commit

clean.py

@@ -0,0 +1,47 @@
+
+raw_student_records = [
+    {"id": "101", "name": "vijay",  "marks": "85.5", "skills": ["Python", "Git", "Python"]},
+    {"id": "102", "name": "ANITA",  "marks": "92",   "skills": ["Java", "SQL"]},
+    {"id": "101", "name": "Vijay",  "marks": "85.5", "skills": ["Python", "Git"]},
+    {"id": "103", "name": "rahul",  "marks": "78.0", "skills": ["Git", "C++", "Git"]},
+]
+
+def clean_records(raw_data):
+    """
+    Cleans raw student records:
+      1. Removes duplicate IDs  (keeps last occurrence)
+      2. Converts id     → int
+      3. Normalizes name → Proper Case
+      4. Converts marks  → float
+      5. Removes duplicate skills using set()
+    Returns a dict keyed by integer student ID.
+    """
+
+    # ── 1. Remove duplicate entries (keep last occurrence per ID) ────────────
+    unique = {}
+    for record in raw_data:
+        unique[record["id"]] = record   # same ID? newer record wins
+
+    # ── 2. Clean each field ──────────────────────────────────────────────────
+    cleaned = {}
+    for sid, record in unique.items():
+        clean_id     = int(sid)                         # "101" → 101
+        clean_name   = record["name"].strip().capitalize()  # "vijay" → "Vijay"
+        clean_marks  = float(record["marks"])           # "85.5" → 85.5
+        clean_skills = set(record["skills"])            # removes duplicates
+
+        cleaned[clean_id] = {
+            "name"  : clean_name,
+            "marks" : clean_marks,
+            "skills": clean_skills,
+        }
+
+    return cleaned
+
+
+# ── Run standalone test (Member A can verify their own work) ─────────────────
+if __name__ == "__main__":
+    result = clean_records(raw_student_records)
+    print("=== [Member A] Cleaned Data Preview ===")
+    for sid, info in sorted(result.items()):
+        print(f"  ID {sid}: {info}")

evaluator.py

@@ -0,0 +1,74 @@
+# ============================================================
+#  FILE   : data_evaluation.py
+#  OWNER  : Team Member B
+#  TASK   : Evaluate the cleaned student records
+#  HOW    : Member B downloads data_cleaning.py from the shared
+#           folder (Google Drive / OneDrive) and keeps BOTH
+#           files in the SAME folder, then runs this file.
+# ============================================================
+
+# ── Member B imports Member A's cleaned data ─────────────────────────────────
+from clean import clean_records, raw_student_records
+
+def evaluate_records(cleaned_data):
+    """
+    Evaluates cleaned student records:
+      1. Determines Pass / Fail  (marks >= 40 → Pass)
+      2. Adds 'pass' key to each record
+      3. Prints a full summary report
+    Returns the final evaluated dictionary.
+    """
+
+    evaluated = {}
+
+    for sid, info in cleaned_data.items():
+        is_pass = info["marks"] >= 40.0          # evaluation logic
+
+        evaluated[sid] = {
+            "name"  : info["name"],
+            "marks" : info["marks"],
+            "skill" : info["skills"],            # rename to match expected output
+            "pass"  : is_pass,
+        }
+
+    return evaluated
+
+
+def print_report(evaluated_data):
+    """Prints a formatted summary report."""
+    print("=" * 55)
+    print("    Final Evaluated Student Records Report")
+    print("=" * 55)
+
+    total   = len(evaluated_data)
+    passed  = sum(1 for s in evaluated_data.values() if s["pass"])
+    failed  = total - passed
+
+    for sid, info in sorted(evaluated_data.items()):
+        status = "✅ PASS" if info["pass"] else "❌ FAIL"
+        print(f"\n  Student ID : {sid}")
+        print(f"  Name       : {info['name']}")
+        print(f"  Marks      : {info['marks']}")
+        print(f"  Skills     : {info['skill']}")
+        print(f"  Result     : {status}")
+
+    print("\n" + "─" * 55)
+    print(f"  Total Students : {total}")
+    print(f"  Passed         : {passed}")
+    print(f"  Failed         : {failed}")
+    print("=" * 55)
+
+    print("\nFinal Dictionary (exact expected output):")
+    print(evaluated_data)
+
+
+# ── Main execution ────────────────────────────────────────────────────────────
+if __name__ == "__main__":
+    # Step 1: Get cleaned data from Member A's file
+    cleaned = clean_records(raw_student_records)
+
+    # Step 2: Evaluate (Member B's job)
+    final   = evaluate_records(cleaned)
+
+    # Step 3: Print the report
+    print_report(final)

student_records.py

@@ -0,0 +1,36 @@
+raw_student_records = [
+    {"id": "101", "name": "vijay",  "marks": "85.5", "skills": ["Python", "Git", "Python"]},
+    {"id": "102", "name": "ANITA",  "marks": "92",   "skills": ["Java", "SQL"]},
+    {"id": "101", "name": "Vijay",  "marks": "85.5", "skills": ["Python", "Git"]},
+    {"id": "103", "name": "rahul",  "marks": "78.0", "skills": ["Git", "C++", "Git"]},
+]
+
+# ---------------------------------------------------------------------------
+# Transform raw_student_records into the required clean dictionary
+# ---------------------------------------------------------------------------
+cleaned_students = {}
+
+for record in raw_student_records:
+    student_id = int(record["id"])           # str  → int
+    name       = record["name"].title()      # any case → Title Case
+    marks      = float(record["marks"])      # str  → float
+    skills     = set(record["skills"])       # list (with duplicates) → set
+    passed     = marks >= 40                 # pass/fail rule
+
+    if student_id not in cleaned_students:
+        # First time we see this id – store it
+        cleaned_students[student_id] = {
+            "name"  : name,
+            "marks" : marks,
+            "skill" : skills,
+            "pass"  : passed,
+        }
+    else:
+        # Duplicate id – merge skills (union) and keep the rest as-is
+        cleaned_students[student_id]["skill"] |= skills
+
+# ---------------------------------------------------------------------------
+# Display result
+# ---------------------------------------------------------------------------
+for sid, info in cleaned_students.items():
+    print(f"{sid}: {info}")