Link : 2.Multiple Linear - Google Drive

#importing the Libraies
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Reading the Dataset
dataset = pd.read_csv('50_Startups.csv')

dataset

dataset.columns

dataset=pd.get_dummies(dataset,drop_first=True)

dataset

indep=dataset[['R&D Spend','Administration', 'Marketing Spend','State_Florida', 'State_New York']]
dep=dataset[['Profit']]

indep

dep

#split into training set and test
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(indep, dep, test_size = 1/3, random_state = 0)

X_train

X_train.shape

y_train

y_train.shape

X_test

X_test.shape

y_test

y_test.shape

from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)#y=W*x1+b0 for this equation we got value for b1 and bo

# Viewing the b1 and bo value
weight=regressor.coef_
print("Weight of the model={}".format(weight))
bais=regressor.intercept_
print("Intercept of the model={}".format(bais))

y_pred=regressor.predict(X_test)

#<https://scikit-learn.org/stable/modules/model_evaluation.html>

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

r_score

import pickle

filename="mulline_final.sav"
pickle.dump(regressor,open(filename,"wb"))

model=pickle.load(open(filename,"rb"))

rd_input=float(input("R&D:"))
admin_input=float(input("Admin"))
mark_input=float(input("Marketing "))
fol_input=int(input("State_flo 0 or 1:"))
new_input=int(input("State_new 0 or 1:"))

result=model.predict([[rd_input,admin_input,mark_input,fol_input,new_input]])

result

Dataset