adding Data Structures and Algorithms II C950

Data Structures and Algorithms II — C950/Task 2 - Python files + Screenshots/data_loader.py

@@ -0,0 +1,96 @@
+# Student ID: 012498637
+# Student Name: Zakaria Benmoulay
+# Course: C950 - Data Structures and Algorithms II
+
+import csv
+from package import Package
+from hash_table import ChainingHashTable
+
+
+def load_packages(filepath):
+    # Let's read packages.csv and load all package records into a hash table.
+    table = ChainingHashTable()
+
+    with open(filepath, newline="", encoding="utf-8") as f:
+        reader = csv.DictReader(f)
+
+        for row in reader:
+            # Build a Package object from each CSV row
+            pkg = Package(
+                package_id=row["PackageID"],
+                address=row["Address"],
+                city=row["City"],
+                state=row["State"],
+                zip_code=row["Zip"],
+                deadline=row["Deadline"],
+                weight=row["Weight"],
+                notes=row["Notes"],
+            )
+            # Insert into the hash table using package ID as the key
+            table.insert(pkg.package_id, pkg)
+
+    # Let's return the hash table keyed by package ID
+    return table
+
+
+def load_distances(filepath):
+    # Let's read distances.csv and build a symmetric 2-D distance matrix.
+    address_list = []
+    raw_rows = []
+
+    with open(filepath, newline="", encoding="utf-8") as f:
+        reader = csv.reader(f)
+
+        # First row contains the column headers (location name + address)
+        header = next(reader)
+
+        # Extract the short street address from each header cell.
+        # Header cells may contain a full location name followed by the
+        # street address separated by whitespace; we take the last part.
+        for cell in header[1:]:  # skip the first "Address" label column
+            parts = [p.strip() for p in cell.replace("\n", "  ").split("  ") if p.strip()]
+            address_list.append(parts[-1] if parts else cell.strip())
+
+        # Read the remaining rows — each row is one location's distances
+        for row in reader:
+            raw_rows.append(row[1:])  # drop the first column (location label)
+
+    m = len(address_list)
+
+    # Create an m×m matrix filled with 0.0
+    matrix = [[0.0] * m for _ in range(m)]
+
+    # Fill in the matrix - the CSV only has the lower triangle
+    for i, row in enumerate(raw_rows):
+        for j, cell in enumerate(row):
+            if cell.strip() == "" or cell is None:
+                continue
+            dist = float(cell)
+            matrix[i][j] = dist
+            matrix[j][i] = dist
+
+    return address_list, matrix
+
+
+def get_distance(address_list, distance_matrix, addr_a, addr_b):
+
+    # Let's find the index of an address using flexible matching.
+    def find_index(addr):
+        addr_clean = addr.strip().lower()
+
+        # Pass 1: exact match (fastest, covers most cases)
+        for i, a in enumerate(address_list):
+            if a.strip().lower() == addr_clean:
+                return i
+
+        # Pass 2: substring match (handles minor formatting differences)
+        for i, a in enumerate(address_list):
+            if addr_clean in a.strip().lower() or a.strip().lower() in addr_clean:
+                return i
+
+        # Raise an error if the address cannot be found.
+        raise ValueError(f"Address not found in distance table: '{addr}'")
+
+    i = find_index(addr_a)
+    j = find_index(addr_b)
+    return distance_matrix[i][j]