Forecast + Optimization

• Regression to find optimal values of 'X' values
• Add a constraint to make it an optimization problem
• Optimization with minimum expense for each track

	#https://raw.githubusercontent.com/justmarkham/scikit-learn-videos/master/data/Advertising.csv
	#https://github.com/georgeblu1/Data-Projects/blob/master/Budget%20Optimization.ipynb
	import pandas as pd
	data = pd.read_csv(r'https://raw.githubusercontent.com/justmarkham/scikit-learn-videos/master/data/Advertising.csv')
	data.head()
	import pandas as pd
	import numpy as np
	import seaborn as sns
	import matplotlib.pyplot as plt
	import math
	import statsmodels.api as sm
	import statsmodels.formula.api as smf
	from statsmodels.tools.eval_measures import rmse
	from sklearn import metrics
	from sklearn.linear_model import LinearRegression
	from sklearn.linear_model import LogisticRegression
	from sklearn.model_selection import train_test_split
	#There should be a linear relationship between target and features. We can use scatterplot to visualize and validate for us.
	sns.pairplot(data, x_vars=['TV','Radio','Newspaper'], y_vars='Sales', size = 4, aspect = 1)
	#Little or no multicollinearity between features
	sns.pairplot(data[['TV','Radio','Newspaper']])
	#Homoscedasticity
	#OLS assumes all residuals drawn from population has constant variance
	sns.residplot(x = data['TV'], y = data["Sales"])
	feature_cols = ['TV', 'Radio', 'Newspaper']
	X = data[feature_cols]
	y = data[["Sales"]]
	# instantiate and fit
	SkLearn_model = LinearRegression()
	SkLearn_result = SkLearn_model.fit(X, y)
	# print the coefficients
	print(SkLearn_result.intercept_)
	print(SkLearn_result.coef_)
	# include Newspaper
	X = data[['TV', 'Radio', 'Newspaper']]
	y = data.Sales
	# Split data
	X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
	# Instantiate model
	lm2 = LinearRegression()
	# Fit Model
	lm2.fit(X_train, y_train)
	# Predict
	y_pred = lm2.predict(X_test)
	# RMSE
	print(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))
	print(metrics.r2_score(y_test,y_pred))
	coefficient = lm2.coef_
	coefficient
	inter = lm2.intercept_
	inter
	!pip install pulp
	#Our budget should be less than 1000
	from pulp import *
	prob = LpProblem("Ads Sales Problem", LpMaximize)
	#x - tv
	#y - radio
	#z - newpaper
	x = LpVariable("x", 0, 200)
	y = LpVariable("y", 0, 500)
	z = LpVariable("z", 0, 500)
	prob += x + y + z <= 1000
	prob += 0.0548*x + 0.1022*y + 0.0007878*y + 4.6338
	status = prob.solve()
	LpStatus[status]
	print(prob)
	for v in prob.variables():
	print(v.name, "=", v.varValue)
	calculation = 0.0548*200 + 0.1022*500 + 0.0007878*0 + 4.6338
	calculation
	prob = LpProblem("Ads Sales Problem with minium in each track", LpMaximize)
	x = LpVariable("x", 50, 200)
	y = LpVariable("y", 50, 500)
	z = LpVariable("z", 50, 500)
	prob += x + y + z <= 1000
	prob += 0.0548*x + 0.1022*y + 0.0007878*y + 4.6338
	status = prob.solve()
	LpStatus[status]
	print(prob)
	for v in prob.variables():
	print(v.name, "=", v.varValue)
	calculation = 0.0548*200 + 0.1022*500 + 0.0007878*50 + 4.6338
	calculation

view raw forecast_Optimization.py hosted with ❤ by GitHub

Keep Exploring!!!