Skip to content

Commit 14b3a3a

Browse files
Merge pull request #1667 from msakande/patch-4
Fix error in forecast API request & schema for TimeGEN-1
2 parents 692cf46 + cd07969 commit 14b3a3a

File tree

1 file changed

+3
-4
lines changed

1 file changed

+3
-4
lines changed

articles/ai-studio/how-to/deploy-models-timegen-1.md

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -134,12 +134,12 @@ For more information about use of the APIs, visit the [reference](#reference-for
134134

135135
#### Forecast API
136136

137-
Use the method `POST` to send the request to the `/forecast_multi_series` route:
137+
Use the method `POST` to send the request to the `/forecast` route:
138138

139139
__Request__
140140

141141
```rest
142-
POST /forecast_multi_series HTTP/1.1
142+
POST /forecast HTTP/1.1
143143
Host: <DEPLOYMENT_URI>
144144
Authorization: Bearer <TOKEN>
145145
Content-type: application/json
@@ -151,8 +151,7 @@ The Payload JSON formatted string contains these parameters:
151151

152152
| Key | Type | Default | Description |
153153
|-----|-----|-----|-----|
154-
| **DataFrame (`df`)** | `DataFrame` | No default. This value must be specified. | The DataFrame on which the function operates. Expected to contain at least these columns:<br><br>`time_col`: Column name in `df` that contains the time indices of the time series. This column is typically a datetime column with regular intervals - for example, hourly, daily, monthly data points.<br><br>`target_col`: Column name in `df` that contains the target variable of the time series, in other words, the variable we wish to predict or analyze.<br><br>Additionally, you can pass multiple time series (stacked in the dataframe) considering another column:<br><br>`id_col`: Column name in `df` that identifies unique time series. Each unique value in this column corresponds to a unique time series.|
155-
| **Forecast Horizon (`h`)** | `int` | No default. This value must be specified. | Forecast horizon |
154+
| **Forecast Horizon (`fh`)** | `int` | No default. This value must be specified. | Forecast horizon |
156155
| **Frequency (`freq`)** | `str` | None |Frequency of the data. By default, the frequency is inferred automatically. For more information, visit [pandas available frequencies](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases). |
157156
| **Identifying Column (`id_col`)** | `str` | `unique_id` | Column that identifies each series.|
158157
|**Time Column (`time_col`)**| `str` |`ds` | Column that identifies each timestep; its values can be timestamps or integers. |

0 commit comments

Comments
 (0)