 +273,7 @@ strategy = {
     'height_cm': 'range:150-200'  # Height in cm
 }
 
-patients = add.augment("@new", n_rows=1000, strategy=strategy)
+patients = add.synthetic("@new", n_rows=1000, strategy=strategy)
 
 # Convert height to meters for expressions
 patients['height_m'] = patients['height_cm'] / 100
@@ -272,19 +288,19 @@ print(result.correlations)
 
 ## 📚 Documentation
 
-- **[Function Documentation](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0/)** - Detailed guides for each function
-- **[Expressions Guide](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0/expressions.html)** - Complete expressions reference
+- **[Function Documentation](https://github.com/sekarkrishna/additory/tree/main/documentation/)** - Detailed guides for each function
+- **[Expressions Guide](https://github.com/sekarkrishna/additory/tree/main/documentation/)** - Complete expressions reference
 
 ## 📄 License
 
-MIT License - see [LICENSE](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/LICENSE) file for details.
+MIT License - see [LICENSE](LICENSE) file for details.
 
 ## 📞 Support
 
 - **Issues**: [GitHub Issues](https://github.com/sekarkrishna/additory/issues)
-- **Documentation**: [Full Documentation](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0)
+- **Documentation**: [Full Documentation](https://github.com/sekarkrishna/additory/tree/main/documentation/)
 
-## 🗺️ v0.1.1 (February 2025)
+## 🗺️ v0.1.1 (January 2026)
 - Enhanced documentation and tutorials
 - Performance optimizations
 - Additional expressions

{additory-0.1.0a2 → additory-0.1.0a4}/README.md

@@ -1,10 +1,10 @@
 # Additory
 
-**A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data support.**
+**A semantic, extensible dataframe transformation engine with expressions, lookup, and augmentation support.**
 
 [![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.1.0a1-orange.svg)](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/)
+[![Version](https://img.shields.io/badge/version-0.1.0a4-orange.svg)](https://github.com/sekarkrishna/additory)
 
 **Author:** Krishnamoorthy Sankaran
 
@@ -17,17 +17,17 @@
 ## 📦 Installation
 
 ```bash
-pip install additory==0.1.0a1
+pip install additory==0.1.0a4
 ```
 
 **Optional GPU support:**
 ```bash
-pip install additory[gpu]==0.1.0a1  # Includes cuDF for GPU acceleration
+pip install additory[gpu]==0.1.0a4  # Includes cuDF for GPU acceleration
 ```
 
 **Development installation:**
 ```bash
-pip install additory[dev]==0.1.0a1  # Includes testing and development tools
+pip install additory[dev]==0.1.0a4  # Includes testing and development tools
 ```
 
 ## 🎯 Core Functions
@@ -35,8 +35,8 @@ pip install additory[dev]==0.1.0a1  # Includes testing and development tools
 | Function | Purpose | Example |
 |----------|---------|---------|
 | `add.to()` | Lookup/join operations | `add.to(df1, from_df=df2, bring='col', against='key')` |
-| `add.augment()` | Generate additional data | `add.augment(df, n_rows=1000)` |
-| `add.synth()` | Synthetic data from schemas | `add.synth("schema.toml", rows=5000)` |
+| `add.synthetic()` | Generate additional data | `add.synthetic(df, n_rows=1000)` |
+| `add.deduce()` | Text-based label deduction | `add.deduce(df, from_column='text', to_column='label')` |
 | `add.scan()` | Data profiling & analysis | `add.scan(df, preset="full")` |
 
 ## 🧬 Available Expressions
@@ -85,7 +85,7 @@ import additory as add
 
 # Works with polars
 df_polars = pl.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
-result = add.augment(df_polars, n_rows=100)
+result = add.synthetic(df_polars, n_rows=100)
 
 # Automatic type detection and conversion
 ```
@@ -159,27 +159,42 @@ patients_with_bsa = add.bsa(patients)
 result = add.fitness_score(add.bmr(add.bmi(patients)))
 ```
 
