semantic-link-labs 0.9.0__py3-none-any.whl → 0.9.2__py3-none-any.whl

sempy_labs/_ml_experiments.py

@@ -1,13 +1,13 @@
 import sempy.fabric as fabric
 import pandas as pd
-import sempy_labs._icons as icons
 from typing import Optional
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
-    lro,
-    pagination,
+    _base_api,
+    _print_success,
+    resolve_item_id,
+    _create_dataframe,
 )
-from sempy.fabric.exceptions import FabricHTTPException
 from uuid import UUID
 
 
@@ -30,16 +30,20 @@ def list_ml_experiments(workspace: Optional[str | UUID] = None) -> pd.DataFrame:
         A pandas dataframe showing the ML models within a workspace.
     """
 
-    df = pd.DataFrame(columns=["ML Experiment Name", "ML Experiment Id", "Description"])
+    columns = {
+        "ML Experiment Name": "string",
+        "ML Experiment Id": "string",
+        "Description": "string",
+    }
+    df = _create_dataframe(columns=columns)
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
 
-    client = fabric.FabricRestClient()
-    response = client.get(f"/v1/workspaces/{workspace_id}/mlExperiments")
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
-
-    responses = pagination(client, response)
+    responses = _base_api(
+        request=f"/v1/workspaces/{workspace_id}/mlExperiments",
+        status_codes=200,
+        uses_pagination=True,
+    )
 
     for r in responses:
         for v in r.get("value", []):
@@ -79,20 +83,23 @@ def create_ml_experiment(
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
 
-    request_body = {"displayName": name}
+    payload = {"displayName": name}
 
     if description:
-        request_body["description"] = description
-
-    client = fabric.FabricRestClient()
-    response = client.post(
-        f"/v1/workspaces/{workspace_id}/mlExperiments", json=request_body
+        payload["description"] = description
+
+    _base_api(
+        request=f"/v1/workspaces/{workspace_id}/mlExperiments",
+        method="post",
+        json=payload,
+        status_codes=[201, 202],
+        lro_return_status_code=True,
     )
-
-    lro(client, response, status_codes=[201, 202])
-
-    print(
-        f"{icons.green_dot} The '{name}' ML experiment has been created within the '{workspace_name}' workspace."
+    _print_success(
+        item_name=name,
+        item_type="ML experiment",
+        workspace_name=workspace_name,
+        action="created",
     )
 
 
@@ -112,18 +119,11 @@ def delete_ml_experiment(name: str, workspace: Optional[str | UUID] = None):
         or if no lakehouse attached, resolves to the workspace of the notebook.
     """
 
-    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    item_id = fabric.resolve_item_id(
-        item_name=name, type="MLExperiment", workspace=workspace_id
-    )
-
-    client = fabric.FabricRestClient()
-    response = client.delete(f"/v1/workspaces/{workspace_id}/mlExperiments/{item_id}")
-
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
-
-    print(
-        f"{icons.green_dot} The '{name}' ML experiment within the '{workspace_name}' workspace has been deleted."
+    item_id = resolve_item_id(item=name, type="MLExperiment", workspace=workspace)
+    fabric.delete_item(item_id=item_id, workspace=workspace)
+    _print_success(
+        item_name=name,
+        item_type="ML Experiment",
+        workspace_name=workspace,
+        action="deleted",
     )

sempy_labs/_ml_models.py

@@ -1,13 +1,13 @@
 import sempy.fabric as fabric
 import pandas as pd
-import sempy_labs._icons as icons
 from typing import Optional
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
-    lro,
-    pagination,
+    _base_api,
+    resolve_item_id,
+    _print_success,
+    _create_dataframe,
 )
-from sempy.fabric.exceptions import FabricHTTPException
 from uuid import UUID
 
 
@@ -30,16 +30,20 @@ def list_ml_models(workspace: Optional[str | UUID] = None) -> pd.DataFrame:
         A pandas dataframe showing the ML models within a workspace.
     """
 
-    df = pd.DataFrame(columns=["ML Model Name", "ML Model Id", "Description"])
+    columns = {
+        "ML Model Name": "string",
+        "ML Model Id": "string",
+        "Description": "string",
+    }
+    df = _create_dataframe(columns=columns)
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
 
