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

> Compute transformations on exogenous regressors

# Feature engineering

```python theme={null}
import numpy as np
import pandas as pd
from nbdev import show_doc

from mlforecast.lag_transforms import ExpandingMean
from mlforecast.utils import generate_daily_series
```

## Setup

```python theme={null}
rng = np.random.RandomState(0)
series = generate_daily_series(100, equal_ends=True)
starts_ends = series.groupby(
    'unique_id', observed=True, as_index=False
)['ds'].agg(['min', 'max'])
prices = []
for r in starts_ends.itertuples():
    dates = pd.date_range(r.min, r.max + 14 * pd.offsets.Day())
    df = pd.DataFrame({'ds': dates, 'price': rng.rand(dates.size)})
    df['unique_id'] = r.Index
    prices.append(df)
prices = pd.concat(prices)
prices['price2'] = prices['price'] * rng.rand(prices.shape[0])
prices.head()
```

|   | ds         | price    | unique\_id | price2   |
| - | ---------- | -------- | ---------- | -------- |
| 0 | 2000-10-05 | 0.548814 | 0          | 0.345011 |
| 1 | 2000-10-06 | 0.715189 | 0          | 0.445598 |
| 2 | 2000-10-07 | 0.602763 | 0          | 0.165147 |
| 3 | 2000-10-08 | 0.544883 | 0          | 0.041373 |
| 4 | 2000-10-09 | 0.423655 | 0          | 0.391577 |

***

<a href="https://github.com/Nixtla/mlforecast/blob/main/mlforecast/feature_engineering.py#L17" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

## transform\_exog

> ```text theme={null}
>  transform_exog (df:~DFType, lags:Optional[Iterable[int]]=None, lag_transf
>                  orms:Optional[Dict[int,List[Union[Callable,Tuple[Callable
>                  ,Any]]]]]=None, id_col:str='unique_id',
>                  time_col:str='ds', num_threads:int=1)
> ```

*Compute lag features for dynamic exogenous regressors.*

|                 | **Type**   | **Default** | **Details**                                                                     |
| --------------- | ---------- | ----------- | ------------------------------------------------------------------------------- |
| df              | DFType     |             | Dataframe with ids, times and values for the exogenous regressors.              |
| lags            | Optional   | None        | Lags of the target to use as features.                                          |
| lag\_transforms | Optional   | None        | Mapping of target lags to their transformations.                                |
| id\_col         | str        | unique\_id  | Column that identifies each serie.                                              |
| time\_col       | str        | ds          | Column that identifies each timestep, its values can be timestamps or integers. |
| num\_threads    | int        | 1           | Number of threads to use when computing the features.                           |
| **Returns**     | **DFType** |             | **Original DataFrame with the computed features**                               |

```python theme={null}
transformed = transform_exog(
    prices,
    lags=[1, 2],
    lag_transforms={1: [ExpandingMean()]}
)
transformed.head()
```

|   | ds         | price    | unique\_id | price2   | price\_lag1 | price\_lag2 | price\_expanding\_mean\_lag1 | price2\_lag1 | price2\_lag2 | price2\_expanding\_mean\_lag1 |
| - | ---------- | -------- | ---------- | -------- | ----------- | ----------- | ---------------------------- | ------------ | ------------ | ----------------------------- |
| 0 | 2000-10-05 | 0.548814 | 0          | 0.345011 | NaN         | NaN         | NaN                          | NaN          | NaN          | NaN                           |
| 1 | 2000-10-06 | 0.715189 | 0          | 0.445598 | 0.548814    | NaN         | 0.548814                     | 0.345011     | NaN          | 0.345011                      |
| 2 | 2000-10-07 | 0.602763 | 0          | 0.165147 | 0.715189    | 0.548814    | 0.632001                     | 0.445598     | 0.345011     | 0.395304                      |
| 3 | 2000-10-08 | 0.544883 | 0          | 0.041373 | 0.602763    | 0.715189    | 0.622255                     | 0.165147     | 0.445598     | 0.318585                      |
| 4 | 2000-10-09 | 0.423655 | 0          | 0.391577 | 0.544883    | 0.602763    | 0.602912                     | 0.041373     | 0.165147     | 0.249282                      |

```python theme={null}
import polars as pl
```

```python theme={null}
prices_pl = pl.from_pandas(prices)
transformed_pl = transform_exog(
    prices_pl,
    lags=[1, 2],
    lag_transforms={1: [ExpandingMean()]},
    num_threads=2,
)
transformed_pl.head()
```

| ds                  | price    | unique\_id | price2   | price\_lag1 | price\_lag2 | price\_expanding\_mean\_lag1 | price2\_lag1 | price2\_lag2 | price2\_expanding\_mean\_lag1 |
| ------------------- | -------- | ---------- | -------- | ----------- | ----------- | ---------------------------- | ------------ | ------------ | ----------------------------- |
| datetime\[ns]       | f64      | i64        | f64      | f64         | f64         | f64                          | f64          | f64          | f64                           |
| 2000-10-05 00:00:00 | 0.548814 | 0          | 0.345011 | NaN         | NaN         | NaN                          | NaN          | NaN          | NaN                           |
| 2000-10-06 00:00:00 | 0.715189 | 0          | 0.445598 | 0.548814    | NaN         | 0.548814                     | 0.345011     | NaN          | 0.345011                      |
| 2000-10-07 00:00:00 | 0.602763 | 0          | 0.165147 | 0.715189    | 0.548814    | 0.632001                     | 0.445598     | 0.345011     | 0.395304                      |
| 2000-10-08 00:00:00 | 0.544883 | 0          | 0.041373 | 0.602763    | 0.715189    | 0.622255                     | 0.165147     | 0.445598     | 0.318585                      |
| 2000-10-09 00:00:00 | 0.423655 | 0          | 0.391577 | 0.544883    | 0.602763    | 0.602912                     | 0.041373     | 0.165147     | 0.249282                      |