edx-enterprise-data 8.7.0__tar.gz → 8.8.0__tar.gz

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/CHANGELOG.rst

@@ -16,6 +16,11 @@ Unreleased
 
 =========================
 
+[8.8.0] - 2024-08-15
+---------------------
+  * feat: Add API endpoints for advance analytics leaderboard data
+  * refactor: Use `response_type` and `chart_type` in advance analytics enrollments API endpoints
+
 [8.7.0] - 2024-08-13
 ---------------------
   * feat: add endpoints to get completion data for an enterprise customer

{edx_enterprise_data-8.7.0/edx_enterprise_data.egg-info → edx_enterprise_data-8.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edx-enterprise-data
-Version: 8.7.0
+Version: 8.8.0
 Summary: Enterprise Reporting
 Home-page: https://github.com/openedx/edx-enterprise-data
 Author: edX

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0/edx_enterprise_data.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edx-enterprise-data
-Version: 8.7.0
+Version: 8.8.0
 Summary: Enterprise Reporting
 Home-page: https://github.com/openedx/edx-enterprise-data
 Author: edX

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/edx_enterprise_data.egg-info/SOURCES.txt

@@ -38,6 +38,7 @@ enterprise_data/api/v1/serializers.py
 enterprise_data/api/v1/urls.py
 enterprise_data/api/v1/views/__init__.py
 enterprise_data/api/v1/views/analytics_enrollments.py
+enterprise_data/api/v1/views/analytics_leaderboard.py
 enterprise_data/api/v1/views/base.py
 enterprise_data/api/v1/views/enterprise_admin.py
 enterprise_data/api/v1/views/enterprise_completions.py
@@ -114,8 +115,10 @@ enterprise_data/tests/test_models.py
 enterprise_data/tests/test_utils.py
 enterprise_data/tests/test_views.py
 enterprise_data/tests/admin_analytics/__init__.py
+enterprise_data/tests/admin_analytics/mock_analytics_data.py
 enterprise_data/tests/admin_analytics/mock_enrollments.py
 enterprise_data/tests/admin_analytics/test_analytics_enrollments.py
+enterprise_data/tests/admin_analytics/test_analytics_leaderboard.py
 enterprise_data/tests/admin_analytics/test_data_loaders.py
 enterprise_data/tests/admin_analytics/test_enterprise_completions.py
 enterprise_data/tests/admin_analytics/test_utils.py

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/__init__.py

@@ -2,4 +2,4 @@
 Enterprise data api application. This Django app exposes API endpoints used by enterprises.
 """
 
-__version__ = "8.7.0"
+__version__ = "8.8.0"

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/admin_analytics/constants.py

@@ -3,7 +3,7 @@
 from enum import Enum
 
 
-class GRANULARITY(Enum):
+class Granularity(Enum):
     """Granularity choices"""
     DAILY = 'Daily'
     WEEKLY = 'Weekly'
@@ -11,7 +11,7 @@ class GRANULARITY(Enum):
     QUARTERLY = 'Quarterly'
 
 
-class CALCULATION(Enum):
+class Calculation(Enum):
     """Calculation choices"""
     TOTAL = 'Total'
     RUNNING_TOTAL = 'Running Total'
@@ -19,9 +19,15 @@ class CALCULATION(Enum):
     MOVING_AVERAGE_7_PERIOD = 'Moving Average (7 Period)'
 
 
-class ENROLLMENT_CSV(Enum):
+class EnrollmentChart(Enum):
     """CSV choices"""
     ENROLLMENTS_OVER_TIME = 'enrollments_over_time'
     TOP_COURSES_BY_ENROLLMENTS = 'top_courses_by_enrollments'
     TOP_SUBJECTS_BY_ENROLLMENTS = 'top_subjects_by_enrollments'
     INDIVIDUAL_ENROLLMENTS = 'individual_enrollments'
+
+
+class ResponseType(Enum):
+    """Response type choices"""
+    JSON = 'json'
+    CSV = 'csv'