-### 🔄 Augment and Synthetic Data
+### 🔄 Synthetic Data Generation
 
-**Augment** generates more data similar to your existing dataset, while **Synthetic** creates entirely new datasets from schema definitions.
-
-**Key Differences:**
-- **Augment**: Learns patterns from existing data to create similar rows
-- **Synthetic**: Uses predefined schemas to generate structured data
+**Synthetic** generates additional data similar to your existing dataset using inline strategies.
 
 ```python
-# Augment existing data (learns from patterns)
-more_customers = add.augment(customers, n_rows=1000)
+# Extend existing data (learns from patterns)
+more_customers = add.synthetic(customers, n_rows=1000)
 
 # Create data from scratch with strategies
-new_data = add.augment("@new", n_rows=500, strategy={
+new_data = add.synthetic("@new", n_rows=500, strategy={
     'id': 'increment:start=1',
     'name': 'choice:[John,Jane,Bob]',
     'age': 'range:18-65'
 })
+```
+
+### 🤖 Text-Based Label Deduction
 
-# Generate from schema file (structured approach)
-customers = add.synth("customer_schema.toml", rows=10000)
+**Deduce** automatically fills in missing labels by learning from your existing labeled examples. Pure Python, no LLMs, offline-first.
+
+```python
+# Deduce missing labels from text
+tickets = pd.DataFrame({
+    "ticket_text": ["Cannot log in", "Billing question", "App crashes", "Need invoice"],
+    "category": ["Technical", "Billing", None, None]
+})
+
+# Automatically fill in missing categories
+result = add.deduce(tickets, from_column="ticket_text", to_column="category")
+
+# Use multiple columns for better accuracy
+result = add.deduce(
+    df,
+    from_column=["title", "description"],
+    to_column="category"
+)
 ```
 
 ## 🧪 Examples
@@ -197,7 +212,7 @@ customers = pd.DataFrame({
 })
 
 # Generate more customers
-customers = add.augment(customers, n_rows=10000)
+customers = add.synthetic(customers, n_rows=10000)
 
 # Add customer tiers
 tiers = pd.DataFrame({
@@ -223,7 +238,7 @@ strategy = {
     'height_cm': 'range:150-200'  # Height in cm
 }
 
-patients = add.augment("@new", n_rows=1000, strategy=strategy)
+patients = add.synthetic("@new", n_rows=1000, strategy=strategy)
 
 # Convert height to meters for expressions
 patients['height_m'] = patients['height_cm'] / 100
@@ -238,19 +253,19 @@ print(result.correlations)
 
 ## 📚 Documentation
 
-- **[Function Documentation](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0/)** - Detailed guides for each function
-- **[Expressions Guide](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0/expressions.html)** - Complete expressions reference
+- **[Function Documentation](https://github.com/sekarkrishna/additory/tree/main/documentation/)** - Detailed guides for each function
+- **[Expressions Guide](https://github.com/sekarkrishna/additory/tree/main/documentation/)** - Complete expressions reference
 
 ## 📄 License
 
-MIT License - see [LICENSE](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/LICENSE) file for details.
+MIT License - see [LICENSE](LICENSE) file for details.
 
 ## 📞 Support
 
 - **Issues**: [GitHub Issues](https://github.com/sekarkrishna/additory/issues)
-- **Documentation**: [Full Documentation](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/documentation/V0.1.0)
+- **Documentation**: [Full Documentation](https://github.com/sekarkrishna/additory/tree/main/documentation/)
 
-## 🗺️ v0.1.1 (February 2025)
+## 🗺️ v0.1.1 (January 2026)
 - Enhanced documentation and tutorials
 - Performance optimizations
 - Additional expressions

{additory-0.1.0a2 → additory-0.1.0a4}/additory/__init__.py

@@ -2,6 +2,9 @@
 
 from .dynamic_api import add as _api_instance
 
+# Version information
+__version__ = "0.1.0a4"
+
 # Expose the API instance normally
 add = _api_instance
 
@@ -12,4 +15,5 @@ def __getattr__(name):
 
 __all__ = [
     "add",
+    "__version__",
 ]

{additory-0.1.0a2 → additory-0.1.0a4}/additory/common/__init__.py

@@ -1,14 +1,14 @@
 """
 Common Utilities Module
 
-Shared functionality used by both augment and synthetic modules:
+Shared functionality used by both synthetic and expressions modules:
 - Distribution functions (normal, uniform, skewed, etc.)
 - List file management (.list format)
 - Pattern file management (.properties format)
 - Fallback resolution logic
 
