2_MLR.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed May  6 17:26:13 2020

@author: narsingrao
"""

import os
os.chdir('/Users/narsingrao/Documents/Satish_ML/Machine Learning A-Z (Codes and Datasets)/Part 2 - Regression/Section 5 - Multiple Linear Regression/Python'
         )
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

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

print(X)

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

print(X)

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)


from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

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))

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))

from sklearn.metrics import r2_score, confusion_matrix
r2_score = r2_score(y_test, y_pred)