Method predict uses new_data's first row as model input but associates result date with new_data's last timestamp + 1*freq about mlforecast HOT 5 CLOSED

import pandas as pd

date_range = pd.date_range(start='2020-01-01', end='2021-01-01', freq='W')
df = pd.DataFrame(date_range, columns=['ds'])
df['unique_id'] = 1 
df['X'] = df['ds'].dt.year +  np.random.uniform( low = -1, high = 1, size= df.shape[0])*1000
df['y'] = df['X'] * 0.8 + np.random.rand()

cut_off = 20
train_df = df[:-cut_off]
train_df_X = train_df.loc[:,'X']
train_df_Y = train_df[['ds', 'y', 'unique_id']]
test_df = df[-cut_off:]
test_df_X = test_df.loc[:,['X', 'ds','unique_id']]
test_df_Y = test_df[['ds', 'y', 'unique_id']]
df.head()
from statsforecast import StatsForecast
StatsForecast.plot(df)

import lightgbm as lgb
from window_ops.expanding import expanding_mean
from window_ops.rolling import rolling_mean

from mlforecast import MLForecast
from sklearn.linear_model import LinearRegression

mlf = MLForecast(
    models = [LinearRegression(), lgb.LGBMRegressor()],
    #lags=[1, 12],
    #lag_transforms={
    #    1: [expanding_mean],
    #    12: [(rolling_mean, 48)],
    #},
    freq = 'W', 
    #date_features = ['week', 'month', 'year']
)
def inspect_input(x):
    from IPython.display import display
    print('inspect_input')
    display(x)
    return x
prep_df =mlf.preprocess(train_df, id_col = 'unique_id', time_col = 'ds', target_col = 'y')
mlf.fit(train_df, id_col = 'unique_id', time_col = 'ds', target_col = 'y')
y_hat = mlf.predict(cut_off,  dynamic_dfs = [test_df_X],  before_predict_callback=inspect_input)
 

y_hat= test_df[['ds','unique_id']]
from sklearn.linear_model import Lasso, LinearRegression  
clf = LinearRegression()
clf.fit(train_df.loc[:,['X']], train_df.loc[:, 'y'])
y_hat_val = clf.predict(test_df.loc[:, ['X']])
y_hat['lr'] = y_hat_val


from sklearn.ensemble import GradientBoostingRegressor
clf = GradientBoostingRegressor()
clf.fit(train_df.loc[:,['X']], train_df.loc[:, 'y'])
y_hat_val = clf.predict(test_df.loc[:,['X']])
y_hat['gb'] = y_hat_val

StatsForecast.plot( test_df_Y, y_hat )