provenanced 0.5.0__tar.gz

provenanced-0.5.0/LICENSE

@@ -0,0 +1,30 @@
+Business Source License 1.1
+
+Licensor: Provenance, Inc.
+Licensed Work: ProveIt
+
+The Licensed Work is provided under the terms of this License. The Licensed
+Work is (c) 2024-2026 Provenance, Inc.
+
+Grant of Rights: Subject to the terms and conditions of this License, the
+Licensor hereby grants you a non-exclusive, worldwide, royalty-free right to
+use, copy, modify, and distribute the Licensed Work, in each case subject to
+the limitations below.
+
+Limitation: You may not use the Licensed Work for a Commercial Offering that
+competes with any product or service offered by the Licensor that includes the
+Licensed Work.
+
+Change Date: Four years from the date the Licensed Work is first publicly
+distributed by the Licensor.
+
+Change License: Apache License, Version 2.0
+
+Notice: This License does not grant you any right in any trademark or logo of
+the Licensor. THE LICENSED WORK IS PROVIDED "AS IS". THE LICENSOR HEREBY
+DISCLAIMS ALL WARRANTIES, WHETHER EXPRESS, IMPLIED, STATUTORY OR OTHERWISE,
+AND SPECIFICALLY DISCLAIMS ALL IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT, WITH RESPECT TO THE LICENSED
+WORK.
+
+For full terms, see https://mariadb.com/bsl11/

provenanced-0.5.0/PKG-INFO

@@ -0,0 +1,176 @@
+Metadata-Version: 2.4
+Name: provenanced
+Version: 0.5.0
+Summary: ProveIt: Cryptographically Provable AI Compliance for Banks
+Author-email: "Provenance, Inc." <info@provenance.ai>
+License-Expression: BUSL-1.1
+Project-URL: Homepage, https://proveit.ai
+Keywords: provenance,ml,machine-learning,data-lineage,audit,compliance,fairness,fair-lending,disparate-impact,documentation,model-risk-management,sr-11-7,ecoa,eu-ai-act,banking
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Financial and Insurance Industry
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Documentation
+Classifier: Topic :: Office/Business :: Financial
+Classifier: Topic :: System :: Logging
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Provides-Extra: fairness
+Requires-Dist: scikit-learn>=1.3; extra == "fairness"
+Provides-Extra: torch
+Requires-Dist: torch>=2.0; extra == "torch"
+Provides-Extra: tensorflow
+Requires-Dist: tensorflow>=2.13; extra == "tensorflow"
+Provides-Extra: xgboost
+Requires-Dist: xgboost>=1.7; extra == "xgboost"
+Provides-Extra: lightgbm
+Requires-Dist: lightgbm>=4.0; extra == "lightgbm"
+Provides-Extra: catboost
+Requires-Dist: catboost>=1.2; extra == "catboost"
+Provides-Extra: shap
+Requires-Dist: scikit-learn>=1.3; extra == "shap"
+Requires-Dist: shap>=0.42; extra == "shap"
+Provides-Extra: dashboard
+Requires-Dist: flask>=2.3; extra == "dashboard"
+Requires-Dist: python-dotenv>=1.0; extra == "dashboard"
+Provides-Extra: postgres
+Requires-Dist: psycopg2-binary>=2.9; extra == "postgres"
+Provides-Extra: otel
+Requires-Dist: opentelemetry-api>=1.20; extra == "otel"
+Requires-Dist: opentelemetry-sdk>=1.20; extra == "otel"
+Provides-Extra: pdf
+Requires-Dist: fpdf2>=2.7; extra == "pdf"
+Provides-Extra: docx
+Requires-Dist: python-docx>=1.0; extra == "docx"
+Provides-Extra: export
+Requires-Dist: fpdf2>=2.7; extra == "export"
+Requires-Dist: python-docx>=1.0; extra == "export"
+Provides-Extra: all
+Requires-Dist: scikit-learn>=1.3; extra == "all"
+Requires-Dist: flask>=2.3; extra == "all"
+Requires-Dist: python-dotenv>=1.0; extra == "all"
+Requires-Dist: psycopg2-binary>=2.9; extra == "all"
+Requires-Dist: shap>=0.42; extra == "all"
+Requires-Dist: opentelemetry-api>=1.20; extra == "all"
+Requires-Dist: opentelemetry-sdk>=1.20; extra == "all"
+Requires-Dist: fpdf2>=2.7; extra == "all"
+Requires-Dist: python-docx>=1.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
+
+# ProveIt
+
+Cryptographically provable AI compliance for banks: tamper-proof provenance tracking, fair lending analysis, and automated compliance documentation.
