additory 0.1.0a1__tar.gz

additory-0.1.0a1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Krishnamoorthy Sankaran
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

additory-0.1.0a1/PKG-INFO

@@ -0,0 +1,293 @@
+Metadata-Version: 2.4
+Name: additory
+Version: 0.1.0a1
+Summary: A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data support.
+Author: Krishnamoorthy Sankaran
+License: MIT
+Project-URL: homepage, https://github.com/sekarkrishna/additory
+Project-URL: documentation, https://github.com/sekarkrishna/additory/tree/main/documentation/V0.1.0
+Project-URL: source, https://github.com/sekarkrishna/additory
+Project-URL: issues, https://github.com/sekarkrishna/additory/issues
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.5
+Requires-Dist: polars>=0.20
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: requests>=2.31
+Requires-Dist: toml>=0.10
+Requires-Dist: scipy>=1.9
+Requires-Dist: numpy>=1.21
+Provides-Extra: gpu
+Requires-Dist: cudf>=24.0; extra == "gpu"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: pytest-xdist>=3.0; extra == "dev"
+Requires-Dist: hypothesis>=6.0; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: coverage>=7.0; extra == "dev"
+Dynamic: license-file
+
+# Additory
+
+**A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data 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/)
+
+**Author:** Krishnamoorthy Sankaran
+
+## 🛠️ Requirements
+
+- **Python**: 3.9+
+- **Core dependencies**: pandas, polars, numpy, scipy
+- **Optional**: cuDF (for GPU support)
+
+## 📦 Installation
+
+```bash
+pip install additory==0.1.0a1
+```
+
+**Optional GPU support:**
+```bash
+pip install additory[gpu]==0.1.0a1  # Includes cuDF for GPU acceleration
+```
+
+**Development installation:**
+```bash
+pip install additory[dev]==0.1.0a1  # Includes testing and development tools
+```
+
+## 🎯 Core Functions
+
+| 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.scan()` | Data profiling & analysis | `add.scan(df, preset="full")` |
+
+## 🧬 Available Expressions
+
+Additory includes 12 built-in health and fitness expressions:
+
+- **`add.bmi()`** - Body Mass Index
+- **`add.bsa()`** - Body Surface Area  
+- **`add.bmr()`** - Basal Metabolic Rate
+- **`add.waist_hip_ratio()`** - Waist-to-Hip Ratio
+- **`add.body_fat_percentage()`** - Body Fat Percentage
+- **`add.ideal_body_weight()`** - Ideal Body Weight
+- **`add.blood_pressure_category()`** - BP Classification
+- **`add.cholesterol_ratio()`** - Cholesterol Ratio
+- **`add.age_category()`** - Age Classification
+- **`add.fitness_score()`** - Overall Fitness Score
+
+```python
+# Health calculations
+patients = pd.DataFrame({
+    'weight_kg': [70, 80, 65],  # Weight in kilograms
+    'height_m': [1.75, 1.80, 1.60],  # Height in meters
+    'age': [25, 35, 45],
+    'gender': ['M', 'F', 'M']
+})
+
+patients_bmi = add.bmi(patients)
+patients_bsa = add.bsa(patients)
+fitness_scores = add.fitness_score(patients)
+
+# Chain multiple expressions
+result = add.fitness_score(add.bmr(add.bmi(patients)))
+```
+
+## 🔧 DataFrame Support
+
+Additory works seamlessly with multiple DataFrame libraries:
+
+- **pandas** - Full support
+- **polars** - Full support
+- **cuDF** - GPU acceleration support
+
+```python
+import polars as pl
+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)
+
+# Automatic type detection and conversion
+```
+
+## ✨ Key Features
+
+### 🔧 Utilities
+
+**add.to() - Data Lookup & Joins**
+Simplified syntax for bringing columns from one dataframe to another.
+
+```python
+# Simple lookup
+orders_with_prices = add.to(
