edx-enterprise-data 8.5.0__tar.gz → 8.6.0__tar.gz

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0}/CHANGELOG.rst

@@ -16,6 +16,10 @@ Unreleased
 
 =========================
 
+[8.6.0] - 2024-08-12
+---------------------
+  * Added API endpoints for advance analytics enrollments data.
+
 [8.5.0] - 2024-08-12
 ---------------------
   * Added a new model and REST endpoint to get Exec Ed LC Module Performance data.

{edx_enterprise_data-8.5.0/edx_enterprise_data.egg-info → edx_enterprise_data-8.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edx-enterprise-data
-Version: 8.5.0
+Version: 8.6.0
 Summary: Enterprise Reporting
 Home-page: https://github.com/openedx/edx-enterprise-data
 Author: edX

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0/edx_enterprise_data.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edx-enterprise-data
-Version: 8.5.0
+Version: 8.6.0
 Summary: Enterprise Reporting
 Home-page: https://github.com/openedx/edx-enterprise-data
 Author: edX

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0}/edx_enterprise_data.egg-info/SOURCES.txt

@@ -21,6 +21,7 @@ enterprise_data/signals.py
 enterprise_data/urls.py
 enterprise_data/utils.py
 enterprise_data/admin_analytics/__init__.py
+enterprise_data/admin_analytics/constants.py
 enterprise_data/admin_analytics/data_loaders.py
 enterprise_data/admin_analytics/database.py
 enterprise_data/admin_analytics/utils.py
@@ -31,9 +32,11 @@ enterprise_data/api/v0/serializers.py
 enterprise_data/api/v0/urls.py
 enterprise_data/api/v0/views.py
 enterprise_data/api/v1/__init__.py
+enterprise_data/api/v1/paginators.py
 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/base.py
 enterprise_data/api/v1/views/enterprise_admin.py
 enterprise_data/api/v1/views/enterprise_learner.py
@@ -109,6 +112,8 @@ 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_enrollments.py
+enterprise_data/tests/admin_analytics/test_analytics_enrollments.py
 enterprise_data/tests/admin_analytics/test_data_loaders.py
 enterprise_data/tests/admin_analytics/test_utils.py
 enterprise_data/tests/api/__init__.py

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0}/enterprise_data/__init__.py

@@ -2,4 +2,4 @@
 Enterprise data api application. This Django app exposes API endpoints used by enterprises.
 """
 
-__version__ = "8.5.0"
+__version__ = "8.6.0"

edx_enterprise_data-8.6.0/enterprise_data/admin_analytics/constants.py

@@ -0,0 +1,27 @@
+"""Advanced Analytics Constants"""
+
+from enum import Enum
+
+
+class GRANULARITY(Enum):
+    """Granularity choices"""
+    DAILY = 'Daily'
+    WEEKLY = 'Weekly'
+    MONTHLY = 'Monthly'
+    QUARTERLY = 'Quarterly'
+
+
+class CALCULATION(Enum):
+    """Calculation choices"""
+    TOTAL = 'Total'
+    RUNNING_TOTAL = 'Running Total'
+    MOVING_AVERAGE_3_PERIOD = 'Moving Average (3 Period)'
+    MOVING_AVERAGE_7_PERIOD = 'Moving Average (7 Period)'
+
+
+class ENROLLMENT_CSV(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'

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0}/enterprise_data/admin_analytics/utils.py

@@ -6,6 +6,7 @@ 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.utils import date_filter, primary_subject_truncate
 
@@ -19,6 +20,54 @@ class ChartType(Enum):
     TOP_SKILLS_COMPLETION = 'top_skills_completion'
 
