In this case, we've implemented the auto ARIMA algorithm on this time-series based dataset to predict the possible value of energy a given number of steps ahead.
The link to the Google colab code is:
https://colab.research.google.com/drive/10LjiCJJ4aNEpLjh6xaT9JYfhowCL-Q8o?usp=sharing
This model has been pickled followed by deployment using Flask.
The source files for the deployment have been made available here as well.
This has three major parts :
-
model.py - This contains code for our Machine Learning model to predict wind speed based on data in 'TexasTurbine.csv' file.
-
app.py - This contains Flask APIs that receives the no. of steps(hours) through GUI or API calls, computes the precited value based on our model and returns it.
-
template - This folder contains the HTML template (index.html) to allow user to no. of steps(hours) detail and displays the predicted wind speed.
Use the package manager pip to install flask.
pip install flask- Ensure that you are in the project home directory. Create the machine learning model by running below command from
command prompt -
python model.py- This would create a serialized version of our model into a file model.pkl
- Run app.py using below command to start Flask API
python app.py- Navigate to URL and you should be able to view the homepage.
