How Python programming can discriminate between linear

This article is mainly to share with you about how Python programming to distinguish the linearity, the need for small partners to look at.

"" "Author:victoriacreated on:2017.9.15 11:45" "" Import pandas as Pdimport NumPy as Npimport matplotlib.pyplot as Pltdef L    DA (X0, X1): "" "Get the optimal params of LDA model given training data. Input:X0:np.array with shape [N1, d] X1:np.array with shape [N2, d] Return:omega:np.array wit h shape [1, d].    Optimal params of LDA. "" "#shape [1, d] mean0 = Np.mean (X0, axis=0, keepdims=true) mean1 = Np.mean (X1, axis=0, keepdims=true) Sw = ( X0-MEAN0). T.dot (X0-mean0) + (X1-MEAN1). T.dot (x1-mean1) Omega = Np.linalg.inv (Sw). dot (mean0-mean1). T) return omegaif __name__== "__main__": #read data from xls Work_book = Pd.read_csv (".. /data/watermelon_3a.csv ", header=none) Positive_data = work_book.values[work_book.values[:,-1] = = 1.0,:] Negative_ data = work_book.values[work_book.values[:,-1] = = 0.0,:] Print (positive_data) #LDA Omega = LDA (negative_data[: , 1:-1], positive_data[:, 1:-1]) #plot Plt.plot (positive_data[:, 1], positive_data[:, 2], "Bo") Plt.plot (negative_data[:, 1], negative_data[:, 2], "r+") lda_left = 0 Lda_right =-(omega[0]*0.9)/omega[1] Plt.plot ([0, 0.9], [Lda_left, Lda_right], ' G ') plt.xlabel (' Density ') plt.ylabel (' s Ugar rate ') plt.title ("LDA") plt.show ()

Related recommendations:

A concise introductory guide to linear discriminant analysis

Linear discriminant Analysis