edx-enterprise-data 9.0.0__py3-none-any.whl → 9.1.0__py3-none-any.whl

enterprise_data/tests/admin_analytics/test_enterprise_completions.py

@@ -1,4 +1,6 @@
-"""Unitest for EnterpriseAdminCompletionsStatsView."""
+"""
+Tests for enterprise completions analytics.
+"""
 from datetime import datetime
 
 import ddt
@@ -7,12 +9,8 @@ from rest_framework import status
 from rest_framework.reverse import reverse
 from rest_framework.test import APITransactionTestCase
 
-from enterprise_data.admin_analytics.utils import ChartType
-from enterprise_data.tests.admin_analytics.mock_analytics_data import (
-    COMPLETIONS_STATS_CSVS,
-    ENROLLMENTS,
-    enrollments_dataframe,
-)
+from enterprise_data.admin_analytics.constants import ResponseType
+from enterprise_data.tests.admin_analytics.mock_analytics_data import ENROLLMENTS
 from enterprise_data.tests.mixins import JWTTestMixin
 from enterprise_data.tests.test_utils import UserFactory
 from enterprise_data_roles.constants import ENTERPRISE_DATA_ADMIN_ROLE
@@ -20,8 +18,10 @@ from enterprise_data_roles.models import EnterpriseDataFeatureRole, EnterpriseDa
 
 
 @ddt.ddt
-class TestCompletionstStatsAPI(JWTTestMixin, APITransactionTestCase):
-    """Tests for EnterrpiseAdminCompletionsStatsView."""
+class TestCompletionsStatsAPI(JWTTestMixin, APITransactionTestCase):
+    """
+    Tests for validating enterprise completions stats endpoint.
+    """
 
     def setUp(self):
         """
@@ -37,99 +37,63 @@ class TestCompletionstStatsAPI(JWTTestMixin, APITransactionTestCase):
         )
         self.client.force_authenticate(user=self.user)
 
-        self.enterprise_id = "ee5e6b3a-069a-4947-bb8d-d2dbc323396c"
+        self.enterprise_id = 'ee5e6b3a-069a-4947-bb8d-d2dbc323396c'
         self.set_jwt_cookie()
 
         self.url = reverse(
-            "v1:enterprise-admin-analytics-completions-stats",
-            kwargs={"enterprise_id": self.enterprise_id},
+            'v1:enterprise-admin-analytics-completions-stats',
+            kwargs={'enterprise_uuid': self.enterprise_id},
         )
 
-        fetch_max_enrollment_datetime_patcher = patch(
-            'enterprise_data.api.v1.views.enterprise_completions.fetch_max_enrollment_datetime',
-            return_value=datetime.now()
+        get_enrollment_date_range_patcher = patch(
+            'enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_enrollment_date_range',
+            return_value=(datetime.now(), datetime.now())
         )
 
-        fetch_max_enrollment_datetime_patcher.start()
-        self.addCleanup(fetch_max_enrollment_datetime_patcher.stop)
+        get_enrollment_date_range_patcher.start()
+        self.addCleanup(get_enrollment_date_range_patcher.stop)
 
     @patch(
-        "enterprise_data.api.v1.views.enterprise_completions.fetch_and_cache_enrollments_data"
+        'enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.'
+        'get_top_subjects_by_completions'
     )
-    def test_get(self, mock_fetch_and_cache_enrollments_data):
-        """
-        Test the GET method for the EnterrpiseAdminCompletionsStatsView works.
-        """
-        mock_fetch_and_cache_enrollments_data.return_value = enrollments_dataframe()
-
-        params = {
-            "start_date": "2020-01-01",
-            "end_date": "2025-08-09",
-            "calculation": "Running Total",
-            "granularity": "Daily",
-        }
-        response = self.client.get(self.url, params)
-        assert response.status_code == status.HTTP_200_OK
-        data = response.json()
-        assert data == {
-            "completions_over_time": [
-                {
-                    "passed_date": "2021-08-25T00:00:00",
-                    "enroll_type": "certificate",
-                    "count": 1,
-                },
-                {
-                    "passed_date": "2021-09-01T00:00:00",
-                    "enroll_type": "certificate",
-                    "count": 2,
-                },
-            ],
-            "top_courses_by_completions": [
-                {
-                    "course_key": "hEmW+tvk03",
-                    "course_title": "Re-engineered tangible approach",
-                    "enroll_type": "certificate",
-                    "count": 2,
-                }
-            ],
-            "top_subjects_by_completions": [
-                {
-                    "course_subject": "business-management",
-                    "enroll_type": "certificate",
-                    "count": 2,
-                }
-            ],
-        }
-
-    @patch("enterprise_data.api.v1.views.enterprise_completions.fetch_and_cache_enrollments_data")
-    @ddt.data(
-        ChartType.COMPLETIONS_OVER_TIME.value,
-        ChartType.TOP_COURSES_BY_COMPLETIONS.value,
-        ChartType.TOP_SUBJECTS_BY_COMPLETIONS.value,
+    @patch(
+        'enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_top_courses_by_completions'
+    )
+    @patch(
+        'enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.'
+        'get_completions_time_series_data'
     )
-    def test_get_csv(self, chart_type, mock_fetch_and_cache_enrollments_data):
+    def test_get(
+            self,
+            mock_get_completions_time_series_data,
+            mock_get_top_courses_by_completions,
+            mock_get_top_subjects_by_completions
+    ):
         """
-        Test that EnterrpiseAdminCompletionsStatsView return correct CSV data.
+        Test the GET method to fetch charts data for enterprise completion works correctly.
         """
-        mock_fetch_and_cache_enrollments_data.return_value = enrollments_dataframe()
+        mock_get_completions_time_series_data.return_value = []
+        mock_get_top_courses_by_completions.return_value = []
+        mock_get_top_subjects_by_completions.return_value = []
+
         params = {
             'start_date': '2020-01-01',
             'end_date': '2025-08-09',
-            'calculation': 'Running Total',
-            'granularity': 'Daily',
-            'response_type': 'csv',
-            'chart_type': chart_type,
         }
         response = self.client.get(self.url, params)
         assert response.status_code == status.HTTP_200_OK
-        assert response["Content-Type"] == "text/csv"
-        # verify the response content
-        assert response.content == COMPLETIONS_STATS_CSVS[chart_type]
+        data = response.json()
+        assert 'completions_over_time' in data
+        assert 'top_courses_by_completions' in data
+        assert 'top_subjects_by_completions' in data
 
 
 @ddt.ddt
-class TestCompletionstAPI(JWTTestMixin, APITransactionTestCase):
-    """Tests for EnterrpiseAdminCompletionsView."""
+class TestCompletionsAPI(JWTTestMixin, APITransactionTestCase):
+    """
+    Tests for validating list endpoint of enterprise completions.
+    """
 
     def setUp(self):
         """
@@ -145,58 +109,79 @@ class TestCompletionstAPI(JWTTestMixin, APITransactionTestCase):
         )
         self.client.force_authenticate(user=self.user)
 
-        self.enterprise_id = "ee5e6b3a-069a-4947-bb8d-d2dbc323396c"
+        self.enterprise_id = 'ee5e6b3a-069a-4947-bb8d-d2dbc323396c'
         self.set_jwt_cookie()
 
         self.url = reverse(
-            "v1:enterprise-admin-analytics-completions",
-            kwargs={"enterprise_id": self.enterprise_id},
+            'v1:enterprise-admin-analytics-completions',
+            kwargs={'enterprise_uuid': self.enterprise_id},
         )
 
-        fetch_max_enrollment_datetime_patcher = patch(
-            'enterprise_data.api.v1.views.enterprise_completions.fetch_max_enrollment_datetime',
-            return_value=datetime.now()
+        get_enrollment_date_range_patcher = patch(
+            'enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_enrollment_date_range',
+            return_value=(datetime.now(), datetime.now())
         )
 
-        fetch_max_enrollment_datetime_patcher.start()
-        self.addCleanup(fetch_max_enrollment_datetime_patcher.stop)
-
-    def verify_enrollment_data(self, results, results_count):
-        """Verify the received enrollment data."""
-        attrs = [
-            "email",
-            "course_title",
-            "course_subject",
-            "passed_date",
-        ]
-
-        assert len(results) == results_count
-
-        filtered_data = []
-        for enrollment in ENROLLMENTS:
-            for result in results:
-                if enrollment["email"] == result["email"]:
-                    filtered_data.append({attr: enrollment[attr] for attr in attrs})
-                    break
-        received_data = sorted(results, key=lambda x: x["email"])
-        expected_data = sorted(filtered_data, key=lambda x: x["email"])
-        assert received_data == expected_data
+        get_enrollment_date_range_patcher.start()
+        self.addCleanup(get_enrollment_date_range_patcher.stop)
 
-    @patch(
-        "enterprise_data.api.v1.views.enterprise_completions.fetch_and_cache_enrollments_data"
-    )
-    def test_get(self, mock_fetch_and_cache_enrollments_data):
+    @patch('enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_completion_count')
+    @patch('enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_all_completions')
+    def test_get(self, mock_get_all_completions, mock_get_completion_count):
         """
-        Test the GET method for the EnterrpiseAdminCompletionsView works.
+        Test the GET method for fetching enterprise completions works correctly.
         """
-        mock_fetch_and_cache_enrollments_data.return_value = enrollments_dataframe()
+        mock_get_all_completions.return_value = ENROLLMENTS
+        mock_get_completion_count.return_value = len(ENROLLMENTS)
 
-        response = self.client.get(self.url, {"page": 1, "page_size": 1})
+        response = self.client.get(self.url + '?page=1&page_size=2')
         assert response.status_code == status.HTTP_200_OK
         data = response.json()
-        assert data["next"] == f"http://testserver{self.url}?page=2&page_size=1"
+        assert data["next"] == f"http://testserver{self.url}?page=2&page_size=2"
         assert data["previous"] is None
         assert data["current_page"] == 1
-        assert data["num_pages"] == 2
-        assert data["count"] == 2
-        self.verify_enrollment_data(data["results"], 1)
+        assert data["num_pages"] == 3
+        assert data["count"] == 5
+
+    @patch('enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_completion_count')
+    @patch('enterprise_data.api.v1.views.analytics_enrollments.FactEnrollmentAdminDashTable.get_all_completions')
+    def test_get_csv(self, mock_get_all_completions, mock_get_completion_count):
+        """
+        Test the GET method for the AdvanceAnalyticsIndividualEnrollmentsView return correct CSV data.
+        """
+        mock_get_all_completions.return_value = ENROLLMENTS
+        mock_get_completion_count.return_value = len(ENROLLMENTS)
+        response = self.client.get(self.url, {"response_type": ResponseType.CSV.value})
+        assert response.status_code == status.HTTP_200_OK
+
+        # verify the response headers
+        assert response["Content-Type"] == "text/csv"
+
+        # verify the response content
+        content = b"".join(response.streaming_content).decode().splitlines()
+        assert len(content) == 6
+
+        # Verify CSV header.
+        assert 'email,course_title,course_subject,enroll_type,passed_date' == content[0]
+
+        # verify the content
+        assert (
+            'rebeccanelson@example.com,Re-engineered tangible approach,business-management,certificate,2021-08-25'
+            in content
+        )
+        assert (
+            'taylorjames@example.com,Re-engineered tangible approach,business-management,certificate,2021-09-01'
+            in content
+        )
+        assert (
+            'ssmith@example.com,Secured static capability,medicine,certificate,'
+            in content
+        )
+        assert (
+            'kathleenmartin@example.com,Horizontal solution-oriented hub,social-sciences,certificate,'
+            in content
+        )
+        assert (
+            'amber79@example.com,Streamlined zero-defect attitude,communication,certificate,'
+            in content
+        )

enterprise_data/admin_analytics/completions_utils.py

@@ -1,261 +0,0 @@
-"""This module contains utility functions for completions analytics."""
-from enterprise_data.utils import date_filter
-
-
-def date_aggregation(level, group, date, df, type_="count"):
-    """Perform date aggregation on a DataFrame.
-
-    This function aggregates data based on the specified level of aggregation (e.g., daily, weekly, monthly, quarterly)
-    and returns the aggregated data.
-
-    Args:
-        level (str): The level of aggregation. Possible values are "Daily", "Weekly", "Monthly", and "Quarterly".
-        group (list): A list of column names to group the data by.
-        date (str): The name of the date column in the DataFrame.
-        df (pandas.DataFrame): The DataFrame containing the data to be aggregated.
-        type_ (str, optional): The type of aggregation to perform. Possible values
-            are "count" and "sum". Defaults to "count".
-
-    Returns:
-        pandas.DataFrame: The aggregated data.
-
-    """
-    if type_ == "count":
-        if level == "Daily":
-            df = df.groupby(group).size().reset_index()
-            group.append("count")
-            df.columns = group
-        elif level == "Weekly":
-            df[date] = df[date].dt.to_period("W").dt.start_time
-            df = df.groupby(group).size().reset_index()
-            group.append("count")
-            df.columns = group
-        elif level == "Monthly":
-            df[date] = df[date].dt.to_period("M").dt.start_time
-            df = df.groupby(group).size().reset_index()
-            group.append("count")
-            df.columns = group
-        elif level == "Quarterly":
-            df[date] = df[date].dt.to_period("Q").dt.start_time
-            df = df.groupby(group).size().reset_index()
-            group.append("count")
-            df.columns = group
-    elif type_ == "sum":
-        if level == "Daily":
-            df = df.groupby(group).sum().reset_index()
-            group.append("sum")
-            df.columns = group
-        elif level == "Weekly":
-            df[date] = df[date].dt.to_period("W").dt.start_time
-            df = df.groupby(group).sum().reset_index()
-            group.append("sum")
-            df.columns = group
-        elif level == "Monthly":
-            df[date] = df[date].dt.to_period("M").dt.start_time
-            df = df.groupby(group).sum().reset_index()
-            group.append("sum")
-            df.columns = group
-        elif level == "Quarterly":
-            df[date] = df[date].dt.to_period("Q").dt.start_time
-            df = df.groupby(group).sum().reset_index()
-            group.append("sum")
-            df.columns = group
-
-    return df
-
-
-def calculation(calc, df, type_="count"):
-    """Perform a calculation on the given DataFrame based on the specified calculation type.
-
-    Args:
-        calc (str): The calculation type. Possible values are "Total", "Running Total",
-                    "Moving Average (3 Period)", and "Moving Average (7 Period)".
-        df (pandas.DataFrame): The filtered enrollments data.
-        type_ (str, optional): The type of calculation to perform. Default is "count".
-
-    Returns:
-        pandas.DataFrame: The aggregated data after performing the calculation.
-    """
-    if type_ == "count":
-        if calc == "Total":
-            pass
-        elif calc == "Running Total":
-            df["count"] = df.groupby("enroll_type")["count"].cumsum()
-        elif calc == "Moving Average (3 Period)":
-            df["count"] = (
-                df.groupby("enroll_type")["count"]
-                .rolling(3)
-                .mean()
-                .droplevel(level=[0])
-            )
-        elif calc == "Moving Average (7 Period)":
-            df["count"] = (
-                df.groupby("enroll_type")["count"]
-                .rolling(7)
-                .mean()
-                .droplevel(level=[0])
-            )
-    elif type_ == "sum":
-        if calc == "Total":
-            pass
-        elif calc == "Running Total":
-            df["sum"] = df.groupby("enroll_type")["sum"].cumsum()
-        elif calc == "Moving Average (3 Period)":
-            df["sum"] = (
-                df.groupby("enroll_type")["sum"].rolling(3).mean().droplevel(level=[0])
-            )
-        elif calc == "Moving Average (7 Period)":
-            df["sum"] = (
-                df.groupby("enroll_type")["sum"].rolling(7).mean().droplevel(level=[0])
-            )
-
-    return df
-
-
-def get_completions_over_time(start_date, end_date, dff, date_agg, calc):
-    """Get agreggated data for completions over time graph.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        dff (pandas.DataFrame): enrollments data
-        date_agg (str): It denotes the granularity of the aggregated date which can be Daily, Weekly, Monthly, Quarterly
-        calc (str): Calculations denoiated the period for the running averages. It can be Total, Running Total, Moving
-            Average (3 Period), Moving Average (7 Period)
-    """
-
-    dff = dff[dff["has_passed"] == 1]
-
-    # Date filtering.
-    dff = date_filter(start=start_date, end=end_date, data_frame=dff, date_column="passed_date")
-
-    # Date aggregation.
-    dff = date_aggregation(
-        level=date_agg, group=["passed_date", "enroll_type"], date="passed_date", df=dff
-    )
-
-    # Calculating metric.
-    dff = calculation(calc=calc, df=dff)
-
-    return dff
-
-
-def get_top_courses_by_completions(start_date, end_date, dff):
-    """Get top 10 courses by completions.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        dff (pandas.DataFrame): Enrollments data
-    """
-
-    dff = dff[dff["has_passed"] == 1]
-
-    # Date filtering.
-    dff = date_filter(start=start_date, end=end_date, data_frame=dff, date_column="passed_date")
-
-    courses = list(
-        dff.groupby(["course_key"]).size().sort_values(ascending=False)[:10].index
-    )
-
-    dff = (
-        dff[dff.course_key.isin(courses)]
-        .groupby(["course_key", "course_title", "enroll_type"])
-        .size()
-        .reset_index()
-    )
-    dff.columns = ["course_key", "course_title", "enroll_type", "count"]
-
-    return dff
-
-
-def get_top_subjects_by_completions(start_date, end_date, dff):
-    """Get top 10 subjects by completions.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        dff (pandas.DataFrame): Enrollments data
-    """
-
-    dff = dff[dff["has_passed"] == 1]
-
-    # Date filtering.
-    dff = date_filter(start=start_date, end=end_date, data_frame=dff, date_column="passed_date")
-
-    subjects = list(
-        dff.groupby(["course_subject"]).size().sort_values(ascending=False)[:10].index
-    )
-
-    dff = (
-        dff[dff.course_subject.isin(subjects)]
-        .groupby(["course_subject", "enroll_type"])
-        .size()
-        .reset_index()
-    )
-    dff.columns = ["course_subject", "enroll_type", "count"]
-
-    return dff
-
-
-def get_csv_data_for_completions_over_time(
-    start_date, end_date, enrollments, date_agg, calc
-):
-    """Get csv data for completions over time graph.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        enrollments (pandas.DataFrame): Filtered enrollments data
-        date_agg (str): it denotes the granularity of the aggregated date which can be Daily, Weekly, Monthly, Quarterly
-        calc (str): calculations denoiated the period for the running averages. It can be Total, Running Total, Moving
-            Average (3 Period), Moving Average (7 Period)
-
-    Returns:
-        dict: csv data
-    """
-
-    dff = get_completions_over_time(start_date, end_date, enrollments, date_agg, calc)
-    dff = dff.pivot(index="passed_date", columns="enroll_type", values="count")
-    filename = (
-        f"Completions Timeseries, {start_date} - {end_date} ({date_agg} {calc}).csv"
-    )
-    return {"filename": filename, "data": dff}
-
-
-def get_csv_data_for_top_courses_by_completions(start_date, end_date, enrollments):
-    """Get csv data for top 10 courses by completions.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        enrollments (pandas.DataFrame): Filtered enrollments data
-
-    Returns:
-        dict: csv data
-    """
-
-    dff = get_top_courses_by_completions(start_date, end_date, enrollments)
-    dff = dff.pivot(
-        index=["course_key", "course_title"], columns="enroll_type", values="count"
-    )
-    filename = f"Top 10 Courses by Completions, {start_date} - {end_date}.csv"
-    return {"filename": filename, "data": dff}
-
-
-def get_csv_data_for_top_subjects_by_completions(start_date, end_date, enrollments):
-    """Get csv data for top 10 subjects by completions.
-
-    Args:
-        start_date (datetime): The start date for the date filter.
-        end_date (datetime): The end date for the date filter.
-        enrollments (pandas.DataFrame): Filtered enrollments data
-
-    Returns:
-        dict: csv data
-    """
-
-    dff = get_top_subjects_by_completions(start_date, end_date, enrollments)
-    dff = dff.pivot(index="course_subject", columns="enroll_type", values="count")
-    filename = f"Top 10 Subjects by Completions, {start_date} - {end_date}.csv"
-    return {"filename": filename, "data": dff}