datatoolpack 0.8.0__tar.gz → 0.10.1__tar.gz

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datatoolpack
-Version: 0.8.0
+Version: 0.10.1
 Summary: Official Python SDK for the AutoData ML data preparation pipeline API
 Home-page: https://autodata.datatoolpack.com
 Author: AutoData Team
@@ -62,7 +62,7 @@ with AutoDataClient(api_key="dtpk_YOUR_API_KEY") as client:
     result = client.process(
         file_path="data.csv",
         target_columns=["price"],
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -162,7 +162,7 @@ client.close()
 result = client.process(
     file_path="data.csv",           # Path to input file (CSV, XLSX, Parquet, ...)
     target_columns=["price"],       # y-column(s) for ML
-    output_rows=20000,              # Target row count in output
+    output_rows=10000,              # Target row count in the synthetic output (default 10000)
     tools={                         # Toggle pipeline steps (all optional)
         "anomaly": False,           # Anomaly detection (off by default)
         "dtc": True,                # Data Type Conversion
@@ -199,7 +199,7 @@ result = client.process(
         {"name": "dsg.csv", "url": "/download/.../dsg.csv", "size": 2097152, "description": "..."},
         {"name": "dsm_train.csv", ...},
     ],
-    "row_count": 20000,
+    "row_count": 10000,
     "duration_seconds": 42.1,
 }
 ```
@@ -289,6 +289,30 @@ client.download_file("/api/v1/download/abc123.../dsg.csv", "dsg.csv")
 
 ---
 
+## Feature Selection (F4)
+
+Rank a completed session's columns by predictive importance — **without re-running the pipeline**. Handy for trimming wide datasets before training.
+
+### `client.recommend_features(session_id, target_columns, methods, top_k)`
+
+```python
+ranking = client.recommend_features(
+    session_id="abc123...",            # a completed session you own
+    target_columns=["price"],          # rank features against these target(s)
+    methods=["mutual_information"],    # one or more methods (see below); default ["mutual_information"]
+    top_k=20,                          # number of top features to return (default 20)
+)
+# {
+#   "ranking":    [{"feature": "sqft", "score": 0.81}, ...],   # combined across methods
+#   "per_method": {"mutual_information": [...], "shap_importance": [...]},
+#   "warnings":   [...],
+# }
+```
+
+**Available methods:** `variance_threshold`, `correlation_pruning`, `mutual_information`, `rfe`, `shap_importance`, `pca`. Pass several to blend their rankings, e.g. `methods=["mutual_information", "shap_importance"]`. (SHAP-based ranking uses a fast LightGBM model on the server; it degrades gracefully to `mutual_information` if those libraries are unavailable.)
+
+---
+
 ## API Keys & Usage
 
 ### `client.list_keys()` — List API keys
@@ -336,6 +360,8 @@ Read data directly from databases and cloud storage instead of uploading files.
 | `kafka`       | Apache Kafka                       | `bootstrap_servers`, `topic`, `group_id`            |
 | `kinesis`     | Amazon Kinesis                     | `stream_name`, `region`, `access_key_id`, `secret_access_key` |
 
+> **More connectors:** AutoData supports 30+ source types. Beyond the common ones above you can also pass `oracle`, `redshift`, `cassandra`, `dynamodb`, `elasticsearch`, `clickhouse`, `timescaledb`, `synapse`, `azure_blob`, `adls`, `sap_hana`, `mqtt`, `opcua`, `influxdb`, `pi_web`, `salesforce`, `hubspot`, `stripe`, `netsuite`, `google_sheets`, `ga4`, `sharepoint`, and `http`/`rest` as `connector_type`. See **Dashboard → Documentation → Connector Data Sources** for each type's required `secrets` fields.
+
 ### Quick connector example
 
