Issue with AutoTS, no parameter "transformers_params"

[ksetdekov]

🐛 Bug

When installing in a fresh venv, version from pip does not support transformers_params argument in lightautoml.addons.autots.base.AutoTS

To Reproduce

Steps to reproduce the behavior:

1. get python Python 3.8.10 (v3.8.10:3d8993a744, May 3 2021, 08:55:58)
2. install lightautoml==0.3.7.3

pip install lightautoml

3. get code from master/examples/demo13.py
4. try to run

import numpy as np
import pandas as pd

from sklearn.metrics import mean_absolute_error

from lightautoml.addons.autots.base import AutoTS
from lightautoml.tasks import Task


np.random.seed(42)

data = pd.read_csv("data/ai92_value_77.csv")
horizon = 30

train = data[:-horizon]
test = data[-horizon:]

roles = {"target": "value", "datetime": "date"}

seq_params = {
    "seq0": {
        "case": "next_values",
        "params": {"n_target": horizon, "history": np.maximum(7, horizon), "step": 1, "test_last": True},
    },
}

# True (then set default values) / False; int, list or np.array
# default: lag_features=30, diff_features=7
transformers_params = {
    "lag_features": [0, 1, 2, 3, 5, 10],
    "lag_time_features": [0, 1, 2],
    "diff_features": [0, 1, 3, 4],
}

task = Task("multi:reg", greater_is_better=False, metric="mae", loss="mae")

automl = AutoTS(
    task,
    seq_params=seq_params,
    trend_params={
        "trend": False,
    },
    transformers_params=transformers_params,
)
train_pred, _ = automl.fit_predict(train, roles, verbose=4)
forecast, _ = automl.predict(train)

print("Check scores...")
print("TEST score: {}".format(mean_absolute_error(test[roles["target"]].values, forecast.data)))

5. get error:

multi:reg isn`t supported in lgb
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[4], line 20
     12 transformers_params = {
     13     "lag_features": [0, 1, 2, 3, 5, 10],
     14     "lag_time_features": [0, 1, 2],
     15     "diff_features": [0, 1, 3, 4],
     16 }
     18 task = Task("multi:reg", greater_is_better=False, metric="mae", loss="mae")
---> 20 automl = AutoTS(
     21     task,
     22     seq_params=seq_params,
     23     trend_params={
     24         "trend": False,
     25     },
     26     transformers_params=transformers_params,
     27 )
     28 train_pred, _ = automl.fit_predict(train, roles, verbose=4)
     29 forecast, _ = automl.predict(train)

TypeError: __init__() got an unexpected keyword argument 'transformers_params'

Expected behavior

• code runs
• get TEST score print at the end

Additional context

• Running with jupyter notebook
• OS: macOS Ventura 13.2

[elineii]

Hi @ksetdekov,

This error occurs because the corresponding functionality is present in the version from the master branch available on github, but not in the latest release on pypi. The bug will be fixed after a fresh release.

Alina