> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rebase.energy/llms.txt
> Use this file to discover all available pages before exploring further.

# How to get historical forecasts

> Get archived past forecasts for a site

## What are historical forecasts

When a forecast is generated it is stored in a data base and can be retrieved at a later time. The issue/update time of the forecast is also stored.
Therefore, it is possible to do ex-post forecast error analysis when the actual generation or demand data become available.

## How to query historical forecasts

To query historical forecasts you will need to provide the following requests parameters.

**Start date** `start_date`
<br /> Specify the starting target period of the forecast.
<br /> Example: `"2024-10-18 00:00"`

**End date** `end_date`
<br /> Specify the ending target period of the forecast.
<br /> Example: `"2024-10-18 23:00"`

**Reference time** `as_of`
<br /> Specify the reference time. The API will return the most recent forecasts which were available at the reference time and cover the period between `start_date` and `end_date`.
If not provided, then by default the request time is considered as reference time.
<br /> Example: `"2024-10-17 12:00"`

**Time zone** `tz`
<br /> Specify the time zone. The default time zone is `UTC`.
<br /> Example: `"CET"`

In the example below we want to query the forecasts for solar site with ID `a923653c-26f1-1b29-955d-ffde5d182276` for the period between `2024-06-28 00:00` and `2024-06-28 01:00` which
were available at 11:00 in the morning the previous day. All times are in UTC.

```python Get historical forecast theme={null}
import requests

api_key = "Your API key" # Set your API key
site_id = "a923653c-26f1-1b29-955d-ffde5d182276" # Set the site ID
start_date = "2024-06-28 00:00" # Set the start date
end_date = "2024-06-28 01:00" # Set the end date
as_of = "2024-06-27 11:00" # Set the reference time


url = f"https://api.rebase.energy/platform/v2/sites/{site_id}/forecast"
headers = {"Authorization": api_key, "Content-Type": "application/json"}
params={
	'start_date': start_date,
	'end_date': end_date,
	'as_of': as_of
}

response = requests.get(url, headers=headers, params=params)
response.raise_for_status()
response = response.json()
```

```python Response example theme={null}
{
    "valid_time": [
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:15:00Z",
        "2024-06-28T00:30:00Z",
        "2024-06-28T00:45:00Z",
        "2024-06-28T01:00:00Z"
    ],
    "forecast": [
        0.0,
        0.0,
        0.0,
        0.0,
        0.0
    ],
    "model_name": [
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical"
    ],
    "model_version": [
        1,
        1,
        1,
        1,
        1
    ],
    "update_time": [
        "2024-06-27T06:00:00Z",
        "2024-06-27T06:00:00Z",
        "2024-06-27T06:00:00Z",
        "2024-06-27T06:00:00Z",
        "2024-06-27T06:00:00Z"
    ]
}
```

The response is a serialized table with the following columns:
<br /> `valid_time`: It contains the target times, i.e. the periods which are forecasted.
<br /> `forecast`: It contains the forecast values.
<br /> `model_name`: It contains the names of the models which create the forecasts.
<br /> `model_version`: It contains the versions of the models which create the forecasts.
<br /> `update_time`: It contains the issue/update time, i.e. the time when the forecasts were updated.

As it can be seen from the response, the update time for the specific forecasts is `2024-06-27 06:00` UTC.
This is the latest available forecast for the specific target periods issued before `2024-06-27 11:00` UTC.

If the reference time is omitted, the request time is considered as reference time.
In this case the API returns the most recent forecast update which was issued at `2024-06-28 00:00` UTC.

```python Response example theme={null}
{
    "valid_time": [
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:15:00Z",
        "2024-06-28T00:30:00Z",
        "2024-06-28T00:45:00Z",
        "2024-06-28T01:00:00Z"
    ],
    "forecast": [
        0.0,
        0.0,
        0.0,
        0.0,
        0.0
    ],
    "model_name": [
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical",
        "Solar_MetOfficeGlobalHiRes_Physical"
    ],
    "model_version": [
        1,
        1,
        1,
        1,
        1
    ],
    "update_time": [
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:00:00Z",
        "2024-06-28T00:00:00Z"
    ]
}
```

## How to query the update times

To query the update times you need to provide the ID of the site.
The API will return all the update times of the forecasts that were generated for the specific site.

```python Get update times theme={null}
import requests

api_key = "Your API key" # Set your API key
site_id = "a923653c-26f1-1b29-955d-ffde5d182276" # Set the site ID

url = f"https://api.rebase.energy/platform/v2/sites/{site_id}/forecast/updates"
headers = {"Authorization": api_key, "Content-Type": "application/json"}

response = requests.get(url, headers=headers)
response.raise_for_status()
response = response.json()
```

```python Response example theme={null}
['2024-06-27T00:00:00Z',
 '2024-06-27T06:00:00Z',
 '2024-06-27T12:00:00Z',
 '2024-06-27T18:00:00Z',
 '2024-06-28T00:00:00Z',
 '2024-06-28T06:00:00Z',
 '2024-06-28T12:00:00Z',
 '2024-06-28T18:00:00Z',
 '2024-06-29T00:00:00Z',
 '2024-06-29T06:00:00Z',
 '2024-06-29T12:00:00Z']
```