Django for Data Science (Boston Python Meetup, March 2025)

A keynote talk showing how to combine data science and web development.

Transcript

1. Django for Data Science Will Vincent Boston Python Meetup (March 2025) Deploying Machine Learning Models with Django
2. Will Vincent • JetBrains/PyCharm Developer Advocate • Django Board Member (2020-2022) • LearnDjango.com • Books: Django for Beginners/APIs/Professionals • Django Chat podcast • Django News newsletter • Open source: awesome-django, DjangoX
3. Image: AlmaBetter.com Image: AlmaBetter.com
5. What is Data Science?
6. What do Data Scientists Do?
7. Python 2010-Today
8. The Rise of Data Science in Python
10. Python Web Frameworks
11. Why Django in 2025?
12. Maths
13. Train a Model
14. Jupyter Notebook - Setup
15. Jupyter Notebook - Layout
16. Iris Dataset
17. Iris Dataset
18. requirements.txt pandas~=2.2.3 scikit-learn~=1.6.1
19. Jupyter Notebook # Load libraries import pandas as pd from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score from sklearn.svm import SVC from joblib import dump, load # Load dataset df = pd.read_csv("data/iris.csv") # Extract features (X) and labels (y) X = df[["SepalLengthCm", "SepalWidthCm", "PetalLengthCm", "PetalWidthCm"]].values y = df["Species"].values # Split into training and testing data X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.20, random_state=1 )
20. Jupyter Notebook # Train the model model = SVC(gamma="auto") model.fit(X_train, y_train) # Make predictions on validation dataset predictions = model.predict(X_test) # Evaluate model accuracy accuracy = accuracy_score(y_test, predictions) print(f"Model Accuracy: {accuracy:.2f}") # Print accuracy score # Save model using joblib dump(model, "models/iris.joblib") # Load model using joblib model = load("models/iris.joblib")
21. # Get input from the user try: sepal_length = float(input("Enter SepalLengthCm: ")) sepal_width = float(input("Enter SepalWidthCm: ")) petal_length = float(input("Enter PetalLengthCm: ")) petal_width = float(input("Enter PetalWidthCm: ")) except ValueError: print("Invalid input. Please enter numeric values.") exit() # Make a prediction input_data = [[sepal_length, sepal_width, petal_length, petal_width]] result = model.predict(input_data) print("Prediction:", result[0]) # Iris Classification with SVM
22. Live Demo?
23. Visualize # requirements.txt pandas~=2.2.3 scikit-learn~=1.6.1 seaborn~=0.13.2 matplotlib~=3.10.0 # Import Seaborn and Matplotlib for visualizations import seaborn as sns import matplotlib.pyplot as plt # Pairplot to visualize relationships between features sns.pairplot(df, hue="Species", diag_kind="kde") plt.show()
25. Django Project
26. Gameplan • Create new Django project • Load joblib file • Forms for users to enter predictions -> see results • Store user info in the database • Deployment?
27. New Django Project
28. ├── django_project │ ├── __init__.py │ ├── asgi.py │ ├── settings.py │ ├── urls.py │ └── wsgi.py ├── manage.py ├── predict │ ├── __init__.py │ ├── admin.py │ ├── apps.py │ ├── migrations │ │ └── __init__.py │ ├── models.py │ ├── tests.py │ └── views.py └── templates
30. Add our ML Model ├── django_project │ ├── __init__.py │ ├── asgi.py │ ├── settings.py │ ├── urls.py │ └── wsgi.py ├── iris.joblib # hi there! ├── manage.py ├── predict │ ├── __init__.py │ ├── admin.py │ ├── apps.py │ ├── migrations │ │ └── __init__.py │ ├── models.py │ ├── tests.py
31. Django Under The Hood: Part 1
32. Djangoʼs MVT Architecture • Model (M) --> Handles database interactions and business logic • View (V) --> Acts as Controller in MVC, process requests and match template • Template (T) --> Presentation layer, HTML+ CSS + data
33. Django Under The Hood: Part 2
34. URLs # django_project/urls.py from django.contrib import admin from django.urls import path, include # new urlpatterns = [ path("admin/", admin.site.urls), path("", include("predict.urls")), # new ] # predict/urls.py from django.urls import path from .views import predict urlpatterns = [ path("", predict, name="predict"),
35. View + Template # predict/views.py from django.shortcuts import render def predict(request): return render(request, "predict.html") <!-- templates/predict.html --> Hello
36. Runserver (again)
37. # predict/views.py import joblib import numpy as np from django.shortcuts import render # Load the trained model model = joblib.load("iris.joblib") def predict(request): prediction = None if request.method == "POST": try: # Get input values from the form sepal_length = float(request.POST.get("sepal_length")) sepal_width = float(request.POST.get("sepal_width")) petal_length = float(request.POST.get("petal_length")) petal_width = float(request.POST.get("petal_width")) # Make a prediction features = np.array( [[sepal_length, sepal_width, petal_length, petal_width]] ) prediction = model.predict(features)[0] except Exception as e: prediction = f"Error: {str(e)}" return render(request, "predict.html", {"prediction": prediction})
38. <!-- templates/predict.html --> <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Iris Prediction</title> <style> body { font-family: Arial, sans-serif; max-width: 400px; margin: 50px auto; text-align: center; } form { display: flex; flex-direction: column; gap: 10px; } input, button { padding: 10px; font-size: 16px; } button { cursor: pointer; background-color: #4CAF50; color: white; border: none; }
39. <!-- templates/predict.html --> ... <body> <h2>Iris Species Predictor</h2> <form method="post"> {% csrf_token %} <input type="number" step="any" name="sepal_length" placeholder="Sepal Length" required> <input type="number" step="any" name="sepal_width" placeholder="Sepal Width" required> <input type="number" step="any" name="petal_length" placeholder="Petal Length" required> <input type="number" step="any" name="petal_width" placeholder="Petal Width" required> <button type="submit">Predict</button> </form> {% if prediction %} <h3>Prediction: {{ prediction }}</h3> {% endif %} </body> </html>
42. Store User Inputs # predict/views.py ... def predict(request): prediction = None form_data = {} # To store user inputs if request.method == "POST": try: # Store form inputs form_data = { "sepal_length": request.POST.get("sepal_length"), "sepal_width": request.POST.get("sepal_width"), "petal_length": request.POST.get("petal_length"), "petal_width": request.POST.get("petal_width"), } # Convert inputs to float and make a prediction features = np.array([[float(v) for v in form_data.values()]]) prediction = model.predict(features)[0] except Exception as e: prediction = f"Error: {str(e)}" return render( request, "predict.html", {"prediction": prediction, "form_data": form_data}
43. Display User Inputs <!-- templates/predict.html --> {% if prediction %} <div class="result"> <h3>Prediction: {{ prediction }}</h3> <p><strong>Inputs:</strong></p> <ul> <li>Sepal Length: {{ form_data.sepal_length }}</li> <li>Sepal Width: {{ form_data.sepal_width }}</li> <li>Petal Length: {{ form_data.petal_length }}</li> <li>Petal Width: {{ form_data.petal_width }}</li> </ul> </div>] {% endif %}
45. Add a Model to Store Predictions # predict/models.py from django.db import models class IrisPrediction(models.Model): sepal_length = models.FloatField() sepal_width = models.FloatField() petal_length = models.FloatField() petal_width = models.FloatField() prediction = models.CharField(max_length=100) created_at = models.DateTimeField(auto_now_add=True) def __str__(self): return f"{self.prediction} ({self.created_at.strftime('%Y-%m-%d %H:%M:%S')})"
46. Update View to Save Predictions # predict/views.py import joblib import numpy as np from django.shortcuts import render from .models import IrisPrediction. # new # Load the trained model model = joblib.load("iris.joblib") def predict(request): prediction = None form_data = {} if request.method == "POST": try: ... # Save prediction to database IrisPrediction.objects.create( sepal_length=form_data["sepal_length"], sepal_width=form_data["sepal_width"], petal_length=form_data["petal_length"], petal_width=form_data["petal_width"], prediction=prediction, )
47. Update Admin # predict/admin.py from django.contrib import admin from .models import IrisPrediction admin.site.register(IrisPrediction)
48. DjangoForDataScience.com
49. Deployment...
50. Deployment Checklist • configure static files and install WhiteNoise • add environment variables with environs • create a .env file and update the .gitignore file • update DEBUG, ALLOWED_HOSTS, SECRET_KEY, and CSRF_TRUSTED_ORIGINS • update DATABASES to run PostgreSQL in production and install psycopg • install Gunicorn as a production WSGI server • create a Procfile • update the requirements.txt file • create a new Heroku project, push the code to it, and start a dyno web process
51. LLMs...
53. LLM Tips 1. Still fancy autocomplete (not AGI) 2. Be aware of training cut-off dates 3. Context is king 4. Prompt tips 5. Vibe coding...
55. Takeaways ✅ Django is great for deploying ML models (web UI + APIs) ✅ Iris dataset is simple but powerful for learning ML deployment ✅ Try deploying a real-world ML model
56. Questions? @wsvincent.bsky.social @wsvincent -- django_irisml & iris_ml fosstodon.org/@wsvincent @william-s-vincent
57. Appendix C More Django architecture diagrams...
58. Django Under The Hood: Part 3
59. Django Under The Hood: Part 4
60. Deployment...
61. 1a. Static Files (.venv) $ mkdir static (.venv) $ mkdir static/css (.venv) $ mkdir static/js (.venv) $ mkdir static/img (.venv) $ touch static/css/.keep (.venv) $ touch static/js/.keep (.venv) $ touch static/img/.keep # django_project/settings.py STATIC_URL = "static/" STATICFILES_DIRS = [BASE_DIR / "static"] # new
62. 1b. Static Files # django_project/settings.py STATIC_URL = "static/" STATICFILES_DIRS = [BASE_DIR / "static"] STATIC_ROOT = BASE_DIR / "staticfiles" # new (.venv) $ python manage.py collectstatic # staticfiles/ └── admin ├── css ├── img ├── js
63. 1c. Static Files <!-- templates/predict.html --> {% load static %} <!DOCTYPE html> ...
64. 1d. Static Files INSTALLED_APPS = [ ... "whitenoise.runserver_nostatic", # new "django.contrib.staticfiles", "predict", ] MIDDLEWARE = [ "django.middleware.security.SecurityMiddleware", "django.contrib.sessions.middleware.SessionMiddleware", "whitenoise.middleware.WhiteNoiseMiddleware", # new ... ] STORAGES = { "default": { "BACKEND": "django.core.files.storage.FileSystemStorage", }, "staticfiles": {
65. 2. Environment Variables # django_project/settings.py from pathlib import Path from environs import Env # new env = Env() # new env.read_env() # new # .gitignore .venv/ __pycache__/ db.sqlite3 .env .idea/