+
+## Install
+
+```bash
+pip install -e .
+pip install -e ".[all]"  # with sklearn, flask, postgres, shap, opentelemetry
+```
+
+## Quick Start
+
+### Provenance Tracking
+
+```python
+import proveit
+
+proveit.configure(dag=True)
+apps = proveit.wrap(apps_df, "applications.csv")
+credit = proveit.wrap(credit_df, "credit_bureau.csv")
+
+df = apps.merge(credit, on="applicant_id")
+risk_score = df["balance"] / df["limit"]
+
+dag = proveit.get_dag_simple(risk_score)
+print(dag.source_nodes)
+```
+
+### Fairness Analysis
+
+```python
+from proveit.fairness import FairLensEngine, FairLensConfig
+
+config = FairLensConfig(
+    protected_columns=["race", "gender", "age"],
+    industry="lending",
+)
+engine = FairLensEngine(config=config)
+results = engine.analyze(
+    model=model, X_train=X_train, y_train=y_train,
+    X_test=X_test, y_test=y_test, protected_data=prot_test,
+)
+print(results.disparate_impact_results)
+```
+
+### Compliance Documentation
+
+```python
+from proveit.docs import AutoDocEngine, TemplateType, ModelMetadata
+
+engine = AutoDocEngine()
+report = engine.generate(
+    template=TemplateType.SR_11_7,
+    model_metadata=ModelMetadata(
+        name="Risk Model v2",
+        version="2.1.0",
+        model_type="XGBoost",
+    ),
+)
+report.save("sr117_report.md")
+```
+
+## CLI
+
+```bash
+proveit fairness analyze --model m.pkl --data d.csv --protected race,sex --industry lending
+proveit docs generate --template sr11-7 --model metadata.json
+proveit docs templates
+proveit dashboard
+```
+
+## Modules
+
+| Module | Description |
+|--------|-------------|
+| `proveit` | Core provenance DAG engine with Merkle tree anchoring |
+| `proveit.fairness` | Disparate impact, proxy detection, LDA search, adverse action codes |
+| `proveit.docs` | SR 11-7, EU AI Act, Model Cards, ECOA, GDPR, NIST AI RMF, dbt |
+| `proveit.compliance` | EU AI Act and ECOA compliance engines |
+| `proveit.persistence` | SQLite, PostgreSQL, DuckDB, S3 storage backends |
+| `proveit.integrations` | Airflow, Kubeflow, Prefect, Dagster, dbt, Vertex AI, SageMaker, Azure ML |
+| `proveit.dashboard` | Flask-based provenance dashboard |
+
+## Test
+
+```bash
+pytest tests/ -v
+```
+
+## Requirements
+
+- Python >= 3.9
+- numpy >= 1.24
+- pandas >= 2.0
+- scikit-learn >= 1.3
+
+## License
+
+Proprietary. Copyright (c) 2024-2026 Provenance, Inc. All rights reserved.

provenanced-0.5.0/README.md

@@ -0,0 +1,100 @@
+# ProveIt
+
+Cryptographically provable AI compliance for banks: tamper-proof provenance tracking, fair lending analysis, and automated compliance documentation.
+
+## Install
+
+```bash
+pip install -e .
