Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 23 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -107,9 +107,9 @@ TimeCopilot is available on PyPI as [`timecopilot`](https://pypi.org/project/tim

and that's it!

!!! Important
- TimeCopilot requires Python 3.10+. Additionally, it currently does not support macOS running on Intel processors (x86_64). If you’re using this setup, you may encounter installation issues with some dependencies like PyTorch. If you need support for this architecture, please create a new issue.
- If on Windows, Python 3.10 is recommended due to some of the packages' current architecture.
**Important !!!**
- TimeCopilot requires Python 3.10+. Additionally, it currently does not support macOS running on Intel processors (x86_64). If you’re using this setup, you may encounter installation issues with some dependencies like PyTorch. If you need support for this architecture, please create a new issue.
- If on Windows, Python 3.10 is recommended due to some of the packages' current architecture.
Comment on lines +110 to +112
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah, this line will break in our docs at timecopilot.dev since we’re using mkdocs-material admonitions. i think we can skip this change from this pr and handle it separately if needed :)

image



---
Expand All @@ -122,6 +122,9 @@ Here is an example to test TimeCopilot:
import pandas as pd
from timecopilot import TimeCopilot

# Use the following line if using a jupyter notebook environment!!!!
nest_asyncio.apply()

Comment on lines +125 to +127
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

very cool!

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess we need import nest_asyncio too

# Load the dataset
# The DataFrame must include at least the following columns:
# - unique_id: Unique identifier for each time series (string)
Expand Down Expand Up @@ -159,6 +162,23 @@ result = tc.forecast(df=df, freq="MS")
# - forecast_analysis: Interpretation of the forecast results
# - user_query_response: Response to the user prompt, if any
print(result.output)

# You can also access the forecast results in the same shape of the
# provided input dataframe.
print(result.fcst_df)

"""
unique_id ds Theta
0 AirPassengers 1961-01-01 440.969208
1 AirPassengers 1961-02-01 429.249237
2 AirPassengers 1961-03-01 490.693176
...
21 AirPassengers 1962-10-01 472.164032
22 AirPassengers 1962-11-01 411.458160
23 AirPassengers 1962-12-01 462.795227
"""

```
```
<details> <summary>Click to expand the full forecast output</summary>

Expand Down
Loading