churnkit 0.75.1a3__tar.gz → 0.76.0a1__tar.gz

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: churnkit
-Version: 0.75.1a3
+Version: 0.76.0a1
 Summary: Structured ML framework for customer churn prediction -- from exploration notebooks to production pipelines, locally or on Databricks.
 Project-URL: Homepage, https://github.com/aladjov/CR
 Project-URL: Documentation, https://github.com/aladjov/CR/wiki
@@ -164,12 +164,14 @@ It serves two audiences:
 
 ## Quick Start
 
-### 1. Install
+### 1. Install (local)
 
 ```bash
 pip install "churnkit[ml]"
 ```
 
+For **Databricks**, see the [Databricks Installation](https://github.com/aladjov/CR/wiki/Databricks-Installation) guide.
+
 ### 2. Bootstrap notebooks into your project
 
 ```bash
@@ -200,6 +202,7 @@ Detailed documentation lives in the [Wiki](https://github.com/aladjov/CR/wiki):
 | Topic | Wiki Page |
 |-------|-----------|
 | Installation options & environment setup | [Getting Started](https://github.com/aladjov/CR/wiki/Getting-Started) |
+| Databricks install & `databricks_init()` setup | [Databricks Installation](https://github.com/aladjov/CR/wiki/Databricks-Installation) |
 | Medallion architecture & system design | [Architecture](https://github.com/aladjov/CR/wiki/Architecture) |
 | Notebook workflow & iteration tracking | [Exploration Loop](https://github.com/aladjov/CR/wiki/Exploration-Loop) |
 | Leakage-safe temporal data preparation | [Temporal Framework](https://github.com/aladjov/CR/wiki/Temporal-Framework) |

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/README.md

@@ -34,12 +34,14 @@ It serves two audiences:
 
 ## Quick Start
 
-### 1. Install
+### 1. Install (local)
 
 ```bash
 pip install "churnkit[ml]"
 ```
 
+For **Databricks**, see the [Databricks Installation](https://github.com/aladjov/CR/wiki/Databricks-Installation) guide.
+
 ### 2. Bootstrap notebooks into your project
 
 ```bash
@@ -70,6 +72,7 @@ Detailed documentation lives in the [Wiki](https://github.com/aladjov/CR/wiki):
 | Topic | Wiki Page |
 |-------|-----------|
 | Installation options & environment setup | [Getting Started](https://github.com/aladjov/CR/wiki/Getting-Started) |
+| Databricks install & `databricks_init()` setup | [Databricks Installation](https://github.com/aladjov/CR/wiki/Databricks-Installation) |
 | Medallion architecture & system design | [Architecture](https://github.com/aladjov/CR/wiki/Architecture) |
 | Notebook workflow & iteration tracking | [Exploration Loop](https://github.com/aladjov/CR/wiki/Exploration-Loop) |
 | Leakage-safe temporal data preparation | [Temporal Framework](https://github.com/aladjov/CR/wiki/Temporal-Framework) |

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "churnkit"
-version = "0.75.1a3"
+version = "0.76.0a1"
 description = "Structured ML framework for customer churn prediction -- from exploration notebooks to production pipelines, locally or on Databricks."
 readme = "README.md"
 license = {text = "Apache-2.0"}

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/src/customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "0.75.1a3"
+__version__ = "0.76.0a1"
 
 # Environment utilities (always available)
 from .core.compat import (
@@ -34,4 +34,14 @@ __all__ = [
     "is_spark_available",
     "is_databricks",
     "is_notebook",
+    # Databricks initialization
+    "databricks_init",
 ]
+
+
+def __getattr__(name: str):
+    if name == "databricks_init":
+        from .integrations.databricks_init import databricks_init
+
+        return databricks_init
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/src/customer_retention/core/compat/__init__.py

@@ -98,6 +98,8 @@ def merge(left: Any, right: Any, how: str = "inner", on: Any = None, **kwargs: A
     return pd.merge(left, right, how=how, on=on, **kwargs)
 