+pip install -e ".[all]"  # with sklearn, flask, postgres, shap, opentelemetry
+```
+
+## Quick Start
+
+### Provenance Tracking
+
+```python
+import proveit
+
+proveit.configure(dag=True)
+apps = proveit.wrap(apps_df, "applications.csv")
+credit = proveit.wrap(credit_df, "credit_bureau.csv")
+
+df = apps.merge(credit, on="applicant_id")
+risk_score = df["balance"] / df["limit"]
+
+dag = proveit.get_dag_simple(risk_score)
+print(dag.source_nodes)
+```
+
+### Fairness Analysis
+
+```python
+from proveit.fairness import FairLensEngine, FairLensConfig
+
+config = FairLensConfig(
+    protected_columns=["race", "gender", "age"],
+    industry="lending",
+)
+engine = FairLensEngine(config=config)
+results = engine.analyze(
+    model=model, X_train=X_train, y_train=y_train,
+    X_test=X_test, y_test=y_test, protected_data=prot_test,
+)
+print(results.disparate_impact_results)
+```
+
+### Compliance Documentation
+
+```python
+from proveit.docs import AutoDocEngine, TemplateType, ModelMetadata
+
+engine = AutoDocEngine()
+report = engine.generate(
+    template=TemplateType.SR_11_7,
+    model_metadata=ModelMetadata(
+        name="Risk Model v2",
+        version="2.1.0",
+        model_type="XGBoost",
+    ),
+)
+report.save("sr117_report.md")
+```
+
+## CLI
+
+```bash
+proveit fairness analyze --model m.pkl --data d.csv --protected race,sex --industry lending
+proveit docs generate --template sr11-7 --model metadata.json
+proveit docs templates
+proveit dashboard
+```
+
+## Modules
+
+| Module | Description |
+|--------|-------------|
+| `proveit` | Core provenance DAG engine with Merkle tree anchoring |
+| `proveit.fairness` | Disparate impact, proxy detection, LDA search, adverse action codes |
+| `proveit.docs` | SR 11-7, EU AI Act, Model Cards, ECOA, GDPR, NIST AI RMF, dbt |
+| `proveit.compliance` | EU AI Act and ECOA compliance engines |
+| `proveit.persistence` | SQLite, PostgreSQL, DuckDB, S3 storage backends |
+| `proveit.integrations` | Airflow, Kubeflow, Prefect, Dagster, dbt, Vertex AI, SageMaker, Azure ML |
+| `proveit.dashboard` | Flask-based provenance dashboard |
+
+## Test
+
+```bash
+pytest tests/ -v
+```
+
+## Requirements
+
+- Python >= 3.9
+- numpy >= 1.24
+- pandas >= 2.0
+- scikit-learn >= 1.3
+
+## License
+
+Proprietary. Copyright (c) 2024-2026 Provenance, Inc. All rights reserved.

provenanced-0.5.0/proveit/__init__.py

@@ -0,0 +1,301 @@
+"""
+ProveIt: Cryptographically Provable AI Compliance for Banks
+
+Tamper-proof data provenance tracking, algorithmic fairness analysis,
+and automated compliance documentation for financial institutions.
+
+Quick start:
+    import proveit
+
+    proveit.configure(api_key="hyd_live_...")  # required
+    df = proveit.wrap(raw_df, "users.csv")
+    dag = proveit.get_dag_simple(df['income'] / df['debt'])
+"""
+
+__version__ = "0.5.0"
+
+# =============================================================================
+# Configuration API  (always available - these ARE the gate)
+# =============================================================================
+from .config import (
+    configure,
+    wrap,
+    get_dag as get_dag_simple,
+    audit as audit_simple,
+    flush,
+    reset,
+    get_stats,
+    tracking,
+    get_tracker,
+)
+
+# =============================================================================
+# Lazy-loaded names: require proveit.configure(api_key=...) before access
+# =============================================================================
+_LAZY_IMPORTS = {
+    # HYDRA-24 DAG System
+    "DAGTracker": ("hydra24_dag", "DAGTracker"),
+    "DAGTrackedSeries": ("hydra24_dag", "DAGTrackedSeries"),
+    "DAGTrackedDataFrame": ("hydra24_dag", "DAGTrackedDataFrame"),
+    "wrap_dataframe": ("hydra24_dag", "wrap_dataframe_dag"),
+    "get_dag": ("hydra24_dag", "get_dag_for_series"),
+    "dag_audit": ("hydra24_dag", "dag_audit"),
+    "ComputationDAG": ("hydra24_dag", "ComputationDAG"),
+    "DAGNode": ("hydra24_dag", "DAGNode"),
+    "DAGEdge": ("hydra24_dag", "DAGEdge"),
+    "NodeType": ("hydra24_dag", "NodeType"),
+
+    # HYDRA-24 Enhanced System