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/admin_analytics/utils.py

@@ -1,13 +1,18 @@
 """
 Utility functions for fetching data from the database.
 """
-from datetime import datetime
+from datetime import datetime, timedelta
 from enum import Enum
 
 from edx_django_utils.cache import TieredCache, get_cache_key
 
-from enterprise_data.admin_analytics.constants import CALCULATION, GRANULARITY
-from enterprise_data.admin_analytics.data_loaders import fetch_engagement_data, fetch_enrollment_data, fetch_skills_data
+from enterprise_data.admin_analytics.constants import Calculation, Granularity
+from enterprise_data.admin_analytics.data_loaders import (
+    fetch_engagement_data,
+    fetch_enrollment_data,
+    fetch_max_enrollment_datetime,
+    fetch_skills_data,
+)
 from enterprise_data.utils import date_filter, primary_subject_truncate
 
 
@@ -23,14 +28,45 @@ class ChartType(Enum):
     TOP_SUBJECTS_BY_COMPLETIONS = 'top_subjects_by_completions'
 
 
+def fetch_enrollments_cache_expiry_timestamp():
+    """Calculate cache expiry timestamp"""
+    # TODO: Implement correct cache expiry logic for `enrollments` data.
+    #       Current cache expiry logic is based on `enterprise_learner_enrollment` table,
+    #       Which has nothing to do with the `enrollments` data. Instead cache expiry should
+    #       be based on `fact_enrollment_admin_dash` table. Currently we have no timestamp in
+    #       `fact_enrollment_admin_dash` table that can be used for cache expiry. Add a new
+    #       column in the table for this purpose and then use that column for cache expiry.
+    last_updated_at = fetch_max_enrollment_datetime()
+    cache_expiry = (
+        last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
+    )
+    return cache_expiry
+
+
+def fetch_engagements_cache_expiry_timestamp():
+    """Calculate cache expiry timestamp"""
+    # TODO: Implement correct cache expiry logic for `engagements` data.
+    #       Current cache expiry logic is based on `enterprise_learner_enrollment` table,
+    #       Which has nothing to do with the `engagements` data. Instead cache expiry should
+    #       be based on `fact_enrollment_engagement_day_admin_dash` table. Currently we have
+    #       no timestamp in `fact_enrollment_engagement_day_admin_dash` table that can be used
+    #       for cache expiry. Add a new column in the table for this purpose and then use that
+    #       column for cache expiry.
+    last_updated_at = fetch_max_enrollment_datetime()
+    cache_expiry = (
+        last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
+    )
+    return cache_expiry
+
+
 def granularity_aggregation(level, group, date, data_frame, aggregation_type="count"):
     """Aggregate data based on granularity"""
     df = data_frame
 
     period_mapping = {
-        GRANULARITY.WEEKLY.value: "W",
-        GRANULARITY.MONTHLY.value: "M",
-        GRANULARITY.QUARTERLY.value: "Q"
+        Granularity.WEEKLY.value: "W",
+        Granularity.MONTHLY.value: "M",
+        Granularity.QUARTERLY.value: "Q"
     }
 
     if level in period_mapping:
@@ -52,15 +88,15 @@ def calculation_aggregation(calc, data_frame, aggregation_type="count"):
     df = data_frame
 
     window_mapping = {
-        CALCULATION.MOVING_AVERAGE_3_PERIOD.value: 3,
-        CALCULATION.MOVING_AVERAGE_7_PERIOD.value: 7,
+        Calculation.MOVING_AVERAGE_3_PERIOD.value: 3,
+        Calculation.MOVING_AVERAGE_7_PERIOD.value: 7,
     }
 
     aggregation_column = "count" if aggregation_type == "count" else "sum"
 