-    client = fabric.FabricRestClient()
-    response = client.get(f"/v1/workspaces/{workspace_id}/mlModels")
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
-
-    responses = pagination(client, response)
+    responses = _base_api(
+        request=f"/v1/workspaces/{workspace_id}/mlModels",
+        status_codes=200,
+        uses_pagination=True,
+    )
 
     for r in responses:
         for v in r.get("value", []):
@@ -79,22 +83,27 @@ def create_ml_model(
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
 
-    request_body = {"displayName": name}
+    payload = {"displayName": name}
 
     if description:
-        request_body["description"] = description
-
-    client = fabric.FabricRestClient()
-    response = client.post(f"/v1/workspaces/{workspace_id}/mlModels", json=request_body)
-
-    lro(client, response, status_codes=[201, 202])
-
-    print(
-        f"{icons.green_dot} The '{name}' ML model has been created within the '{workspace_name}' workspace."
+        payload["description"] = description
+
+    _base_api(
+        request=f"/v1/workspaces/{workspace_id}/mlModels",
+        method="post",
+        status_codes=[201, 202],
+        payload=payload,
+        lro_return_status_code=True,
+    )
+    _print_success(
+        item_name=name,
+        item_type="ML Model",
+        workspace_name=workspace_name,
+        action="created",
     )
 
 
-def delete_ml_model(name: str, workspace: Optional[str | UUID] = None):
+def delete_ml_model(name: str | UUID, workspace: Optional[str | UUID] = None):
     """
     Deletes a Fabric ML model.
 
@@ -102,26 +111,16 @@ def delete_ml_model(name: str, workspace: Optional[str | UUID] = None):
 
     Parameters
     ----------
-    name: str
-        Name of the ML model.
+    name: str | uuid.UUID
+        Name or ID of the ML model.
     workspace : str | uuid.UUID, default=None
         The Fabric workspace name or ID.
         Defaults to None which resolves to the workspace of the attached lakehouse
         or if no lakehouse attached, resolves to the workspace of the notebook.
     """
 
-    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    item_id = fabric.resolve_item_id(
-        item_name=name, type="MLModel", workspace=workspace
-    )
-
-    client = fabric.FabricRestClient()
-    response = client.delete(f"/v1/workspaces/{workspace_id}/mlModels/{item_id}")
-
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
-
-    print(
-        f"{icons.green_dot} The '{name}' ML model within the '{workspace_name}' workspace has been deleted."
+    item_id = resolve_item_id(item=name, type="MLModel", workspace=workspace)
+    fabric.delete_item(item_id=item_id, workspace=workspace)
+    _print_success(
+        item_name=name, item_type="ML Model", workspace_name=workspace, action="deleted"
     )

sempy_labs/_model_dependencies.py

@@ -287,6 +287,8 @@ def measure_dependency_tree(
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
     (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
+    fabric.refresh_tom_cache(workspace=workspace)
+
     dfM = fabric.list_measures(dataset=dataset_id, workspace=workspace_id)
     dfM_filt = dfM[dfM["Measure Name"] == measure_name]
 

sempy_labs/_notebooks.py

@@ -7,8 +7,9 @@ import requests
 from sempy._utils._log import log
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
-    lro,
     _decode_b64,
+    _base_api,
+    resolve_item_id,
 )
 from sempy.fabric.exceptions import FabricHTTPException
 import os
@@ -22,15 +23,13 @@ def _get_notebook_definition_base(
 ) -> pd.DataFrame:
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-    item_id = fabric.resolve_item_id(
-        item_name=notebook_name, type="Notebook", workspace=workspace_id
+    item_id = resolve_item_id(item=notebook_name, type="Notebook", workspace=workspace)
+    result = _base_api(
+        request=f"v1/workspaces/{workspace_id}/notebooks/{item_id}/getDefinition",
+        method="post",
+        lro_return_json=True,
+        status_codes=None,
     )
-    client = fabric.FabricRestClient()
-    response = client.post(
-        f"v1/workspaces/{workspace_id}/notebooks/{item_id}/getDefinition",
-    )
-
-    result = lro(client, response).json()
 
     return pd.json_normalize(result["definition"]["parts"])
 
@@ -185,10 +184,9 @@ def create_notebook(
     """
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-    client = fabric.FabricRestClient()
-    notebook_payload = base64.b64encode(notebook_content)
+    notebook_payload = base64.b64encode(notebook_content).decode("utf-8")
 
