Welcome back to Obviously AI university.

In our last video, we explained how to prepare your data for TimeSeries analysis.

In this video, we’ll walk through how to upload a CSV dataset to Obviously AI.  

CSV files allow data to be saved in a tabular format. They are one of the most widely used data formats for machine learning and data analysis. And now that our data is machine learning-ready, we can begin uploading it to Obviously AI.  we

Lets review how to do that:

• To add a new CSV file, we’ll simply click on the Add Dataset button, click upload a CSV, and select the file we wish to upload.
• Once uploaded, we can add a display name. Next we check the requirements and confirm they’re met. We’ll need to define if we’d  like to use this dataset for simple AutoML predictions or for TimeSeries. Once that’s done, we can hit upload.
• Once uploaded, we get a chance to review everything before we start making predictions. You’ll get a list of all the columns in the dataset and whether that column is fit for prediction or not. We can also see how many empty values that column has and we have the option to change the column type.
• Once we’re satisfied, we simply hit continue, and that’s it! 

We’ve successfully uploaded our CSV file with all our data and, just like that, we’re ready to start making predictions. All it took was a few clicks!

For further videos and educational content subscribe to our YouTube channel today to check out our Obviously AI University course and learn more about how you can leverage no-code AI to transform your business.

If you’d like to see Obviously AI in action, book a demo on obviously.ai/demo.

Welcome back to Obviously AI university.

In our last video, we cleaned up our dataset for making a AutoML predictions with Obviously AI

In this video, we are going to look at the data prep requirements for making TimeSeries predictions.

This is the first step in the model-building process. It’s also the most important step. That’s because high-quality, machine learning-ready datasets will ensure we get the most accurate predictions. Once complete, everything from model building, hyperparameter tuning and deployment, and training the AI model is automatically handled by Obviously AI. 

We only need two columns to get started with our TimeSeries model. The first is the date column and the second is the prediction column.

So let’s dive in:

1. First let’s look at our date column.
2. A date column can be structured in varying levels. For example, it could be daily, weekly, monthly, or even quarterly. 
3. This means that each value in the dataset is recorded at that date.
4. When setting up the date column, we recommend using the YYYY-MM-DD with hyphens, or YYYY/MM/DD dashes. This ensures that the machine reads the dates correctly. 
5. That’s it, that’s all you’ll need to do to ensure the date column is prepared.
6. Next, let’s look at the prediction column.
7. A Prediction column for TimeSeries contains the historical value of something we want to predict in the future, recorded at regular intervals. This kind of data can be sales, demand, volume, or price.
8. The prediction column for time series always has to be a number. This could be whole numbers, decimals, or negative values.
9. Make sure there are no units to the numbers. For instance, we should just see“10” in the revenue column, not  “10 USD” or “$10.”
10. If you’re in need of a reference, you’ll find a sample dataset here and a checklist for preparing datasets here.

Okay! We’ve covered a lot, so let’s do a quick recap of what we learned so far. 

In this video, we learned how to prepare our data for TimeSeries. While the process isn’t as long as AutoML, it’s important to spend time getting it machine-learning ready. This ensures we’re going to have the most accurate predictions possible. And remember what we said in our previous video: our world class dedicated Data Science team comes with your Obviously AI account. They will take care of data prep to help you focus on making better business decisions.

For further videos and educational content subscribe to our YouTube channel today and check out our comprehensive Obviously AI University course and learn more about how you can leverage no-code AI to transform your business.

If you’d like to see Obviously AI in action, book a demo on obviously.ai/demo.