 ```python
@@ -363,7 +389,7 @@ with AutoDataClient(api_key="dtpk_...") as client:
         table="orders",
         target_columns=["price"],
         secrets={"connection_string": "postgresql://user:pass@host/db"},
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -452,7 +478,7 @@ result = client.process_from_connector(
     table="orders",
     target_columns=["price"],
     secrets={"connection_string": "postgresql://..."},
-    output_rows=20000,
+    output_rows=10000,
     incremental=True,          # Only fetch new rows since last sync
     type_casts={"age": "int"}, # Override column types before processing
     wait=True,
@@ -474,7 +500,7 @@ client.write_output(
     if_exists="replace",       # "replace", "append", "fail", or "merge"
     merge_keys=["id"],         # column names for merge matching (when if_exists='merge')
 )
-# {"success": True, "rows_written": 20000, "table": "ml_prepared_data"}
+# {"success": True, "rows_written": 10000, "table": "ml_prepared_data"}
 ```
 
 ---
@@ -639,6 +665,65 @@ client.delete_scheduled_run(run_id="run-id")
 
 ---
 
+## Triggers (F7)
+
+Auto-start a pipeline when an external event fires — an inbound webhook, a connector watermark advancing, another pipeline completing, or a quality alert. Triggers are feature-flagged on the server (`FEATURE_FLAG_TRIGGERS`); if the flag is off, these endpoints return `404`.
+
+### `client.create_trigger(name, trigger_type, config, target_pipeline_config, enabled)`
+
+```python
+trigger = client.create_trigger(
+    name="Reprocess on new S3 batch",
+    trigger_type="inbound_webhook",   # inbound_webhook | watermark_advance | pipeline_completion | quality_alert
+    config={},                         # type-specific (see table below)
+    target_pipeline_config={           # the pipeline to run when the trigger fires
+        "source_type": "s3",
+        "credential_id": "cred-uuid",
+        "table": "incoming/sales.csv",
+        "target_columns": ["revenue"],
+        "output_rows": 10000,
+    },
+    enabled=True,
+)
+# For inbound_webhook the secret is returned ONLY once — save it now:
+print(trigger["webhook_secret"], trigger["inbound_url"])
+```
+
+**Trigger types & their `config`:**
+
+| `trigger_type`        | `config` keys |
+|-----------------------|---------------|
+| `inbound_webhook`     | optional `{"hmac_key": "..."}` — require HMAC-SHA256-signed requests |
+| `watermark_advance`   | `{"credential_id", "table", "watermark_column", "min_advance"}` |
+| `pipeline_completion` | `{}` — chain off another pipeline finishing |
+| `quality_alert`       | `{}` — fire when a quality-alert rule trips |
+
+```python
+# List / fetch / update / delete
+triggers = client.list_triggers()
+t        = client.get_trigger(trigger_id)
+client.update_trigger(trigger_id, enabled=False)   # name | enabled | config | target_pipeline_config
+client.delete_trigger(trigger_id)
+
+# Dry-run: validate config + target WITHOUT firing
+report = client.test_trigger(trigger_id)
+# {"would_fire": True, "checks": {...}}
+```
+
+**Firing an inbound webhook** from your own system:
+
+```bash
+curl -X POST "https://autodata.datatoolpack.com/trigger/inbound/<webhook_secret>" \
+     -H "Content-Type: application/json" \
+     -d '{"any": "payload"}'
+# If you set an hmac_key, also sign the raw body:
+#   X-Signature: sha256=<hex HMAC-SHA256 of the request body>
+```
+
+Inbound firing is rate-limited and HMAC-verified server-side; repeated failures auto-disable the trigger.
+
+---
+
 ## Folder Listeners
 
 Automatically trigger pipelines when new files appear in cloud storage:
@@ -819,6 +904,11 @@ with AutoDataClient() as client:
 | `list_keys()` | List all API keys for the account |
 | `get_usage()` | Get credit usage statistics |
 
+### Feature Selection
+| Method | Description |
+|--------|-------------|
+| `recommend_features(session_id, target_columns, ...)` | Rank a completed session's features (F4) |
+
 ### Connectors
 | Method | Description |
 |--------|-------------|
@@ -866,6 +956,16 @@ with AutoDataClient() as client:
 | `toggle_scheduled_run(run_id)` | Enable/disable a scheduled run |
 | `run_scheduled_now(run_id)` | Trigger a scheduled run immediately |
 
+### Triggers
+| Method | Description |
+|--------|-------------|
+| `list_triggers()` | List your triggers |
+| `create_trigger(name, trigger_type, ...)` | Create an event trigger (F7) |
+| `get_trigger(trigger_id)` | Fetch one trigger |
+| `update_trigger(trigger_id, ...)` | Update a trigger |
+| `delete_trigger(trigger_id)` | Delete a trigger |
+| `test_trigger(trigger_id)` | Dry-run a trigger without firing |
+
 ### Folder Listeners
 | Method | Description |
 |--------|-------------|

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/README.md

@@ -25,7 +25,7 @@ with AutoDataClient(api_key="dtpk_YOUR_API_KEY") as client:
     result = client.process(
         file_path="data.csv",
         target_columns=["price"],
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -125,7 +125,7 @@ client.close()
 result = client.process(
     file_path="data.csv",           # Path to input file (CSV, XLSX, Parquet, ...)
     target_columns=["price"],       # y-column(s) for ML
-    output_rows=20000,              # Target row count in output
+    output_rows=10000,              # Target row count in the synthetic output (default 10000)
     tools={                         # Toggle pipeline steps (all optional)
         "anomaly": False,           # Anomaly detection (off by default)
         "dtc": True,                # Data Type Conversion
@@ -162,7 +162,7 @@ result = client.process(
         {"name": "dsg.csv", "url": "/download/.../dsg.csv", "size": 2097152, "description": "..."},
         {"name": "dsm_train.csv", ...},
     ],
-    "row_count": 20000,
+    "row_count": 10000,
     "duration_seconds": 42.1,
 }
 ```
@@ -252,6 +252,30 @@ client.download_file("/api/v1/download/abc123.../dsg.csv", "dsg.csv")
 
