ChangePoint detection for not daily data
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 107
- PR merge metrics
- No merged PRs in 30d
Description
My data consists of records taken every 20 seconds, as shown below. However, when I performed change point detection with the following parameters, I was able to detect change points, but as shown in the attached figure, the trend line ended up being straight. I've read through the documentation but haven't been able to resolve this issue. I would appreciate it if you could help me.
data
beh_time | count
2023-01-01 10:01:20 | 50
2023-01-01 10:01:40 | 47
2023-01-01 10:02:00 | 46
2023-01-01 10:02:20 | 48
2023-01-01 10:02:40 | 52
....
parameter
res = model.find_trend_changepoints(
df=df,
time_col="beh_time", # time column name
value_col="count",
actual_changepoint_min_distance=timedelta(seconds=300),
resample_freq=timedelta(seconds=20),
regularization_strength=0.1,)
result
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the reported model.find_trend_changepoints call and its time_col, value_col, resample_freq, and regularization_strength parameters. Review the relevant documentation and reproduce the supplied 20-second data example; done means explaining or correcting why the resulting trend line is straight.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100