Plotting spectrum of a signal - python

from numpy.fft import fft
from numpy import array
a = array([1.0, 1.0, 1.0, 1.0, 0.0, 0.0, 0.0, 0.0]
print( ' '.join("%5.3f" % abs(f) for f in fft(a)) )
I am using this code to get fft of a signal but how can I plot the fft.
Thanks

Here is an example I wrote to plot a wav file.
It is slightly more complicated because it deals with a stereo sound file by averaging the left and right channels. And it plots both the signal and the fft.
from __future__ import print_function, division
import wave
import numpy as np
import matplotlib.pyplot as plt
wr = wave.open('input.wav', 'r')
sz = wr.getframerate()
q = 5 # time window to analyze in seconds
c = 12 # number of time windows to process
sf = 1.5 # signal scale factor
for num in range(c):
print('Processing from {} to {} s'.format(num*q, (num+1)*q))
avgf = np.zeros(int(sz/2+1))
snd = np.array([])
# The sound signal for q seconds is concatenated. The fft over that
# period is averaged to average out noise.
for j in range(q):
da = np.fromstring(wr.readframes(sz), dtype=np.int16)
left, right = da[0::2]*sf, da[1::2]*sf
lf, rf = abs(np.fft.rfft(left)), abs(np.fft.rfft(right))
snd = np.concatenate((snd, (left+right)/2))
avgf += (lf+rf)/2
avgf /= q
# Plot both the signal and frequencies.
plt.figure(1)
a = plt.subplot(211) # signal
r = 2**16/2
a.set_ylim([-r, r])
a.set_xlabel('time [s]')
a.set_ylabel('signal [-]')
x = np.arange(44100*q)/44100
plt.plot(x, snd)
b = plt.subplot(212) # frequencies
b.set_xscale('log')
b.set_xlabel('frequency [Hz]')
b.set_ylabel('|amplitude|')
plt.plot(abs(avgf))
plt.savefig('simple{:02d}.png'.format(num))
plt.clf()
Below is one of the plots it generated. Colours et cetera are different from the default because of my custom matplotlibrc.

Related

How to take Red pixel at image and transform Red pixel to probability transform and perform KL divergence at python

I am trying to extract red pixel at image and transform to probability density function to perform KL divergence at python
For the next i would like to perform with 2 image red pixel and calculate KL divergence
This is what i already do, sorry if noob and mess code
from PIL import Image
import matplotlib.pyplot as plt
import numpy as np
from scipy.stats.kde import gaussian_kde
from numpy import linspace
from scipy.interpolate import UnivariateSpline
from scipy.stats import norm
import tensorflow as tf
import seaborn as sns
sns.set()
from scipy.stats import entropy
def getRed(redVal):
return '#%02x%02x%02x' % (redVal, 0, 0)
def getGreen(greenVal):
return '#%02x%02x%02x' % (0, greenVal, 0)
def getBlue(blueVal):
return '#%02x%02x%02x' % (0, 0, blueVal)
# Create an Image with specific RGB value
image = Image.open("C:/Users/ahsan/Downloads/bunga/1.png")
# Modify the color of two pixels
image.putpixel((0,1), (1,1,5))
image.putpixel((0,2), (2,1,5))
# Display the image
plt.imshow(image)
plt.show()
# Get the color histogram of the image
histogram = image.histogram()
# Take only the Red counts
l1 = histogram[0:256]
# Take only the Blue counts
l2 = histogram[256:512]
# Take only the Green counts
l3 = histogram[512:768]
plt.figure(0)
# R histogram
for i in range(0, 256):
plt.bar(i, l1[i], color = getRed(i), edgecolor=getRed(i), alpha=0.3)
plt.figure(3)
data = l1
kde = gaussian_kde( data )
dist_space = linspace( min(data), max(data), 100 )
# plot the results
plt.plot( dist_space, kde(dist_space) )
plt.show()
def kl(p, q):
"""Kullback-Leibler divergence D(P || Q) for discrete distributions
Parameters
----------
p, q : array-like, dtype=float, shape=n
Discrete probability distributions.
"""
p = np.asarray(p, dtype=np.float)
q = np.asarray(q, dtype=np.float)
return np.sum(np.where(p != 0, p * np.log(p / q), 0))
plt.plot(x, q, c='red')
p=l1 #Just example i will try with 2 image
q=l2 # Just ecample would like to try with 2 image
assert entropy(p, q) == kl(p, q)
But i am still can't calculate the KL divergence

How to compute dBm from FFT results?

I computed a sinewave of 4Hz, applied FFT and calculated the amplitude, the amplitude is an array of 500 length, I want to convert each element in that array to dBm form, and draw a spectrogram. however I can't seem to get the calculation right.
I saw that general formula:
valueDBFS = 20np.log10(abs(value))
so I tried using it and I get only negative results..
Here is my full code (edited):
# Python example - Fourier transform using numpy.fft method
import numpy as np
import matplotlib.pyplot as plotter
from os import times
from PIL import Image
import numpy as np
# How many time points are needed i,e., Sampling Frequency
samplingFrequency = 100
# At what intervals time points are sampled
samplingInterval = 1 / samplingFrequency
# Begin time perod of the signals
beginTime = 0
# End time period of the signals
endTime = 10
# Frequency of the signals
signal1Frequency = 4
signal2Frequency = 70
# Time points
time = np.arange(beginTime, endTime, samplingInterval)
# Create two sine waves
amplitude1 = 100 * np.sin(2*np.pi*signal1Frequency*time)
fourierTransform = np.fft.fft(amplitude1)
fourierTransform = fourierTransform[range(int(len(amplitude1)/2))] # Exclude sampling frequency
tpCount = len(amplitude1)
values = np.arange(int(tpCount/2))
timePeriod = tpCount/samplingFrequency
frequencies = values/timePeriod
valueDBFS = 20*np.log10(abs(fourierTransform))
print(valueDBFS)
#SPECTROGRAM
w, h = 500, 500
data = np.zeros((h, w, 3), dtype=np.uint8)
time = time[:len(time)//2]
for i in range(500):
for j in range(500):
color = abs(fourierTransform)[i]
data[i,j] = [color, color, color]
img = Image.fromarray(data, 'RGB')
img.show()
The maximum value of your amplitude is 1, and log10(1) is 0, everything else will be less than that - for example log10(0.9) = -0,0458.
So that part of your code works fine, the logs should be negative in your example! - Try defining your amplitude like this:
amplitude1 = 100 * np.sin(2*np.pi*signal1Frequency*time)
That should give plenty of positive results.

