02. Data Exploration

Data Exploration Heading

Data Exploration

ND320 C4 L3 02 Data Exploration

Data Exploration Summary

We just went over the dataset we will be using throughout this lesson from PhysioNet. We learned from reading the Experimental Protocol that there is PPG, ECG, 3-channel accelerometer data. And the 8 participants are doing the 4 following activities:

  1. Walking
  2. Jogging
  3. Biking Lower Resistance
  4. Biking Higher Resistance

For this lesson we will be focused on accelerometer data for building our activity classifier.

ND320 C4 L3 03 Plotting

Data Exploration Recap

Summary

The dataset we will be using comes from the Wrist PPG During Exercise dataset on Physionet. Physionet is a great resource for biomedical time-series signals. It has many datasets with various signals in various disease conditions and all the data is available under an open license. The Wrist PPG dataset contains data from 8 subjects. The protocol contained four activities -- walking on a treadmill, running on a treadmill, low-intensity cycling on an exercise bike, and high-intensity cycling. While the dataset contains ECG and PPG signals as well, we will only be using the accelerometer signal for this project.

We explore the summary statistics of this dataset and look at the raw data. Like most real datasets, this one is not perfect. It is unbalanced in terms of numbers of subjects as well as the total number of data points.

Notebook Review

If you wanted to interact with the notebook in the video, you can access it here in the repo /activity-classifier/walkthroughs/data-exploration/ or in the workspace below.

The dataset that will be used throughout this lesson can be found at the top of the lesson directory at /activity-classifier/data/.

Code

If you need a code on the https://github.com/udacity.

Heading

Exercise 1: Data Exploration

Instructions

  1. Complete the Offline or Online instructions below.
  2. Read through the whole .ipynb.
  3. Complete all the code cells that contain ## Your Code Goes Here.

Offline

  1. In the repo which you can access here in the repo /activity-classifier/exercises/1-data-exploration/) you should find the following files:
  • 1_data_exploration.ipynb
  1. The dataset that will be used throughout this lesson can be found at the top of the lesson directory at /activity-classifier/data/.
  2. Open up the python notebook and associated files in your desired editor.

Note: Instructions can be found in Introduction to Wearable Data's Concept Developer Workflow for how to set up your local environment.

Online

  1. Go to the next concept and the 1_data_exploration.ipynb should be open and the workspace should already contain the appropriate data folder.

Next Concept