Last active
October 12, 2019 10:05
-
-
Save prajwalsingh/6a84cce16d33f91bd42d178e744e6a2a to your computer and use it in GitHub Desktop.
Logistic Regression From Scratch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| sepal_length | sepal_width | petal_length | petal_width | species | |
|---|---|---|---|---|---|
| 5.1 | 3.5 | 1.4 | 0.2 | 0 | |
| 4.9 | 3 | 1.4 | 0.2 | 0 | |
| 4.7 | 3.2 | 1.3 | 0.2 | 0 | |
| 4.6 | 3.1 | 1.5 | 0.2 | 0 | |
| 5 | 3.6 | 1.4 | 0.2 | 0 | |
| 5.4 | 3.9 | 1.7 | 0.4 | 0 | |
| 4.6 | 3.4 | 1.4 | 0.3 | 0 | |
| 5 | 3.4 | 1.5 | 0.2 | 0 | |
| 4.4 | 2.9 | 1.4 | 0.2 | 0 | |
| 4.9 | 3.1 | 1.5 | 0.1 | 0 | |
| 5.4 | 3.7 | 1.5 | 0.2 | 0 | |
| 4.8 | 3.4 | 1.6 | 0.2 | 0 | |
| 4.8 | 3 | 1.4 | 0.1 | 0 | |
| 4.3 | 3 | 1.1 | 0.1 | 0 | |
| 5.8 | 4 | 1.2 | 0.2 | 0 | |
| 5.7 | 4.4 | 1.5 | 0.4 | 0 | |
| 5.4 | 3.9 | 1.3 | 0.4 | 0 | |
| 5.1 | 3.5 | 1.4 | 0.3 | 0 | |
| 5.7 | 3.8 | 1.7 | 0.3 | 0 | |
| 5.1 | 3.8 | 1.5 | 0.3 | 0 | |
| 5.4 | 3.4 | 1.7 | 0.2 | 0 | |
| 5.1 | 3.7 | 1.5 | 0.4 | 0 | |
| 4.6 | 3.6 | 1 | 0.2 | 0 | |
| 5.1 | 3.3 | 1.7 | 0.5 | 0 | |
| 4.8 | 3.4 | 1.9 | 0.2 | 0 | |
| 5 | 3 | 1.6 | 0.2 | 0 | |
| 5 | 3.4 | 1.6 | 0.4 | 0 | |
| 5.2 | 3.5 | 1.5 | 0.2 | 0 | |
| 5.2 | 3.4 | 1.4 | 0.2 | 0 | |
| 4.7 | 3.2 | 1.6 | 0.2 | 0 | |
| 4.8 | 3.1 | 1.6 | 0.2 | 0 | |
| 5.4 | 3.4 | 1.5 | 0.4 | 0 | |
| 5.2 | 4.1 | 1.5 | 0.1 | 0 | |
| 5.5 | 4.2 | 1.4 | 0.2 | 0 | |
| 4.9 | 3.1 | 1.5 | 0.1 | 0 | |
| 5 | 3.2 | 1.2 | 0.2 | 0 | |
| 5.5 | 3.5 | 1.3 | 0.2 | 0 | |
| 4.9 | 3.1 | 1.5 | 0.1 | 0 | |
| 4.4 | 3 | 1.3 | 0.2 | 0 | |
| 5.1 | 3.4 | 1.5 | 0.2 | 0 | |
| 5 | 3.5 | 1.3 | 0.3 | 0 | |
| 4.5 | 2.3 | 1.3 | 0.3 | 0 | |
| 4.4 | 3.2 | 1.3 | 0.2 | 0 | |
| 5 | 3.5 | 1.6 | 0.6 | 0 | |
| 5.1 | 3.8 | 1.9 | 0.4 | 0 | |
| 4.8 | 3 | 1.4 | 0.3 | 0 | |
| 5.1 | 3.8 | 1.6 | 0.2 | 0 | |
| 4.6 | 3.2 | 1.4 | 0.2 | 0 | |
| 5.3 | 3.7 | 1.5 | 0.2 | 0 | |
| 5 | 3.3 | 1.4 | 0.2 | 0 | |
| 7 | 3.2 | 4.7 | 1.4 | 1 | |
| 6.4 | 3.2 | 4.5 | 1.5 | 1 | |
| 6.9 | 3.1 | 4.9 | 1.5 | 1 | |
| 5.5 | 2.3 | 4 | 1.3 | 1 | |
| 6.5 | 2.8 | 4.6 | 1.5 | 1 | |
| 5.7 | 2.8 | 4.5 | 1.3 | 1 | |
| 6.3 | 3.3 | 4.7 | 1.6 | 1 | |
| 4.9 | 2.4 | 3.3 | 1 | 1 | |
| 6.6 | 2.9 | 4.6 | 1.3 | 1 | |