+    "ProvenanceTracker": ("hydra24_simple", "ProvenanceTracker"),
+    "TrackedSeries": ("hydra24_simple", "TrackedSeries"),
+    "TrackedDataFrame": ("hydra24_simple", "TrackedDataFrame"),
+    "wrap_dataframe_simple": ("hydra24_simple", "wrap_dataframe"),
+    "audit": ("hydra24_simple", "audit"),
+    "audit_series_diversity": ("hydra24_simple", "audit_series_diversity"),
+    "OpCode": ("hydra24_simple", "OpCode"),
+    "MAX_PAIRS": ("hydra24_simple", "MAX_PAIRS"),
+
+    # Persistence
+    "create_storage": ("persistence.factory", "create_storage"),
+    "init_database": ("persistence", "init_database"),
+    "get_schema_ddl": ("persistence", "get_schema_ddl"),
+    "PostgreSQLStorage": ("persistence", "PostgreSQLStorage"),
+    "reconstruct_dag": ("persistence", "reconstruct_dag"),
+    "query_by_fingerprint": ("persistence", "query_by_fingerprint"),
+    "query_by_source": ("persistence", "query_by_source"),
+
+    # Fairness
+    "FairLensEngine": ("fairness", "FairLensEngine"),
+    "FairLensConfig": ("fairness", "FairLensConfig"),
+
+    # Documentation
+    "AutoDocEngine": ("docs", "AutoDocEngine"),
+    "TemplateType": ("docs", "TemplateType"),
+
+    # Vendor Readiness
+    "VendorDueDiligencePackage": ("vendor", "VendorDueDiligencePackage"),
+    "CertificationTracker": ("vendor", "CertificationTracker"),
+    "PlatformHealthCheck": ("vendor", "PlatformHealthCheck"),
+
+    # Governance
+    "ModelRecord": ("governance", "ModelRecord"),
+    "ModelRegistry": ("governance", "ModelRegistry"),
+    "PIIDetector": ("governance", "PIIDetector"),
+    "RetentionPolicyEngine": ("governance", "RetentionPolicyEngine"),
+    "RegulatoryCalendar": ("governance", "RegulatoryCalendar"),
+
+    # Examiner
+    "ExaminerPackage": ("examiner", "ExaminerPackage"),
+    "ModelCardGenerator": ("examiner", "ModelCardGenerator"),
+
+    # Compliance
+    "ComplianceScorer": ("compliance.score", "ComplianceScorer"),
+    "AttestationManager": ("compliance.cro_features", "AttestationManager"),
+    "PeerBenchmark": ("compliance.cro_features", "PeerBenchmark"),
+    "QuickWinRecommender": ("compliance.cro_features", "QuickWinRecommender"),
+    "RegulatoryChangeAssessor": ("compliance.cro_features", "RegulatoryChangeAssessor"),
+    "RemediationQueue": ("compliance.cro_features", "RemediationQueue"),
+    "RiskHeatmap": ("compliance.cro_features", "RiskHeatmap"),
+    "ExceptionTracker": ("governance.exception_tracker", "ExceptionTracker"),
+    "ComplianceException": ("governance.exception_tracker", "ComplianceException"),
+}
+
+
+def __getattr__(name: str):
+    """Lazy-load proveit classes; require configure() first in production."""
+    if name in _LAZY_IMPORTS:
+        import os
+        from .config import _config
+
+        _testing = (
+            os.environ.get("PROVEIT_TESTING")
+            or os.environ.get("HYDRA24_TESTING")
+        )
+        if not _config._initialized and not _testing:
+            raise RuntimeError(
+                f"ProveIt not configured. Call proveit.configure(api_key='...') "
+                f"before accessing proveit.{name}.\n"
+                "Get your API key at https://proveit.ai/signup"
+            )
+
+        module_name, real_name = _LAZY_IMPORTS[name]
+        import importlib
+        try:
+            mod = importlib.import_module(f".{module_name}", __package__)
+        except ImportError as exc:
+            raise AttributeError(
+                f"proveit.{name} requires an optional dependency: {exc}"
+            ) from exc
+        obj = getattr(mod, real_name)
+        globals()[name] = obj
+        return obj
+
+    raise AttributeError(f"module 'proveit' has no attribute {name!r}")
+
+
+# =============================================================================
+# Public API
+# =============================================================================
+__all__ = [
+    # Version
+    "__version__",
+
+    # Simplified API (easiest - recommended for new users)
+    "configure",
+    "wrap",
+    "get_dag_simple",
+    "audit_simple",
+    "flush",
+    "reset",
+    "get_stats",
+    "tracking",
