This device is not compatible.
You will learn to:
Perform various preprocessing steps such as handling missing values and data skewness, scaling, etc.
Perform exploratory data analysis and create meaningful visualizations.
Build simple neural networks with Keras and TensorFlow.
Train and evaluate models using various metrics and visualizations.
Skills
Data Science
Data Visualisation
Deep Learning
Prerequisites
Hands-on experience with Python
Basic understanding of Keras
Basic understanding of deep learning fundamentals
Technologies
Keras
Python
seaborn
TensorFlow
Project Description
In this project, we’ll use the Python Keras library to create neural networks and use them to predict diabetes with patient health data.
We’ll load and analyze the data using pandas, visualize it using matplotlib and seaborn. We’ll perform data cleaning, preprocessing and feature selection, and then split it into training, validation and testing datasets using NumPy. After the data is ready, we will train simple deep learning models using Keras. We will then plot the training curves and perform model evaluation using scikit-learn.
Project Tasks
1
Getting Started
Task 0: Introduction
Task 1: Import the Libraries
Task 2: Load the Dataset
2
Exploratory Data Analysis
Task 3: List the Missing Values and Display Dataset Description
Task 4: Create a Pairplot
3
Preprocessing
Task 5: Handle Zero Values
Task 6: Handle Skewness and Feature Scaling
Task 7: Create Dataset Splits
4
Model Training
Task 8: Create the Model
Task 9: Train the Model
Task 10: Print the Training Curves
5
Performance Evaluation
Task 11: Create a Confusion Matrix
Task 12: Compute the Classification Metrics
Congratulations!