-    if calc == CALCULATION.RUNNING_TOTAL.value:
+    if calc == Calculation.RUNNING_TOTAL.value:
         df[aggregation_column] = df.groupby("enroll_type")[aggregation_column].cumsum()
-    elif calc in [CALCULATION.MOVING_AVERAGE_3_PERIOD.value, CALCULATION.MOVING_AVERAGE_7_PERIOD.value]:
+    elif calc in [Calculation.MOVING_AVERAGE_3_PERIOD.value, Calculation.MOVING_AVERAGE_7_PERIOD.value]:
         df[aggregation_column] = (
             df.groupby("enroll_type")[aggregation_column]
             .rolling(window_mapping[calc])

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/api/v1/paginators.py

@@ -72,7 +72,7 @@ class AdvanceAnalyticsPagination(PageNumberPagination):
         max_page_size (int): The maximum allowed page size.
     """
     page_size_query_param = "page_size"
-    page_size = 10
+    page_size = 50
     max_page_size = 100
 
     def paginate_queryset(self, queryset, request, view=None):

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/api/v1/serializers.py

@@ -5,7 +5,7 @@ from uuid import UUID
 
 from rest_framework import serializers
 
-from enterprise_data.admin_analytics.constants import CALCULATION, ENROLLMENT_CSV, GRANULARITY
+from enterprise_data.admin_analytics.constants import Calculation, EnrollmentChart, Granularity, ResponseType
 from enterprise_data.models import (
     EnterpriseAdminLearnerProgress,
     EnterpriseAdminSummarizeInsights,
@@ -237,23 +237,28 @@ class EnterpriseExecEdLCModulePerformanceSerializer(serializers.ModelSerializer)
 
 class AdvanceAnalyticsQueryParamSerializer(serializers.Serializer):  # pylint: disable=abstract-method
     """Serializer for validating query params"""
+    RESPONSE_TYPES = [
+        ResponseType.JSON.value,
+        ResponseType.CSV.value
+    ]
     GRANULARITY_CHOICES = [
-        GRANULARITY.DAILY.value,
-        GRANULARITY.WEEKLY.value,
-        GRANULARITY.MONTHLY.value,
-        GRANULARITY.QUARTERLY.value
+        Granularity.DAILY.value,
+        Granularity.WEEKLY.value,
+        Granularity.MONTHLY.value,
+        Granularity.QUARTERLY.value
     ]
     CALCULATION_CHOICES = [
-        CALCULATION.TOTAL.value,
-        CALCULATION.RUNNING_TOTAL.value,
-        CALCULATION.MOVING_AVERAGE_3_PERIOD.value,
-        CALCULATION.MOVING_AVERAGE_7_PERIOD.value
+        Calculation.TOTAL.value,
+        Calculation.RUNNING_TOTAL.value,
+        Calculation.MOVING_AVERAGE_3_PERIOD.value,
+        Calculation.MOVING_AVERAGE_7_PERIOD.value
     ]
 
     start_date = serializers.DateField(required=False)
     end_date = serializers.DateField(required=False)
     granularity = serializers.CharField(required=False)
     calculation = serializers.CharField(required=False)
+    response_type = serializers.CharField(required=False)
 
     def validate(self, attrs):
         """
@@ -270,6 +275,17 @@ class AdvanceAnalyticsQueryParamSerializer(serializers.Serializer):  # pylint: d
 
         return attrs
 
+    def validate_response_type(self, value):
+        """
+        Validate the response_type value.
+
+        Raises:
+            serializers.ValidationError: If response_type is not one of the valid choices in `RESPONSE_TYPES`.
+        """
+        if value not in self.RESPONSE_TYPES:
+            raise serializers.ValidationError(f"response_type must be one of {self.RESPONSE_TYPES}")
+        return value
+
     def validate_granularity(self, value):
         """
         Validate the granularity value.
@@ -293,32 +309,25 @@ class AdvanceAnalyticsQueryParamSerializer(serializers.Serializer):  # pylint: d
         return value
 