 This module eliminates code duplication and provides consistent behavior
-across augment and synthetic data generation.
+across synthetic and expression data generation.
 """
 
 from .distributions import (

{additory-0.1.0a2 → additory-0.1.0a4}/additory/common/backend.py

@@ -180,11 +180,14 @@ def get_arrow_bridge():
         - Use for all cross-backend conversions
         - Handles pandas/polars/cuDF via Arrow
     """
-    from additory.core.backends.arrow_bridge import EnhancedArrowBridge
+    from additory.core.backends.arrow_bridge import EnhancedArrowBridge, ArrowBridgeError
     
     # Singleton pattern
     if not hasattr(get_arrow_bridge, '_instance'):
-        get_arrow_bridge._instance = EnhancedArrowBridge()
+        try:
+            get_arrow_bridge._instance = EnhancedArrowBridge()
+        except ArrowBridgeError:
+            get_arrow_bridge._instance = None
     
     return get_arrow_bridge._instance
 
@@ -194,7 +197,7 @@ def to_polars(df: Any, backend_type: BackendType = None) -> 'pl.DataFrame':
     Convert any dataframe to Polars via Arrow bridge.
     
     This is the primary conversion function for the Polars-only architecture.
-    All operations (expressions, augment, etc.) use this to convert input
+    All operations (expressions, synthetic, etc.) use this to convert input
     dataframes to Polars for processing.
     
     Args:
@@ -224,7 +227,7 @@ def to_polars(df: Any, backend_type: BackendType = None) -> 'pl.DataFrame':
         )
     
     # Fast path: already Polars
-    if isinstance(df, pl.DataFrame):
+    if HAS_POLARS and isinstance(df, pl.DataFrame):
         return df
     
     # Validate input
@@ -240,6 +243,13 @@ def to_polars(df: Any, backend_type: BackendType = None) -> 'pl.DataFrame':
     # Convert via Arrow bridge
     try:
         bridge = get_arrow_bridge()
+        if bridge is None:
+            # Fallback: direct conversion for pandas
+            if backend_type == "pandas":
+                if isinstance(df, pd.DataFrame):
+                    return pl.from_pandas(df)
+            raise RuntimeError("Arrow bridge not available and cannot convert non-pandas DataFrame")
+        
         arrow_table = bridge.to_arrow(df, backend_type)
         pl_df = bridge.from_arrow(arrow_table, "polars")
         return pl_df
@@ -309,6 +319,12 @@ def from_polars(pl_df: 'pl.DataFrame', target_backend: BackendType) -> Any:
     # Convert via Arrow bridge
     try:
         bridge = get_arrow_bridge()
+        if bridge is None:
+            # Fallback: direct conversion for pandas
+            if target_backend == "pandas":
+                return pl_df.to_pandas()
+            raise RuntimeError("Arrow bridge not available and cannot convert to non-pandas DataFrame")
+        
         arrow_table = bridge.to_arrow(pl_df, "polars")
         result_df = bridge.from_arrow(arrow_table, target_backend)
         return result_df

{additory-0.1.0a2 → additory-0.1.0a4}/additory/common/distributions.py

@@ -1,5 +1,5 @@
 """
-Distribution Strategies for Data Augmentation
+Distribution Strategies for Synthetic Data Generation
 
 Provides statistical distribution-based data generation:
 - Normal (Gaussian) distribution

{additory-0.1.0a2 → additory-0.1.0a4}/additory/common/sample_data.py

@@ -8,8 +8,8 @@ loaded on-demand using the existing .add file parser.
 Usage:
     from additory.common.sample_data import get_sample_dataset
     
-    # For augment
-    df = get_sample_dataset("augment", "sample")
+    # For synthetic
+    df = get_sample_dataset("synthetic", "sample")
     
     # For expressions (future)
     df = get_sample_dataset("expressions", "sample")
@@ -25,7 +25,7 @@ from additory.common.exceptions import ValidationError
 
 
 def get_sample_dataset(
-    module: str = "augment",
+    module: str = "synthetic",
     block: str = "sample",
     dataset_type: str = "clean"
 ) -> pl.DataFrame:
@@ -33,12 +33,12 @@ def get_sample_dataset(
     Load a sample dataset from .add files.
     
     This function provides centralized access to sample datasets across
-    all additory modules (augment, expressions, utilities). Sample datasets
+    all additory modules (synthetic, expressions, utilities). Sample datasets
     are stored as .add files in the reference/ directory structure.
     
