import numpy 
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
 
data = pd.read_csv('Folds5x2_pp.csv')
data.head() 

def CostFunction(X,y,theta):
  inner = np.power((X*theta.T)-y,2)
  return np.sum(inner)/(2*len(X))

col = data.shape[1]
X = data.iloc[:,0:col-1]
y = data.iloc[:,col-1:col]
X = np.matrix(X.values)
y = np.matrix(y.values)
theta = np.matrix(np.array([0,0,0,0,0]))
temp = np.matrix(np.zeros(theta.shape))
CostFunction(X,y,theta)

def gradientDescent(X,y,theta,alpha,iters):
  temp = np.matrix(np.zeros(theta.shape))
  parameters = int(theta.ravel().shape[1])
  cost = np.zeros(iters)
  for i in range(iters):
    error = (X*theta.T)-y
    
    for j in range(parameters):
      term = np.multiply(error,X[:,j])
      temp[0,j] = theta[0,j] - (alpha/len(X))*np.sum(term)
      
    theta = temp
    cost[i] = CostFunction(X,y,theta)
    
  return theta,cost

predicted = X*g.T
predicted = predicted.flatten().A[0]
y_f= y.flatten().A[0]
fig, ax = plt.subplots()
ax.scatter(y_f,predicted)
ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax.set_xlabel('Measured')
ax.set_ylabel('Predicted')
plt.show()

from sklearn import linear_model 
model = linear_model.LinearRegression() 
model.fit(X, y)