 ---
 
+## Feature Selection (F4)
+
+Rank a completed session's columns by predictive importance — **without re-running the pipeline**. Handy for trimming wide datasets before training.
+
+### `client.recommend_features(session_id, target_columns, methods, top_k)`
+
+```python
+ranking = client.recommend_features(
+    session_id="abc123...",            # a completed session you own
+    target_columns=["price"],          # rank features against these target(s)
+    methods=["mutual_information"],    # one or more methods (see below); default ["mutual_information"]
+    top_k=20,                          # number of top features to return (default 20)
+)
+# {
+#   "ranking":    [{"feature": "sqft", "score": 0.81}, ...],   # combined across methods
+#   "per_method": {"mutual_information": [...], "shap_importance": [...]},
+#   "warnings":   [...],
+# }
+```
+
+**Available methods:** `variance_threshold`, `correlation_pruning`, `mutual_information`, `rfe`, `shap_importance`, `pca`. Pass several to blend their rankings, e.g. `methods=["mutual_information", "shap_importance"]`. (SHAP-based ranking uses a fast LightGBM model on the server; it degrades gracefully to `mutual_information` if those libraries are unavailable.)
+
+---
+
 ## API Keys & Usage
 
 ### `client.list_keys()` — List API keys
@@ -299,6 +323,8 @@ Read data directly from databases and cloud storage instead of uploading files.
 | `kafka`       | Apache Kafka                       | `bootstrap_servers`, `topic`, `group_id`            |
 | `kinesis`     | Amazon Kinesis                     | `stream_name`, `region`, `access_key_id`, `secret_access_key` |
 
+> **More connectors:** AutoData supports 30+ source types. Beyond the common ones above you can also pass `oracle`, `redshift`, `cassandra`, `dynamodb`, `elasticsearch`, `clickhouse`, `timescaledb`, `synapse`, `azure_blob`, `adls`, `sap_hana`, `mqtt`, `opcua`, `influxdb`, `pi_web`, `salesforce`, `hubspot`, `stripe`, `netsuite`, `google_sheets`, `ga4`, `sharepoint`, and `http`/`rest` as `connector_type`. See **Dashboard → Documentation → Connector Data Sources** for each type's required `secrets` fields.
+
 ### Quick connector example
 
 ```python
@@ -326,7 +352,7 @@ with AutoDataClient(api_key="dtpk_...") as client:
         table="orders",
         target_columns=["price"],
         secrets={"connection_string": "postgresql://user:pass@host/db"},
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -415,7 +441,7 @@ result = client.process_from_connector(
     table="orders",
     target_columns=["price"],
     secrets={"connection_string": "postgresql://..."},
-    output_rows=20000,
+    output_rows=10000,
     incremental=True,          # Only fetch new rows since last sync
     type_casts={"age": "int"}, # Override column types before processing
     wait=True,
@@ -437,7 +463,7 @@ client.write_output(
     if_exists="replace",       # "replace", "append", "fail", or "merge"
     merge_keys=["id"],         # column names for merge matching (when if_exists='merge')
 )
-# {"success": True, "rows_written": 20000, "table": "ml_prepared_data"}
+# {"success": True, "rows_written": 10000, "table": "ml_prepared_data"}
 ```
 