     Args:
-        module: Module name ("augment", "expressions", "utilities")
-        block: Block name within the .add file ("sample" for augment)
+        module: Module name ("synthetic", "expressions", "utilities")
+        block: Block name within the .add file ("sample" for synthetic)
         dataset_type: Type of sample data ("clean" or "unclean")
     
     Returns:
@@ -48,8 +48,8 @@ def get_sample_dataset(
         ValidationError: If module, block, or dataset_type not found
     
     Examples:
-        >>> # Load augment sample dataset
-        >>> df = get_sample_dataset("augment", "sample")
+        >>> # Load synthetic sample dataset
+        >>> df = get_sample_dataset("synthetic", "sample")
         >>> print(df.shape)
         (50, 10)
         
@@ -57,7 +57,7 @@ def get_sample_dataset(
         >>> df = get_sample_dataset("expressions", "sample", "clean")
         >>> df_unclean = get_sample_dataset("expressions", "sample", "unclean")
     
-    Sample Dataset Structure (augment):
+    Sample Dataset Structure (synthetic):
         - id: Sequential numeric IDs (1-50)
         - emp_id: Employee IDs with pattern (EMP_001 - EMP_050)
         - order_id: Order IDs with different padding (ORD_0001 - ORD_0050)
@@ -72,8 +72,8 @@ def get_sample_dataset(
     # Construct path to .add file
     base_path = Path(__file__).parent.parent.parent / "reference"
     
-    if module == "augment":
-        add_file_path = base_path / "augment_definitions" / f"{block}_0.1.add"
+    if module == "synthetic":
+        add_file_path = base_path / "synthetic_definitions" / f"{block}_0.1.add"
     elif module == "expressions":
         add_file_path = base_path / "expressions_definitions" / f"{block}_0.1.add"
     elif module == "utilities":
@@ -81,7 +81,7 @@ def get_sample_dataset(
     else:
         raise ValidationError(
             f"Unknown module '{module}'. "
-            f"Valid modules: augment, expressions, utilities"
+            f"Valid modules: synthetic, expressions, utilities"
         )
     
     # Check if file exists
@@ -141,7 +141,7 @@ def list_available_samples() -> dict:
         >>> samples = list_available_samples()
         >>> print(samples)
         {
-            'augment': ['sample'],
+            'synthetic': ['sample'],
             'expressions': ['sample'],
             'utilities': []
         }
@@ -149,15 +149,15 @@ def list_available_samples() -> dict:
     base_path = Path(__file__).parent.parent.parent / "reference"
     available = {}
     
-    # Check augment
-    augment_path = base_path / "augment_definitions"
-    if augment_path.exists():
-        available['augment'] = [
+    # Check synthetic
+    synthetic_path = base_path / "synthetic_definitions"
+    if synthetic_path.exists():
+        available['synthetic'] = [
             f.stem.rsplit('_', 1)[0]  # Remove version suffix
-            for f in augment_path.glob("*.add")
+            for f in synthetic_path.glob("*.add")
         ]
     else:
-        available['augment'] = []
+        available['synthetic'] = []
     
     # Check expressions
     expressions_path = base_path / "expressions_definitions"

{additory-0.1.0a2 → additory-0.1.0a4}/additory/core/backends/arrow_bridge.py

@@ -16,6 +16,13 @@ try:
 except ImportError as e:
     ARROW_AVAILABLE = False
     IMPORT_ERROR = str(e)
+    # Create dummy classes for type annotations
+    class pa:
+        Table = Any
+    class pl:
+        DataFrame = Any
+    class pd:
+        DataFrame = Any
 
 from ..logging import log_info, log_warning
 from .cudf_bridge import get_cudf_bridge

{additory-0.1.0a2 → additory-0.1.0a4}/additory/core/config.py

@@ -329,14 +329,14 @@ def set_custom_formula_path(path):
 
 # backend preference setting
 
-_backend_preference: str | None = None  # "cpu", "gpu", or None
+_backend_preference: Optional[str] = None  # "cpu", "gpu", or None
 
-def set_backend_preference(mode: str | None):
+def set_backend_preference(mode: Optional[str]):
     global _backend_preference
     if mode not in (None, "cpu", "gpu"):
         raise ValueError("backend must be 'cpu', 'gpu', or None")
     _backend_preference = mode
 
-def get_backend_preference() -> str | None:
+def get_backend_preference() -> Optional[str]:
     return _backend_preference