🧪 Lab 02: Document Modeling¶

Topics: Embedding vs Referencing, one-to-many, many-to-many

---

In [7]:

from pymongo import MongoClient, ReadPreference
from pymongo.read_concern import ReadConcern
from pymongo.write_concern import WriteConcern
from pymongo.errors import ConnectionFailure
from bson import ObjectId
from datetime import datetime, timedelta, timezone
import pprint

USE_ATLAS = False
ATLAS_URI  = "mongodb+srv://<username>:<password>@<cluster>.mongodb.net/?retryWrites=true&w=majority"
DOCKER_URI = "mongodb://127.0.0.1:27017/?directConnection=true"

uri = ATLAS_URI if USE_ATLAS else DOCKER_URI
client = MongoClient(uri, serverSelectionTimeoutMS=5000)
try:
    client.admin.command("ping")
    print("✅ Connected to", "Atlas" if USE_ATLAS else "Docker MongoDB")
except ConnectionFailure as e:
    print("❌ Connection failed:", e)

db = client["mongo_labs"]
pp = pprint.PrettyPrinter(indent=2)

from pymongo import MongoClient, ReadPreference from pymongo.read_concern import ReadConcern from pymongo.write_concern import WriteConcern from pymongo.errors import ConnectionFailure from bson import ObjectId from datetime import datetime, timedelta, timezone import pprint USE_ATLAS = False ATLAS_URI = "mongodb+srv://<username>:<password>@<cluster>.mongodb.net/?retryWrites=true&w=majority" DOCKER_URI = "mongodb://127.0.0.1:27017/?directConnection=true" uri = ATLAS_URI if USE_ATLAS else DOCKER_URI client = MongoClient(uri, serverSelectionTimeoutMS=5000) try: client.admin.command("ping") print("✅ Connected to", "Atlas" if USE_ATLAS else "Docker MongoDB") except ConnectionFailure as e: print("❌ Connection failed:", e) db = client["mongo_labs"] pp = pprint.PrettyPrinter(indent=2)

✅ Connected to Docker MongoDB

Embedding (co-accessed data)¶

In [8]:

db.users_embedded.drop()
user_id = db.users_embedded.insert_one({"name":"Alice","email":"alice@example.com","address":{"city":"NYC","state":"NY"},"tags":["premium"]}).inserted_id
user = db.users_embedded.find_one({"email":"alice@example.com"})
print("City:", user["address"]["city"])

db.users_embedded.drop() user_id = db.users_embedded.insert_one({"name":"Alice","email":"alice@example.com","address":{"city":"NYC","state":"NY"},"tags":["premium"]}).inserted_id user = db.users_embedded.find_one({"email":"alice@example.com"}) print("City:", user["address"]["city"])

City: NYC

In [9]:

# Query on embedded field
for u in db.users_embedded.find({"address.city":"NYC"},{"_id":0,"name":1}):
    print(u["name"])

# Query on embedded field for u in db.users_embedded.find({"address.city":"NYC"},{"_id":0,"name":1}): print(u["name"])

Alice

Referencing (unbounded growth)¶

In [10]:

db.users_ref.drop()
db.orders_ref.drop()
bob_id = db.users_ref.insert_one({"name":"Bob","email":"bob@example.com"}).inserted_id
db.orders_ref.insert_many([{"userId":bob_id,"status":"delivered","total":349.99},{"userId":bob_id,"status":"pending","total":49.99}])
user = db.users_ref.find_one({"_id":bob_id})
orders = list(db.orders_ref.find({"userId":bob_id}))
print(f"{user['name']}: {len(orders)} orders")

db.users_ref.drop() db.orders_ref.drop() bob_id = db.users_ref.insert_one({"name":"Bob","email":"bob@example.com"}).inserted_id db.orders_ref.insert_many([{"userId":bob_id,"status":"delivered","total":349.99},{"userId":bob_id,"status":"pending","total":49.99}]) user = db.users_ref.find_one({"_id":bob_id}) orders = list(db.orders_ref.find({"userId":bob_id})) print(f"{user['name']}: {len(orders)} orders")

Bob: 2 orders

$lookup (runtime join)¶

In [11]:

result = list(db.users_ref.aggregate([{"$match":{"_id":bob_id}},{"$lookup":{"from":"orders_ref","localField":"_id","foreignField":"userId","as":"orders"}}]))
print("Joined orders:", len(result[0]["orders"]))

result = list(db.users_ref.aggregate([{"$match":{"_id":bob_id}},{"$lookup":{"from":"orders_ref","localField":"_id","foreignField":"userId","as":"orders"}}])) print("Joined orders:", len(result[0]["orders"]))

Joined orders: 2

Many-to-Many (edge collection)¶

In [12]:

db.courses.drop()
db.students.drop()
db.enrollments.drop()
db.courses.insert_many([{"_id":ObjectId("c00000000000000000000001"),"title":"MongoDB"},{"_id":ObjectId("c00000000000000000000002"),"title":"Aggregation"}])
db.students.insert_many([{"_id":ObjectId("s00000000000000000000001"),"name":"Dave"},{"_id":ObjectId("s00000000000000000000002"),"name":"Eve"}])
db.enrollments.insert_many([{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000001")},{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000002")}])
db.enrollments.create_index("studentId")
db.enrollments.create_index("courseId")
courses = list(db.enrollments.find({"studentId":ObjectId("s00000000000000000000001")}))
print("Dave enrolled in:", len(courses), "courses")

db.courses.drop() db.students.drop() db.enrollments.drop() db.courses.insert_many([{"_id":ObjectId("c00000000000000000000001"),"title":"MongoDB"},{"_id":ObjectId("c00000000000000000000002"),"title":"Aggregation"}]) db.students.insert_many([{"_id":ObjectId("s00000000000000000000001"),"name":"Dave"},{"_id":ObjectId("s00000000000000000000002"),"name":"Eve"}]) db.enrollments.insert_many([{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000001")},{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000002")}]) db.enrollments.create_index("studentId") db.enrollments.create_index("courseId") courses = list(db.enrollments.find({"studentId":ObjectId("s00000000000000000000001")})) print("Dave enrolled in:", len(courses), "courses")

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
File ~/Programming/MongoDBLeaning/venv/lib/python3.9/site-packages/bson/objectid.py:112, in ObjectId.__init__(self, oid)
    111 try:
--> 112     self.__id = bytes.fromhex(oid)
    113 except (TypeError, ValueError):

ValueError: non-hexadecimal number found in fromhex() arg at position 0

During handling of the above exception, another exception occurred:

InvalidId                                 Traceback (most recent call last)
Cell In[12], line 5
      3 db.enrollments.drop()
      4 db.courses.insert_many([{"_id":ObjectId("c00000000000000000000001"),"title":"MongoDB"},{"_id":ObjectId("c00000000000000000000002"),"title":"Aggregation"}])
----> 5 db.students.insert_many([{"_id":ObjectId("s00000000000000000000001"),"name":"Dave"},{"_id":ObjectId("s00000000000000000000002"),"name":"Eve"}])
      6 db.enrollments.insert_many([{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000001")},{"studentId":ObjectId("s00000000000000000000001"),"courseId":ObjectId("c00000000000000000000002")}])
      7 db.enrollments.create_index("studentId")

File ~/Programming/MongoDBLeaning/venv/lib/python3.9/site-packages/bson/objectid.py:114, in ObjectId.__init__(self, oid)
    112         self.__id = bytes.fromhex(oid)
    113     except (TypeError, ValueError):
--> 114         _raise_invalid_id(oid)
    115 else:
    116     _raise_invalid_id(oid)

File ~/Programming/MongoDBLeaning/venv/lib/python3.9/site-packages/bson/objectid.py:37, in _raise_invalid_id(oid)
     36 def _raise_invalid_id(oid: str) -> NoReturn:
---> 37     raise InvalidId(
     38         "%r is not a valid ObjectId, it must be a 12-byte input"
     39         " or a 24-character hex string" % oid
     40     )

InvalidId: 's00000000000000000000001' is not a valid ObjectId, it must be a 12-byte input or a 24-character hex string