 ---
@@ -602,6 +628,65 @@ client.delete_scheduled_run(run_id="run-id")
 
 ---
 
+## Triggers (F7)
+
+Auto-start a pipeline when an external event fires — an inbound webhook, a connector watermark advancing, another pipeline completing, or a quality alert. Triggers are feature-flagged on the server (`FEATURE_FLAG_TRIGGERS`); if the flag is off, these endpoints return `404`.
+
+### `client.create_trigger(name, trigger_type, config, target_pipeline_config, enabled)`
+
+```python
+trigger = client.create_trigger(
+    name="Reprocess on new S3 batch",
+    trigger_type="inbound_webhook",   # inbound_webhook | watermark_advance | pipeline_completion | quality_alert
+    config={},                         # type-specific (see table below)
+    target_pipeline_config={           # the pipeline to run when the trigger fires
+        "source_type": "s3",
+        "credential_id": "cred-uuid",
+        "table": "incoming/sales.csv",
+        "target_columns": ["revenue"],
+        "output_rows": 10000,
+    },
+    enabled=True,
+)
+# For inbound_webhook the secret is returned ONLY once — save it now:
+print(trigger["webhook_secret"], trigger["inbound_url"])
+```
+
+**Trigger types & their `config`:**
+
+| `trigger_type`        | `config` keys |
+|-----------------------|---------------|
+| `inbound_webhook`     | optional `{"hmac_key": "..."}` — require HMAC-SHA256-signed requests |
+| `watermark_advance`   | `{"credential_id", "table", "watermark_column", "min_advance"}` |
+| `pipeline_completion` | `{}` — chain off another pipeline finishing |
+| `quality_alert`       | `{}` — fire when a quality-alert rule trips |
+
+```python
+# List / fetch / update / delete
+triggers = client.list_triggers()
+t        = client.get_trigger(trigger_id)
+client.update_trigger(trigger_id, enabled=False)   # name | enabled | config | target_pipeline_config
+client.delete_trigger(trigger_id)
+
+# Dry-run: validate config + target WITHOUT firing
+report = client.test_trigger(trigger_id)
+# {"would_fire": True, "checks": {...}}
+```
+
+**Firing an inbound webhook** from your own system:
+
+```bash
+curl -X POST "https://autodata.datatoolpack.com/trigger/inbound/<webhook_secret>" \
+     -H "Content-Type: application/json" \
+     -d '{"any": "payload"}'
+# If you set an hmac_key, also sign the raw body:
+#   X-Signature: sha256=<hex HMAC-SHA256 of the request body>
+```
+
+Inbound firing is rate-limited and HMAC-verified server-side; repeated failures auto-disable the trigger.
+
+---
+
 ## Folder Listeners
 
 Automatically trigger pipelines when new files appear in cloud storage:
@@ -782,6 +867,11 @@ with AutoDataClient() as client:
 | `list_keys()` | List all API keys for the account |
 | `get_usage()` | Get credit usage statistics |
 
+### Feature Selection
+| Method | Description |
+|--------|-------------|
+| `recommend_features(session_id, target_columns, ...)` | Rank a completed session's features (F4) |
+
 ### Connectors
 | Method | Description |
 |--------|-------------|
@@ -829,6 +919,16 @@ with AutoDataClient() as client:
 | `toggle_scheduled_run(run_id)` | Enable/disable a scheduled run |
 | `run_scheduled_now(run_id)` | Trigger a scheduled run immediately |
 
+### Triggers
+| Method | Description |
+|--------|-------------|
+| `list_triggers()` | List your triggers |
+| `create_trigger(name, trigger_type, ...)` | Create an event trigger (F7) |
+| `get_trigger(trigger_id)` | Fetch one trigger |
+| `update_trigger(trigger_id, ...)` | Update a trigger |
+| `delete_trigger(trigger_id)` | Delete a trigger |
+| `test_trigger(trigger_id)` | Dry-run a trigger without firing |
+
 ### Folder Listeners
 | Method | Description |
 |--------|-------------|

