semantic-link-labs 0.9.10__py3-none-any.whl → 0.10.0__py3-none-any.whl

sempy_labs/lakehouse/_livy_sessions.py

@@ -0,0 +1,137 @@
+from sempy_labs._helper_functions import (
+    resolve_workspace_id,
+    resolve_lakehouse_id,
+    _base_api,
+    _create_dataframe,
+    _update_dataframe_datatypes,
+)
+import pandas as pd
+from typing import Optional
+from uuid import UUID
+
+
+def list_livy_sessions(
+    lakehouse: Optional[str | UUID] = None, workspace: Optional[str | UUID] = None
+) -> pd.DataFrame:
+    """
+    Shows a list of livy sessions from the specified item identifier.
+
+    This is a wrapper function for the following API: `Livy Sessions - List Livy Sessions <https://learn.microsoft.com/rest/api/fabric/lakehouse/livy-sessions/list-livy-sessions>`_.
+
+    Service Principal Authentication is supported (see `here <https://github.com/microsoft/semantic-link-labs/blob/main/notebooks/Service%20Principal.ipynb>`_ for examples).
+
+    Parameters
+    ----------
+    lakehouse : str | uuid.UUID, default=None
+        The Fabric lakehouse name or ID.
+        Defaults to None which resolves to the lakehouse attached to the notebook.
+    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.
+
+    Returns
+    -------
+    pandas.DataFrame
+        A pandas dataframe showing a list of livy sessions from the specified item identifier.
+    """
+
+    columns = {
+        "Spark Application Id": "string",
+        "State:": "string",
+        "Livy Id": "string",
+        "Origin": "string",
+        "Attempt Number": "int",
+        "Max Number Of Attempts": "int",
+        "Livy Name": "string",
+        "Submitter Id": "string",
+        "Submitter Type": "string",
+        "Item Workspace Id": "string",
+        "Item Id": "string",
+        "Item Reference Type": "string",
+        "Item Name": "string",
+        "Item Type": "string",
+        "Job Type": "string",
+        "Submitted Date Time": "str",
+        "Start Date Time": "str",
+        "End Date Time": "string",
+        "Queued Duration Value": "int",
+        "Queued Duration Time Unit": "string",
+        "Running Duration Value": "int",
+        "Running Duration Time Unit": "string",
+        "Total Duration Value": "int",
+        "Total Duration Time Unit": "string",
+        "Job Instance Id": "string",
+        "Creator Item Workspace Id": "string",
+        "Creator Item Id": "string",
+        "Creator Item Reference Type": "string",
+        "Creator Item Name": "string",
+        "Creator Item Type": "string",
+        "Cancellation Reason": "string",
+        "Capacity Id": "string",
+        "Operation Name": "string",
+        "Runtime Version": "string",
+        "Livy Session Item Resource Uri": "string",
+    }
+    df = _create_dataframe(columns=columns)
+
+    workspace_id = resolve_workspace_id(workspace)
+    lakehouse_id = resolve_lakehouse_id(lakehouse, workspace_id)
+
+    responses = _base_api(
+        request=f"/v1/workspaces/{workspace_id}/lakehouses/{lakehouse_id}/livySessions",
+        uses_pagination=True,
+        client="fabric_sp",
+    )
+
+    dfs = []
+
+    for r in responses:
+        for v in r.get("value", []):
+            queued_duration = v.get("queuedDuration", {})
+            running_duration = v.get("runningDuration", {})
+            total_duration = v.get("totalDuration", {})
+            new_data = {
+                "Spark Application Id": v.get("sparkApplicationId"),
+                "State:": v.get("state"),
+                "Livy Id": v.get("livyId"),
+                "Origin": v.get("origin"),
+                "Attempt Number": v.get("attemptNumber"),
+                "Max Number Of Attempts": v.get("maxNumberOfAttempts"),
+                "Livy Name": v.get("livyName"),
+                "Submitter Id": v["submitter"].get("id"),
+                "Submitter Type": v["submitter"].get("type"),
+                "Item Workspace Id": v["item"].get("workspaceId"),
+                "Item Id": v["item"].get("itemId"),
+                "Item Reference Type": v["item"].get("referenceType"),
+                "Item Name": v.get("itemName"),
+                "Item Type": v.get("itemType"),
+                "Job Type": v.get("jobType"),
+                "Submitted Date Time": v.get("submittedDateTime"),
+                "Start Date Time": v.get("startDateTime"),
+                "End Date Time": v.get("endDateTime"),
+                "Queued Duration Value": queued_duration.get("value"),
+                "Queued Duration Time Unit": queued_duration.get("timeUnit"),
+                "Running Duration Value": running_duration.get("value"),
+                "Running Duration Time Unit": running_duration.get("timeUnit"),
+                "Total Duration Value": total_duration.get("value"),
+                "Total Duration Time Unit": total_duration.get("timeUnit"),
+                "Job Instance Id": v.get("jobInstanceId"),
+                "Creator Item Workspace Id": v["creatorItem"].get("workspaceId"),
+                "Creator Item Id": v["creatorItem"].get("itemId"),
+                "Creator Item Reference Type": v["creatorItem"].get("referenceType"),
+                "Creator Item Name": v.get("creatorItemName"),
+                "Creator Item Type": v.get("creatorItemType"),
+                "Cancellation Reason": v.get("cancellationReason"),
+                "Capacity Id": v.get("capacityId"),
+                "Operation Name": v.get("operationName"),
+                "Runtime Version": v.get("runtimeVersion"),
+                "Livy Session Item Resource Uri": v.get("livySessionItemResourceUri"),
+            }
+            dfs.append(pd.DataFrame(new_data, index=[0]))
+
+    if dfs:
+        df = pd.concat(dfs, ignore_index=True)
+        _update_dataframe_datatypes(dataframe=df, column_map=columns)
+
+    return df