 
-class AdvanceAnalyticsEnrollmentSerializer(AdvanceAnalyticsQueryParamSerializer):  # pylint: disable=abstract-method
-    """Serializer for validating Advance Analytics Enrollments API"""
-    CSV_TYPES = [
-        ENROLLMENT_CSV.INDIVIDUAL_ENROLLMENTS.value
+class AdvanceAnalyticsEnrollmentStatsSerializer(
+    AdvanceAnalyticsQueryParamSerializer
+):  # pylint: disable=abstract-method
+    """Serializer for validating Advance Analytics Enrollments Stats API"""
+    CHART_TYPES = [
+        EnrollmentChart.ENROLLMENTS_OVER_TIME.value,
+        EnrollmentChart.TOP_COURSES_BY_ENROLLMENTS.value,
+        EnrollmentChart.TOP_SUBJECTS_BY_ENROLLMENTS.value
     ]
 
-    csv_type = serializers.CharField(required=False)
+    chart_type = serializers.CharField(required=False)
 
-    def validate_csv_type(self, value):
+    def validate_chart_type(self, value):
         """
-        Validate the csv_type value.
+        Validate the chart_type value.
 
         Raises:
-            serializers.ValidationError: If csv_type is not one of the valid choices
+            serializers.ValidationError: If chart_type is not one of the valid choices
         """
-        if value not in self.CSV_TYPES:
-            raise serializers.ValidationError(f"csv_type must be one of {self.CSV_TYPES}")
+        if value not in self.CHART_TYPES:
+            raise serializers.ValidationError(f"chart_type must be one of {self.CHART_TYPES}")
         return value
-
-
-class AdvanceAnalyticsEnrollmentStatsSerializer(
-    AdvanceAnalyticsEnrollmentSerializer
-):  # pylint: disable=abstract-method
-    """Serializer for validating Advance Analytics Enrollments Stats API"""
-    CSV_TYPES = [
-        ENROLLMENT_CSV.ENROLLMENTS_OVER_TIME.value,
-        ENROLLMENT_CSV.TOP_COURSES_BY_ENROLLMENTS.value,
-        ENROLLMENT_CSV.TOP_SUBJECTS_BY_ENROLLMENTS.value
-    ]

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/api/v1/urls.py

@@ -15,6 +15,7 @@ from enterprise_data.api.v1.views.analytics_enrollments import (
     AdvanceAnalyticsEnrollmentStatsView,
     AdvanceAnalyticsIndividualEnrollmentsView,
 )
+from enterprise_data.api.v1.views.analytics_leaderboard import AdvanceAnalyticsLeaderboardView
 from enterprise_data.constants import UUID4_REGEX
 
 app_name = 'enterprise_data_api_v1'
@@ -53,32 +54,37 @@ urlpatterns = [
         name='enterprise-admin-insights'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})$',
+        fr'^admin/analytics/(?P<enterprise_id>{UUID4_REGEX})$',
         enterprise_admin_views.EnterpriseAdminAnalyticsAggregatesView.as_view(),
         name='enterprise-admin-analytics-aggregates'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments/stats$',
+        fr'^admin/analytics/(?P<enterprise_uuid>{UUID4_REGEX})/leaderboard$',
+        AdvanceAnalyticsLeaderboardView.as_view(),
+        name='enterprise-admin-analytics-leaderboard'
+    ),
+    re_path(
+        fr'^admin/analytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments/stats$',
         AdvanceAnalyticsEnrollmentStatsView.as_view(),
         name='enterprise-admin-analytics-enrollments-stats'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments$',
+        fr'^admin/analytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments$',
         AdvanceAnalyticsIndividualEnrollmentsView.as_view(),
         name='enterprise-admin-analytics-enrollments'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})/skills/stats',
+        fr'^admin/analytics/(?P<enterprise_id>{UUID4_REGEX})/skills/stats',
         enterprise_admin_views.EnterpriseAdminAnalyticsSkillsView.as_view(),
         name='enterprise-admin-analytics-skills'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})/completions/stats$',
+        fr'^admin/analytics/(?P<enterprise_id>{UUID4_REGEX})/completions/stats$',
         enterprise_completions_views.EnterrpiseAdminCompletionsStatsView.as_view(),
         name='enterprise-admin-analytics-completions-stats'
     ),
     re_path(
-        fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})/completions$',
+        fr'^admin/analytics/(?P<enterprise_id>{UUID4_REGEX})/completions$',
         enterprise_completions_views.EnterrpiseAdminCompletionsView.as_view(),
         name='enterprise-admin-analytics-completions'
     ),

