Portfolio
Codes based on exercises from the Applied Data Science with Python Specialization taught by the University of Michigan
Click here
- Breast Cancer Wisconsin (Diagnostic)
- Mushroom classification
- Credit Card Transactions Fraud Detection
- Blight violations in the city of Detroit
- Spam detection
Create a classifier that can help diagnose patients using the Breast Cancer Wisconsin (Diagnostic) Database.
Train a model to predict whether or not a mushroom is poisonous using the UCI Mushroom Data Set.
Train several models and evaluate how effectively they predict instances of fraud using the Credit Card Transactions Fraud Detection Dataset.
Predict whether a given blight ticket will be paid on time.
Explore text message data and create models to predict if a message is spam or not.
Codes based on exercises from the Data Engineering Foundations Specialization taught by IBM Skills Network
Click here
- Chicago datasets
Analyze real world datasets from the city of Chicago with SQL and Python.
Codes based on exercises from the Data Science Fundamentals with Python and SQL Specialization taught by IBM Skills Network
Click here
- Teaching ratings
Explore teaching ratings for professors with different characteristics and see if there are external influences on the teaching evaluation score.
Codes based on exercises from the Deep Learning Specialization taught by DeepLearning.AI
Click here
- Cat/Non-Cat classifier
- Finger signs
- Alpaca recognition
- Car detection
- Image segmentation
- Face recognition
- Neural style transfer
- Writing like Shakespeare
- Jazz solo
- Emojify
- Neural Machine Translation
- Trigger word detection
Create and compare a deep neural network and convolutional neural network fot cat recognition.
Build a convolutional neural network and train the ResNet50V2 architecture to classify a collection of 6 signs representing numbers from 0 to 5.
Use transfer learning with a pre-trained MobileNetV2 to build an Alpaca/Not Alpaca classifier.
Implement object detection for autonomous driving using the YOLO (You Only Look Once) object detection system.
Build a U-Net (CNN for image segmentation) to predict a label for every pixel in an image from a self-driving dataset.
Build a face recognition system using a pre-trained FaceNet model.
Implement a Neural Style Transfer (NST) model to generate novel artistic images.
Implement a Shakespeare poem generator using Long Short-Term Memory (LSTM) cells.
Train a Long Short-Term Memory (LSTM) network to generate music.
Build a Long Short-Term Memory (LSTM) model that takes word embeddings as input to predict the most appropriate emoji.
Build a Neural Machine Translation (NMT) model to translate human-readable dates into machine-readable dates.
Implement an algorithm for trigger word detection.