Contact Form

Use Case

Predictive Machine Learning
Avocado Price Predictions

Summary:

Task: Use Polyture’s AutoML to Make Avocado Price Predictions
Data From: Kaggle
Polyture Version: 0.13.13
Contact: team@polyture.com

Steps Taken:

  • Uploaded the dataset into the data warehouse
  • Ran Data Transform (Remove Unnecessary Columns)
  • Created a Train Test split
  • Utilized an AutoML node to create and avocado price prediction model
  • Deploy the model and use the test data to validate model performance
  • Merged predicted price and time data together with Column Append
  • Created Visualizations and Export the prediction data

Walk-Through:

Upload and Warehousing

The first step is to import  import the historical Avocado pricing data CSV file into the Data Warehouse.

Import Data / Select Data Type

We then grab a CSV data source node from the Import panel, and select the file imported to the warehouse.

In the “Quick Insights” panel, we have to correct the data type of the date column and change it from float to date/time.

Perform Column Filter

Next we use a “Column Filter” node and attach it to the CSV data source.

In the options panel on the bottom right, we select the columns we wish to include in the dataset we will run AutoML on.

Perform Train / Test Data Split

To get a more accurate prediction, we are going to split the data into train and test tables.

We achieve this by connecting a “Train Test Split” node.

In the Settings panel, we select for data randomization, and split percentage.

Send Data to AutoML

We now take the training data from the split node and attach it to three separate “Send to AutoML” nodes.

We then give each node a name within the settings panel.

Create AutoML Experiments | Apply Parameters

Navigate to the main navigation panel on the left hand side, navigate to “AutoML” and select “New Experiment”.

The system will prompt us to give the experiment a name.

We then click “Settings” and select the data source, as well as the predict column. Polyture’s AutoML will automatically detect the AutoML Type (Classification / Regression).

Train the Model

Hit the green “Start” button. Polyture will instantly begin training and testing different models. You can use the AutoML dashboard panels to evaluate the performance of the models.

Deploy the AutoML Node

Drag and connect a “Deploy AutoML Model” node to the Test data from the “Train Test Split”node.

In an example like this, we use the test data in place of production data as a means to quickly validate the performance of the trained model.

Within the settings panel of the “Deploy AutoML Model” node, select the AutoML model that was trained earlier.

Merge Prediction & Time Data

Drag in and connect a “Column Filter” node, and select the date value.

Then, drag in and connect a “Column Append” node, and connect the Avocado price prediction data (from the output of the deployed AutoML model) with the Date/Time column from the test data.

Create the Graph

Drag in and connect a “Dashboard Graph” node.

Click on the Graph Editor button to enter the editor.

For this project, we will select Time Series with the X axis being Date/Time and the Y axis being predicted Avocado Prices.

Resize and Space the Graphs in Dashboard View

For the best view of the created graphs, we open up the “Dashboard” view.

In the Dashboard view, we can resize the graphs to achieve the best possible visual presentation.

Export Predictive Data

Now that we have generated the graphs, we want to export a CSV file of the data.

To do so, we drag in an “Export Data” node and connect it to the “Column Append” node. From the export settings panel, we select CSV and give the file a name.