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/datatoolpack/__init__.py

@@ -1,4 +1,4 @@
 from .client import AutoDataClient, AutoDataError
 
-__version__ = "0.8.0"
+__version__ = "0.10.1"
 __all__ = ["AutoDataClient", "AutoDataError", "__version__"]

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/datatoolpack/client.py

@@ -12,7 +12,7 @@ Usage::
     result = client.process(
         file_path="data.csv",
         target_columns=["price"],
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 """
@@ -776,20 +776,29 @@ class AutoDataClient:
         Args:
             connector_type: One of the supported types:
 
-                Databases / warehouses:
+                Databases:
                   ``sql`` (Postgres/MySQL/MSSQL via SQLAlchemy URL),
-                  ``snowflake``, ``bigquery``, ``redshift``, ``oracle``,
-                  ``databricks``, ``fabric`` (Microsoft Fabric).
+                  ``mongodb``, ``oracle``, ``cassandra``, ``dynamodb``,
+                  ``elasticsearch``.
 
-                NoSQL:
-                  ``mongodb``, ``cassandra``, ``dynamodb``, ``elasticsearch``.
+                Data warehouses:
+                  ``snowflake``, ``bigquery``, ``redshift``, ``clickhouse``,
+                  ``databricks``, ``fabric`` (Microsoft Fabric),
+                  ``synapse`` (Azure Synapse), ``sap_hana`` (SAP HANA).
 
-                Object storage / data lakes:
+                Object storage / data lakes / files:
                   ``s3``, ``gcs``, ``azure_blob``, ``adls_gen2`` (Azure
-                  Data Lake Storage Gen2), ``delta`` (Delta Lake).
+                  Data Lake Storage Gen2), ``delta`` (Delta Lake),
+                  ``google_sheets``.
 
-                Streaming:
-                  ``kafka``, ``kinesis``.
+                Streaming & IoT / time-series:
+                  ``kafka``, ``kinesis``, ``mqtt``, ``opcua`` (OPC-UA),
+                  ``influxdb``, ``timescaledb``, ``pi_web_api``
+                  (OSIsoft/AVEVA PI).
+
+                SaaS & apps:
+                  ``salesforce``, ``hubspot``, ``stripe``, ``ga4``
+                  (Google Analytics 4), ``netsuite``, ``sharepoint``.
 
                 Generic:
                   ``http`` (REST/HTTP API).
@@ -934,7 +943,11 @@ class AutoDataClient:
             custom_query:   Optional SQL query (overrides *table*).
             output_rows:    Target row count in output dataset.
             tools:          Toggle pipeline steps (same as :meth:`process`).
+                            Set ``tools["feature_selection"]=True`` to run F4
+                            feature selection between DTC and MDH.
             advanced_params: Fine-grained parameters (same as :meth:`process`).
+                            ``feature_selection_config`` = ``{method, top_k,
+                            threshold}`` configures the F4 stage when enabled.
             wait:           Block until processing completes.
             poll_interval:  Seconds between status polls.
             download_path:  Directory to save results.
@@ -982,6 +995,11 @@ class AutoDataClient:
             body["enable_cds"] = bool(tls.get("cds", True))
             body["enable_dsm"] = bool(tls.get("dsm", True))
             body["enable_dsg"] = bool(tls.get("dsg", True))
+            body["enable_feature_selection"] = bool(tls.get("feature_selection", False))  # F4 (opt-in)
+        # F4 — feature selection config: {method, top_k, threshold}
+        fs_cfg = adv.get("feature_selection_config")
+        if fs_cfg:
+            body["feature_selection_config"] = fs_cfg
         if credential_id:
             body["credential_id"] = credential_id
         if secrets:
@@ -1024,6 +1042,110 @@ class AutoDataClient:
             final["dataframes"] = self.get_dataframes(session_id, names=output_preferences)
         return final
 