 
+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"
+    }
+
+    if level in period_mapping:
+        df[date] = df[date].dt.to_period(period_mapping[level]).dt.start_time
+
+    agg_column_name = "count"
+    if aggregation_type == "count":
+        df = df.groupby(group).size().reset_index()
+    elif aggregation_type == "sum":
+        df = df.groupby(group).sum().reset_index()
+        agg_column_name = "sum"
+
+    df.columns = group + [agg_column_name]
+    return df
+
+
+def calculation_aggregation(calc, data_frame, aggregation_type="count"):
+    """Aggregate data based on calculation"""
+    df = data_frame
+
+    window_mapping = {
+        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:
+        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]:
+        df[aggregation_column] = (
+            df.groupby("enroll_type")[aggregation_column]
+            .rolling(window_mapping[calc])
+            .mean()
+            .droplevel(level=[0])
+        )
+
+    return df
+
+
 def get_cache_timeout(cache_expiry):
     """
     Helper method to calculate cache timeout in seconds.

edx_enterprise_data-8.6.0/enterprise_data/api/v1/paginators.py

@@ -0,0 +1,121 @@
+"""Custom paginator for the Advance Analytics API."""
+
+import math
+from dataclasses import dataclass
+from typing import Any
+
+from rest_framework.exceptions import NotFound
+from rest_framework.pagination import PageNumberPagination
+from rest_framework.response import Response
+
+
+@dataclass
+class Page:
+    """
+    A class representing a single page of paginated data.
+
+    Attributes:
+        data (Any): The data contained in the current page.
+        count (int): The total number of items across all pages.
+        num_pages (int): The total number of pages.
+        current_page (int): The current page number.
+    """
+    data: Any
+    count: int
+    num_pages: int
+    current_page: int
+
+    def has_next(self):
+        """
+        Check if there is a next page.
+
+        Returns:
+            bool: True if there is a next page, False otherwise.
+        """
+        return self.current_page < self.num_pages
+
+    def has_previous(self):
+        """
+        Check if there is a previous page.
+
+        Returns:
+            bool: True if there is a previous page, False otherwise.
+        """
+        return self.current_page > 1
+
+    def next_page_number(self):
+        """
+        Get the next page number.
+
+        Returns:
+            int: The next page number.
+        """
+        return self.current_page + 1
+
+    def previous_page_number(self):
+        """
+        Get the previous page number.
+
+        Returns:
+            int: The previous page number.
+        """
+        return self.current_page - 1
+
+
+class AdvanceAnalyticsPagination(PageNumberPagination):
+    """
+    Custom pagination class for advanced analytics.
+
+    Attributes:
+        page_size_query_param (str): The query parameter for the page size.
+        page_size (int): The default page size.
+        max_page_size (int): The maximum allowed page size.
+    """
+    page_size_query_param = "page_size"
+    page_size = 10
+    max_page_size = 100
+
+    def paginate_queryset(self, queryset, request, view=None):
+        """
+        Paginate a given dataframe based on the request parameters.
+
+        Args:
+            queryset (pd.DataFrame): The dataframe to paginate.
+            request (Request): The request object containing query parameters.
+            view (View, optional): The view that is calling the paginator.
+
+        Returns:
+            Page: A Page object. `data` attribute of the object will contain the paginated data.
+        """
+        dataframe = queryset
+
+        self.request = request  # pylint: disable=attribute-defined-outside-init
+        page_size = self.get_page_size(request)
+        if not page_size:
+            return None
+
+        total_rows = dataframe.shape[0]
+        num_pages = math.ceil(total_rows / page_size)
+
+        page_number = int(request.query_params.get(self.page_query_param) or 1)
+        if page_number <= 0 or page_number > num_pages:
+            raise NotFound('Invalid page.')
+
+        start_index = (page_number - 1) * page_size
+        end_index = min(start_index + page_size, total_rows)
+        data_frame_page = dataframe.iloc[start_index:end_index]
+
+        # pylint: disable=attribute-defined-outside-init
+        self.page = Page(data_frame_page, total_rows, num_pages, page_number)
+
+        return self.page
+
+    def get_paginated_response(self, data):
+        return Response({
+            'next': self.get_next_link(),
+            'previous': self.get_previous_link(),
+            'count': self.page.count,
+            'num_pages': self.page.num_pages,
+            'current_page': self.page.current_page,
+            'results': data
+        })

{edx_enterprise_data-8.5.0 → edx_enterprise_data-8.6.0}/enterprise_data/api/v1/serializers.py

@@ -5,6 +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.models import (
     EnterpriseAdminLearnerProgress,
     EnterpriseAdminSummarizeInsights,
@@ -227,3 +228,92 @@ class EnterpriseExecEdLCModulePerformanceSerializer(serializers.ModelSerializer)
     class Meta:
         model = EnterpriseExecEdLCModulePerformance
         fields = '__all__'
+
+
+class AdvanceAnalyticsQueryParamSerializer(serializers.Serializer):  # pylint: disable=abstract-method
+    """Serializer for validating query params"""
+    GRANULARITY_CHOICES = [
+        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
+    ]
+
+    start_date = serializers.DateField(required=False)
+    end_date = serializers.DateField(required=False)
+    granularity = serializers.CharField(required=False)
+    calculation = serializers.CharField(required=False)
+
+    def validate(self, attrs):
+        """
+        Validate the query params.
+
+        Raises:
+            serializers.ValidationError: If start_date is greater than end_date.
+        """
+        start_date = attrs.get('start_date')
+        end_date = attrs.get('end_date')
+
+        if start_date and end_date and start_date > end_date:
+            raise serializers.ValidationError("start_date should be less than or equal to end_date.")
+
+        return attrs
+
+    def validate_granularity(self, value):
+        """
+        Validate the granularity value.
+
+        Raises:
+            serializers.ValidationError: If granularity is not one of the valid choices.
+        """
+        if value not in self.GRANULARITY_CHOICES:
+            raise serializers.ValidationError(f"Granularity must be one of {self.GRANULARITY_CHOICES}")
+        return value
+
+    def validate_calculation(self, value):
+        """
+        Validate the calculation value.
+
+        Raises:
+            serializers.ValidationError: If calculation is not one of the valid choices
+        """
+        if value not in self.CALCULATION_CHOICES:
+            raise serializers.ValidationError(f"Calculation must be one of {self.CALCULATION_CHOICES}")
+        return value
+
+
+class AdvanceAnalyticsEnrollmentSerializer(AdvanceAnalyticsQueryParamSerializer):  # pylint: disable=abstract-method
+    """Serializer for validating Advance Analytics Enrollments API"""
+    CSV_TYPES = [
+        ENROLLMENT_CSV.INDIVIDUAL_ENROLLMENTS.value
+    ]
+
+    csv_type = serializers.CharField(required=False)
+
+    def validate_csv_type(self, value):
+        """
+        Validate the csv_type value.
+
+        Raises:
+            serializers.ValidationError: If csv_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}")
+        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-8.5.0 → edx_enterprise_data-8.6.0}/enterprise_data/api/v1/urls.py

@@ -10,6 +10,10 @@ from django.urls import re_path
 from enterprise_data.api.v1.views import enterprise_admin as enterprise_admin_views
 from enterprise_data.api.v1.views import enterprise_learner as enterprise_learner_views
 from enterprise_data.api.v1.views import enterprise_offers as enterprise_offers_views
+from enterprise_data.api.v1.views.analytics_enrollments import (
+    AdvanceAnalyticsEnrollmentStatsView,
+    AdvanceAnalyticsIndividualEnrollmentsView,
+)
 from enterprise_data.constants import UUID4_REGEX
 
 app_name = 'enterprise_data_api_v1'
@@ -52,6 +56,16 @@ urlpatterns = [
         enterprise_admin_views.EnterpriseAdminAnalyticsAggregatesView.as_view(),
         name='enterprise-admin-analytics-aggregates'
     ),
+    re_path(
+        fr'^admin/anlaytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments/stats$',
+        AdvanceAnalyticsEnrollmentStatsView.as_view(),
+        name='enterprise-admin-analytics-enrollments-stats'
+    ),
+    re_path(
+        fr'^admin/anlaytics/(?P<enterprise_uuid>{UUID4_REGEX})/enrollments$',
+        AdvanceAnalyticsIndividualEnrollmentsView.as_view(),
+        name='enterprise-admin-analytics-enrollments'
+    ),
     re_path(
         fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})/skills/stats',
         enterprise_admin_views.EnterpriseAdminAnalyticsSkillsView.as_view(),