A template to process data for machine learning models

data_preprocessing_template.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

# Importing the dataset
data = pd.read_csv('Data.csv')

# Separate independent and dependent variables
X = data.iloc[:, :-1].values
y = data.iloc[:, 3].values

# Splitting dataset into training set and test set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=0)

"""# Feature scaling
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)"""