WEBVTT

00:00:00.000 --> 00:00:00.100
Hi!

00:00:01.480 --> 00:00:05.300
For preparing time series data, I use the CHECK-IN in future.

00:05.740 --> 00:00:09.080
The CHECK-IN requires that the data is in a single file.

00:00:09.560 --> 00:00:15.300
If your raw data is still in multiple tables, you'll need to format the files correctly.

00:00:15.700 --> 00:00:24.200
In this video, I'll show you how to easily and conveniently transform your data into the right format using two prepared tools.

00:00:25.290 --> 00:00:29.020
For this, we provide a prompt template and a Jupyter Notebook.

00:00:29.640 --> 00:00:32.100
I'll show you the easiest way to use them right now.

00:00:32.760 --> 00:00:39.220
I'll start with an AI chatbot like ChatGPT, Gemini, or an internal company chatbot.

00:00:39.860 --> 00:00:42.100
For this video, I'll be using Gemini.

00:00:43.400 --> 00:00:54.280
You don't have to give the chatbot all of your data. Instead, it will ask you for the necessary information about your data's structure, like file and column names, in a dialogue.

00:00:55.440 --> 00:01:04.140
Here, you should make sure that these names don't contain any confidential information, unless you're using a system that is specifically approved for it.

00:01:05.300 --> 00:01:06.400
This is what it looks like.

00:01:06.760 --> 00:01:10.220
You copy and paste the prepared template into the chatbot.

00:01:11.940 --> 00:01:13.620
Then it starts asking questions.

00:01:14.840 --> 00:01:17.380
First, it asks you for the names of your files.

00:01:17.840 --> 00:01:20.820
It's best to just copy and paste the file path directly.

00:01:21.240 --> 00:01:23.420
I'll call the first file ORDR for now.

00:01:23.920 --> 00:01:26.080
Then I'll add the second file as well.

00:01:27.600 --> 00:01:33.080
The chatbot briefly confirms what it understood, and that's the great advantage of this interview approach.

00:01:33.520 --> 00:01:37.760
If anything is unclear, the chatbot can ask for clarification, and you can respond.

00:01:39.160 --> 00:01:44.380
And vice versa, if you're not sure what the chatbot wants to know, you can also ask.

00:01:46.000 --> 00:01:49.060
I'll switch to a chat where I've already gone through all the steps.

00:01:50.300 --> 00:01:55.020
So, after we've answered all the questions here, the chatbot creates a complete Python script.

00:01:56.220 --> 00:02:00.740
It also gives us some tips on how to use it and explains what it did in the background.

00:02:01.360 --> 00:02:05.280
You can simply copy this code block after you've reviewed it.

00:02:06.060 --> 00:02:10.240
This brings us to tool number 2, our specially created notebook.

00:02:11.280 --> 00:02:16.740
Here, you paste the code snippet, click the run symbol, and get immediate feedback.

00:02:18.880 --> 00:02:20.780
In our case, everything worked right away.

00:02:23.640 --> 00:02:26.740
The result is a single, prepared file.

00:02:27.500 --> 00:02:30.000
With that, we can start forecasting right away.

00:02:31.320 --> 00:02:35.420
We'll show you how to create the forecasts in another linked video.

00:02:35.720 --> 00:02:40.000
Or you can grab another notebook that best suits your case.

00:02:40.540 --> 00:02:47.240
For getting started, for example, the Getting Started notebook or one of the use case templates for sales or demand forecasts.

00:02:49.220 --> 00:02:53.000
One more thing for those who prefer to fill out the template with the information directly:

00:02:53.140 --> 00:02:57.260
You can find the template in the Notebooks folder, under Prompt-Templates.

00:02:58.040 --> 00:03:01.920
It's basically a text template that explains the chatbot's task.

00:03:02.860 --> 00:03:09.800
Instead of doing the interview, you could also manually fill this template with your information and send it directly to the chatbot.

00:03:10.060 --> 00:03:15.320
However, we find the interview approach more intuitive, and it has worked very well for us.

00:03:15.880 --> 00:03:17.700
That's why we wanted to share it with you.

00:03:18.480 --> 00:03:19.720
We look forward to your feedback.

00:03:21.040 --> 00:03:26.660
If you have any questions, you can always contact us at support@future-forecasting.de.

00:03:27.080 --> 00:03:28.460
Happy forecasting!