{edx_enterprise_data-8.7.0 → edx_enterprise_data-8.8.0}/enterprise_data/api/v1/views/analytics_enrollments.py

@@ -1,5 +1,5 @@
 """Advance Analytics for Enrollments"""
-from datetime import datetime, timedelta
+from datetime import datetime
 
 from edx_rbac.decorators import permission_required
 from edx_rest_framework_extensions.auth.jwt.authentication import JwtAuthentication
@@ -8,37 +8,22 @@ from rest_framework.views import APIView
 
 from django.http import HttpResponse, StreamingHttpResponse
 
-from enterprise_data.admin_analytics.constants import CALCULATION, ENROLLMENT_CSV, GRANULARITY
-from enterprise_data.admin_analytics.data_loaders import fetch_max_enrollment_datetime
+from enterprise_data.admin_analytics.constants import Calculation, EnrollmentChart, Granularity, ResponseType
 from enterprise_data.admin_analytics.utils import (
     calculation_aggregation,
     fetch_and_cache_enrollments_data,
+    fetch_enrollments_cache_expiry_timestamp,
     granularity_aggregation,
 )
 from enterprise_data.api.v1.paginators import AdvanceAnalyticsPagination
 from enterprise_data.api.v1.serializers import (
-    AdvanceAnalyticsEnrollmentSerializer,
     AdvanceAnalyticsEnrollmentStatsSerializer,
+    AdvanceAnalyticsQueryParamSerializer,
 )
 from enterprise_data.renderers import IndividualEnrollmentsCSVRenderer
 from enterprise_data.utils import date_filter
 
 
-def fetch_enrollments_cache_expiry_timestamp():
-    """Calculate cache expiry timestamp"""
-    # TODO: Implement correct cache expiry logic for `enrollments` data.
-    #       Current cache expiry logic is based on `enterprise_learner_enrollment` table,
-    #       Which has nothing to do with the `enrollments` data. Instead cache expiry should
-    #       be based on `fact_enrollment_admin_dash` table. Currently we have no timestamp in
-    #       `fact_enrollment_admin_dash` table that can be used for cache expiry. Add a new
-    #       column in the table for this purpose and then use that column for cache expiry.
-    last_updated_at = fetch_max_enrollment_datetime()
-    cache_expiry = (
-        last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
-    )
-    return cache_expiry
-
-
 class AdvanceAnalyticsIndividualEnrollmentsView(APIView):
     """
     API for getting the advance analytics individual enrollments data.
@@ -50,7 +35,7 @@ class AdvanceAnalyticsIndividualEnrollmentsView(APIView):
     @permission_required('can_access_enterprise', fn=lambda request, enterprise_uuid: enterprise_uuid)
     def get(self, request, enterprise_uuid):
         """Get individual enrollments data"""
-        serializer = AdvanceAnalyticsEnrollmentSerializer(data=request.GET)
+        serializer = AdvanceAnalyticsQueryParamSerializer(data=request.GET)
         serializer.is_valid(raise_exception=True)
 
         cache_expiry = fetch_enrollments_cache_expiry_timestamp()
@@ -59,7 +44,7 @@ class AdvanceAnalyticsIndividualEnrollmentsView(APIView):
         # get values from query params or use default values
         start_date = serializer.data.get('start_date', enrollments_df.enterprise_enrollment_date.min())
         end_date = serializer.data.get('end_date', datetime.now())
-        csv_type = request.query_params.get('csv_type')
+        response_type = request.query_params.get('response_type', ResponseType.JSON.value)
 