+    "get_tracker",
+
+    # HYDRA-24 DAG (advanced API)
+    "DAGTracker",
+    "DAGTrackedSeries",
+    "DAGTrackedDataFrame",
+    "wrap_dataframe",
+    "get_dag",
+    "dag_audit",
+    "ComputationDAG",
+    "DAGNode",
+    "DAGEdge",
+    "NodeType",
+
+    # HYDRA-24 Enhanced
+    "ProvenanceTracker",
+    "TrackedSeries",
+    "TrackedDataFrame",
+    "wrap_dataframe_simple",
+    "audit",
+    "audit_series_diversity",
+    "OpCode",
+    "MAX_PAIRS",
+
+    # Storage factory
+    "create_storage",
+
+    # Persistence (optional)
+    "init_database",
+    "get_schema_ddl",
+    "PostgreSQLStorage",
+    "reconstruct_dag",
+    "query_by_fingerprint",
+    "query_by_source",
+
+    # Fairness
+    "FairLensEngine",
+    "FairLensConfig",
+
+    # Docs
+    "AutoDocEngine",
+    "TemplateType",
+
+    # Vendor Readiness
+    "VendorDueDiligencePackage",
+    "CertificationTracker",
+    "PlatformHealthCheck",
+
+    # Data Governance & Model Registry
+    "ModelRecord",
+    "ModelRegistry",
+    "PIIDetector",
+    "RetentionPolicyEngine",
+    "RegulatoryCalendar",
+
+    # Examiner Package
+    "ExaminerPackage",
+    "ModelCardGenerator",
+
+    # Compliance Scoring
+    "ComplianceScorer",
+
+    # CRO Features
+    "AttestationManager",
+    "ComplianceException",
+    "ExceptionTracker",
+    "PeerBenchmark",
+    "QuickWinRecommender",
+    "RegulatoryChangeAssessor",
+    "RemediationQueue",
+    "RiskHeatmap",
+
+    # Logging
+    "setup_logging",
+]
+
+
+# =============================================================================
+# Production Logging Setup
+# =============================================================================
+
+def setup_logging(
+    level: str = "INFO",
+    fmt: str = "json",
+    include_timestamp: bool = True,
+) -> None:
+    """Configure logging for production bank deployments.
+
+    Sets up structured logging across all ``proveit.*`` loggers so that
+    output is compatible with log aggregation tools (Splunk, ELK,
+    Datadog, CloudWatch Logs).
+
+    Args:
+        level: Log level (``"DEBUG"``, ``"INFO"``, ``"WARNING"``, ``"ERROR"``).
+        fmt: ``"json"`` for structured JSON lines (default, recommended
+             for production), or ``"text"`` for human-readable output.
+        include_timestamp: Include ISO-8601 timestamps (default ``True``).
+
+    Example::
+
+        import proveit
+        proveit.setup_logging(level="INFO", fmt="json")
+    """
+    import logging
+    import json as _json
+    import sys
+    from datetime import datetime, timezone
+
+    numeric_level = getattr(logging, level.upper(), logging.INFO)
+
+    class _JSONFormatter(logging.Formatter):
+        def format(self, record: logging.LogRecord) -> str:
+            entry = {
+                "logger": record.name,
+                "level": record.levelname,
+                "message": record.getMessage(),
+            }
+            if include_timestamp:
+                entry["timestamp"] = (
+                    datetime.fromtimestamp(record.created, tz=timezone.utc)
+                    .isoformat()
+                )
+            if record.exc_info and record.exc_info[0] is not None:
+                entry["exception"] = self.formatException(record.exc_info)
+            return _json.dumps(entry, default=str)
+
+    class _TextFormatter(logging.Formatter):
+        _fmt_ts = "%(asctime)s %(name)s %(levelname)s %(message)s"
+        _fmt_no_ts = "%(name)s %(levelname)s %(message)s"
+
+        def __init__(self, with_ts: bool = True) -> None:
+            super().__init__(
+                fmt=self._fmt_ts if with_ts else self._fmt_no_ts,
+                datefmt="%Y-%m-%dT%H:%M:%S%z",
+            )
+
+    root_logger = logging.getLogger("proveit")
+    root_logger.setLevel(numeric_level)
+
+    root_logger.handlers.clear()
+
+    handler = logging.StreamHandler(sys.stderr)
+    handler.setLevel(numeric_level)
+
+    if fmt == "json":
+        handler.setFormatter(_JSONFormatter())
+    else:
+        handler.setFormatter(_TextFormatter(with_ts=include_timestamp))
+
+    root_logger.addHandler(handler)