feat: initial FDP content - Data Science Pipeline with Colab notebook

fdp-colab-content/generate_dataset.py

@@ -0,0 +1,42 @@
+import pandas as pd
+import numpy as np
+
+np.random.seed(42)
+n = 300
+
+departments = np.random.choice(["Science", "Commerce", "Arts", "Engineering"], n)
+attendance = np.random.choice(["Regular", "Irregular", "Borderline"], n, p=[0.4, 0.3, 0.3])
+fav_colors = np.random.choice(["Red", "Blue", "Green", "Yellow", "Purple", "Orange"], n)
+study_hours = np.round(np.random.uniform(2, 25, n), 1)
+assign_sub = np.round(np.random.uniform(40, 100, n), 0)
+backlogs = np.random.randint(0, 6, n)
+
+# Stress logic
+# High if: irregular attendance OR backlogs>=3 OR study_hours<5 OR assign_sub<55
+stress = ((attendance == "Irregular") | 
+          (backlogs >= 3) | 
+          (study_hours < 5) | 
+          (assign_sub < 55)).astype(int)
+
+# Add some noise so it's not 100% predictable
+flip = np.random.choice([0, 1], n, p=[0.9, 0.1])
+stress = stress ^ flip  # XOR flip 10%
+
+df = pd.DataFrame({
+    "Student_ID": ["S{:03d}".format(i+1) for i in range(n)],
+    "Department": departments,
+    "Attendance_Level": attendance,
+    "Favorite_Color": fav_colors,
+    "Weekly_Study_Hours": study_hours,
+    "Assignment_Submission_Pct": assign_sub.astype(int),
+    "Backlogs_Count": backlogs,
+    "Stress_Level": stress
+})
+
+df.to_csv("/root/fdp-workshop/fdp-colab-content/student_stress_data.csv", index=False)
+print("Dataset generated: {} rows, {} cols".format(len(df), len(df.columns)))
+print("Stress distribution:")
+print(df["Stress_Level"].value_counts().to_string())
+print("\nSample:")
+print(df.head(3).to_string())
+print("\nUnique colors: {}".format(df["Favorite_Color"].unique()))