         # filter enrollments by date
         enrollments = date_filter(start_date, end_date, enrollments_df, "enterprise_enrollment_date")
@@ -77,11 +62,12 @@ class AdvanceAnalyticsIndividualEnrollmentsView(APIView):
         enrollments["enterprise_enrollment_date"] = enrollments["enterprise_enrollment_date"].dt.date
         enrollments = enrollments.sort_values(by="enterprise_enrollment_date", ascending=False).reset_index(drop=True)
 
-        if csv_type == ENROLLMENT_CSV.INDIVIDUAL_ENROLLMENTS.value:
+        if response_type == ResponseType.CSV.value:
+            filename = f"""individual_enrollments, {start_date} - {end_date}.csv"""
             return StreamingHttpResponse(
                 IndividualEnrollmentsCSVRenderer().render(self._stream_serialized_data(enrollments)),
                 content_type="text/csv",
-                headers={"Content-Disposition": 'attachment; filename="individual_enrollments.csv"'},
+                headers={"Content-Disposition": f'attachment; filename="{filename}"'},
             )
 
         paginator = self.pagination_class()
@@ -121,11 +107,12 @@ class AdvanceAnalyticsEnrollmentStatsView(APIView):
         # get values from query params or use default
         start_date = serializer.data.get('start_date', enrollments_df.enterprise_enrollment_date.min())
         end_date = serializer.data.get('end_date', datetime.now())
-        granularity = serializer.data.get('granularity', GRANULARITY.DAILY.value)
-        calculation = serializer.data.get('calculation', CALCULATION.TOTAL.value)
-        csv_type = serializer.data.get('csv_type')
+        granularity = serializer.data.get('granularity', Granularity.DAILY.value)
+        calculation = serializer.data.get('calculation', Calculation.TOTAL.value)
+        response_type = serializer.data.get('response_type', ResponseType.JSON.value)
+        chart_type = serializer.data.get('chart_type')
 
-        if csv_type is None:
+        if response_type == ResponseType.JSON.value:
             data = {
                 "enrollments_over_time": self.construct_enrollments_over_time(
                     enrollments_df.copy(),
@@ -146,26 +133,28 @@ class AdvanceAnalyticsEnrollmentStatsView(APIView):
                 ),
             }
             return Response(data)
-        elif csv_type == ENROLLMENT_CSV.ENROLLMENTS_OVER_TIME.value:
-            return self.construct_enrollments_over_time_csv(
-                enrollments_df.copy(),
-                start_date,
-                end_date,
-                granularity,
-                calculation,
-            )
-        elif csv_type == ENROLLMENT_CSV.TOP_COURSES_BY_ENROLLMENTS.value:
-            return self.construct_top_courses_by_enrollments_csv(
-                enrollments_df.copy(),
-                start_date,
-                end_date,
-            )
-        elif csv_type == ENROLLMENT_CSV.TOP_SUBJECTS_BY_ENROLLMENTS.value:
-            return self.construct_top_subjects_by_enrollments_csv(
-                enrollments_df.copy(),
-                start_date,
-                end_date,
-            )
+
+        if response_type == ResponseType.CSV.value:
+            if chart_type == EnrollmentChart.ENROLLMENTS_OVER_TIME.value:
+                return self.construct_enrollments_over_time_csv(
+                    enrollments_df.copy(),
+                    start_date,
+                    end_date,
+                    granularity,
+                    calculation,
+                )
+            elif chart_type == EnrollmentChart.TOP_COURSES_BY_ENROLLMENTS.value:
+                return self.construct_top_courses_by_enrollments_csv(
+                    enrollments_df.copy(),
+                    start_date,
+                    end_date,
+                )
+            elif chart_type == EnrollmentChart.TOP_SUBJECTS_BY_ENROLLMENTS.value:
+                return self.construct_top_subjects_by_enrollments_csv(
+                    enrollments_df.copy(),
+                    start_date,
+                    end_date,
+                )
 
     def enrollments_over_time_common(self, enrollments_df, start_date, end_date, granularity, calculation):
         """
@@ -175,8 +164,8 @@ class AdvanceAnalyticsEnrollmentStatsView(APIView):
             enrollments_df {DataFrame} -- DataFrame of enrollments
             start_date {datetime} -- Enrollment start date in the format 'YYYY-MM-DD'
             end_date {datetime} -- Enrollment end date in the format 'YYYY-MM-DD'
-            granularity {str} -- Granularity of the data. One of GRANULARITY choices
-            calculation {str} -- Calculation of the data. One of CALCULATION choices
+            granularity {str} -- Granularity of the data. One of Granularity choices
+            calculation {str} -- Calculation of the data. One of Calculation choices
         """
         # filter enrollments by date
         enrollments = date_filter(start_date, end_date, enrollments_df, "enterprise_enrollment_date")
@@ -202,8 +191,8 @@ class AdvanceAnalyticsEnrollmentStatsView(APIView):
             enrollments_df {DataFrame} -- DataFrame of enrollments
             start_date {datetime} -- Enrollment start date in the format 'YYYY-MM-DD'
             end_date {datetime} -- Enrollment end date in the format 'YYYY-MM-DD'
-            granularity {str} -- Granularity of the data. One of GRANULARITY choices
-            calculation {str} -- Calculation of the data. One of CALCULATION choices
+            granularity {str} -- Granularity of the data. One of Granularity choices
+            calculation {str} -- Calculation of the data. One of Calculation choices
         """
         enrollments = self.enrollments_over_time_common(enrollments_df, start_date, end_date, granularity, calculation)
 
@@ -218,8 +207,8 @@ class AdvanceAnalyticsEnrollmentStatsView(APIView):
             enrollments_df {DataFrame} -- DataFrame of enrollments
             start_date {datetime} -- Enrollment start date in the format 'YYYY-MM-DD'
             end_date {datetime} -- Enrollment end date in the format 'YYYY-MM-DD'
-            granularity {str} -- Granularity of the data. One of GRANULARITY choices
-            calculation {str} -- Calculation of the data. One of CALCULATION choices
+            granularity {str} -- Granularity of the data. One of Granularity choices
+            calculation {str} -- Calculation of the data. One of Calculation choices
         """
         enrollments = self.enrollments_over_time_common(enrollments_df, start_date, end_date, granularity, calculation)
 