+    orders, 
+    from_df=products, 
+    bring='price', 
+    against='product_id'
+)
+
+# Multiple columns and keys
+enriched = add.to(
+    orders,
+    from_df=products,
+    bring=['price', 'category'],
+    against=['product_id', 'region']
+)
+```
+
+**add.onehotencoding() - Categorical Encoding**
+Convert categorical columns to one-hot encoded format.
+
+```python
+# One-hot encoding (single column)
+encoded = add.onehotencoding(df, 'category')
+```
+
+**add.harmonize_units() - Unit Standardization**
+Standardize units across your dataset.
+
+```python
+# Unit harmonization
+standardized = add.harmonize_units(
+    df, 
+    value_column='temperature', 
+    unit_column='unit',
+    target_unit='C'
+)
+```
+
+### 🧮 Expressions
+
+Pre-built calculations for health, fitness, and common metrics. Simple examples:
+
+```python
+# Create patient data with correct column names
+patients = pd.DataFrame({
+    'weight_kg': [70, 80, 65],  # Weight in kilograms
+    'height_m': [1.75, 1.80, 1.60],  # Height in meters
+    'age': [25, 35, 45],
+    'gender': ['M', 'F', 'M']
+})
+
+# Calculate BMI
+patients_with_bmi = add.bmi(patients)
+
+# Calculate Body Surface Area
+patients_with_bsa = add.bsa(patients)
+
+# Chain multiple expressions
+result = add.fitness_score(add.bmr(add.bmi(patients)))
+```
+
+### 🔄 Augment and Synthetic Data
+
+**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
+
+```python
+# Augment existing data (learns from patterns)
+more_customers = add.augment(customers, n_rows=1000)
+
+# Create data from scratch with strategies
+new_data = add.augment("@new", n_rows=500, strategy={
+    'id': 'increment:start=1',
+    'name': 'choice:[John,Jane,Bob]',
+    'age': 'range:18-65'
+})
+
+# Generate from schema file (structured approach)
+customers = add.synth("customer_schema.toml", rows=10000)
+```
+
+## 🧪 Examples
+
+### E-commerce Data Pipeline
+```python
+import pandas as pd
+import additory as add
+
+# Start with small customer sample
+customers = pd.DataFrame({
+    'customer_id': [1, 2, 3],
+    'age': [25, 35, 45],
+    'region': ['North', 'South', 'East']
+})
+
+# Generate more customers
+customers = add.augment(customers, n_rows=10000)
+
+# Add customer tiers
+tiers = pd.DataFrame({
+    'customer_id': range(1, 4),  # Match original IDs
+    'tier': ['Gold', 'Silver', 'Bronze']
+})
+
+# Use pipeline approach
+result = (customers
+    .pipe(add.to, from_df=tiers, bring='tier', against='customer_id')
+    .pipe(add.scan, preset="quick"))
+
+print(result.summary())
+```
+
+### Healthcare Data Analysis
+```python
+# Create patient data from scratch
+strategy = {
+    'patient_id': 'increment:start=1',
+    'age': 'range:18-80',
+    'weight_kg': 'range:50-120',  # Weight in kg
+    'height_cm': 'range:150-200'  # Height in cm
+}
+
+patients = add.augment("@new", n_rows=1000, strategy=strategy)
+
+# Convert height to meters for expressions
+patients['height_m'] = patients['height_cm'] / 100
+
+# Calculate health metrics using pipeline
+result = (patients
+    .pipe(add.bmi)
+    .pipe(add.scan, preset="correlations"))
+
+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
+
+## 📄 License
+
+MIT License - see [LICENSE](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/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)
+
+## 🗺️ v0.1.1 (February 2025)
+- Enhanced documentation and tutorials
+- Performance optimizations
+- Additional expressions
+- Advanced synthetic data patterns
+
+---
+
+**Made with ❤️ for data scientists, analysts, and developers who love working with data.**

