Welcome to Kim's Neural Network Challenge #1

where we use Standard Scaler, TensorFlow, and Sklearn for deep learning with neural networks.

Overview

Showcasing Python, Pandas, Sklearn, and Tensor Flow, the challenge gathers information about student loan risks. It separates the data in train and test and scales the data. It creates a Sequential model with two hidden layers and one output layer and compiles the data using binary_crossentropy loss function, adam optimizer, and the accuracy evaluation metric. The model is then evaluated, saved as keras file, and reloaded. The reloaded model is used to make predictions and a classification report is printed.

Program

└───root
    │   README.md
    │   student_loans_with_deep_learning.ipynb
    └───student_loans.keras

Step 1:

Navigate to the "student_loans_with_deep_learning.ipynb" file in GitHub repo. The output for each panel can be viewed in the "Preview" panel.

Alternatively,

Step 1:

Clone the repository.

Step 2:

Go to Google Colab

Step 3:

File upload

Step 4:

Select "student_loans_with_deep_learning.ipynb".

Step 5:

Under "Runtime", select "Run All".

Step 6:

Review output panels.

Resources

The data was supplied as starter code y ASU edX Boot Camps, LLC.

The data is located at https://static.bc-edx.com/ai/ail-v-1-0/m18/lms/datasets/student-loans.csv