sempy_labs/report/__init__.py

@@ -3,6 +3,7 @@ from sempy_labs.report._save_report import (
 )
 from sempy_labs.report._reportwrapper import (
     ReportWrapper,
+    connect_report,
 )
 from sempy_labs.report._paginated import (
     get_report_datasources,
@@ -50,4 +51,5 @@ __all__ = [
     "get_report_datasources",
     "download_report",
     "save_report_as_pbip",
+    "connect_report",
 ]

sempy_labs/report/_download_report.py

@@ -22,7 +22,7 @@ def download_report(
     """
     Downloads the specified report from the specified workspace to a Power BI .pbix file.
 
-    This is a wrapper function for the following API: `Reports - Export Report In Group <https://learn.microsoft.com/rest/api/power-bi/reports/export-report-in-group>`.
+    This is a wrapper function for the following API: `Reports - Export Report In Group <https://learn.microsoft.com/rest/api/power-bi/reports/export-report-in-group>`_.
 
     Parameters
     ----------

sempy_labs/report/_generate_report.py

@@ -178,6 +178,7 @@ def update_report_from_reportjson(
     )
 
 
+@log
 def get_report_definition(
     report: str | UUID,
     workspace: Optional[str | UUID] = None,
@@ -206,7 +207,10 @@ def get_report_definition(
     """
 
     return get_item_definition(
-        item=report, type="Report", workspace=workspace, return_dataframe=True
+        item=report,
+        type="Report",
+        workspace=workspace,
+        return_dataframe=return_dataframe,
     )
 
 

sempy_labs/report/_report_helper.py

@@ -1,14 +1,5 @@
-import sempy.fabric as fabric
-from typing import Tuple, Optional
-import sempy_labs._icons as icons
-import re
-import base64
-import json
 import requests
-from uuid import UUID
-from sempy_labs._helper_functions import (
-    resolve_workspace_name_and_id,
-)
+import sempy_labs._icons as icons
 
 
 vis_type_mapping = {
@@ -47,10 +38,9 @@ vis_type_mapping = {
     "decompositionTreeVisual": "Decomposition tree",
     "qnaVisual": "Q&A",
     "aiNarratives": "Narrative",
-    "scorecard": "Metrics (Preview)",
+    "scorecard": "Goals (Preview)",
     "rdlVisual": "Paginated report",
     "cardVisual": "Card (new)",
-    "advancedSlicerVisual": "Slicer (new)",
     "actionButton": "Button",
     "bookmarkNavigator": "Bookmark navigator",
     "image": "Image",
@@ -58,8 +48,33 @@ vis_type_mapping = {
     "pageNavigator": "Page navigator",
     "shape": "Shape",
     "Group": "Group",
+    "listSlicer": "List Slicer",
+    "advancedSlicerVisual": "Button Slicer",
+    "FlowVisual_C29F1DCC_81F5_4973_94AD_0517D44CC06A": "Power Automate for Power BI",
 }
 
+
+def generate_visual_file_path(page_file_path: str, visual_id: str) -> str:
+
+    return page_file_path.split("/page.json")[0] + f"/visuals/{visual_id}.json"
+
+
+def resolve_visual_type(visual_type: str) -> str:
+    vt_lower = visual_type.lower()
+
+    vis_map_lower = {k.lower(): v for k, v in vis_type_mapping.items()}
+    flipped_lower = {v.lower(): k for k, v in vis_type_mapping.items()}
+
+    if vt_lower in vis_map_lower:
+        resolved = vis_map_lower.get(vt_lower)
+    elif vt_lower in flipped_lower:
+        resolved = flipped_lower.get(vt_lower)
+    else:
+        raise ValueError(f"{icons.red_dot} Unknown visual type: {visual_type}")
+
+    return resolved
+
+
 page_type_mapping = {
     (320, 240): "Tooltip",
     (816, 1056): "Letter",
@@ -70,22 +85,6 @@ page_type_mapping = {
 page_types = ["Tooltip", "Letter", "4:3", "16:9"]
 
