dotnet / dotnet/machinelearning-modelbuilder

Forecast Prediction Data Is Different From Graph Data

Open
#2,119 1 comment 0 reactions 1 assignee Claimed by @LittleLittleCloud View on GitHub
Reported by: Customer Stale
Dominant language
Dockerfile
Stars
285
Forks
66
PR merge metrics
No merged PRs in 30d

Description

**System Information (please complete the following information):**
- Model Builder Version (available in Manage Extensions dialog): 16.13.1.2210302
- Visual Studio Version: 2022 (17.1.6)

**Describe the bug**
- On which step of the process did you run into an issue: Forecasting Prediction generates different table and graph
- Clear description of the problem:

The data inside the table is different from the data on the graph

here is the table data
starting from this (from row 1)
![1](https://user-images.githubusercontent.com/8480565/168205232-1b5c53a8-0e6a-4e1f-a32b-55997d59f99b.png)

ends here (row 100)
![2](https://user-images.githubusercontent.com/8480565/168205448-c8d4081a-4e07-4e79-ab2b-1e1ca55a1ef1.png)

and this is the graph
(its weird because it ends at row 98 not 100)
![3](https://user-images.githubusercontent.com/8480565/168205284-2fe01686-e636-4a86-ae4e-1ab9b640f726.png)

The last "Open" value was suppose to be 9310.237, but in the graph it was 6969

**To Reproduce**
Steps to reproduce the behavior:
1. Train the model
2. Evaluate the model

**Expected behavior**
I expect the data in the table match with the data from the graph. I do not know which prediction is the correct one. Is it the table data or the graph data, because both represents different outcome.

**Screenshots**
Screenshots are at the links above

**Additional context**
Here is my data for training
[stocks.csv](https://github.com/dotnet/machinelearning-modelbuilder/files/8683898/stocks.csv)

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.