-    request_body = {
+    payload = {
         "displayName": name,
         "definition": {
             "format": "ipynb",
@@ -202,11 +200,15 @@ def create_notebook(
         },
     }
     if description is not None:
-        request_body["description"] = description
-
-    response = client.post(f"v1/workspaces/{workspace_id}/notebooks", json=request_body)
-
-    lro(client, response, status_codes=[201, 202])
+        payload["description"] = description
+
+    _base_api(
+        request=f"v1/workspaces/{workspace_id}/notebooks",
+        payload=payload,
+        method="post",
+        lro_return_status_code=True,
+        status_codes=[201, 202],
+    )
 
     print(
         f"{icons.green_dot} The '{name}' notebook was created within the '{workspace_name}' workspace."
@@ -232,15 +234,11 @@ def update_notebook_definition(
     """
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-    client = fabric.FabricRestClient()
     notebook_payload = base64.b64encode(notebook_content)
-    notebook_id = fabric.resolve_item_id(
-        item_name=name, type="Notebook", workspace=workspace_id
-    )
+    item_id = resolve_item_id(item=name, type="Notebook", workspace=workspace)
+    type = _get_notebook_type(notebook_name=name, workspace=workspace)
 
-    type = _get_notebook_type(notebook_name=name, workspace=workspace_id)
-
-    request_body = {
+    payload = {
         "definition": {
             "parts": [
                 {
@@ -252,13 +250,14 @@ def update_notebook_definition(
         },
     }
 
-    response = client.post(
-        f"v1/workspaces/{workspace_id}/notebooks/{notebook_id}/updateDefinition",
-        json=request_body,
+    _base_api(
+        request=f"v1/workspaces/{workspace_id}/notebooks/{item_id}/updateDefinition",
+        payload=payload,
+        method="post",
+        lro_return_status_code=True,
+        status_codes=None,
     )
 
-    lro(client, response, return_status_code=True)
-
     print(
         f"{icons.green_dot} The '{name}' notebook was updated within the '{workspace_name}' workspace."
     )

sempy_labs/_one_lake_integration.py

@@ -37,6 +37,8 @@ def export_model_to_onelake(
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
     (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
+    fabric.refresh_tom_cache(workspace=workspace)
+
     if destination_workspace is None:
         destination_workspace = workspace_name
         destination_workspace_id = workspace_id

sempy_labs/_query_scale_out.py

@@ -3,11 +3,13 @@ import pandas as pd
 from sempy_labs._helper_functions import (
     resolve_workspace_name_and_id,
     resolve_dataset_name_and_id,
+    _update_dataframe_datatypes,
+    _base_api,
+    _create_dataframe,
 )
 from sempy._utils._log import log
 from typing import Optional, Tuple
 import sempy_labs._icons as icons
-from sempy.fabric.exceptions import FabricHTTPException
 from uuid import UUID
 
 
@@ -31,13 +33,10 @@ def qso_sync(dataset: str | UUID, workspace: Optional[str | UUID] = None):
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
     (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
-    client = fabric.PowerBIRestClient()
-    response = client.post(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/queryScaleOut/sync"
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/queryScaleOut/sync",
+        method="post",
     )
-
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
     print(
         f"{icons.green_dot} QSO sync initiated for the '{dataset_name}' semantic model within the '{workspace_name}' workspace."
     )
@@ -67,35 +66,36 @@ def qso_sync_status(
         2 pandas dataframes showing the query scale-out sync status.
     """
 
-    df = pd.DataFrame(
-        columns=[
-            "Scale Out Status",
-            "Sync Start Time",
-            "Sync End Time",
-            "Commit Version",
-            "Commit Timestamp",
-            "Target Sync Version",
-            "Target Sync Timestamp",
-            "Trigger Reason",
-            "Min Active Read Version",
-            "Min Active Read Timestamp",
-        ]
-    )
-    dfRep = pd.DataFrame(
-        columns=["Replica ID", "Replica Type", "Replica Version", "Replica Timestamp"]
-    )
+    columns = {
+        "Scale Out Status": "string",
+        "Sync Start Time": "datetime",
+        "Sync End Time": "datetime",
+        "Commit Version": "int",
+        "Commit Timestamp": "datetime",
+        "Target Sync Version": "int",
+        "Target Sync Timestamp": "datetime",
+        "Trigger Reason": "string",
+        "Min Active Read Version": "int",
+        "Min Active Read Timestamp": "datetime",
+    }
+    df = _create_dataframe(columns=columns)
+
+    columns_rep = {
+        "Replica ID": "string",
+        "Replica Type": "string",
+        "Replica Version": "string",
+        "Replica Timestamp": "datetime",
+    }
+
+    dfRep = _create_dataframe(columns=columns_rep)
 