 
-def get_web_url(report: str, workspace: Optional[str | UUID] = None):
-
-    (workspace_name, workspace_id) = resolve_workspace_name_and_id(workspace)
-
-    dfR = fabric.list_reports(workspace=workspace_id)
-    dfR_filt = dfR[dfR["Name"] == report]
-
-    if len(dfR_filt) == 0:
-        raise ValueError(
-            f"{icons.red_dot} The '{report}' report does not exist within the '{workspace_name}' workspace."
-        )
-    web_url = dfR_filt["Web Url"].iloc[0]
-
-    return web_url
-
-
 def populate_custom_visual_display_names():
 
     url = "https://catalogapi.azure.com/offers?api-version=2018-08-01-beta&storefront=appsource&$filter=offerType+eq+%27PowerBIVisuals%27"
@@ -128,106 +127,6 @@ def populate_custom_visual_display_names():
         vis_type_mapping[vizId] = displayName
 
 
-def resolve_page_name(self, page_name: str) -> Tuple[str, str, str]:
-
-    dfP = self.list_pages()
-    if any(r["Page Name"] == page_name for _, r in dfP.iterrows()):
-        valid_page_name = page_name
-        dfP_filt = dfP[dfP["Page Name"] == page_name]
-        valid_display_name = dfP_filt["Page Display Name"].iloc[0]
-        file_path = dfP_filt["File Path"].iloc[0]
-    elif any(r["Page Display Name"] == page_name for _, r in dfP.iterrows()):
-        valid_display_name = page_name
-        dfP_filt = dfP[dfP["Page Display Name"] == page_name]
-        valid_page_name = dfP_filt["Page Name"].iloc[0]
-        file_path = dfP_filt["File Path"].iloc[0]
-    else:
-        raise ValueError(
-            f"{icons.red_dot} Invalid page name. The '{page_name}' page does not exist in the '{self._report}' report within the '{self._workspace}' workspace."
-        )
-
-    return valid_page_name, valid_display_name, file_path
-
-
-def visual_page_mapping(self) -> Tuple[dict, dict]:
-
-    page_mapping = {}
-    visual_mapping = {}
-    rd = self.rdef
-    for _, r in rd.iterrows():
-        file_path = r["path"]
-        payload = r["payload"]
-        if file_path.endswith("/page.json"):
-            pattern_page = r"/pages/(.*?)/page.json"
-            page_name = re.search(pattern_page, file_path).group(1)
-            obj_file = base64.b64decode(payload).decode("utf-8")
-            obj_json = json.loads(obj_file)
-            page_id = obj_json.get("name")
-            page_display = obj_json.get("displayName")
-            page_mapping[page_name] = (page_id, page_display)
-    for _, r in rd.iterrows():
-        file_path = r["path"]
-        payload = r["payload"]
-        if file_path.endswith("/visual.json"):
-            pattern_page = r"/pages/(.*?)/visuals/"
-            page_name = re.search(pattern_page, file_path).group(1)
-            visual_mapping[file_path] = (
-                page_mapping.get(page_name)[0],
-                page_mapping.get(page_name)[1],
-            )
-
-    return page_mapping, visual_mapping
-
-
-def resolve_visual_name(
-    self, page_name: str, visual_name: str
-) -> Tuple[str, str, str, str]:
-    """
-    Obtains the page name, page display name, and the file path for a given page in a report.
-
-    Parameters
-    ----------
-    page_name : str
-        The name of the page of the report - either the page name (GUID) or the page display name.
-    visual_name : str
-        The name of the visual of the report.
-
-    Returns
-    -------
-    Tuple[str, str, str, str] Page name, page display name, visual name, file path from the report definition.
-
-    """
-
-    dfV = self.list_visuals()
-    if any(
-        (r["Page Name"] == page_name) & (r["Visual Name"] == visual_name)
-        for _, r in dfV.iterrows()
-    ):
-        valid_page_name = page_name
-        dfV_filt = dfV[
-            (dfV["Page Name"] == page_name) & (dfV["Visual Name"] == visual_name)
-        ]
-        file_path = dfV_filt["File Path"].iloc[0]
-        valid_display_name = dfV_filt["Page Display Name"].iloc[0]
-    elif any(
-        (r["Page Display Name"] == page_name) & (r["Visual Name"] == visual_name)
-        for _, r in dfV.iterrows()
-    ):
-        valid_display_name = page_name
-        dfV_filt = dfV[
-            (dfV["Page Display Name"] == page_name)
-            & (dfV["Visual Name"] == visual_name)
-        ]
-        file_path = dfV_filt["File Path"].iloc[0]
-        valid_page_name = dfV_filt["Page Name"].iloc[0]
-    else:
-        raise ValueError(
-            f"{icons.red_dot} Invalid page/visual name. The '{visual_name}' visual on the '{page_name}' page does not exist in the '{self._report}' report within the '{self._workspace}' workspace."
-        )
-
-    return valid_page_name, valid_display_name, visual_name, file_path
-
-
 def find_entity_property_pairs(data, result=None, keys_path=None):
 
     if result is None: