churnkit 0.76.0a2__tar.gz → 0.76.1a1__tar.gz

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: churnkit
-Version: 0.76.0a2
+Version: 0.76.1a1
 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

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/exploration_notebooks/01_data_discovery.ipynb

@@ -137,10 +137,12 @@
     "# =============================================================================\n",
     "\n",
     "# DATA_PATH: Path to your data file (CSV, Parquet, or Delta)\n",
-    "DATA_PATH = \"../tests/fixtures/customer_retention_retail.csv\"\n",
+    "DATA_PATH = \"../tests/fixtures/customer_emails.csv\"\n",
+    "# or databricks /Volumes/churnkit/landing/datasets/customer_emails.csv\n",
+    "\n",
     "\n",
     "# TARGET_COLUMN: Your prediction target (set to None for auto-detection)\n",
-    "TARGET_COLUMN = \"unsubscribed\"\n",
+    "TARGET_COLUMN = None\n",
     "\n",
     "# ENTITY_COLUMN: Customer/user ID column (set to None for auto-detection)\n",
     "ENTITY_COLUMN = None\n",
@@ -169,7 +171,7 @@
     "#\n",
     "# EVENT-LEVEL (multiple rows per customer):\n",
     "# DATA_PATH = \"../tests/fixtures/customer_transactions.csv\"\n",
-    "DATA_PATH = \"../tests/fixtures/customer_emails.csv\"\n",
+    "# DATA_PATH = \"../tests/fixtures/customer_emails.csv\"\n",
     "# =============================================================================\n",
     "\n",
     "# OUTPUT_DIR: All outputs go here (gitignored)\n",

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "churnkit"
-version = "0.76.0a2"
+version = "0.76.1a1"
 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-0.76.0a2 → churnkit-0.76.1a1}/scripts/.claude/settings.local.json

@@ -3,7 +3,8 @@
     "allow": [
       "Bash(python -m pytest:*)",
       "Bash(python -m ruff check:*)",
-      "Bash(ruff check:*)"
+      "Bash(ruff check:*)",
+      "Bash(grep:*)"
     ]
   }
 }

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/src/customer_retention/__init__.py

@@ -17,7 +17,7 @@ Main module categories:
                 llm_context, iteration)
 """
 
-__version__ = "0.76.0a2"
+__version__ = "0.76.1a1"
 
 # Environment utilities (always available)
 from .core.compat import (

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/src/customer_retention/analysis/notebook_progress.py

@@ -5,7 +5,16 @@ from pathlib import Path
 from typing import Optional
 
 from customer_retention.core.compat import is_databricks
-from customer_retention.core.config.experiments import get_notebook_experiments_dir
+from customer_retention.core.config.experiments import get_notebook_experiments_dir, reload_config
+
+
+def _ensure_databricks_config_loaded() -> None:
+    if not is_databricks():
+        return
+    reload_config()
+
+
+_ensure_databricks_config_loaded()
 
 
 def track_and_export_previous(current_notebook: str) -> None:

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/src/customer_retention/core/config/experiments.py

@@ -1,7 +1,49 @@
+import json
 import os
 from pathlib import Path
 from typing import Optional
 
+_DATABRICKS_CONFIG_FILENAME = ".churnkit_config.json"
+
+
+def _workspace_config_path(workspace_path: str) -> Path:
+    return Path(f"/Workspace/{workspace_path}") / _DATABRICKS_CONFIG_FILENAME
+
+
+def _read_config_file(path: Path) -> dict | None:
+    try:
+        return json.loads(path.read_text()) if path.exists() else None
+    except (json.JSONDecodeError, OSError):
+        return None
+
+
+def _load_persisted_databricks_config() -> dict | None:
+    if not os.environ.get("DATABRICKS_RUNTIME_VERSION"):
+        return None
+    workspace_path = os.environ.get("CR_WORKSPACE_PATH")
+    if workspace_path:
+        return _read_config_file(_workspace_config_path(workspace_path))
+    cwd = Path.cwd()
+    for _ in range(5):
+        result = _read_config_file(cwd / _DATABRICKS_CONFIG_FILENAME)
+        if result:
+            return result
+        if cwd.parent == cwd:
+            break
+        cwd = cwd.parent
+    return None
+
+
+def persist_databricks_config(experiments_dir: str, catalog: str, schema: str, workspace_path: str | None = None) -> None:
+    if not workspace_path:
+        return
+    try:
+        _workspace_config_path(workspace_path).write_text(json.dumps({
+            "experiments_dir": experiments_dir, "catalog": catalog, "schema": schema,
+        }))
+    except OSError:
+        pass
+
 
 def _find_project_root() -> Path:
     path = Path(__file__).parent
@@ -17,6 +59,9 @@ def get_experiments_dir(default: Optional[str] = None) -> Path:
         return Path(os.environ["CR_EXPERIMENTS_DIR"])
     if default:
         return Path(default)
+    persisted = _load_persisted_databricks_config()
+    if persisted and "experiments_dir" in persisted:
+        return Path(persisted["experiments_dir"])
     return _find_project_root() / "experiments"
 
 
@@ -64,6 +109,21 @@ WORKSPACE_PATH = get_workspace_path()
 EXPERIMENT_NAME = get_experiment_name()
 