 
+native_pd = _pandas
+
 Timestamp = _pandas.Timestamp
 Timedelta = _pandas.Timedelta
 DatetimeIndex = _pandas.DatetimeIndex
@@ -213,6 +215,7 @@ compat = PandasCompat()
 
 __all__ = [
     "pd",
+    "native_pd",
     "DataFrame",
     "Series",
     "Timestamp",

churnkit-0.76.0a1/src/customer_retention/core/config/__init__.py

@@ -0,0 +1,74 @@
+from .column_config import ColumnConfig, ColumnType, DatasetGranularity
+from .experiments import (
+    CATALOG,
+    DATA_DIR,
+    EXPERIMENT_NAME,
+    EXPERIMENTS_DIR,
+    FEATURE_STORE_DIR,
+    FINDINGS_DIR,
+    MLRUNS_DIR,
+    OUTPUT_DIR,
+    SCHEMA,
+    WORKSPACE_PATH,
+    get_catalog,
+    get_data_dir,
+    get_experiment_name,
+    get_experiments_dir,
+    get_feature_store_dir,
+    get_findings_dir,
+    get_mlruns_dir,
+    get_notebook_experiments_dir,
+    get_schema,
+    get_workspace_path,
+    setup_experiments_structure,
+)
+from .pipeline_config import (
+    BronzeConfig,
+    DedupStrategy,
+    GoldConfig,
+    ModelingConfig,
+    PathConfig,
+    PipelineConfig,
+    SilverConfig,
+    ValidationConfig,
+)
+from .source_config import DataSourceConfig, FileFormat, Grain, SourceType
+
+__all__ = [
+    "ColumnType",
+    "ColumnConfig",
+    "DatasetGranularity",
+    "SourceType",
+    "FileFormat",
+    "Grain",
+    "DataSourceConfig",
+    "DedupStrategy",
+    "BronzeConfig",
+    "SilverConfig",
+    "GoldConfig",
+    "ModelingConfig",
+    "ValidationConfig",
+    "PathConfig",
+    "PipelineConfig",
+    "CATALOG",
+    "SCHEMA",
+    "WORKSPACE_PATH",
+    "EXPERIMENT_NAME",
+    "EXPERIMENTS_DIR",
+    "FINDINGS_DIR",
+    "DATA_DIR",
+    "MLRUNS_DIR",
+    "FEATURE_STORE_DIR",
+    "OUTPUT_DIR",
+    "get_catalog",
+    "get_schema",
+    "get_workspace_path",
+    "get_experiment_name",
+    "get_experiments_dir",
+    "get_findings_dir",
+    "get_data_dir",
+    "get_mlruns_dir",
+    "get_feature_store_dir",
+    "get_notebook_experiments_dir",
+    "setup_experiments_structure",
+]

{churnkit-0.75.1a3 → churnkit-0.76.0a1}/src/customer_retention/core/config/experiments.py

@@ -36,12 +36,32 @@ def get_feature_store_dir(default: Optional[str] = None) -> Path:
     return get_experiments_dir(default) / "feature_repo"
 
 
+def get_catalog(default: str = "main") -> str:
+    return os.environ.get("CR_CATALOG", default)
+
+
+def get_schema(default: str = "default") -> str:
+    return os.environ.get("CR_SCHEMA", default)
+
+
+def get_workspace_path(default: str | None = None) -> str | None:
+    return os.environ.get("CR_WORKSPACE_PATH", default)
+
+
+def get_experiment_name(default: str = "customer_retention") -> str:
+    return os.environ.get("CR_EXPERIMENT_NAME", default)
+
+
 EXPERIMENTS_DIR = get_experiments_dir()
 FINDINGS_DIR = get_findings_dir()
 DATA_DIR = get_data_dir()
 MLRUNS_DIR = get_mlruns_dir()
 FEATURE_STORE_DIR = get_feature_store_dir()
 OUTPUT_DIR = FINDINGS_DIR
+CATALOG = get_catalog()
+SCHEMA = get_schema()
+WORKSPACE_PATH = get_workspace_path()
+EXPERIMENT_NAME = get_experiment_name()
 
 
 def setup_experiments_structure(experiments_dir: Optional[Path] = None) -> None: