My First Machine Learning Model. Simple Linear Regression Model to predict the profit of companies.

Importing necessary libraries

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline        

data = pd.read_csv('1000_Companies.csv')
data        

Spitting Data into dependent and independent variables

X = data[['R&D Spend', 'Administration', 'Marketing Spend', 'State']]
X        

y = data['Profit']
y        

We have some text data in our dataset which is the "State" column. Machine Learning models cannot understand text data so we will have to convert this text data to numerical data.?

X['State'].unique()        

X = pd.get_dummies(X, columns = ['State'])
X        

Model Building Using train test split from sickit learn?

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)        

We want to predict profit which is a continuous variable so we will have to use linear regression.

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

Prediction

y_predict = reg.predict(X_test)
y_predict        

Model Evaluation using R-Squared Value

from sklearn.metrics import r2_score
r2_score(y_test, y_predict)        

Model evaluation score is 0.91 which means our model will predict profit up to 91% accuracy.