OriaGr

#Written by Oria Gruber
#Related blog post - https://oriamathematics.wordpress.com/2016/08/04/intro-to-machine-learning-linear-regression/
import numpy as np
import matplotlib.pyplot as plt

#Code for blog post regarding Linear Regression

def predict(X, W):
    return np.dot(X, W)

OriaGr

#blog post - https://oriamathematics.wordpress.com/2016/08/06/machine-learning-multiple-and-multivariate-linear-regression/
import numpy as np
import numpy.matlib
import matplotlib.pyplot as plt

#Code for blog post regarding Linear Regression

def Rsquared(X, Y, W):
    m = Y.shape[0]
    SSres = cost(X, Y, W)

OriaGr

#Data used for this code is https://github.com/OriaGr/Blog-posts trXnew and trYnew
#Blog Post - https://oriamathematics.wordpress.com/2016/08/08/linear-regression-finale-multivariate-lr-with-real-example/
import numpy as np
import numpy.matlib
import matplotlib.pyplot as plt

def predict(X, W):
    return np.dot(X, W)

def gradient(X, Y, W, regTerm=0):

OriaGr

#blog post https://oriamathematics.wordpress.com/2016/08/12/binary-classification-with-logistic-regression/
import numpy as np
import matplotlib.pyplot as plt

def predict(X, W):
    return 1/(1+np.exp(-np.dot(X, W)))

def logLikelihood(X, Y, W):
    m = X.shape[0]
    predictions = predict(X, W)

OriaGr

#related blog post - https://oriamathematics.wordpress.com/2016/08/21/multivariate-logistic-regression-with-example-mnist/
import numpy as np
import matplotlib.pyplot as plt

def predictProbabilities(X,W):
    return np.exp(np.dot(X, W))/np.sum(np.exp(np.dot(X, W)), axis=1)[:, None]#sum by columns

def logLikelihood(X, Y, W):
    probabilities = predictProbabilities(X, W)
    probsOfActualLabels = np.sum(Y * probabilities, axis=1) #Element-wise multiplication, sum by columns