ml_pipeline_1.py

# importing required libraries
import pandas as pd
from sklearn.compose import ColumnTransformer 
from sklearn.impute import SimpleImputer
import category_encoders as ce
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline

# read the training data set
data = pd.read_csv('dataset/train_kOBLwZA.csv')

# top rows of the data
data.head()

# seperate the independent and target variables
train_x = data.drop(columns=['Item_Outlet_Sales'])
train_y = data['Item_Outlet_Sales']