Improvement

.vscode/launch.json

@@ -13,7 +13,10 @@
             ],
             "django": true,
             "autoStartBrowser": true,
-            "program": "${workspaceFolder}\\src\\manage.py",
+            "program": "${workspaceFolder}/src/manage.py",
+            "preLaunchTask": "Setup Django Project",
+            "console": "integratedTerminal",
+            "justMyCode": true
         }
     ]
 }

.vscode/tasks.json

@@ -1,6 +1,20 @@
 {
     "version": "2.0.0",
     "tasks": [
+        {
+            "label": "Setup Django Project",
+            "type": "process",
+            "command": "python",
+            "args": [
+                "${workspaceFolder}/run.py",
+                "--setup-only"
+            ],
+            "presentation": {
+                "reveal": "always",
+                "panel": "new"
+            },
+            "problemMatcher": []
+        },
         {
             "label": "Create Virtual Environment",
             "type": "shell",

README.md

@@ -17,47 +17,28 @@
 ## Getting Started 🚀
 
 ### Prerequisites
+
 - Python 3.12 or higher
 - pip (Python package manager)
-- Download [merged_dataframe.csv](https://drive.google.com/file/d/1MVRHs_CwKTBR2Rpakx920f277IcJ0q6X/view) and place it in the `src/data_access` directory.
+- ~~Download [merged_dataframe.csv](https://drive.google.com/file/d/1MVRHs_CwKTBR2Rpakx920f277IcJ0q6X/view) and place it in the `src/data_access` directory.~~
+- The dataset is gotten during the setup process.
 
 ### Installation
 
 1. Clone the repository:
-   ```
-   git clone https://github.com/SP-SDU/Undershelf.git
-   cd Undershelf
-   ```
 
-2. Create and activate a virtual environment:
    ```bash
-   # Windows
-   python -m venv .venv
-   .\.venv\Scripts\activate
-
-   # Linux/MacOS
-   python -m venv .venv
-   source .venv/bin/activate
-   ```
-
-3. Install dependencies:
-   ```
-   pip install -r requirements.txt
+   git clone https://github.com/SP-SDU/Undershelf.git
+   cd Undershelf
    ```
 
-### Running the Application (Or debug F5 in VSCode)
+### Setup and Running the Application
 
-1. Ensure virtual environment is activated (you should see `(.venv)` in your terminal)
+Press `F5` in VS Code to start debugging or run it in terminal:
 
-2. Start the django server:
-   ```
-   python src/manage.py runserver
-   ```
-
-3. Open your browser and navigate to:
-   ```
-   http://localhost:8000
-   ```
+```bash
+python run.py
+```
 
 ### Available Commands 🔧
 
@@ -76,9 +57,11 @@ The following commands are available in addition to those explained above:
 ## Contributing 🤝
 
 1. **Clone** Open [GitHub Desktop](https://desktop.github.com/), go to `File > Clone Repository`, and enter:
+
      ```
      https://github.com/SP-SDU/Undershelf
      ```
+
 2. **Branch**: In GitHub Desktop, switch to `main` and create a new branch (e.g., `add-login-feature`).
 3. **Commit & Push**: Commit changes in GitHub Desktop, then click `Push origin`.
 4. **Pull Request**: Open a pull request on GitHub, choosing `main` as the base branch, and tag a teammate for review.
@@ -92,4 +75,3 @@ Join the [Discord server](https://discord.gg/a2ARm52WwE) for discussions and upd
 ## License 📝
 
 Distributed under the Apache 2.0 License. See [LICENSE](LICENSE) for details.
-

run.py

@@ -0,0 +1,187 @@
+import argparse
+import os
+import platform
+import subprocess
+import urllib.request
+import venv
+import zipfile
+
+
+def run_command(command, description=None):
+    if description:
+        print(f"\033[92m{description}...\033[0m")
+
+    process = subprocess.Popen(
+        command,
+        shell=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        universal_newlines=True,
+    )
+
+    if process.stdout:
+        for line in process.stdout:
+            print(line, end="")
+
+    process.wait()
+    if process.returncode != 0:
+        print(f"\033[91mCommand failed with return code {process.returncode}\033[0m")
+        return False
+    return True
+
+
+def get_venv_python_path():
+    if platform.system() == "Windows":
+        python_exe = os.path.join(os.getcwd(), ".venv", "Scripts", "python.exe")
+    else:
+        python_exe = os.path.join(os.getcwd(), ".venv", "bin", "python")
+    return python_exe
+
+
+def create_venv_if_not_exists():
+    if not os.path.exists(".venv"):
+        print("\033[92mCreating virtual environment...\033[0m")
+        venv.create(".venv", with_pip=True)
+        return True
+    return False
+
+
+def parse_arguments():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--setup-only",
+        action="store_true",
+    )
+    return parser.parse_args()
+
+
+def create_superuser(python_exe):
+    print("\033[92mCreating superuser if needed...\033[0m")
+
+    os.environ.setdefault("DJANGO_SUPERUSER_USERNAME", "root")
+    os.environ.setdefault("DJANGO_SUPERUSER_PASSWORD", "root")
+    os.environ.setdefault("DJANGO_SUPERUSER_EMAIL", "root@undershelf.com")
+
+    run_command(
+        f"{python_exe} src/manage.py createsuperuser --noinput", "Creating superuser"
+    )
+
+
+def check_if_data_exists(python_exe):
+    check_script = (
+        "import os; "
+        "os.environ.setdefault('DJANGO_SETTINGS_MODULE','config.settings'); "
+        "import django; django.setup(); "
+        "from data_access.models import Book; "
+        "print(1 if Book.objects.count()>0 else 0)"
+    )
+
+    try:
+        result = subprocess.run(
+            [python_exe, "-c", check_script],
+            capture_output=True,
+            text=True,
+            cwd=os.path.join(os.getcwd(), "src"),
+        )
+
+        return result.returncode == 0 and result.stdout.strip() == "1"
+    except Exception as e:
+        print(f"\033[93mWarning: Could not check database: {e}\033[0m")
+        return False
+
+
+def download_or_get_csv():
+    csv_path = os.path.join("src", "data_access", "merged_dataframe.csv")
+
+    if os.path.exists(csv_path):
+        print("\033[92mCSV file found.\033[0m")
+        return csv_path
+
+    print("\033[93mCSV file not found. Downloading...\033[0m")
+    url = "https://drive.usercontent.google.com/download?id=1MVRHs_CwKTBR2Rpakx920f277IcJ0q6X&authuser=0&confirm=t"
+    zip_path = os.path.join("src", "data_access", "merged_dataframe.zip")
+
+    try:
+        os.makedirs(os.path.dirname(csv_path), exist_ok=True)
+
+        # Download the ZIP file
+        print("\033[92mDownloading ZIP file...\033[0m")
+        with urllib.request.urlopen(url) as response:
+            if response.getcode() != 200:
+                raise Exception(f"HTTP error: {response.getcode()}")
+
+            with open(zip_path, "wb") as file:
+                chunk_size = 8192
+                while True:
+                    chunk = response.read(chunk_size)
+                    if not chunk:
+                        break
+                    file.write(chunk)
+
+        # Extract the ZIP file
+        print("\033[92mExtracting ZIP file...\033[0m")
+        data_access_dir = os.path.join("src", "data_access")
+        with zipfile.ZipFile(zip_path, "r") as zip_ref:
+            zip_ref.extractall(data_access_dir)
+
+        # Remove the ZIP file after extraction
+        os.remove(zip_path)
+
+        if os.path.exists(csv_path):
+            print("\033[92mCSV file extracted successfully.\033[0m")
+            return csv_path
+        else:
+            print("\033[91mNo CSV file found in the extracted ZIP.\033[0m")
+            return None
+
+    except Exception as e:
+        print(f"\033[91mError processing file: {e}\033[0m")
+        return None
+
+
+def main():
+    create_venv_if_not_exists()
+    python_exe = get_venv_python_path()
+
+    run_command(
+        f"{python_exe} -m pip install -r requirements.txt",
+        "Installing requirements",
+    )
+    run_command(
+        f"{python_exe} src/manage.py makemigrations",
+        "Making migrations",
+    )
+    run_command(f"{python_exe} src/manage.py migrate", "Running migrations")
+
+    create_superuser(python_exe)
+
+    print("\033[92mChecking if data needs to be imported...\033[0m")
+    if not check_if_data_exists(python_exe):
+        csv_path = download_or_get_csv()
+        if not csv_path:
+            print("\033[91mFailed to get CSV file. Exiting.\033[0m")
+            exit(1)
+        run_command(
+            f"{python_exe} src/manage.py import_data {csv_path}",
+            "Importing data from CSV",
+        )
+    else:
+        print("\033[92mData already exists in the database. Skipping import.\033[0m")
+
+    args = parse_arguments()
+    if args.setup_only:
+        print("\033[92mSetup complete.\033[0m")
+    else:
+        print("\033[92mStarting development server...\033[0m")
+        print("\033[93mPress Ctrl+C to stop the server\033[0m")
+        subprocess.call([python_exe, "src/manage.py", "runserver"])
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except KeyboardInterrupt:
+        print("\n\033[93mInterrupted. Exiting.\033[0m")
+    except Exception as e:
+        print(f"\n\033[91mAn error occurred: {e}\033[0m")
+        exit(1)

src/business_logic/bfs.py

@@ -0,0 +1,63 @@
+from collections import defaultdict, deque
+from typing import List
+
+from data_access.models import Book
+
+
+class GraphRecommender:
+    """
+    Graph-based recommender using BFS.
+    Nodes: books; edges: same author or same category.
+    """
+
+    @staticmethod
+    def get_recommendations(
+        start_book_id: str, max_depth: int = 2, max_results: int = 10
+    ) -> List[Book]:
+        # Build feature maps: author -> books, category -> books
+        author_map = defaultdict(set)
+        category_map = defaultdict(set)
+
+        all_books = list(Book.objects.only("id", "authors", "categories"))  # O(n)
+        for b in all_books:  # O(n * f)
+            if b.authors:
+                for author in b.authors.split(","):
+                    author_map[author.strip().lower()].add(b.id)
+            if b.categories:
+                for cat in b.categories.split(","):
+                    category_map[cat.strip().lower()].add(b.id)
+
+        visited = set([start_book_id])
+        queue = deque([(start_book_id, 0)])
+        recommendations = []
+
+        while queue and len(recommendations) < max_results:
+            current_id, depth = queue.popleft()
+            if depth >= max_depth:
+                continue
+
+            # neighbors by author
+            b = Book.objects.only("id", "authors", "categories").get(pk=current_id)
+            neighbors = set()
+            if b.authors:
+                for author in b.authors.split(","):
+                    neighbors |= author_map[author.strip().lower()]
+            if b.categories:
+                for cat in b.categories.split(","):
+                    neighbors |= category_map[cat.strip().lower()]
+
+            for nb_id in neighbors:
+                if nb_id not in visited:
+                    visited.add(nb_id)
+                    queue.append((nb_id, depth + 1))
+                    if nb_id != start_book_id:
+                        recommendations.append(nb_id)
+                        if len(recommendations) >= max_results:
+                            break
+
+        # Fetch Book instances preserving order
+        books = list(Book.objects.filter(id__in=recommendations))
+        # maintain recommendation order
+        id_to_book = {book.id: book for book in books}
+        ordered = [id_to_book[rid] for rid in recommendations if rid in id_to_book]
+        return ordered