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
     (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
-    client = fabric.PowerBIRestClient()
-    response = client.get(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/queryScaleOut/syncStatus"
+    response = _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/queryScaleOut/syncStatus"
     )
 
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
-
     o = response.json()
     sos = o.get("scaleOutStatus")
 
@@ -125,17 +125,8 @@ def qso_sync_status(
                 [dfRep, pd.DataFrame(new_data, index=[0])], ignore_index=True
             )
 
-        df["Sync Start Time"] = pd.to_datetime(df["Sync Start Time"])
-        df["Sync End Time"] = pd.to_datetime(df["Sync End Time"])
-        df["Commit Timestamp"] = pd.to_datetime(df["Commit Timestamp"])
-        df["Target Sync Timestamp"] = pd.to_datetime(df["Target Sync Timestamp"])
-        df["Min Active Read Timestamp"] = pd.to_datetime(
-            df["Min Active Read Timestamp"]
-        )
-        dfRep["Replica Timestamp"] = pd.to_datetime(dfRep["Replica Timestamp"])
-        df["Commit Version"] = df["Commit Version"].astype("int")
-        df["Target Sync Version"] = df["Target Sync Version"].astype("int")
-        df["Min Active Read Version"] = df["Min Active Read Version"].astype("int")
+        _update_dataframe_datatypes(dataframe=df, column_map=columns)
+        _update_dataframe_datatypes(dataframe=dfRep, column_map=columns_rep)
 
         return df, dfRep
     else:
@@ -170,14 +161,13 @@ def disable_qso(
     (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
     (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
-    request_body = {"queryScaleOutSettings": {"maxReadOnlyReplicas": "0"}}
+    payload = {"queryScaleOutSettings": {"maxReadOnlyReplicas": "0"}}
 
-    client = fabric.PowerBIRestClient()
-    response = client.patch(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}", json=request_body
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}",
+        method="patch",
+        payload=payload,
     )
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
 
     df = list_qso_settings(dataset=dataset_id, workspace=workspace_id)
 
@@ -233,7 +223,7 @@ def set_qso(
         disable_qso(dataset=dataset_id, workspace=workspace_id)
         return
 
-    request_body = {
+    payload = {
         "queryScaleOutSettings": {
             "autoSyncReadOnlyReplicas": auto_sync,
             "maxReadOnlyReplicas": max_read_only_replicas,
@@ -248,13 +238,11 @@ def set_qso(
             dataset=dataset_id, storage_format="Large", workspace=workspace_id
         )
 
-    client = fabric.PowerBIRestClient()
-    response = client.patch(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}",
-        json=request_body,
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}",
+        method="patch",
+        payload=payload,
     )
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
 
     df = list_qso_settings(dataset=dataset_id, workspace=workspace_id)
     print(
@@ -296,9 +284,9 @@ def set_semantic_model_storage_format(
     storageFormats = ["Small", "Large"]
 
     if storage_format == "Large":
-        request_body = {"targetStorageMode": "PremiumFiles"}
+        payload = {"targetStorageMode": "PremiumFiles"}
     elif storage_format == "Small":
-        request_body = {"targetStorageMode": "Abf"}
+        payload = {"targetStorageMode": "Abf"}
     else:
         raise ValueError(
             f"{icons.red_dot} Invalid storage format value. Valid options: {storageFormats}."
@@ -313,12 +301,11 @@ def set_semantic_model_storage_format(
         )
         return
 
-    client = fabric.PowerBIRestClient()
-    response = client.patch(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}", json=request_body
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}",
+        method="patch",
+        payload=payload,
     )
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
     print(
         f"{icons.green_dot} The semantic model storage format for the '{dataset_name}' semantic model within the '{workspace_name}' workspace has been set to '{storage_format}'."
     )
@@ -351,17 +338,16 @@ def list_qso_settings(
     if dataset is not None:
         (dataset_name, dataset_id) = resolve_dataset_name_and_id(dataset, workspace_id)
 
-    df = pd.DataFrame(
-        columns=[
-            "Dataset Id",
-            "Dataset Name",
-            "Storage Mode",
-            "QSO Auto Sync Enabled",
-            "QSO Max Read Only Replicas",
-        ]
-    )
-    client = fabric.PowerBIRestClient()
-    response = client.get(f"/v1.0/myorg/groups/{workspace_id}/datasets")
+    columns = {
+        "Dataset Id": "string",
+        "Dataset Name": "string",
+        "Storage Mode": "string",
+        "QSO Auto Sync Enabled": "bool",
+        "QSO Max Read Only Replicas": "int",
+    }
+    df = _create_dataframe(columns=columns)
+
+    response = _base_api(request=f"/v1.0/myorg/groups/{workspace_id}/datasets")
 
     for v in response.json().get("value", []):
         tsm = v.get("targetStorageMode")
@@ -382,8 +368,7 @@ def list_qso_settings(
         }
         df = pd.concat([df, pd.DataFrame(new_data, index=[0])], ignore_index=True)
 
-    df["QSO Auto Sync Enabled"] = df["QSO Auto Sync Enabled"].astype("bool")
-    df["QSO Max Read Only Replicas"] = df["QSO Max Read Only Replicas"].astype("int")
+    _update_dataframe_datatypes(dataframe=df, column_map=columns)
 
     if dataset is not None:
         df = df[df["Dataset Id"] == dataset_id]
@@ -411,7 +396,6 @@ def set_workspace_default_storage_format(
     # https://learn.microsoft.com/en-us/rest/api/power-bi/groups/update-group#defaultdatasetstorageformat
 
     storageFormats = ["Small", "Large"]
-
     storage_format = storage_format.capitalize()
 
     if storage_format not in storageFormats:
@@ -433,16 +417,14 @@ def set_workspace_default_storage_format(
         )
         return
 
-    request_body = {
+    payload = {
         "name": workspace_name,
         "defaultDatasetStorageFormat": storage_format,
     }
 
-    client = fabric.PowerBIRestClient()
-    response = client.patch(f"/v1.0/myorg/groups/{workspace_id}", json=request_body)
-
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}", method="patch", payload=payload
+    )
 
     print(
         f"{icons.green_dot} The default storage format for the '{workspace_name}' workspace has been updated to '{storage_format}."

sempy_labs/_refresh_semantic_model.py

@@ -5,11 +5,12 @@ from sempy_labs._helper_functions import (
     _get_partition_map,
     _process_and_display_chart,
     resolve_dataset_name_and_id,
+    _update_dataframe_datatypes,
+    _base_api,
 )
 from typing import Any, List, Optional, Union
 from sempy._utils._log import log
 import sempy_labs._icons as icons
-from sempy.fabric.exceptions import FabricHTTPException
 import pandas as pd
 import warnings
 import ipywidgets as widgets
@@ -311,14 +312,10 @@ def cancel_dataset_refresh(
 
         request_id = rr_filt["Request Id"].iloc[0]
 
-    client = fabric.PowerBIRestClient()
-
-    response = client.delete(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/refreshes/{request_id}"
+    _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/refreshes/{request_id}",
+        method="delete",
     )
-
-    if response.status_code != 200:
-        raise FabricHTTPException(response)
     print(
         f"{icons.green_dot} The '{request_id}' refresh request for the '{dataset_name}' semantic model within the '{workspace_name}' workspace has been cancelled."
     )
@@ -365,9 +362,8 @@ def get_semantic_model_refresh_history(
         ]
     )
 
-    client = fabric.PowerBIRestClient()
-    response = client.get(
-        f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/refreshes"
+    response = _base_api(
+        request=f"/v1.0/myorg/groups/{workspace_id}/datasets/{dataset_id}/refreshes"
     )
     data = []
 
@@ -429,8 +425,10 @@ def get_semantic_model_refresh_history(
     # df[date_cols] = df[date_cols].apply(pd.to_datetime)
 
     if "Attempt Id" in df.columns:
-        df["Attempt Id"] = df["Attempt Id"].astype(int)
-        # date_cols = ["Attempt Start Time", "Attempt End Time"]
-        # df[date_cols] = df[date_cols].apply(pd.to_datetime)
+        column_map = {
+            "Attempt Id": "int",
+        }
+
+        _update_dataframe_datatypes(dataframe=df, column_map=column_map)
 
     return df