# ORIGINAL SINE WAVE %pylab inline import numpy as np import matplotlib.pyplot as plt #creating x-variables and labelling it time time = np.arange(0,4*np.pi,0.05) amplitude = np.sin(time) # we want to plot the sinwave using amplitude and time. plt.plot(time,amplitude) # labelling the graph, x-axis and the y-axis plt.title("SINE WAVE") plt.xlabel('Time') plt.ylabel('Amplitude') #let's try plotting what we have so far plt.grid(True) plt.axhline(y=0, color='red') plt.show()

noise = np.random.normal(0,0.4,len(time)) amplitude_new = amplitude + noise plt.plot(time,amplitude_new) plt.show()

noise = np.random.normal(0,0.6,len(time)) amplitude_new = amplitude + noise plt.plot(time,amplitude_new) plt.show()

noise = np.random.normal(0,0.8,len(time)) amplitude_new = amplitude + noise plt.plot(time,amplitude_new) plt.show()

noise = np.random.normal(0,10,len(time)) amplitude_new = amplitude + noise plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE ONE noise1 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise1 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE TWO noise2 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise2 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE THREE noise3 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise3 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE FOUR noise4 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise4 plt.plot(time,amplitude_new) plt.show()

# NOISY WAVE FIVE noise5 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise5 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE SIX noise6 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise6 plt.plot(time,amplitude_new) plt.show()

### NOISY WAVE SEVEN noise7 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise7 plt.plot(time,amplitude_new) plt.show()

### NOISY WAVE EIGHT noise8 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise8 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE NINE #noise 9 noise9 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise9 plt.plot(time,amplitude_new) plt.show()

#NOISY WAVE TEN #noise 10 noise10 = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise10 plt.plot(time,amplitude_new) plt.show()

noise = np.random.normal(0,0.2,len(time)) amplitude_new = amplitude + noise plt.plot(time,amplitude_new) from statsmodels.nonparametric.smoothers_lowess import lowess filtered=lowess(amplitude_new,time,frac=0.2) #filtered plt.plot(filtered[: ,0],filtered[: ,1],'black',linewidth=3) plt.show()

averaged_noise =(noise1 +noise2+noise3+noise4+noise5+noise6+noise7+noise8+noise9+noise10)/10 averaged_amplitude = averaged_noise + amplitude plt.ylabel('Amplitude') #let's try plotting what we have so far plt.grid(True) plt.axhline(y=0, color='red') plt.plot(time,averaged_amplitude) #ylim = (-1,1) plt.show()

n = 5000 final_sig = 0 for i in range(n): noise = np.random.normal(0,0.2,len(time)) noisy_sig = amplitude+noise final_sig += noisy_sig final_sig /= n plt.plot(time,final_sig) ylim = (-1,1)

import matplotlib.pyplot as plt img1 = plt.imread("/work/sample_images/im0.png",) plt.imshow(img1) img2 = plt.imread("/work/sample_images/im6.png",) plt.imshow(img2) img3 = plt.imread("/work/sample_images/im12.png",) plt.imshow(img3) img4 = plt.imread("/work/sample_images/im18.png",) plt.imshow(img4) img5 = plt.imread("/work/sample_images/im24.png",) plt.imshow(img5) img6 = plt.imread("/work/sample_images/im30.png",) plt.imshow(img6) img7 = plt.imread("/work/sample_images/im36.png",) plt.imshow(img7) img8 = plt.imread("/work/sample_images/im42.png",) plt.imshow(img8) img13 = plt.imread("/work/sample_images/im72.png",) plt.imshow(img13) img12 = plt.imread("/work/sample_images/im66.png",) plt.imshow(img12) img11 = plt.imread("/work/sample_images/im60.png",) plt.imshow(img11) img10 = plt.imread("/work/sample_images/im54.png",) plt.imshow(img10) #plt.show() img9 = plt.imread("/work/sample_images/im48.png",) plt.imshow(img9) #plt.show() img_tot =(img1+img2+img3+img4+img5+img6+img7+img8+img9+img10+img11+img12+img13)/13 plt.imshow(img_tot) plt.show() c=abs(img_tot - img2) plt.imshow(c) plt.show()

#!apt update && apt install ffmpeg libsm6 libxext6 -y up img9 = plt.imread("/work/sample_images/im0.png",) im = img9.astype(float) im/=255 im=im.mean(axis=2) plt.imshow(im,cmap="gray") plt.show()

import glob import matplotlib.pyplot as plt from matplotlib.image import imread filepath = "/work/sample_images/*.png" image=0 fin_image=0 counter = 0 for i in glob.iglob(filepath): image = imread(i) img = image.astype(float) img/=255 img=img.mean(axis=2) fin_image+=img counter+=1 fin_image/=counter b=plt.imshow(fin_image,cmap = "gray") plt.show()

plt.imshow(img,cmap="gray") plt.show()

import matplotlib.pyplot as plt ## subtracting a random image from the averaged image. plt.imshow(abs(fin_image - img)>0.0005, cmap='gray') plt.show()