+    def recommend_features(
+        self,
+        session_id: str,
+        target_columns: List[str],
+        methods: Optional[List[str]] = None,
+        top_k: int = 20,
+    ) -> Dict:
+        """Rank a completed session's columns (F4) without re-running the pipeline.
+
+        Args:
+            session_id:      A completed session owned by the caller.
+            target_columns:  Target column name(s) to rank features against.
+            methods:         Ranking methods — any of ``variance_threshold``,
+                             ``correlation_pruning``, ``mutual_information``,
+                             ``rfe``, ``shap_importance``, ``pca``. Defaults to
+                             ``["mutual_information"]``.
+            top_k:           Number of top features to return (default 20).
+
+        Returns:
+            Dict with ``ranking`` (combined), ``per_method``, and ``warnings``.
+        """
+        body = {
+            "session_id": session_id,
+            "target_columns": target_columns,
+            "methods": methods or ["mutual_information"],
+            "top_k": top_k,
+        }
+        r = self._request("POST", self._url("/feature-selection/recommend"), json=body)
+        self._raise_for_error(r)
+        return r.json()
+
+    # ── F7 — Triggers ─────────────────────────────────────────────────────
+    def list_triggers(self) -> List[Dict]:
+        """List the caller's triggers (webhook secrets are never returned)."""
+        r = self._request("GET", self._url("/triggers"))
+        self._raise_for_error(r)
+        return r.json().get("triggers", [])
+
+    def create_trigger(
+        self,
+        name: str,
+        trigger_type: str,
+        config: Optional[Dict] = None,
+        target_pipeline_config: Optional[Dict] = None,
+        enabled: bool = True,
+    ) -> Dict:
+        """Create a trigger that auto-starts a pipeline on an external event.
+
+        Args:
+            name:           Human-readable trigger name.
+            trigger_type:   One of ``inbound_webhook``, ``watermark_advance``,
+                            ``pipeline_completion``, ``quality_alert``.
+            config:         Type-specific config. ``watermark_advance`` needs
+                            ``{credential_id, table, watermark_column,
+                            min_advance}``; ``inbound_webhook`` accepts an
+                            optional ``{hmac_key}``.
+            target_pipeline_config: The pipeline to run when fired — a
+                            connector data source + pipeline params
+                            (``{source_type, credential_id, table,
+                            target_columns, output_rows, ...}``).
+            enabled:        Whether the trigger is active (default True).
+
+        Returns:
+            The created trigger. For ``inbound_webhook`` the response
+            includes ``webhook_secret`` and ``inbound_url`` — this is the
+            ONLY time the secret is returned, so save it now.
+        """
+        body = {
+            "name": name,
+            "trigger_type": trigger_type,
+            "config": config or {},
+            "target_pipeline_config": target_pipeline_config or {},
+            "enabled": enabled,
+        }
+        r = self._request("POST", self._url("/triggers"), json=body)
+        self._raise_for_error(r)
+        return r.json().get("trigger", r.json())
+
+    def get_trigger(self, trigger_id: str) -> Dict:
+        """Fetch one trigger by id (secret not included)."""
+        r = self._request("GET", self._url(f"/triggers/{trigger_id}"))
+        self._raise_for_error(r)
+        return r.json().get("trigger", r.json())
+
+    def update_trigger(self, trigger_id: str, **fields) -> Dict:
+        """Update a trigger. Accepts ``name``, ``enabled``, ``config``,
+        ``target_pipeline_config``. The webhook secret is immutable."""
+        r = self._request("PUT", self._url(f"/triggers/{trigger_id}"), json=fields)
+        self._raise_for_error(r)
+        return r.json().get("trigger", r.json())
+
+    def delete_trigger(self, trigger_id: str) -> bool:
+        """Delete a trigger. Returns True on success."""
+        r = self._request("DELETE", self._url(f"/triggers/{trigger_id}"))
+        self._raise_for_error(r)
+        return True
+
+    def test_trigger(self, trigger_id: str) -> Dict:
+        """Dry-run a trigger: validate its config + target without firing.
+        Returns a report with ``would_fire`` and per-check details."""
+        r = self._request("POST", self._url(f"/triggers/{trigger_id}/test"))
+        self._raise_for_error(r)
+        return r.json()
+
     def write_output(
         self,
         session_id: str,

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/datatoolpack.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datatoolpack
-Version: 0.8.0
+Version: 0.10.1
 Summary: Official Python SDK for the AutoData ML data preparation pipeline API
 Home-page: https://autodata.datatoolpack.com
 Author: AutoData Team
@@ -62,7 +62,7 @@ with AutoDataClient(api_key="dtpk_YOUR_API_KEY") as client:
     result = client.process(
         file_path="data.csv",
         target_columns=["price"],
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -162,7 +162,7 @@ client.close()
 result = client.process(
     file_path="data.csv",           # Path to input file (CSV, XLSX, Parquet, ...)
     target_columns=["price"],       # y-column(s) for ML
-    output_rows=20000,              # Target row count in output
+    output_rows=10000,              # Target row count in the synthetic output (default 10000)
     tools={                         # Toggle pipeline steps (all optional)
         "anomaly": False,           # Anomaly detection (off by default)
         "dtc": True,                # Data Type Conversion
@@ -199,7 +199,7 @@ result = client.process(
         {"name": "dsg.csv", "url": "/download/.../dsg.csv", "size": 2097152, "description": "..."},
         {"name": "dsm_train.csv", ...},
     ],
-    "row_count": 20000,
+    "row_count": 10000,
     "duration_seconds": 42.1,
 }
 ```
@@ -289,6 +289,30 @@ client.download_file("/api/v1/download/abc123.../dsg.csv", "dsg.csv")
 
 ---
 
+## Feature Selection (F4)
+
+Rank a completed session's columns by predictive importance — **without re-running the pipeline**. Handy for trimming wide datasets before training.
+
+### `client.recommend_features(session_id, target_columns, methods, top_k)`
+
+```python
+ranking = client.recommend_features(
+    session_id="abc123...",            # a completed session you own
+    target_columns=["price"],          # rank features against these target(s)
+    methods=["mutual_information"],    # one or more methods (see below); default ["mutual_information"]
+    top_k=20,                          # number of top features to return (default 20)
+)
+# {
+#   "ranking":    [{"feature": "sqft", "score": 0.81}, ...],   # combined across methods
+#   "per_method": {"mutual_information": [...], "shap_importance": [...]},
+#   "warnings":   [...],
+# }
+```
+
+**Available methods:** `variance_threshold`, `correlation_pruning`, `mutual_information`, `rfe`, `shap_importance`, `pca`. Pass several to blend their rankings, e.g. `methods=["mutual_information", "shap_importance"]`. (SHAP-based ranking uses a fast LightGBM model on the server; it degrades gracefully to `mutual_information` if those libraries are unavailable.)
+
+---
+
 ## API Keys & Usage
 
 ### `client.list_keys()` — List API keys
@@ -336,6 +360,8 @@ Read data directly from databases and cloud storage instead of uploading files.
 | `kafka`       | Apache Kafka                       | `bootstrap_servers`, `topic`, `group_id`            |
 | `kinesis`     | Amazon Kinesis                     | `stream_name`, `region`, `access_key_id`, `secret_access_key` |
 
+> **More connectors:** AutoData supports 30+ source types. Beyond the common ones above you can also pass `oracle`, `redshift`, `cassandra`, `dynamodb`, `elasticsearch`, `clickhouse`, `timescaledb`, `synapse`, `azure_blob`, `adls`, `sap_hana`, `mqtt`, `opcua`, `influxdb`, `pi_web`, `salesforce`, `hubspot`, `stripe`, `netsuite`, `google_sheets`, `ga4`, `sharepoint`, and `http`/`rest` as `connector_type`. See **Dashboard → Documentation → Connector Data Sources** for each type's required `secrets` fields.
+
 ### Quick connector example
 
 ```python
@@ -363,7 +389,7 @@ with AutoDataClient(api_key="dtpk_...") as client:
         table="orders",
         target_columns=["price"],
         secrets={"connection_string": "postgresql://user:pass@host/db"},
-        output_rows=20000,
+        output_rows=10000,
     )
     print(result["files"])
 ```
@@ -452,7 +478,7 @@ result = client.process_from_connector(
     table="orders",
     target_columns=["price"],
     secrets={"connection_string": "postgresql://..."},
-    output_rows=20000,
+    output_rows=10000,
     incremental=True,          # Only fetch new rows since last sync
     type_casts={"age": "int"}, # Override column types before processing
     wait=True,
@@ -474,7 +500,7 @@ client.write_output(
     if_exists="replace",       # "replace", "append", "fail", or "merge"
     merge_keys=["id"],         # column names for merge matching (when if_exists='merge')
 )
-# {"success": True, "rows_written": 20000, "table": "ml_prepared_data"}
+# {"success": True, "rows_written": 10000, "table": "ml_prepared_data"}
 ```
 
 ---
@@ -639,6 +665,65 @@ client.delete_scheduled_run(run_id="run-id")
 