 
+def reload_config() -> None:
+    global EXPERIMENTS_DIR, FINDINGS_DIR, DATA_DIR, MLRUNS_DIR, FEATURE_STORE_DIR
+    global OUTPUT_DIR, CATALOG, SCHEMA, WORKSPACE_PATH, EXPERIMENT_NAME
+    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:
     base = experiments_dir or get_experiments_dir()
     directories = [

{churnkit-0.76.0a2 → churnkit-0.76.1a1}/src/customer_retention/integrations/databricks_init.py

@@ -22,7 +22,7 @@ class DatabricksInitResult:
             "CR_CATALOG": self.catalog,
             "CR_SCHEMA": self.schema,
             "CR_EXPERIMENT_NAME": self.experiment_name,
-            "CR_EXPERIMENTS_DIR": f"/Workspace/{self.workspace_path}/experiments" if self.workspace_path else "",
+            "CR_EXPERIMENTS_DIR": f"/Volumes/{self.catalog}/{self.schema}/experiments",
         }
         if self.workspace_path:
             env_vars["CR_WORKSPACE_PATH"] = self.workspace_path
@@ -38,10 +38,16 @@ def databricks_init(
     model_name: str = "customer_retention",
 ) -> DatabricksInitResult:
     _validate_databricks_environment()
+    if workspace_path:
+        workspace_path = _normalize_workspace_path(workspace_path)
+        _ensure_workspace_directory(workspace_path)
     _set_environment_variables(catalog, schema, workspace_path)
+    _persist_config(catalog, schema, workspace_path)
     resolved_experiment_name = experiment_name or _resolve_experiment_name_from_notebook_path()
     resolved_experiment_name = _make_absolute_experiment_path(resolved_experiment_name, workspace_path)
     _set_experiment_name_env_var(resolved_experiment_name)
+    _reload_config_constants()
+    _setup_experiment_directories()
     _configure_mlflow_experiment(resolved_experiment_name)
     notebooks_copied: list[str] = []
     if copy_notebooks and workspace_path:
@@ -69,15 +75,36 @@ def _validate_databricks_environment() -> None:
 def _set_environment_variables(catalog: str, schema: str, workspace_path: str | None) -> None:
     os.environ["CR_CATALOG"] = catalog
     os.environ["CR_SCHEMA"] = schema
+    os.environ["CR_EXPERIMENTS_DIR"] = f"/Volumes/{catalog}/{schema}/experiments"
     if workspace_path:
         os.environ["CR_WORKSPACE_PATH"] = workspace_path
-        os.environ["CR_EXPERIMENTS_DIR"] = f"/Workspace/{workspace_path}/experiments"
 
 
 def _set_experiment_name_env_var(experiment_name: str) -> None:
     os.environ["CR_EXPERIMENT_NAME"] = experiment_name
 
 
+def _persist_config(catalog: str, schema: str, workspace_path: str | None) -> None:
+    from customer_retention.core.config.experiments import persist_databricks_config
+
+    persist_databricks_config(f"/Volumes/{catalog}/{schema}/experiments", catalog, schema, workspace_path)
+
+
+def _reload_config_constants() -> None:
+    from customer_retention.core.config.experiments import reload_config
+
+    reload_config()
+
+
+def _setup_experiment_directories() -> None:
+    from customer_retention.core.config.experiments import setup_experiments_structure
+
+    try:
+        setup_experiments_structure()
+    except OSError:
+        pass
+
+
 def _resolve_experiment_name_from_notebook_path() -> str:
     try:
         dbutils = _get_dbutils()
@@ -98,6 +125,12 @@ def _get_dbutils() -> Any | None:
         return None
 
 
+def _normalize_workspace_path(workspace_path: str) -> str:
+    if workspace_path.startswith("/Workspace/"):
+        return workspace_path[len("/Workspace/"):]
+    return workspace_path
+
+
 def _make_absolute_experiment_path(experiment_name: str, workspace_path: str | None) -> str:
     if experiment_name.startswith("/"):
         return experiment_name
@@ -118,6 +151,13 @@ def _configure_mlflow_experiment(experiment_name: str) -> None:
         pass
 
 
+def _ensure_workspace_directory(workspace_path: str) -> None:
+    try:
+        Path(f"/Workspace/{workspace_path}").mkdir(parents=True, exist_ok=True)
+    except OSError:
+        pass
+
+
 def _copy_exploration_notebooks(workspace_path: str) -> list[str]:
     from customer_retention.generators.notebook_generator.project_init import ProjectInitializer
 
@@ -139,11 +179,14 @@ def _copy_exploration_notebooks(workspace_path: str) -> list[str]:
 
 
 def _display_init_summary(result: DatabricksInitResult) -> None:
-    print("ChurnKit Databricks Initialization Complete")
+    from customer_retention import __version__
+
+    print(f"ChurnKit v{__version__} Databricks Initialization Complete")
     print("=" * 45)
     print(f"  Catalog:          {result.catalog}")
     print(f"  Schema:           {result.schema}")
     print(f"  Experiment:       {result.experiment_name}")
+    print(f"  Experiments Dir:  /Volumes/{result.catalog}/{result.schema}/experiments")
     print(f"  Workspace Path:   {result.workspace_path or '(not set)'}")
     print(f"  Model Name:       {result.model_name}")
     if result.notebooks_copied: