As a freelance Data Scientist with over 3 years of experience in prompt engineering, AI, data analytics, and machine learning, I specialize in developing predictive models and leveraging data to drive business insights. My expertise in statistical modeling and machine learning techniques, combined with my experience in prompt engineering and AI, has helped me develop solutions for a range of industries, from finance to healthcare. I am passionate about solving complex problems with data and collaborating with cross-functional teams to drive innovation. I am seeking new opportunities to apply my skills and continue to grow in the field of data science.Expertise in:
- Developing and deploying machine learning models, including deep learning, NLP, and computer vision
- Conducting data analytics and creating visualizations to communicate insights effectively
- Working with a variety of programming languages, including Python, R, Java, and SQL, to manipulate and analyze data
- Using data science tools such as TensorFlow, PyTorch, scikit-learn, Pandas, NumPy, and others to build and optimize models
- Designing and implementing data pipelines and managing cloud computing resources
- Applying prompt engineering techniques to optimize natural language generation and processing
I have a passion for:
- Developing innovative solutions
- Exploring new technologies
- Making a positive impact
- Continuous learning
- Collaborating with others
- Jupyter Notebook
- Google Colab
- Git and GitHub
- Tableau or PowerBI
- Apache Hadoop and Spark
- TensorFlow , PyTorch
- Scikit-Learn
- Pandas, NumPy, and Matplotlib
- SQL and NoSQL databases
- Docker and Kubernetes
- Machine learning algorithms and frameworks
- Programming languages such as Python, R, Java, SQL
- Data wrangling and cleaning
- Data visualization and presentation
- Statistics and probability
- Natural language processing (NLP) and text mining
- Computer vision and image processing
- Big data technologies and distributed computing
- Cloud computing platforms and services
- Deep learning and neural networks
- Communication
- Problem-solving
- Critical thinking
- Collaboration
- Time management
- Adaptability
- Creativity
- Attention to detail
- Continuous learning
This project is an interactive web application that recognizes handwritten digits using the k-Nearest Neighbors (k-NN) algorithm and Streamlit. The app allows users to draw a digit on the screen and get a prediction for the corresponding digit from 0 to 9.
- Python
- NumPy
- scikit-learn
- Streamlit
The project is based on the MNIST dataset of handwritten digits, which includes 70,000 images of size 28x28 pixels. The k-NN algorithm is used to train a model on the dataset and predict the digit labels. The app uses a Streamlit interface to allow users to draw a digit on the screen, preprocess the image, and feed it to the k-NN model to get a prediction.
The app includes the following features:
- Interactive drawing canvas to draw digits with the mouse or touchpad
- Preprocessing of the image to normalize the pixel values and center the digit
- Prediction of the digit label using the k-NN model
- Display of the predicted digit label and its probability score
To use the app, you can follow these steps:
- Clone the GitHub repository to your local machine.
- Install the required Python packages using
pip install -r requirements.txt
. - Run the app using
streamlit run app.py
. - Draw a digit on the canvas using the mouse or touchpad.
- Click the "Predict" button to get the predicted digit label and its probability score.
Some possible improvements for the app include:
- Using a more complex machine learning model to improve accuracy
- Adding support for recognizing multiple digits in the same image
- Deploying the app to a web server for online access
- Adding more features to the user interface, such as color selection and brush size control
Link to the GitHub repository for this project: Digits-Recognition-App-kNN-Streamlit
Feel free to reach out to me if you're interested in collaborating on a project or have any questions about my work!