Mooc Analytics Guide

import pandas as pd

# Load OULAD dataset (publicly available)
students = pd.read_csv("studentInfo.csv")
assessments = pd.read_csv("assessments.csv")
interactions = pd.read_csv("studentVle.csv")

# Basic engagement metric: total clicks per student per course
engagement = (
    interactions
    .groupby(["id_student", "code_module", "code_presentation"])
    .agg(total_clicks=("sum_click", "sum"),
         active_days=("date", "nunique"))
    .reset_index()
)
print(engagement.describe())

import numpy as np

def regularity_index(daily_counts: np.ndarray) -> float:
    """
    Compute regularity index based on Shannon entropy.
    Lower values indicate more regular study patterns.
    daily_counts: array of click counts per day over the course.
    """
    total = daily_counts.sum()
    if total == 0:
        return float("nan")
    probs = daily_counts / total
    probs = probs[probs > 0]
    entropy = -np.sum(probs * np.log2(probs))
    max_entropy = np.log2(len(daily_counts))
    return round(entropy / max_entropy, 4)  # normalized [0, 1]

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import TimeSeriesSplit
from sklearn.metrics import roc_auc_score

# Feature engineering: weekly aggregates
features = [
    "clicks_week", "video_time_week", "forum_posts_week",
    "assignments_submitted", "avg_score", "days_since_last_login",
    "regularity_index", "week_number"
]

X = weekly_features[features]
y = weekly_features["dropped_next_week"]

# Time-aware cross-validation (no future leakage)
tscv = TimeSeriesSplit(n_splits=5)
aucs = []
for train_idx, test_idx in tscv.split(X):
    model = GradientBoostingClassifier(
        n_estimators=200, max_depth=4, learning_rate=0.1
    )
    model.fit(X.iloc[train_idx], y.iloc[train_idx])
    pred = model.predict_proba(X.iloc[test_idx])[:, 1]
    aucs.append(roc_auc_score(y.iloc[test_idx], pred))

print(f"Mean AUC: {np.mean(aucs):.3f} +/- {np.std(aucs):.3f}")

def compute_video_metrics(events: pd.DataFrame) -> dict:
    """
    Process video clickstream events into engagement metrics.
    events: DataFrame with columns [user_id, video_id, event_type,
            timestamp, position_seconds, video_duration]
    """
    plays = events[events.event_type == "play"]
    pauses = events[events.event_type == "pause"]
    seeks = events[events.event_type == "seek"]

    total_duration = events.video_duration.iloc[0]
    watched_positions = set()

    for _, row in plays.iterrows():
        start = int(row.position_seconds)
        # Estimate 10-second watch window per play event
        for sec in range(start, min(start + 10, int(total_duration))):
            watched_positions.add(sec)

    return {
        "play_count": len(plays),
        "pause_count": len(pauses),
        "seek_count": len(seeks),
        "coverage_ratio": len(watched_positions) / max(total_duration, 1),
        "replay_indicator": len(plays) > 1,
    }