additory-0.1.0a1/README.md

@@ -0,0 +1,261 @@
+# Additory
+
+**A semantic, extensible dataframe transformation engine with expressions, lookup, synthetic data, and sample-data 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/)
+
+**Author:** Krishnamoorthy Sankaran
+
+## 🛠️ Requirements
+
+- **Python**: 3.9+
+- **Core dependencies**: pandas, polars, numpy, scipy
+- **Optional**: cuDF (for GPU support)
+
+## 📦 Installation
+
+```bash
+pip install additory==0.1.0a1
+```
+
+**Optional GPU support:**
+```bash
+pip install additory[gpu]==0.1.0a1  # Includes cuDF for GPU acceleration
+```
+
+**Development installation:**
+```bash
+pip install additory[dev]==0.1.0a1  # Includes testing and development tools
+```
+
+## 🎯 Core Functions
+
+| 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.scan()` | Data profiling & analysis | `add.scan(df, preset="full")` |
+
+## 🧬 Available Expressions
+
+Additory includes 12 built-in health and fitness expressions:
+
+- **`add.bmi()`** - Body Mass Index
+- **`add.bsa()`** - Body Surface Area  
+- **`add.bmr()`** - Basal Metabolic Rate
+- **`add.waist_hip_ratio()`** - Waist-to-Hip Ratio
+- **`add.body_fat_percentage()`** - Body Fat Percentage
+- **`add.ideal_body_weight()`** - Ideal Body Weight
+- **`add.blood_pressure_category()`** - BP Classification
+- **`add.cholesterol_ratio()`** - Cholesterol Ratio
+- **`add.age_category()`** - Age Classification
+- **`add.fitness_score()`** - Overall Fitness Score
+
+```python
+# Health calculations
+patients = pd.DataFrame({
+    'weight_kg': [70, 80, 65],  # Weight in kilograms
+    'height_m': [1.75, 1.80, 1.60],  # Height in meters
+    'age': [25, 35, 45],
+    'gender': ['M', 'F', 'M']
+})
+
+patients_bmi = add.bmi(patients)
+patients_bsa = add.bsa(patients)
+fitness_scores = add.fitness_score(patients)
+
+# Chain multiple expressions
+result = add.fitness_score(add.bmr(add.bmi(patients)))
+```
+
+## 🔧 DataFrame Support
+
+Additory works seamlessly with multiple DataFrame libraries:
+
+- **pandas** - Full support
+- **polars** - Full support
+- **cuDF** - GPU acceleration support
+
+```python
+import polars as pl
+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)
+
+# Automatic type detection and conversion
+```
+
+## ✨ Key Features
+
+### 🔧 Utilities
+
+**add.to() - Data Lookup & Joins**
+Simplified syntax for bringing columns from one dataframe to another.
+
+```python
+# Simple lookup
+orders_with_prices = add.to(
+    orders, 
+    from_df=products, 
+    bring='price', 
+    against='product_id'
+)
+
+# Multiple columns and keys
+enriched = add.to(
+    orders,
+    from_df=products,
+    bring=['price', 'category'],
+    against=['product_id', 'region']
+)
+```
+
+**add.onehotencoding() - Categorical Encoding**
+Convert categorical columns to one-hot encoded format.
+
+```python
+# One-hot encoding (single column)
+encoded = add.onehotencoding(df, 'category')
+```
+
+**add.harmonize_units() - Unit Standardization**
+Standardize units across your dataset.
+
+```python
+# Unit harmonization
+standardized = add.harmonize_units(
+    df, 
+    value_column='temperature', 
+    unit_column='unit',
+    target_unit='C'
+)
+```
+
+### 🧮 Expressions
+
+Pre-built calculations for health, fitness, and common metrics. Simple examples:
+
+```python
+# Create patient data with correct column names
+patients = pd.DataFrame({
+    'weight_kg': [70, 80, 65],  # Weight in kilograms
+    'height_m': [1.75, 1.80, 1.60],  # Height in meters
+    'age': [25, 35, 45],
+    'gender': ['M', 'F', 'M']
+})
+
+# Calculate BMI
+patients_with_bmi = add.bmi(patients)
+
+# Calculate Body Surface Area
+patients_with_bsa = add.bsa(patients)
+
+# Chain multiple expressions
+result = add.fitness_score(add.bmr(add.bmi(patients)))
+```
+
+### 🔄 Augment and Synthetic Data
+
+**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
+
+```python
+# Augment existing data (learns from patterns)
+more_customers = add.augment(customers, n_rows=1000)
+
+# Create data from scratch with strategies
+new_data = add.augment("@new", n_rows=500, strategy={
+    'id': 'increment:start=1',
+    'name': 'choice:[John,Jane,Bob]',
+    'age': 'range:18-65'
+})
+
+# Generate from schema file (structured approach)
+customers = add.synth("customer_schema.toml", rows=10000)
+```
+
+## 🧪 Examples
+
+### E-commerce Data Pipeline
+```python
+import pandas as pd
+import additory as add
+
+# Start with small customer sample
+customers = pd.DataFrame({
+    'customer_id': [1, 2, 3],
+    'age': [25, 35, 45],
+    'region': ['North', 'South', 'East']
+})
+
+# Generate more customers
+customers = add.augment(customers, n_rows=10000)
+
+# Add customer tiers
+tiers = pd.DataFrame({
+    'customer_id': range(1, 4),  # Match original IDs
+    'tier': ['Gold', 'Silver', 'Bronze']
+})
+
+# Use pipeline approach
+result = (customers
+    .pipe(add.to, from_df=tiers, bring='tier', against='customer_id')
+    .pipe(add.scan, preset="quick"))
+
+print(result.summary())
+```
+
+### Healthcare Data Analysis
+```python
+# Create patient data from scratch
+strategy = {
+    'patient_id': 'increment:start=1',
+    'age': 'range:18-80',
+    'weight_kg': 'range:50-120',  # Weight in kg
+    'height_cm': 'range:150-200'  # Height in cm
+}
+
+patients = add.augment("@new", n_rows=1000, strategy=strategy)
+
+# Convert height to meters for expressions
+patients['height_m'] = patients['height_cm'] / 100
+
+# Calculate health metrics using pipeline
+result = (patients
+    .pipe(add.bmi)
+    .pipe(add.scan, preset="correlations"))
+
+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
+
+## 📄 License
+
+MIT License - see [LICENSE](https://github.com/sekarkrishna/additory/tree/main/V0.1.0a1/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)
+
+## 🗺️ v0.1.1 (February 2025)
+- Enhanced documentation and tutorials
+- Performance optimizations
+- Additional expressions
+- Advanced synthetic data patterns
+
+---
+
+**Made with ❤️ for data scientists, analysts, and developers who love working with data.**

