multiple_regression.py

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn import datasets


dataset = pd.read_csv('50_Startups.csv')
x = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values


# encoding
ct = ColumnTransformer(
    transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')
x = np.array(ct.fit_transform(x))

# splitting of the 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)

# training
regressor = LinearRegression()
regressor.fit(x_train, y_train)

# predicting the test set result
y_pred = regressor.predict(x_test)
np.set_printoptions(precision=2)
print(np.concatenate((y_pred.reshape(len(y_pred), 1), y_test.reshape(len(y_test), 1)), 1))