edx-enterprise-data 8.3.1__py3-none-any.whl → 8.4.0__py3-none-any.whl

{edx_enterprise_data-8.3.1.dist-info → edx_enterprise_data-8.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edx-enterprise-data
-Version: 8.3.1
+Version: 8.4.0
 Summary: Enterprise Reporting
 Home-page: https://github.com/openedx/edx-enterprise-data
 Author: edX

{edx_enterprise_data-8.3.1.dist-info → edx_enterprise_data-8.4.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-enterprise_data/__init__.py,sha256=9P5euSdqQ9R848n450LMmcWN8bT4_wUPcxDHek9waKk,123
+enterprise_data/__init__.py,sha256=V3f8VWSTHKMmk7VgKNYsFMadFosPMVNgWxHub9YqP9c,123
 enterprise_data/apps.py,sha256=aF6hZwDfI2oWj95tUTm_2ikHueQj-jLj-u0GrgzpsQI,414
 enterprise_data/clients.py,sha256=GvQupy5TVYfO_IKC3yzXSAgNP54r-PtIjidM5ws9Iks,3947
 enterprise_data/constants.py,sha256=uCKjfpdlMYFZJsAj3n9RMw4Cmg5_6s3NuwocO-fch3s,238
@@ -8,11 +8,11 @@ enterprise_data/paginators.py,sha256=YPrC5TeXFt-ymenT2H8H2nCbDCnAzJQlH9kFPElRxWE
 enterprise_data/renderers.py,sha256=WVt0qy9Ippdnl404Zsq-MruB9oQfY6h87ZzpScYBeaw,1770
 enterprise_data/signals.py,sha256=8eqNPnlvmfsKf19lGWv5xTIuBgQIqR8EZSp9UYzC8Rc,1024
 enterprise_data/urls.py,sha256=bqtKF5OEWEwrNmHG3os-pZNuNsmjlhxEqp7yM4TbPf4,243
-enterprise_data/utils.py,sha256=UruTQLJcEl-q5UWGPnJZrnBnV1OvzBvhuoB_JkRY4Is,2328
+enterprise_data/utils.py,sha256=kNO4nW_GBpBiIBlVUkCb4Xo0k1oVshT8nDOBP5eWoV8,2643
 enterprise_data/admin_analytics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-enterprise_data/admin_analytics/data_loaders.py,sha256=jP9CgUt_93Bl_ak1_6dBPN4PAEdDT1da3sEMjJ45NLg,4281
+enterprise_data/admin_analytics/data_loaders.py,sha256=x1XNYdtJV1G9cv0SeBZqYitRV8-GlJXtEZ2cc2OJU7M,5415
 enterprise_data/admin_analytics/database.py,sha256=mNS_9xE5h6O7oMMzr6kr6LDTTSNvKzo8vaM-YG8tOd8,1312
-enterprise_data/admin_analytics/utils.py,sha256=Cock_rTtHkBEKcG3cq7VcYRPEuxC_SyJBlZn9KdVeCA,2465
+enterprise_data/admin_analytics/utils.py,sha256=J6E9JhZedWkJQ9TJJF_z95sL5Oka1_x7gs_st4Z35Yo,8420
 enterprise_data/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 enterprise_data/api/urls.py,sha256=POqc_KATHdnpMf9zHtpO46pKD5KAlAExtx7G6iylLcU,273
 enterprise_data/api/v0/__init__.py,sha256=1aAzAYU5hk-RW6cKUxa1645cbZMxn7GIZ7OMjWc9MKI,46
@@ -21,10 +21,10 @@ enterprise_data/api/v0/urls.py,sha256=vzJjqIo_S3AXWs9Us8XTaJc3FnxLbYzAkmLyuDQqum
 enterprise_data/api/v0/views.py,sha256=4RslZ4NZOU-844bnebEQ71ji2utRY7jEijqC45oQQD0,14380
 enterprise_data/api/v1/__init__.py,sha256=1aAzAYU5hk-RW6cKUxa1645cbZMxn7GIZ7OMjWc9MKI,46
 enterprise_data/api/v1/serializers.py,sha256=AOHumabnzwK59nytoOZEWhA3f9EL_CV-bXPsYSH3LI8,8263
-enterprise_data/api/v1/urls.py,sha256=IQMAD9sZp0QeJa2cUd-WxwugWaW4hHZetQGulTjnrGc,1633
+enterprise_data/api/v1/urls.py,sha256=m5B01cZuInVsJkRdUloHC45fHxSJKQMSzBSCgU2GpkA,1855
 enterprise_data/api/v1/views/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 enterprise_data/api/v1/views/base.py,sha256=FTAxlz5EzvAY657wzVgzhJPFSCHHzct7IDcvm71Smt8,866
-enterprise_data/api/v1/views/enterprise_admin.py,sha256=mvpufYoqyaGbHuclRpFj-cQxeME1j4L6S6qQ72Rxem0,4727
+enterprise_data/api/v1/views/enterprise_admin.py,sha256=hBUj5XPyyBwpyNED62lLlV1etRK9vHRS6aYnZLTF2w0,8081
 enterprise_data/api/v1/views/enterprise_learner.py,sha256=yABjJje3CT8I8YOhWr1_tTkdKtnGJom8eu3EFz_-0BU,18517
 enterprise_data/api/v1/views/enterprise_offers.py,sha256=VifxgqTLFLVw4extYPlHcN1N_yjXcsYsAlYEnAbpb10,1266
 enterprise_data/fixtures/enterprise_enrollment.json,sha256=6onPXXR29pMdTdbl_mn81sDi3Re5jkLUZz2TPMB_1IY,5786
@@ -94,11 +94,11 @@ enterprise_data/tests/mixins.py,sha256=YifptI9mtOhAWnBGyPUy4kX5OJNSDP3DvW2vb1E2t
 enterprise_data/tests/test_clients.py,sha256=xBPHF9cgEFqNJoL4klOoYh_sVS3scZGcX0Ltc9Ghp7A,6336
 enterprise_data/tests/test_filters.py,sha256=ZBbLl9Sgj5mJ7lTWoaFcEPwuxPDpIbMo2n_Fhurc0T8,7263
 enterprise_data/tests/test_models.py,sha256=MWBY-LY5TPBjZ4GlvpM-h4W-BvRKr2Rml8Bzg1NPZ9M,3234
-enterprise_data/tests/test_utils.py,sha256=itT-LvZwgJbLCSpqVCYA2TpCV9uKGi4TeVoelRfx-48,17327
+enterprise_data/tests/test_utils.py,sha256=vbmYM7DMN-lHS2p4yaa0Yd6uSGXd2qoZRDE9X3J4Sec,18385
 enterprise_data/tests/test_views.py,sha256=UvDRNTxruy5zBK_KgUy2cBMbwlaTW_vkM0-TCXbQZiY,69667
 enterprise_data/tests/admin_analytics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-enterprise_data/tests/admin_analytics/test_data_loaders.py,sha256=b4BjN88FX9WjE6XJjkJZnoEvWVB_DovBGJ_wh-HgT9I,3514
-enterprise_data/tests/admin_analytics/test_utils.py,sha256=4qL_ZK-sGzbMMqiOrBrPmzdIPno7KohiaIfd7FMehic,5260
+enterprise_data/tests/admin_analytics/test_data_loaders.py,sha256=o3denJ4aUS1pI5Crksl4C6m-NtCBm8ynoHBnLkf-v2U,4641
+enterprise_data/tests/admin_analytics/test_utils.py,sha256=y33HXy6BDOoftdcz3qYlOYhgx7JSXDki-OLzBdTpiwA,11449
 enterprise_data/tests/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 enterprise_data/tests/api/v0/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 enterprise_data/tests/api/v0/test_serializers.py,sha256=Gfty6gy6OQLN318uL1OCPhAZOqSUL50FWc0nC23VMnc,6257
@@ -106,7 +106,7 @@ enterprise_data/tests/api/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 enterprise_data/tests/api/v1/test_serializers.py,sha256=DwgEHcyOP3oqNUPB2O-NkJGeO_cYs9XJiq7791vJLZE,3682
 enterprise_data/tests/api/v1/test_views.py,sha256=rLqUHfar0HdBNtz33hQxd_0qUUgr7Ku3KwQSQ1B4Ypg,15213
 enterprise_data/tests/api/v1/views/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-enterprise_data/tests/api/v1/views/test_enterprise_admin.py,sha256=A7QY4RR6BwzxSsC9equXau8_PER25-KbufCNZyGdYBI,3025
+enterprise_data/tests/api/v1/views/test_enterprise_admin.py,sha256=7FCPpfFrv-pisJ9cxt3B-KIf-KM3a7XzQ8MweLp23wI,4783
 enterprise_data_roles/__init__.py,sha256=toCpbypm2uDoWVw29_em9gPFNly8vNUS__C0b4TCqEg,112
 enterprise_data_roles/admin.py,sha256=QNP0VeWE092vZzpyxOA5UJK1nNGl5e71B1J0RCwo_nU,998
 enterprise_data_roles/apps.py,sha256=nKi8TyuQ5Q6WGtKs5QeXvUTc3N-YQjKhyBnm2EM3Bng,260
@@ -147,8 +147,8 @@ enterprise_reporting/tests/test_send_enterprise_reports.py,sha256=WtL-RqGgu2x5PP
 enterprise_reporting/tests/test_utils.py,sha256=Zt_TA0LVb-B6fQGkUkAKKVlUKKnQh8jnw1US1jKe7g8,9493
 enterprise_reporting/tests/test_vertica_client.py,sha256=-R2yNCGUjRtoXwLMBloVFQkFYrJoo613VCr61gwI3kQ,140
 enterprise_reporting/tests/utils.py,sha256=xms2LM7DV3wczXEfctOK1ddel1EE0J_YSr17UzbCDy4,1401
-edx_enterprise_data-8.3.1.dist-info/LICENSE,sha256=dql8h4yceoMhuzlcK0TT_i-NgTFNIZsgE47Q4t3dUYI,34520
-edx_enterprise_data-8.3.1.dist-info/METADATA,sha256=Wb7AA7AgVPyoHB7_BzDnbnjcZ_-xx1nXtUCf0vkrAs8,1569
-edx_enterprise_data-8.3.1.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-edx_enterprise_data-8.3.1.dist-info/top_level.txt,sha256=f5F2kU-dob6MqiHJpgZkFzoCD5VMhsdpkTV5n9Tvq3I,59
-edx_enterprise_data-8.3.1.dist-info/RECORD,,
+edx_enterprise_data-8.4.0.dist-info/LICENSE,sha256=dql8h4yceoMhuzlcK0TT_i-NgTFNIZsgE47Q4t3dUYI,34520
+edx_enterprise_data-8.4.0.dist-info/METADATA,sha256=o0b8zqSTviYu9WVM9aDEK6ozyC_PBJlKxUQJC3fNZic,1569
+edx_enterprise_data-8.4.0.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+edx_enterprise_data-8.4.0.dist-info/top_level.txt,sha256=f5F2kU-dob6MqiHJpgZkFzoCD5VMhsdpkTV5n9Tvq3I,59
+edx_enterprise_data-8.4.0.dist-info/RECORD,,

enterprise_data/__init__.py

@@ -2,4 +2,4 @@
 Enterprise data api application. This Django app exposes API endpoints used by enterprises.
 """
 
-__version__ = "8.3.1"
+__version__ = "8.4.0"

enterprise_data/admin_analytics/data_loaders.py

@@ -135,3 +135,48 @@ def fetch_max_enrollment_datetime():
     if not results:
         return None
     return pandas.to_datetime(results[0][0])
+
+
+def fetch_skills_data(enterprise_uuid: str):
+    """
+    Fetch skills data from the database for the given enterprise customer.
+
+    Arguments:
+        enterprise_uuid (str): The UUID of the enterprise customer.
+
+    Returns:
+        (pandas.DataFrame): The skills data.
+    """
+
+    enterprise_uuid = enterprise_uuid.replace('-', '')
+
+    cols = [
+        'course_number',
+        'skill_type',
+        'skill_name',
+        'skill_url',
+        'confidence',
+        'skill_rank',
+        'course_title',
+        'course_key',
+        'level_type',
+        'primary_subject_name',
+        'date',
+        'enterprise_customer_uuid',
+        'enterprise_customer_name',
+        'enrolls',
+        'completions',
+    ]
+    query = get_select_query(
+        table='skills_daily_rollup_admin_dash', columns=cols, enterprise_uuid=enterprise_uuid
+    )
+
+    skills = run_query(query=query)
+
+    if not skills:
+        raise Http404(f'No skills data found for enterprise {enterprise_uuid}')
+
+    skills = pandas.DataFrame(numpy.array(skills), columns=cols)
+    skills['date'] = skills['date'].astype('datetime64[ns]')
+
+    return skills

enterprise_data/admin_analytics/utils.py

@@ -2,10 +2,21 @@
 Utility functions for fetching data from the database.
 """
 from datetime import datetime
+from enum import Enum
 
 from edx_django_utils.cache import TieredCache, get_cache_key
 
-from enterprise_data.admin_analytics.data_loaders import fetch_engagement_data, fetch_enrollment_data
+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
+
+
+class ChartType(Enum):
+    """
+    Chart types.
+    """
+    BUBBLE = 'bubble'
+    TOP_SKILLS_ENROLLMENT = 'top_skills_enrollment'
+    TOP_SKILLS_COMPLETION = 'top_skills_completion'
 
 
 def get_cache_timeout(cache_expiry):
@@ -79,3 +90,168 @@ def fetch_and_cache_engagements_data(enterprise_id, cache_expiry):
             cache_key, engagements, get_cache_timeout(cache_expiry)
         )
         return engagements
+
+
+def fetch_and_cache_skills_data(enterprise_id, cache_expiry):
+    """
+    Helper method to fetch and cache skills data.
+
+    Arguments:
+        enterprise_id (str): UUID of the enterprise customer in string format.
+        cache_expiry (datetime): Datetime object denoting the cache expiry.
+
+    Returns:
+        (pandas.DataFrame): The skills data.
+    """
+    cache_key = get_cache_key(
+        resource='enterprise-admin-analytics-aggregate-skills',
+        enterprise_customer=enterprise_id,
+    )
+    cached_response = TieredCache.get_cached_response(cache_key)
+
+    if cached_response.is_found:
+        return cached_response.value
+    else:
+        skills = fetch_skills_data(enterprise_id)
+        TieredCache.set_all_tiers(
+            cache_key, skills, get_cache_timeout(cache_expiry)
+        )
+        return skills
+
+
+def get_skills_bubble_chart_df(skills_filtered):
+    """ Get the skills data for the bubble chart.
+
+    Args:
+        skills_filtered (list): The skills data.
+
+    Returns:
+        (pandas.DataFrame): The skills data for the bubble chart.
+    """
+
+    # Group by skill_name and skill_type, and aggregate enrolls and completions
+    skills_aggregated = (
+        skills_filtered.groupby(['skill_name', 'skill_type'], as_index=False)
+        .agg(enrolls=('enrolls', 'sum'), completions=('completions', 'sum'))
+    )
+
+    # Convert enrolls and completions to integers
+    skills_aggregated['enrolls'] = skills_aggregated['enrolls'].astype(int)
+    skills_aggregated['completions'] = skills_aggregated['completions'].astype(int)
+
+    # Sort the dataframe by enrolls and completions in descending order
+    skills_aggregated = skills_aggregated.sort_values(by=['enrolls', 'completions'], ascending=False)
+
+    return skills_aggregated
+
+
+def get_top_skills_enrollment(skills_filtered):
+    """ Get the top skills by enrolls.
+
+    Args:
+        skills_filtered (pandas.DataFrame): The skills data.
+
+    Returns:
+        (pandas.DataFrame): The top skills by enrolls data
+    """
+
+    # Get the top 10 skills by enrolls
+    top_skills = (
+        skills_filtered.groupby('skill_name')
+        .enrolls.sum()
+        .sort_values(ascending=False)
+        .head(10)
+        .index
+    )
+
+    # Apply primary_subject_truncate to the primary_subject_name column
+    skills_filtered['primary_subject_name'] = skills_filtered['primary_subject_name'].apply(primary_subject_truncate)
+
+    # Filter data for the top skills and aggregate enrolls by skill_name and primary_subject_name
+    top_skills_enrollment_data = (
+        skills_filtered[skills_filtered.skill_name.isin(top_skills)]
+        .groupby(['skill_name', 'primary_subject_name'], as_index=False)
+        .agg(count=('enrolls', 'sum'))
+    )
+
+    # Sort the dataframe by primary_subject_name
+    top_skills_enrollment_data = top_skills_enrollment_data.sort_values(by="primary_subject_name")
+
+    return top_skills_enrollment_data
+
+
+def get_top_skills_completion(skills_filtered):
+    """ Get the top skills by completions.
+
+    Args:
+        skills_filtered (pandas.DataFrame): The skills data.
+
+    Returns:
+        (pandas.DataFrame): The top skills by completions
+    """
+
+    # Get the top 10 skills by completions
+    top_skills = (
+        skills_filtered.groupby('skill_name')
+        .completions.sum()
+        .sort_values(ascending=False)
+        .head(10)
+        .index
+    )
+
+    # Apply primary_subject_truncate to the primary_subject_name column
+    skills_filtered['primary_subject_name'] = skills_filtered['primary_subject_name'].apply(primary_subject_truncate)
+
+    # Filter data for the top skills and aggregate completions by skill_name and primary_subject_name
+    top_skills_completion_data = (
+        skills_filtered[skills_filtered.skill_name.isin(top_skills)]
+        .groupby(['skill_name', 'primary_subject_name'], as_index=False)
+        .agg(count=('completions', 'sum'))
+    )
+
+    # Sort the dataframe by primary_subject_name
+    top_skills_completion_data = top_skills_completion_data.sort_values(by='primary_subject_name')
+
+    return top_skills_completion_data
+
+
+def get_skills_chart_data(chart_type, start_date, end_date, skills):
+    """
+    Get chart data for skill charts.
+
+    Arguments:
+        chart_type (ChartType): The type of chart to generate.
+        start_date (datetime): The start date for the date filter.
+        end_date (datetime): The end date for the date filter.
+        skills (pandas.DataFrame): The skills data.
+    """
+    skills_filtered = date_filter(start=start_date, end=end_date, data_frame=skills.copy(), date_column='date')
+    if chart_type == ChartType.BUBBLE:
+        return get_skills_bubble_chart_df(skills_filtered=skills_filtered.copy())
+    elif chart_type == ChartType.TOP_SKILLS_ENROLLMENT:
+        return get_top_skills_enrollment(skills_filtered=skills_filtered.copy())
+    elif chart_type == ChartType.TOP_SKILLS_COMPLETION:
+        return get_top_skills_completion(skills_filtered=skills_filtered.copy())
+    else:
+        raise ValueError(f"Invalid chart type: {chart_type}")
+
+
+def get_top_skills_csv_data(skills, start_date, end_date):
+    """ Get the top skills data for CSV download.
+
+    Args:
+        skills (pandas.DataFrame): The skills data.
+        start_date (str): The start date for the date filter.
+        end_date (str): The end date for the date filter.
+
+    Returns:
+        (pandas.DataFrame): The top skills data for CSV download.
+    """
+    dff = get_skills_chart_data(
+        chart_type=ChartType.BUBBLE,
+        start_date=start_date,
+        end_date=end_date,
+        skills=skills.copy(),
+    )
+    dff = dff.sort_values(by='enrolls', ascending=False)
+    return dff

enterprise_data/api/v1/urls.py

@@ -47,6 +47,11 @@ urlpatterns = [
         enterprise_admin_views.EnterpriseAdminAnalyticsAggregatesView.as_view(),
         name='enterprise-admin-analytics-aggregates'
     ),
+    re_path(
+        fr'^admin/anlaytics/(?P<enterprise_id>{UUID4_REGEX})/skills/stats',
+        enterprise_admin_views.EnterpriseAdminAnalyticsSkillsView.as_view(),
+        name='enterprise-admin-analytics-skills'
+    ),
 ]
 
 urlpatterns += router.urls

enterprise_data/api/v1/views/enterprise_admin.py

@@ -1,6 +1,7 @@
 """
 Views for enterprise admin api v1.
 """
+
 from datetime import datetime, timedelta
 
 from edx_rbac.decorators import permission_required
@@ -9,8 +10,17 @@ from rest_framework.response import Response
 from rest_framework.status import HTTP_200_OK, HTTP_404_NOT_FOUND
 from rest_framework.views import APIView
 
+from django.http import HttpResponse
+
 from enterprise_data.admin_analytics.data_loaders import fetch_max_enrollment_datetime
-from enterprise_data.admin_analytics.utils import fetch_and_cache_engagements_data, fetch_and_cache_enrollments_data
+from enterprise_data.admin_analytics.utils import (
+    ChartType,
+    fetch_and_cache_engagements_data,
+    fetch_and_cache_enrollments_data,
+    fetch_and_cache_skills_data,
+    get_skills_chart_data,
+    get_top_skills_csv_data,
+)
 from enterprise_data.api.v1 import serializers
 from enterprise_data.models import EnterpriseAdminLearnerProgress, EnterpriseAdminSummarizeInsights
 from enterprise_data.utils import date_filter
@@ -20,10 +30,13 @@ class EnterpriseAdminInsightsView(APIView):
     """
     API for getting the enterprise admin insights.
     """
+
     authentication_classes = (JwtAuthentication,)
-    http_method_names = ['get']
+    http_method_names = ["get"]
 
-    @permission_required('can_access_enterprise', fn=lambda request, enterprise_id: enterprise_id)
+    @permission_required(
+        "can_access_enterprise", fn=lambda request, enterprise_id: enterprise_id
+    )
     def get(self, request, enterprise_id):
         """
         HTTP GET endpoint to retrieve the enterprise admin insights
@@ -33,16 +46,24 @@ class EnterpriseAdminInsightsView(APIView):
         learner_engagement = {}
 
         try:
-            learner_progress = EnterpriseAdminLearnerProgress.objects.get(enterprise_customer_uuid=enterprise_id)
-            learner_progress = serializers.EnterpriseAdminLearnerProgressSerializer(learner_progress).data
-            response_data['learner_progress'] = learner_progress
+            learner_progress = EnterpriseAdminLearnerProgress.objects.get(
+                enterprise_customer_uuid=enterprise_id
+            )
+            learner_progress = serializers.EnterpriseAdminLearnerProgressSerializer(
+                learner_progress
+            ).data
+            response_data["learner_progress"] = learner_progress
         except EnterpriseAdminLearnerProgress.DoesNotExist:
             pass
 
         try:
-            learner_engagement = EnterpriseAdminSummarizeInsights.objects.get(enterprise_customer_uuid=enterprise_id)
-            learner_engagement = serializers.EnterpriseAdminSummarizeInsightsSerializer(learner_engagement).data
-            response_data['learner_engagement'] = learner_engagement
+            learner_engagement = EnterpriseAdminSummarizeInsights.objects.get(
+                enterprise_customer_uuid=enterprise_id
+            )
+            learner_engagement = serializers.EnterpriseAdminSummarizeInsightsSerializer(
+                learner_engagement
+            ).data
+            response_data["learner_engagement"] = learner_engagement
         except EnterpriseAdminSummarizeInsights.DoesNotExist:
             pass
 
@@ -57,53 +78,156 @@ class EnterpriseAdminAnalyticsAggregatesView(APIView):
     """
     API for getting the enterprise admin analytics aggregates.
     """
+
     authentication_classes = (JwtAuthentication,)
-    http_method_names = ['get']
+    http_method_names = ["get"]
 
-    @permission_required('can_access_enterprise', fn=lambda request, enterprise_id: enterprise_id)
+    @permission_required(
+        "can_access_enterprise", fn=lambda request, enterprise_id: enterprise_id
+    )
     def get(self, request, enterprise_id):
         """
         HTTP GET endpoint to retrieve the enterprise admin aggregate data.
         """
-        serializer = serializers.AdminAnalyticsAggregatesQueryParamsSerializer(data=request.GET)
+        serializer = serializers.AdminAnalyticsAggregatesQueryParamsSerializer(
+            data=request.GET
+        )
         serializer.is_valid(raise_exception=True)
 
         last_updated_at = fetch_max_enrollment_datetime()
-        cache_expiry = last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
+        cache_expiry = (
+            last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
+        )
 
-        enrollment = fetch_and_cache_enrollments_data(enterprise_id, cache_expiry).copy()
-        engagement = fetch_and_cache_engagements_data(enterprise_id, cache_expiry).copy()
+        enrollment = fetch_and_cache_enrollments_data(
+            enterprise_id, cache_expiry
+        ).copy()
+        engagement = fetch_and_cache_engagements_data(
+            enterprise_id, cache_expiry
+        ).copy()
         # Use start and end date if provided by the client, if client has not provided then use
         # 1. minimum enrollment date from the data as the start_date
         # 2. today's date as the end_date
-        start_date = serializer.data.get('start_date', enrollment.enterprise_enrollment_date.min())
-        end_date = serializer.data.get('end_date', datetime.now())
+        start_date = serializer.data.get(
+            "start_date", enrollment.enterprise_enrollment_date.min()
+        )
+        end_date = serializer.data.get("end_date", datetime.now())
 
         # Date filtering.
         dff = date_filter(
-            start=start_date, end=end_date, data_frame=enrollment.copy(), date_column='enterprise_enrollment_date'
+            start=start_date,
+            end=end_date,
+            data_frame=enrollment.copy(),
+            date_column="enterprise_enrollment_date",
         )
 
         enrolls = len(dff)
         courses = len(dff.course_key.unique())
 
-        dff = date_filter(start=start_date, end=end_date, data_frame=enrollment.copy(), date_column='passed_date')
+        dff = date_filter(
+            start=start_date,
+            end=end_date,
+            data_frame=enrollment.copy(),
+            date_column="passed_date",
+        )
 
         completions = dff.has_passed.sum()
 
         # Date filtering.
-        dff = date_filter(start=start_date, end=end_date, data_frame=engagement.copy(), date_column='activity_date')
+        dff = date_filter(
+            start=start_date,
+            end=end_date,
+            data_frame=engagement.copy(),
+            date_column="activity_date",
+        )
 
         hours = round(dff.learning_time_seconds.sum() / 60 / 60, 1)
         sessions = dff.is_engaged.sum()
 
-        return Response(data={
-            'enrolls': enrolls,
-            'courses': courses,
-            'completions': completions,
-            'hours': hours,
-            'sessions': sessions,
-            'last_updated_at': last_updated_at.date() if last_updated_at else None,
-            'min_enrollment_date': enrollment.enterprise_enrollment_date.min().date(),
-            'max_enrollment_date': enrollment.enterprise_enrollment_date.max().date(),
-        }, status=HTTP_200_OK)
+        return Response(
+            data={
+                "enrolls": enrolls,
+                "courses": courses,
+                "completions": completions,
+                "hours": hours,
+                "sessions": sessions,
+                "last_updated_at": last_updated_at.date() if last_updated_at else None,
+                "min_enrollment_date": enrollment.enterprise_enrollment_date.min().date(),
+                "max_enrollment_date": enrollment.enterprise_enrollment_date.max().date(),
+            },
+            status=HTTP_200_OK,
+        )
+
+
+class EnterpriseAdminAnalyticsSkillsView(APIView):
+    """
+    API for getting the enterprise admin analytics skills data.
+    """
+    authentication_classes = (JwtAuthentication,)
+    http_method_names = ['get']
+
+    @permission_required(
+        'can_access_enterprise', fn=lambda request, enterprise_id: enterprise_id
+    )
+    def get(self, request, enterprise_id):
+        """HTTP GET endpoint to retrieve the enterprise admin skills aggregated data.
+
+        Args:
+            request (HttpRequest): request object
+            enterprise_id (str): UUID of the enterprise customer
+
+        Returns:
+            response(HttpResponse): response object
+        """
+        serializer = serializers.AdminAnalyticsAggregatesQueryParamsSerializer(
+            data=request.GET
+        )
+        serializer.is_valid(raise_exception=True)
+
+        start_date = serializer.data.get("start_date")
+        end_date = serializer.data.get("end_date", datetime.now())
+
+        last_updated_at = fetch_max_enrollment_datetime()
+        cache_expiry = (
+            last_updated_at + timedelta(days=1) if last_updated_at else datetime.now()
+        )
+        skills = fetch_and_cache_skills_data(enterprise_id, cache_expiry).copy()
+
+        if request.GET.get("format") == "csv":
+            csv_data = get_top_skills_csv_data(skills, start_date, end_date)
+            response = HttpResponse(content_type='text/csv')
+            filename = f"Skills by Enrollment and Completion, {start_date} - {end_date}.csv"
+            response['Content-Disposition'] = f'attachment; filename="{filename}"'
+            csv_data.to_csv(path_or_buf=response, index=False)
+            return response
+
+        top_skills = get_skills_chart_data(
+            chart_type=ChartType.BUBBLE,
+            start_date=start_date,
+            end_date=end_date,
+            skills=skills,
+        )
+        top_skills_enrollments = get_skills_chart_data(
+            chart_type=ChartType.TOP_SKILLS_ENROLLMENT,
+            start_date=start_date,
+            end_date=end_date,
+            skills=skills,
+        )
+        top_skills_by_completions = get_skills_chart_data(
+            chart_type=ChartType.TOP_SKILLS_COMPLETION,
+            start_date=start_date,
+            end_date=end_date,
+            skills=skills,
+        )
+
+        response_data = {
+            "top_skills": top_skills.to_dict(orient="records"),
+            "top_skills_by_enrollments": top_skills_enrollments.to_dict(
+                orient="records"
+            ),
+            "top_skills_by_completions": top_skills_by_completions.to_dict(
+                orient="records"
+            ),
+        }
+
+        return Response(data=response_data, status=HTTP_200_OK)

enterprise_data/tests/admin_analytics/test_data_loaders.py

@@ -13,8 +13,13 @@ from enterprise_data.admin_analytics.data_loaders import (
     fetch_engagement_data,
     fetch_enrollment_data,
     fetch_max_enrollment_datetime,
+    fetch_skills_data,
+)
+from enterprise_data.tests.test_utils import (
+    get_dummy_engagements_data,
+    get_dummy_enrollments_data,
+    get_dummy_skills_data,
 )
-from enterprise_data.tests.test_utils import get_dummy_engagements_data, get_dummy_enrollments_data
 
 
 class TestDataLoaders(TestCase):
@@ -84,3 +89,27 @@ class TestDataLoaders(TestCase):
             with pytest.raises(Http404) as error:
                 fetch_enrollment_data(enterprise_uuid)
             error.value.message = f'No enrollment data found for enterprise {enterprise_uuid}'
+
+    def test_fetch_skills_data(self):
+        """
+        Validate the fetch_skills_data function.
+        """
+        with patch('enterprise_data.admin_analytics.data_loaders.run_query') as mock_run_query:
+            enterprise_uuid = str(uuid4())
+            mock_run_query.return_value = [
+                list(item.values()) for item in get_dummy_skills_data(enterprise_uuid)
+            ]
+
+            skills_data = fetch_skills_data(enterprise_uuid)
+            self.assertEqual(skills_data.shape, (10, 15))
+
+    def test_fetch_skills_data_empty_data(self):
+        """
+        Validate the fetch_skills_data function behavior when no data is returned from the query.
+        """
+        with patch('enterprise_data.admin_analytics.data_loaders.run_query') as mock_run_query:
+            mock_run_query.return_value = []
+            enterprise_uuid = str(uuid4())
+            with pytest.raises(Http404) as error:
+                fetch_skills_data(enterprise_uuid)
+            error.value.message = f'No skills data found for enterprise {enterprise_uuid}'

enterprise_data/tests/admin_analytics/test_utils.py

@@ -3,6 +3,7 @@ Test the utility functions in the admin_analytics app.
 """
 from datetime import datetime, timedelta
 
+import pandas
 from mock import patch
 
 from django.test import TestCase
@@ -10,8 +11,13 @@ from django.test import TestCase
 from enterprise_data.admin_analytics.utils import (
     fetch_and_cache_engagements_data,
     fetch_and_cache_enrollments_data,
+    fetch_and_cache_skills_data,
     get_cache_timeout,
+    get_skills_bubble_chart_df,
+    get_top_skills_completion,
+    get_top_skills_enrollment,
 )
+from enterprise_data.utils import date_filter
 
 
 class TestUtils(TestCase):
@@ -100,3 +106,136 @@ class TestUtils(TestCase):
                 self.assertEqual(enrollments, 'cached-engagements')
                 self.assertEqual(mock_tiered_cache.get_cached_response.call_count, 1)
                 self.assertEqual(mock_tiered_cache.set_all_tiers.call_count, 0)
+
+    def test_fetch_and_cache_skills_data(self):
+        """
+        Validate the fetch_and_cache_skills_data function.
+        """
+        with patch('enterprise_data.admin_analytics.utils.fetch_skills_data') as mock_fetch_skills_data:
+            with patch('enterprise_data.admin_analytics.utils.TieredCache') as mock_tiered_cache:
+                # Simulate the scenario where the data is not found in the cache.
+                mock_tiered_cache.get_cached_response.return_value.is_found = False
+                mock_fetch_skills_data.return_value = 'skills'
+                skills = fetch_and_cache_skills_data('enterprise_id', datetime.now() + timedelta(seconds=10))
+                self.assertEqual(skills, 'skills')
+                self.assertEqual(mock_tiered_cache.get_cached_response.call_count, 1)
+                self.assertEqual(mock_tiered_cache.set_all_tiers.call_count, 1)
+
+    def test_fetch_and_cache_skills_data_with_data_cache_found(self):
+        """
+        Validate the fetch_and_cache_skills_data function.
+        """
+        with patch('enterprise_data.admin_analytics.utils.fetch_skills_data') as mock_fetch_skills_data:
+            with patch('enterprise_data.admin_analytics.utils.TieredCache') as mock_tiered_cache:
+                # Simulate the scenario where the data is found in the cache.
+                mock_tiered_cache.get_cached_response.return_value.is_found = True
+                mock_tiered_cache.get_cached_response.return_value.value = 'cached-skills'
+                mock_fetch_skills_data.return_value = 'skills'
+
+                skills = fetch_and_cache_skills_data('enterprise_id', datetime.now() + timedelta(seconds=10))
+                self.assertEqual(skills, 'cached-skills')
+                self.assertEqual(mock_tiered_cache.get_cached_response.call_count, 1)
+                self.assertEqual(mock_tiered_cache.set_all_tiers.call_count, 0)
+
+    def test_get_skills_bubble_chart_df(self):
+        """
+        Validate the get_skills_bubble_chart_df function.
+        """
+        # Mock skills data
+        skills = pandas.DataFrame({
+            'skill_name': ['Skill A', 'Skill B', 'Skill C'],
+            'skill_type': ['Type 1', 'Type 2', 'Type 1'],
+            'enrolls': [100, 200, 150],
+            'completions': [50, 100, 75],
+            'date': [datetime.now(), datetime.now(), datetime.now()],
+        })
+
+        # Define the expected result
+        expected_result = pandas.DataFrame({
+            'skill_name': ['Skill B', 'Skill C', 'Skill A'],
+            'skill_type': ['Type 2', 'Type 1', 'Type 1'],
+            'enrolls': [200, 150, 100],
+            'completions': [100, 75, 50]
+        })
+        # Reset the index for the expected result
+        expected_result = expected_result.reset_index(drop=True)
+
+        start_date = datetime.now() - timedelta(days=10)
+        end_date = datetime.now()
+        filtered_skills = date_filter(start_date, end_date, skills, 'date')
+        # Call the function
+        result = get_skills_bubble_chart_df(filtered_skills)
+
+        # Reset the index for the result
+        result = result.reset_index(drop=True)
+
+        # Assert the result
+        pandas.testing.assert_frame_equal(result, expected_result)
+
+    def test_get_top_skills_enrollment(self):
+        """
+        Validate the get_top_skills_enrollment function.
+        """
+        # Mock skills data
+        skills = pandas.DataFrame({
+            'primary_subject_name': ['engineering', 'communication', 'engineering', 'other'],
+            'skill_name': ['Skill A', 'Skill B', 'Skill A', 'Skill D'],
+            'enrolls': [100, 200, 150, 300],
+            'completions': [50, 100, 75, 150],
+            'date': [datetime.now(), datetime.now(), datetime.now(), datetime.now()],
+        })
+
+        # Define the expected result
+        expected_result = pandas.DataFrame({
+            'skill_name': ['Skill B', 'Skill A', 'Skill D'],
+            'primary_subject_name': ['communication', 'engineering', 'other'],
+            'count': [200, 250, 300]
+        })
+        # Reset the index for the expected result
+        expected_result = expected_result.reset_index(drop=True)
+        start_date = datetime.now() - timedelta(days=10)
+        end_date = datetime.now()
+        filtered_skills = date_filter(start_date, end_date, skills, 'date')
+
+        # Call the function
+        result = get_top_skills_enrollment(filtered_skills)
+
+        # Reset the index for the result
+        result = result.reset_index(drop=True)
+
+        # Assert the result
+        pandas.testing.assert_frame_equal(result, expected_result)
+
+    def test_get_top_skills_completion(self):
+        """
+        Validate the get_top_skills_completion function.
+        """
+        # Mock skills data
+        skills = pandas.DataFrame({
+            'skill_name': ['Skill A', 'Skill B', 'Skill C', 'Skill D'],
+            'primary_subject_name': ['communication', 'engineering', 'communication', 'other'],
+            'enrolls': [100, 200, 150, 300],
+            'completions': [50, 100, 75, 150],
+            'date': [datetime.now(), datetime.now(), datetime.now(), datetime.now()]
+        })
+
+        # Define the expected result
+        expected_result = pandas.DataFrame({
+            'skill_name': ['Skill A', 'Skill C', 'Skill B', 'Skill D'],
+            'primary_subject_name': ['communication', 'communication', 'engineering', 'other'],
+            'count': [50, 75, 100, 150]
+        })
+        # Reset the index for the expected result
+        expected_result = expected_result.reset_index(drop=True)
+        start_date = datetime.now() - timedelta(days=10)
+        end_date = datetime.now()
+        filtered_skills = date_filter(start_date, end_date, skills, 'date')
+
+        # Call the function
+        result = get_top_skills_completion(filtered_skills)
+
+        # Reset the index for the result
+        result = result.reset_index(drop=True)
+
+        # Assert the result
+        pandas.testing.assert_frame_equal(result, expected_result)

enterprise_data/tests/api/v1/views/test_enterprise_admin.py

@@ -2,6 +2,7 @@
 Test cases for enterprise_admin views
 """
 from unittest import mock
+from uuid import uuid4
 
 import ddt
 from mock import patch
@@ -16,6 +17,7 @@ from enterprise_data.tests.test_utils import (
     get_dummy_engagements_data,
     get_dummy_enrollments_data,
     get_dummy_enterprise_api_data,
+    get_dummy_skills_data,
 )
 from enterprise_data_roles.constants import ENTERPRISE_DATA_ADMIN_ROLE
 from enterprise_data_roles.models import EnterpriseDataFeatureRole, EnterpriseDataRoleAssignment
@@ -80,3 +82,50 @@ class TestEnterpriseAdminAnalyticsAggregatesView(JWTTestMixin, APITransactionTes
             assert 'last_updated_at' in response.json()
             assert 'min_enrollment_date' in response.json()
             assert 'max_enrollment_date' in response.json()
+
+
+@ddt.ddt
+@mark.django_db
+class TestEnterpriseAdminAnalyticsSkillsView(JWTTestMixin, APITransactionTestCase):
+    """
+    Tests for EnterpriseAdminAnalyticsSkillsView.
+    """
+
+    def setUp(self):
+        """
+        Setup method.
+        """
+        super().setUp()
+        self.user = UserFactory()
+        self.enterprise_id = uuid4()
+        self.set_jwt_cookie(context=f'{self.enterprise_id}')
+
+    def _mock_run_query(self, query):
+        """
+        mock implementation of run_query.
+        """
+        if 'skills_daily_rollup_admin_dash' in query:
+            return [
+                list(item.values()) for item in get_dummy_skills_data(self.enterprise_id)
+            ]
+        else:
+            return [
+                list(item.values()) for item in get_dummy_skills_data(self.enterprise_id)
+            ]
+
+    def test_get_admin_analytics_skills(self):
+        """
+        Test to get admin analytics skills.
+        """
+        params = {'start_date': '2021-01-01', 'end_date': '2025-12-31'}
+        url = reverse('v1:enterprise-admin-analytics-skills', kwargs={'enterprise_id': self.enterprise_id})
+        with patch('enterprise_data.admin_analytics.data_loaders.run_query', side_effect=self._mock_run_query):
+            response = self.client.get(url, params)
+            assert response.status_code == status.HTTP_200_OK
+            data = response.json()
+            assert 'top_skills' in data
+            assert 'top_skills_by_enrollments' in data
+            assert 'top_skills_by_completions' in data
+            assert len(data['top_skills']) == 10
+            assert len(data['top_skills_by_enrollments']) == 10
+            assert len(data['top_skills_by_completions']) == 10

enterprise_data/tests/test_utils.py

@@ -418,3 +418,31 @@ def get_dummy_enrollments_data(enterprise_uuid: str, count=10):
             'has_passed': FAKER.boolean(),
         } for _ in range(count)
     ]
+
+
+def get_dummy_skills_data(enterprise_uuid: str, count=10):
+    """
+    Utility method to get dummy skills data.
+    """
+    return [
+        {
+            'course_number': FAKER.random_int(min=1),
+            'skill_type': 'skill_type',
+            'skill_name': ' '.join(FAKER.words(nb=2)).title(),
+            'skill_url': FAKER.url(),
+            'confidence': FAKER.random_int(min=1),
+            'skill_rank': FAKER.random_int(min=1),
+            'course_title': ' '.join(FAKER.words(nb=5)).title(),
+            'course_key': FAKER.slug(),
+            'level_type': 'level_type',
+            'primary_subject_name': ' '.join(FAKER.words(nb=2)).title(),
+            'date': FAKER.date_time_between(
+                start_date='-2M',
+                end_date='+2M',
+            ),
+            'enterprise_customer_uuid': enterprise_uuid,
+            'enterprise_customer_name': ' '.join(FAKER.words(nb=2)).title(),
+            'enrolls': FAKER.random_int(min=1),
+            'completions': FAKER.random_int(min=1),
+        } for _ in range(count)
+    ]

enterprise_data/utils.py

@@ -82,3 +82,19 @@ def date_filter(start, end, data_frame, date_column):
         (pandas.DataFrame): The filtered DataFrame.
     """
     return data_frame[(start <= data_frame[date_column]) & (data_frame[date_column] <= end)]
+
+
+def primary_subject_truncate(x):
+    """
+    Truncate primary subject to a few categories.
+    """
+    if x in [
+        "business-management",
+        "computer-science",
+        "data-analysis-statistics",
+        "engineering",
+        "communication",
+    ]:
+        return x
+    else:
+        return "other"