additory-0.1.0a1/additory/__init__.py

@@ -0,0 +1,15 @@
+# additory/__init__.py
+
+from .dynamic_api import add as _api_instance
+
+# Expose the API instance normally
+add = _api_instance
+
+# Module-level __getattr__ to forward dynamic attributes
+def __getattr__(name):
+    # Delegate all unknown attributes to the API instance
+    return getattr(_api_instance, name)
+
+__all__ = [
+    "add",
+]

additory-0.1.0a1/additory/analysis/__init__.py

@@ -0,0 +1,48 @@
+"""
+Analysis Module for Data Profiling
+
+Provides comprehensive data analysis capabilities:
+- Distribution detection and fitting
+- Correlation analysis
+- Cardinality analysis
+- Data quality metrics
+- Data profiling and scanning
+"""
+
+from additory.analysis.distributions import (
+    detect_distributions,
+    fit_distribution,
+    DistributionFit
+)
+from additory.analysis.correlations import (
+    calculate_correlations,
+    CorrelationResult
+)
+from additory.analysis.cardinality import (
+    analyze_cardinality,
+    CardinalityInfo
+)
+from additory.analysis.quality import (
+    analyze_quality,
+    QualityMetrics
+)
+from additory.analysis.scan import (
+    scan,
+    ScanResult,
+    ColumnInfo
+)
+
+__all__ = [
+    'detect_distributions',
+    'fit_distribution',
+    'DistributionFit',
+    'calculate_correlations',
+    'CorrelationResult',
+    'analyze_cardinality',
+    'CardinalityInfo',
+    'analyze_quality',
+    'QualityMetrics',
+    'scan',
+    'ScanResult',
+    'ColumnInfo',
+]