# How should I improve my Vectorized Gradient descent linear regression model?

I wrote a vectorized Gradient descent implementation of the linear regression model. The Dataset looks something like:

It's Not Working properly as I am getting negative R Squared error I don't understand why ?? Should I decrease Alpha or No. of Iterations or is there any problem in my implementation what should I do?

My Regression plot looks something like below I don't know why I am getting such a line.

My Cost Function Error plot with respect to the number of iterations in Gradient descent looks something like below

R Squared Error is: -3.744682246118262

My Code Snippet:

import numpy as np
from sklearn.model_selection import train_test_split
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd

def CostFunction(Theta,DataMatrix):
Size = DataMatrix.shape[0]
Error = 0
for i in range(0,Size):
Feature = np.vstack(([1],np.array(DataMatrix[i][:-1]).reshape(-1,1)))
Error += (np.transpose(Theta).dot(Feature) - DataMatrix[i][-1]) ** 2
return (1/(2*Size))*Error

def GradientDescent(Theta,Alpha,DataMatrix,Iterations):
Progress = []
Iterate = 0
Size = DataMatrix.shape[0]
Error = np.zeros((DataMatrix.shape[1],1))
while(Iterations):
for i in range(0,Size):
Feature = np.vstack(([1],np.array(DataMatrix[i][:-1]).reshape(-1,1)))        #Last Entry is Label Thats Why
Error += (np.transpose(Theta).dot(Feature) - DataMatrix[i][-1])*Feature
Theta -= Alpha*(1/Size)*Error
if(Iterations % 10 == 0):
Progress.append([Iterate,CostFunction(Theta,DataMatrix)])
Iterate += 10
Iterations -= 1
return [Theta,Progress]

def ProgressCurve(Progress):
Progress = [[i[0],i[1].ravel()[0]] for i in Progress]
sns.lineplot(x = np.array(Progress)[:,0],y =  np.array(Progress)[:,1],marker = '*')
plt.show()

def Prediction(Theta,Test):
Predicted = []
for i in range(0,Test.size):
Feature = np.vstack(([1],np.array(Test[i]).reshape(-1,1)))
Predicted.append(np.transpose(Theta).dot(Feature))
return Predicted

def Error_Metric(Actual,Predicted):
Actual = np.array(Actual,dtype = 'float64').reshape(-1,1)
Predicted = np.array(Predicted,dtype = 'float64').reshape(-1,1)
Error = (Actual - Predicted) ** 2
Variance = (Actual - np.mean(Actual)*np.ones((Actual.shape[0],1))) ** 2
return (1 - np.sum(Error)/np.sum(Variance))

def RegressionLine(X,Y,Orig_X,Orig_Y):
Y = [i[0].ravel()[0] for i in Y]
sns.scatterplot(x = Orig_X,y = Orig_Y,color = "blue")
sns.lineplot(x = X,y = Y,color = "red")
plt.show()

X = 2*np.random.rand(1000)
Y = 4 + 3*X + np.random.randn(1000)
X_Train,X_Test,Y_Train,Y_Test = train_test_split(X,Y,test_size = 0.3,random_state = 0)
DataFrame = pd.DataFrame()
DataFrame['X'] = X_Train
DataFrame['Y'] = Y_Train
DataMatrix = DataFrame.as_matrix()
ThetaParams = np.random.randn(2,1)
Theta,Progress = GradientDescent(ThetaParams,0.001,DataMatrix,50)
Prediction_Out = Prediction(Theta,np.array(X_Test))
Error = Error_Metric(Y_Test,Prediction_Out)
ProgressCurve(Progress)
RegressionLine(X_Test,Prediction_Out,X,Y)
print(Error)


## 1 Answer

It seems like number of iterations is very small compare to learning rate. (50 vs 0.001). The optimizer can't converge when we look at the fitted line plot.

Try to increase number of iterations, it will help you. You can check this beautiful work and my another answer about the problem.