| 5.2 | 2.7 | 3.9 | 1.4 | 1 | |
| 5 | 2 | 3.5 | 1 | 1 | |
| 5.9 | 3 | 4.2 | 1.5 | 1 | |
| 6 | 2.2 | 4 | 1 | 1 | |
| 6.1 | 2.9 | 4.7 | 1.4 | 1 | |
| 5.6 | 2.9 | 3.6 | 1.3 | 1 | |
| 6.7 | 3.1 | 4.4 | 1.4 | 1 | |
| 5.6 | 3 | 4.5 | 1.5 | 1 | |
| 5.8 | 2.7 | 4.1 | 1 | 1 | |
| 6.2 | 2.2 | 4.5 | 1.5 | 1 | |
| 5.6 | 2.5 | 3.9 | 1.1 | 1 | |
| 5.9 | 3.2 | 4.8 | 1.8 | 1 | |
| 6.1 | 2.8 | 4 | 1.3 | 1 | |
| 6.3 | 2.5 | 4.9 | 1.5 | 1 | |
| 6.1 | 2.8 | 4.7 | 1.2 | 1 | |
| 6.4 | 2.9 | 4.3 | 1.3 | 1 | |
| 6.6 | 3 | 4.4 | 1.4 | 1 | |
| 6.8 | 2.8 | 4.8 | 1.4 | 1 | |
| 6.7 | 3 | 5 | 1.7 | 1 | |
| 6 | 2.9 | 4.5 | 1.5 | 1 | |
| 5.7 | 2.6 | 3.5 | 1 | 1 | |
| 5.5 | 2.4 | 3.8 | 1.1 | 1 | |
| 5.5 | 2.4 | 3.7 | 1 | 1 | |
| 5.8 | 2.7 | 3.9 | 1.2 | 1 | |
| 6 | 2.7 | 5.1 | 1.6 | 1 | |
| 5.4 | 3 | 4.5 | 1.5 | 1 | |
| 6 | 3.4 | 4.5 | 1.6 | 1 | |
| 6.7 | 3.1 | 4.7 | 1.5 | 1 | |
| 6.3 | 2.3 | 4.4 | 1.3 | 1 | |
| 5.6 | 3 | 4.1 | 1.3 | 1 | |
| 5.5 | 2.5 | 4 | 1.3 | 1 | |
| 5.5 | 2.6 | 4.4 | 1.2 | 1 | |
| 6.1 | 3 | 4.6 | 1.4 | 1 | |
| 5.8 | 2.6 | 4 | 1.2 | 1 | |
| 5 | 2.3 | 3.3 | 1 | 1 | |
| 5.6 | 2.7 | 4.2 | 1.3 | 1 | |
| 5.7 | 3 | 4.2 | 1.2 | 1 | |
| 5.7 | 2.9 | 4.2 | 1.3 | 1 | |
| 6.2 | 2.9 | 4.3 | 1.3 | 1 | |
| 5.1 | 2.5 | 3 | 1.1 | 1 | |
| 5.7 | 2.8 | 4.1 | 1.3 | 1 | |
| 6.3 | 3.3 | 6 | 2.5 | 2 | |
| 5.8 | 2.7 | 5.1 | 1.9 | 2 | |
| 7.1 | 3 | 5.9 | 2.1 | 2 | |
| 6.3 | 2.9 | 5.6 | 1.8 | 2 | |
| 6.5 | 3 | 5.8 | 2.2 | 2 | |
| 7.6 | 3 | 6.6 | 2.1 | 2 | |
| 4.9 | 2.5 | 4.5 | 1.7 | 2 | |
| 7.3 | 2.9 | 6.3 | 1.8 | 2 | |
| 6.7 | 2.5 | 5.8 | 1.8 | 2 | |
| 7.2 | 3.6 | 6.1 | 2.5 | 2 | |
| 6.5 | 3.2 | 5.1 | 2 | 2 | |
| 6.4 | 2.7 | 5.3 | 1.9 | 2 | |
| 6.8 | 3 | 5.5 | 2.1 | 2 | |
| 5.7 | 2.5 | 5 | 2 | 2 | |
| 5.8 | 2.8 | 5.1 | 2.4 | 2 | |
| 6.4 | 3.2 | 5.3 | 2.3 | 2 | |
| 6.5 | 3 | 5.5 | 1.8 | 2 | |
| 7.7 | 3.8 | 6.7 | 2.2 | 2 | |
| 7.7 | 2.6 | 6.9 | 2.3 | 2 | |
| 6 | 2.2 | 5 | 1.5 | 2 | |
| 6.9 | 3.2 | 5.7 | 2.3 | 2 | |
| 5.6 | 2.8 | 4.9 | 2 | 2 | |
| 7.7 | 2.8 | 6.7 | 2 | 2 | |
| 6.3 | 2.7 | 4.9 | 1.8 | 2 | |
| 6.7 | 3.3 | 5.7 | 2.1 | 2 | |
| 7.2 | 3.2 | 6 | 1.8 | 2 | |
| 6.2 | 2.8 | 4.8 | 1.8 | 2 | |
| 6.1 | 3 | 4.9 | 1.8 | 2 | |
| 6.4 | 2.8 | 5.6 | 2.1 | 2 | |
| 7.2 | 3 | 5.8 | 1.6 | 2 | |
| 7.4 | 2.8 | 6.1 | 1.9 | 2 | |
| 7.9 | 3.8 | 6.4 | 2 | 2 | |
| 6.4 | 2.8 | 5.6 | 2.2 | 2 | |
| 6.3 | 2.8 | 5.1 | 1.5 | 2 | |
| 6.1 | 2.6 | 5.6 | 1.4 | 2 | |
| 7.7 | 3 | 6.1 | 2.3 | 2 | |
| 6.3 | 3.4 | 5.6 | 2.4 | 2 | |
| 6.4 | 3.1 | 5.5 | 1.8 | 2 | |
| 6 | 3 | 4.8 | 1.8 | 2 | |
| 6.9 | 3.1 | 5.4 | 2.1 | 2 | |
| 6.7 | 3.1 | 5.6 | 2.4 | 2 | |
| 6.9 | 3.1 | 5.1 | 2.3 | 2 | |
| 5.8 | 2.7 | 5.1 | 1.9 | 2 | |
| 6.8 | 3.2 | 5.9 | 2.3 | 2 | |
| 6.7 | 3.3 | 5.7 | 2.5 | 2 | |
| 6.7 | 3 | 5.2 | 2.3 | 2 | |
| 6.3 | 2.5 | 5 | 1.9 | 2 | |
| 6.5 | 3 | 5.2 | 2 | 2 | |
| 6.2 | 3.4 | 5.4 | 2.3 | 2 | |
| 5.9 | 3 | 5.1 | 1.8 | 2 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| import matplotlib.style as style | |
| from matplotlib import pyplot as plt | |
| import pandas as pd | |
| def cost_function(trainingData, thetai, m): | |
| cost = 0.0 | |
| for data in trainingData: | |
| X = np.array([[1], [data[0]], [data[1]]],dtype='float32') | |
| H = thetai.dot(X)[0] | |
| Z = 1/(1+np.exp(-H)) | |
| cost += ( - data[2] * np.log(Z) - (1-data[2]) * np.log(1-Z) ) | |
| return float(cost)/float(m) | |
| def logistic_reg(trainingData, m, testingData): | |
| learning_rate = 0.1 | |
| thetai = np.random.random((1,3)) | |
| # print(thetai) | |
| global_error = cost_function(trainingData, thetai, m) | |
| # print(global_error) | |
| prev_error = 0.0 | |
| try: | |
| while prev_error != global_error and global_error >= 0.13: | |
| prev_error = global_error | |
| dthetai = np.zeros((1,3),dtype='float32') | |
| for data in trainingData: | |
| X = np.array([[1], [data[0]], [data[1]]],dtype='float32') | |
| H = thetai.dot(X)[0] | |
| Z = 1/(1+np.exp(-H)) | |
| dthetai[0,0] += ( Z - data[2] ) * X[0] | |
| dthetai[0,1] += ( Z - data[2] ) * X[1] | |
| dthetai[0,2] += ( Z - data[2] ) * X[2] | |
| dthetai[0,0] /= float(m) | |
| dthetai[0,1] /= float(m) | |
| dthetai[0,2] /= float(m) | |
| thetai = thetai - (learning_rate * dthetai) | |
| global_error = cost_function(trainingData, thetai, m) | |
| print(global_error) | |
| except: | |
| pass | |
| pred = 0 | |
| for data in testingData: | |
| X = np.array([[1], [data[0]], [data[1]]],dtype='float32') | |
| H = thetai.dot(X)[0] | |
| Z = 1/(1+np.exp(-H)) | |
| if Z>=0.5: | |
| Z = 1 | |
| else: | |
| Z = 0 | |
| print('Target : {0} \t Predict : {1}'.format(data[2],Z)) | |
| if data[2]==Z: | |
| pred+=1 | |
| print('Accuracy : {0}%'.format((float(pred)/len(testingData))*100)) | |
| # style.use('seaborn') | |
| # plt.scatter(trainingData[trainingData[:,2]==1,0],trainingData[trainingData[:,2]==1,1],color='r') | |
| # plt.scatter(trainingData[trainingData[:,2]==0,0],trainingData[trainingData[:,2]==0,1],color='b') | |
| # x = np.linspace(np.min(trainingData[:,1]),np.max(trainingData[:,1]),100) | |
| # y = thetai[0,0]+thetai[0,1]*x + thetai[0,2]*x | |
| # plt.plot(x,y, color='g') | |
| # # plt.scatter(data[data[:,2]==2,0],data[data[:,2]==2,1],color='g') | |
| # plt.xlabel('petal_length') | |
| # plt.ylabel('petal_width') | |
| # plt.show() | |
| if __name__ == '__main__': | |
| # Data : sepal_length , sepal_width, petal_length, petal_width, species | |
| # setosa = 0 | |
| # versicolor = 1 | |
| # virginica = 2 -> 0 | |
| df = pd.read_csv('iris.csv') | |
| # print(df['petal_length']) | |
| data = np.array(list(zip(df['petal_length'],df['petal_width'],df['species']))) | |
| temp = data[data[:,2]==1] | |
| trainingData = temp[:30,:] | |
| testingData = temp[30:,:] | |
| temp = data[data[:,2]==2] | |
| temp[:,2] = 0 | |
| trainingData = np.append(trainingData, temp[:30,:], axis=0) | |
| testingData = np.append(testingData, temp[30:,:], axis=0) | |
| # print(trainingData) | |
| # print(len(trainingData)) | |
| # print(len(testingData)) | |
| # print(data[data[:,2]==0,0]) | |
| # print(len(data[data[:,2]==1,1])) | |
| # print(len(data[data[:,2]==2,1])) | |
| # style.use('seaborn') | |
| # plt.scatter(trainingData[trainingData[:,2]==1,0],trainingData[trainingData[:,2]==1,1],color='r') | |
| # plt.scatter(trainingData[trainingData[:,2]==2,0],trainingData[trainingData[:,2]==2,1],color='b') | |
| # # plt.scatter(data[data[:,2]==2,0],data[data[:,2]==2,1],color='g') | |
| # plt.xlabel('petal_length') | |
| # plt.ylabel('petal_width') | |
| # plt.show() | |
| logistic_reg(trainingData, len(trainingData), testingData) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment