This is Ordinary least squares Linear Regression from sklearn.linear_module.
Syntax :
sklearn.linear_model.LinearRegression(fit_intercept=True, normalize=False, copy_X=True, n_jobs=1):
Parameters :
fit_intercept : [boolean, Default is True] Whether to calculate intercept for the model.
normalize : [boolean, Default is False] Normalisation before regression.
copy_X : [boolean, Default is True] If true, make a copy of X else overwritten.
n_jobs : [int, Default is 1] If -1 all CPU’s are used. This will speedup the working for large datasets to process.
In the given dataset, R&D Spend, Administration Cost and Marketing Spend of 50 Companies are given along with the profit earned. The target is to prepare ML model which can predict the profit value of a company if the value of its R&D Spend, Administration Cost and Marketing Spend are given.
To download dataset click here.
Code: Use of Linear Regression to predict the Companies Profit
# Importing the libraries import numpy as np import pandas as pd # Importing the dataset print ("Dataset.head() \n ", dataset.head()) # Input values x = dataset.iloc[:, :-1].values print("\nFirst 10 Input Values : \n", x[0:10, :]) |
print ("Dataset Info : \n") print (dataset.info()) |
# Input values x = dataset.iloc[:, :-1].values print("\nFirst 10 Input Values : \n", x[0:10, :]) # Output values y = dataset.iloc[:, 3].values y1 = y y1 = y1.reshape(-1, 1) print("\n\nFirst 10 Output true value : \n", y1[0:10, :]) |
# Dividing input and output data to train and test data # Training : Testing = 80 : 20 from sklearn.cross_validation import train_test_split xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size = 0.2, random_state = 0) # Feature Scaling # Multilinear regression takes care of Feature Scaling # So we need not do it manually # Fitting Multi Linear regression model to training model from sklearn.linear_model import LinearRegression regressor = LinearRegression() regressor.fit(xtrain, ytrain) # predicting the test set results y_pred = regressor.predict(xtest) y_pred1 = y_pred y_pred1 = y_pred1.reshape(-1,1) print("\n RESULT OF LINEAR REGRESSION PREDICTION : ") print ("\nFirst 10 Predicted value : \n", y_pred1[0:10, :]) |