edx_enterprise_data-8.8.0/enterprise_data/api/v1/views/analytics_leaderboard.py

@@ -0,0 +1,120 @@
+"""Advance Analytics for Leaderboard"""
+from datetime import datetime
+
+import numpy as np
+import pandas as pd
+from edx_rbac.decorators import permission_required
+from edx_rest_framework_extensions.auth.jwt.authentication import JwtAuthentication
+from rest_framework.views import APIView
+
+from django.http import StreamingHttpResponse
+
+from enterprise_data.admin_analytics.constants import ResponseType
+from enterprise_data.admin_analytics.utils import (
+    fetch_and_cache_engagements_data,
+    fetch_and_cache_enrollments_data,
+    fetch_engagements_cache_expiry_timestamp,
+    fetch_enrollments_cache_expiry_timestamp,
+)
+from enterprise_data.api.v1.paginators import AdvanceAnalyticsPagination
+from enterprise_data.api.v1.serializers import AdvanceAnalyticsQueryParamSerializer
+from enterprise_data.renderers import LeaderboardCSVRenderer
+from enterprise_data.utils import date_filter
+
+
+class AdvanceAnalyticsLeaderboardView(APIView):
+    """
+    API for getting the advance analytics leaderboard data.
+    """
+    authentication_classes = (JwtAuthentication,)
+    pagination_class = AdvanceAnalyticsPagination
+    http_method_names = ['get']
+
+    @permission_required('can_access_enterprise', fn=lambda request, enterprise_uuid: enterprise_uuid)
+    def get(self, request, enterprise_uuid):
+        """Get leaderboard data"""
+        serializer = AdvanceAnalyticsQueryParamSerializer(data=request.GET)
+        serializer.is_valid(raise_exception=True)
+
+        enrollments_cache_expiry = fetch_enrollments_cache_expiry_timestamp()
+        enrollments_df = fetch_and_cache_enrollments_data(enterprise_uuid, enrollments_cache_expiry)
+
+        engagements_cache_expiry = fetch_engagements_cache_expiry_timestamp()
+        engagements_df = fetch_and_cache_engagements_data(enterprise_uuid, engagements_cache_expiry)
+
+        start_date = serializer.data.get('start_date', enrollments_df.enterprise_enrollment_date.min())
+        end_date = serializer.data.get('end_date', datetime.now())
+        response_type = serializer.data.get('response_type', ResponseType.JSON.value)
+
+        # only include learners who have passed the course
+        enrollments_df = enrollments_df[enrollments_df["has_passed"] == 1]
+
+        # filter enrollments by date
+        enrollments_df = date_filter(start_date, end_date, enrollments_df, "passed_date")
+
+        completions = enrollments_df.groupby(["email"]).size().reset_index()
+        completions.columns = ["email", "course_completions"]
+
+        # filter engagements by date
+        engagements_df = date_filter(start_date, end_date, engagements_df, "activity_date")
+
+        engage = (
+            engagements_df.groupby(["email"])
+            .agg({"is_engaged": ["sum"], "learning_time_seconds": ["sum"]})
+            .reset_index()
+        )
+        engage.columns = ["email", "daily_sessions", "learning_time_seconds"]
+        engage["learning_time_hours"] = round(
+            engage["learning_time_seconds"].astype("float") / 60 / 60, 1
+        )
+        engage["average_session_length"] = round(
+            engage["learning_time_hours"] / engage["daily_sessions"].astype("float"), 1
+        )
+
+        leaderboard_df = engage.merge(completions, on="email", how="left")
+        leaderboard_df = leaderboard_df.sort_values(
+            by=["learning_time_hours", "daily_sessions", "course_completions"],
+            ascending=[False, False, False],
+        )
+
+        # move the aggregated row with email 'null' to the end of the table
+        idx = leaderboard_df.index[leaderboard_df['email'] == 'null']
+        leaderboard_df.loc[idx, 'email'] = 'learners who have not shared consent'
+        leaderboard_df = pd.concat([leaderboard_df.drop(idx), leaderboard_df.loc[idx]])
+
+        # convert `nan` values to `None` because `nan` is not JSON serializable
+        leaderboard_df = leaderboard_df.replace(np.nan, None)
+
+        if response_type == ResponseType.CSV.value:
+            filename = f"""Leaderboard, {start_date} - {end_date}.csv"""
+            leaderboard_df = leaderboard_df[
+                [
+                    "email",
+                    "learning_time_hours",
+                    "daily_sessions",
+                    "average_session_length",
+                    "course_completions",
+                ]
+            ]
+            return StreamingHttpResponse(
+                LeaderboardCSVRenderer().render(self._stream_serialized_data(leaderboard_df)),
+                content_type="text/csv",
+                headers={"Content-Disposition": f'attachment; filename="{filename}"'},
+            )
+
+        paginator = self.pagination_class()
+        page = paginator.paginate_queryset(leaderboard_df, request)
+        serialized_data = page.data.to_dict(orient='records')
+        response = paginator.get_paginated_response(serialized_data)
+
+        return response
+
+    def _stream_serialized_data(self, leaderboard_df, chunk_size=50000):
+        """
+        Stream the serialized data.
+        """
+        total_rows = leaderboard_df.shape[0]
+        for start_index in range(0, total_rows, chunk_size):
+            end_index = min(start_index + chunk_size, total_rows)
+            chunk = leaderboard_df.iloc[start_index:end_index]
+            yield from chunk.to_dict(orient='records')