enhance(apps/analytics): add computation logic for activity progress

apps/analytics/src/modules/__init__.py

@@ -4,3 +4,4 @@
 from .aggregated_course_analytics import *
 from .participant_performance import *
 from .instance_activity_performance import *
+from .activity_progress import *

apps/analytics/src/modules/activity_progress/__init__.py

@@ -0,0 +1,4 @@
+from .get_course_progress_activities import get_course_progress_activities
+from .compute_progress_counts import compute_progress_counts
+from .save_practice_quiz_progress import save_practice_quiz_progress
+from .save_microlearning_progress import save_microlearning_progress

apps/analytics/src/modules/activity_progress/compute_progress_counts.py

@@ -0,0 +1,41 @@
+import pandas as pd
+
+
+def compute_progress_counts(activity):
+    started_count = 0
+    completed_count = 0
+    repeated_count = 0
+
+    if len(activity["responses"]) != 0:
+        # count number of elements in activity stacks
+        num_elements = 0
+        for stack in activity["stacks"]:
+            num_elements += len(stack["elements"])
+
+        # group the activity responses by participant and count them
+        df_responses = pd.DataFrame(activity["responses"])
+        df_statistics = (
+            df_responses[["id", "trialsCount", "participantId"]]
+            .groupby("participantId")
+            .agg({"id": "count", "trialsCount": "min"})
+            .rename(columns={"id": "count", "trialsCount": "min_trials"})
+        )
+
+        # compute number of participants that have started the activity
+        started_count = len(df_statistics[df_statistics["count"] <= num_elements])
+
+        # compute number of participants that have completed the activity
+        completed_count = len(df_statistics[df_statistics["count"] == num_elements])
+
+        # count the number of participants that have repeated the activity (completed and min_trials >= 2)
+        repeated_count = len(
+            df_statistics[
+                (df_statistics["count"] == num_elements)
+                & (df_statistics["min_trials"] >= 2)
+            ]
+        )
+
+    else:
+        print("No responses found for activity", activity["id"])
+
+    return started_count, completed_count, repeated_count

apps/analytics/src/modules/activity_progress/get_course_progress_activities.py

@@ -0,0 +1,14 @@
+def get_course_progress_activities(db, course_id):
+    pqs = db.practicequiz.find_many(
+        where={"courseId": course_id},
+        include={"stacks": {"include": {"elements": True}}, "responses": True},
+    )
+    pqs = list(map(lambda x: x.dict(), pqs))
+
+    mls = db.microlearning.find_many(
+        where={"courseId": course_id},
+        include={"stacks": {"include": {"elements": True}}, "responses": True},
+    )
+    mls = list(map(lambda x: x.dict(), mls))
+
+    return pqs, mls

apps/analytics/src/modules/activity_progress/save_microlearning_progress.py

@@ -0,0 +1,21 @@
+def save_microlearning_progress(
+    db,
+    course_participants,
+    started_count,
+    completed_count,
+    course_id,
+    ml_id,
+):
+    values = {
+        "totalCourseParticipants": course_participants,
+        "startedCount": started_count,
+        "completedCount": completed_count,
+    }
+    creation_values = values.copy()
+    creation_values["course"] = {"connect": {"id": course_id}}
+    creation_values["microLearning"] = {"connect": {"id": ml_id}}
+
+    db.activityprogress.upsert(
+        where={"microLearningId": ml_id},
+        data={"create": creation_values, "update": values},
+    )

apps/analytics/src/modules/activity_progress/save_practice_quiz_progress.py

@@ -0,0 +1,23 @@
+def save_practice_quiz_progress(
+    db,
+    course_participants,
+    started_count,
+    completed_count,
+    repeated_count,
+    course_id,
+    quiz_id,
+):
+    values = {
+        "totalCourseParticipants": course_participants,
+        "startedCount": started_count,
+        "completedCount": completed_count,
+        "repeatedCount": repeated_count,
+    }
+    creation_values = values.copy()
+    creation_values["course"] = {"connect": {"id": course_id}}
+    creation_values["practiceQuiz"] = {"connect": {"id": quiz_id}}
+
+    db.activityprogress.upsert(
+        where={"practiceQuizId": quiz_id},
+        data={"create": creation_values, "update": values},
+    )

apps/analytics/src/notebooks/activity_progress.ipynb

@@ -0,0 +1,147 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Preparation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "from datetime import datetime\n",
+    "from prisma import Prisma\n",
+    "import pandas as pd\n",
+    "import sys\n",
+    "\n",
+    "# set the python path correctly for module imports to work\n",
+    "sys.path.append(\"../../\")\n",
+    "\n",
+    "from src.modules.participant_course_analytics.get_running_past_courses import (\n",
+    "    get_running_past_courses,\n",
+    ")\n",
+    "from src.modules.activity_progress.get_course_progress_activities import (\n",
+    "    get_course_progress_activities,\n",
+    ")\n",
+    "from src.modules.activity_progress.compute_progress_counts import (\n",
+    "    compute_progress_counts,\n",
+    ")\n",
+    "from src.modules.activity_progress.save_practice_quiz_progress import (\n",
+    "    save_practice_quiz_progress,\n",
+    ")\n",
+    "from src.modules.activity_progress.save_microlearning_progress import (\n",
+    "    save_microlearning_progress,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = Prisma()\n",
+    "\n",
+    "# set the environment variable DATABASE_URL to the connection string of your database\n",
+    "os.environ[\"DATABASE_URL\"] = \"postgresql://klicker:klicker@localhost:5432/klicker-prod\"\n",
+    "\n",
+    "db.connect()\n",
+    "\n",
+    "# Script settings\n",
+    "verbose = False"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Compute Activity Progress"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Fetch all courses from the database\n",
+    "df_courses = get_running_past_courses(db)\n",
+    "\n",
+    "# Iterate over the course and fetch all question responses linked to it\n",
+    "for idx, course in df_courses.iterrows():\n",
+    "    course_id = course[\"id\"]\n",
+    "    print(f\"Processing course\", idx, \"of\", len(df_courses), \"with id\", course_id)\n",
+    "\n",
+    "    # extract number of participants\n",
+    "    course_participants = len(course[\"participations\"])\n",
+    "\n",
+    "    # fetch all practice quizzes and microlearnings linked to the course\n",
+    "    pqs, mls = get_course_progress_activities(db, course_id)\n",
+    "\n",
+    "    for quiz in pqs:\n",
+    "        started_count, completed_count, repeated_count = compute_progress_counts(quiz)\n",
+    "\n",
+    "        # store results in database table\n",
+    "        save_practice_quiz_progress(\n",
+    "            db,\n",
+    "            course_participants,\n",
+    "            started_count,\n",
+    "            completed_count,\n",
+    "            repeated_count,\n",
+    "            course_id,\n",
+    "            quiz[\"id\"],\n",
+    "        )\n",
+    "\n",
+    "    for ml in mls:\n",
+    "        started_count, completed_count, repeated_count = compute_progress_counts(ml)\n",
+    "\n",
+    "        # store results in database table\n",
+    "        save_microlearning_progress(\n",
+    "            db,\n",
+    "            course_participants,\n",
+    "            started_count,\n",
+    "            completed_count,\n",
+    "            course_id,\n",
+    "            ml[\"id\"],\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Disconnect from the database\n",
+    "db.disconnect()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "analytics-fkWWeYLw-py3.12",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

apps/analytics/src/notebooks/instance_activity_performance.ipynb

@@ -26,11 +26,21 @@
     "from src.modules.participant_course_analytics.get_running_past_courses import (\n",
     "    get_running_past_courses,\n",
     ")\n",
-    "from src.modules.instance_activity_performance.get_course_activities import get_course_activities\n",
-    "from src.modules.instance_activity_performance.compute_instance_performance import compute_instance_performance\n",
-    "from src.modules.instance_activity_performance.agg_activity_performance import agg_activity_performance\n",
-    "from src.modules.instance_activity_performance.save_instance_performances import save_instance_performances\n",
-    "from src.modules.instance_activity_performance.save_activity_performance import save_activity_performance"
+    "from src.modules.instance_activity_performance.get_course_activities import (\n",
+    "    get_course_activities,\n",
+    ")\n",
+    "from src.modules.instance_activity_performance.compute_instance_performance import (\n",
+    "    compute_instance_performance,\n",
+    ")\n",
+    "from src.modules.instance_activity_performance.agg_activity_performance import (\n",
+    "    agg_activity_performance,\n",
+    ")\n",
+    "from src.modules.instance_activity_performance.save_instance_performances import (\n",
+    "    save_instance_performances,\n",
+    ")\n",
+    "from src.modules.instance_activity_performance.save_activity_performance import (\n",
+    "    save_activity_performance,\n",
+    ")"
    ]
   },
   {
@@ -89,7 +99,9 @@
     "        save_instance_performances(db, df_instance_performance, course_id)\n",
     "\n",
     "        # save activity performance data\n",
-    "        save_activity_performance(db, activity_performance, course_id, practice_quiz_id=quiz[\"id\"])\n",
+    "        save_activity_performance(\n",
+    "            db, activity_performance, course_id, practice_quiz_id=quiz[\"id\"]\n",
+    "        )\n",
     "\n",
     "    for ml in mls:\n",
     "        # compute instance performances\n",
@@ -103,10 +115,14 @@
     "        activity_performance = agg_activity_performance(df_instance_performance)\n",
     "\n",
     "        # save instance performance data\n",
-    "        save_instance_performances(db, df_instance_performance, course_id, total_only=True)\n",
+    "        save_instance_performances(\n",
+    "            db, df_instance_performance, course_id, total_only=True\n",
+    "        )\n",
     "\n",
     "        # save activity performance data\n",
-    "        save_activity_performance(db, activity_performance, course_id, microlearning_id=ml[\"id\"])"
+    "        save_activity_performance(\n",
+    "            db, activity_performance, course_id, microlearning_id=ml[\"id\"]\n",
+    "        )"
    ]
   },
   {