 ---
 
+## Triggers (F7)
+
+Auto-start a pipeline when an external event fires — an inbound webhook, a connector watermark advancing, another pipeline completing, or a quality alert. Triggers are feature-flagged on the server (`FEATURE_FLAG_TRIGGERS`); if the flag is off, these endpoints return `404`.
+
+### `client.create_trigger(name, trigger_type, config, target_pipeline_config, enabled)`
+
+```python
+trigger = client.create_trigger(
+    name="Reprocess on new S3 batch",
+    trigger_type="inbound_webhook",   # inbound_webhook | watermark_advance | pipeline_completion | quality_alert
+    config={},                         # type-specific (see table below)
+    target_pipeline_config={           # the pipeline to run when the trigger fires
+        "source_type": "s3",
+        "credential_id": "cred-uuid",
+        "table": "incoming/sales.csv",
+        "target_columns": ["revenue"],
+        "output_rows": 10000,
+    },
+    enabled=True,
+)
+# For inbound_webhook the secret is returned ONLY once — save it now:
+print(trigger["webhook_secret"], trigger["inbound_url"])
+```
+
+**Trigger types & their `config`:**
+
+| `trigger_type`        | `config` keys |
+|-----------------------|---------------|
+| `inbound_webhook`     | optional `{"hmac_key": "..."}` — require HMAC-SHA256-signed requests |
+| `watermark_advance`   | `{"credential_id", "table", "watermark_column", "min_advance"}` |
+| `pipeline_completion` | `{}` — chain off another pipeline finishing |
+| `quality_alert`       | `{}` — fire when a quality-alert rule trips |
+
+```python
+# List / fetch / update / delete
+triggers = client.list_triggers()
+t        = client.get_trigger(trigger_id)
+client.update_trigger(trigger_id, enabled=False)   # name | enabled | config | target_pipeline_config
+client.delete_trigger(trigger_id)
+
+# Dry-run: validate config + target WITHOUT firing
+report = client.test_trigger(trigger_id)
+# {"would_fire": True, "checks": {...}}
+```
+
+**Firing an inbound webhook** from your own system:
+
+```bash
+curl -X POST "https://autodata.datatoolpack.com/trigger/inbound/<webhook_secret>" \
+     -H "Content-Type: application/json" \
+     -d '{"any": "payload"}'
+# If you set an hmac_key, also sign the raw body:
+#   X-Signature: sha256=<hex HMAC-SHA256 of the request body>
+```
+
+Inbound firing is rate-limited and HMAC-verified server-side; repeated failures auto-disable the trigger.
+
+---
+
 ## Folder Listeners
 
 Automatically trigger pipelines when new files appear in cloud storage:
@@ -819,6 +904,11 @@ with AutoDataClient() as client:
 | `list_keys()` | List all API keys for the account |
 | `get_usage()` | Get credit usage statistics |
 
+### Feature Selection
+| Method | Description |
+|--------|-------------|
+| `recommend_features(session_id, target_columns, ...)` | Rank a completed session's features (F4) |
+
 ### Connectors
 | Method | Description |
 |--------|-------------|
@@ -866,6 +956,16 @@ with AutoDataClient() as client:
 | `toggle_scheduled_run(run_id)` | Enable/disable a scheduled run |
 | `run_scheduled_now(run_id)` | Trigger a scheduled run immediately |
 
+### Triggers
+| Method | Description |
+|--------|-------------|
+| `list_triggers()` | List your triggers |
+| `create_trigger(name, trigger_type, ...)` | Create an event trigger (F7) |
+| `get_trigger(trigger_id)` | Fetch one trigger |
+| `update_trigger(trigger_id, ...)` | Update a trigger |
+| `delete_trigger(trigger_id)` | Delete a trigger |
+| `test_trigger(trigger_id)` | Dry-run a trigger without firing |
+
 ### Folder Listeners
 | Method | Description |
 |--------|-------------|

{datatoolpack-0.8.0 → datatoolpack-0.10.1}/setup.py

@@ -7,7 +7,7 @@ with open(os.path.join(here, "README.md"), encoding="utf-8") as f:
 
 setup(
     name="datatoolpack",
-    version="0.8.0",
+    version="0.10.1",
     description="Official Python SDK for the AutoData ML data preparation pipeline API",
     long_description=long_description,
     long_description_content_type="text/markdown",