From Amplitude or FFT to dB

I've a Python code which performs FFT on a wav file and plot the amplitude vs time / amplitude vs freq graphs. I want to calculate dB from these graphs (they are long arrays). I do not want to calculate exact dBA, I just want to see a linear relationship after my calculations. I've dB meter, I will compare it. Here is my code:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function
import scipy.io.wavfile as wavfile
import scipy
import scipy.fftpack
import numpy as np
from matplotlib import pyplot as plt
fs_rate, signal = wavfile.read("output.wav")
print ("Frequency sampling", fs_rate)
l_audio = len(signal.shape)
print ("Channels", l_audio)
if l_audio == 2:
signal = signal.sum(axis=1) / 2
N = signal.shape[0]
print ("Complete Samplings N", N)
secs = N / float(fs_rate)
print ("secs", secs)
Ts = 1.0/fs_rate # sampling interval in time
print ("Timestep between samples Ts", Ts)
t = scipy.arange(0, secs, Ts) # time vector as scipy arange field / numpy.ndarray
FFT = abs(scipy.fft(signal))
FFT_side = FFT[range(N//4)] # one side FFT range
freqs = scipy.fftpack.fftfreq(signal.size, t[1]-t[0])
fft_freqs = np.array(freqs)
freqs_side = freqs[range(N//4)] # one side frequency range
fft_freqs_side = np.array(freqs_side)
makespositive = signal[44100:]*(-1)
logal = np.log10(makespositive)
sn1 = np.mean(logal[1:44100])
sn2 = np.mean(logal[44100:88200])
sn3 = np.mean(logal[88200:132300])
sn4 = np.mean(logal[132300:176400])
print(sn1)
print(sn2)
print(sn3)
print(sn4)
abs(FFT_side)
for a in range(500):
FFT_side[a] = 0
plt.subplot(311)
p1 = plt.plot(t[44100:], signal[44100:], "g") # plotting the signal
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.subplot(312)
p1 = plt.plot(t[44100:], logal, "r") # plotting the signal
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.subplot(313)
p3 = plt.plot(freqs_side, abs(FFT_side), "b") # plotting the positive fft spectrum
plt.xlabel('Frequency (Hz)')
plt.ylabel('Count single-sided')
plt.show()
First plot is amplitude vs time, second one is logarithm of previous graph and the last one is FFT.
In sn1,sn2 part I tried to calculate dB from signal. First I took log and then calculated mean value for each second. It did not give me a clear relationship. I also tried this and did not worked.
import numpy as np
import matplotlib.pyplot as plt
import scipy.io.wavfile as wf
fs, signal = wf.read('output.wav') # Load the file
ref = 32768 # 0 dBFS is 32678 with an int16 signal
N = 8192
win = np.hamming(N)
x = signal[0:N] * win # Take a slice and multiply by a window
sp = np.fft.rfft(x) # Calculate real FFT
s_mag = np.abs(sp) * 2 / np.sum(win) # Scale the magnitude of FFT by window and factor of 2,
# because we are using half of FFT spectrum
s_dbfs = 20 * np.log10(s_mag / ref) # Convert to dBFS
freq = np.arange((N / 2) + 1) / (float(N) / fs) # Frequency axis
plt.plot(freq, s_dbfs)
plt.grid(True)
So which steps should I perform? (Sum/mean all freq amplitudes then take log or reverse, or perform it for signal etc.)
import numpy as np
import matplotlib.pyplot as plt
import scipy.io.wavfile as wf
fs, signal = wf.read('db1.wav')
signal2 = signal[44100:]
chunk_size = 44100
num_chunk = len(signal2) // chunk_size
sn = []
for chunk in range(0, num_chunk):
sn.append(np.mean(signal2[chunk*chunk_size:(chunk+1)*chunk_size].astype(float)**2))
print(sn)
logsn = 20*np.log10(sn)
print(logsn)
Output:
[4.6057844427695475e+17, 5.0025315250895744e+17, 5.028593412665193e+17, 4.910948397471887e+17]
[353.26607217 353.98379668 354.02893044 353.82330741]
A decibel meter measures a signal's mean power. So from your time signal recording you can calculate the mean signal power with:
chunk_size = 44100
num_chunk = len(signal) // chunk_size
sn = []
for chunk in range(0, num_chunk):
sn.append(np.mean(signal[chunk*chunk_size:(chunk+1)*chunk_size]**2))
Then the corresponding mean signal power in decibels is simply given by:
logsn = 10*np.log10(sn)
A equivalent relationship could also be obtained for a frequency domain signal with the use of Parseval's theorem, but in your case would require unecessary FFT computations (this relationship is mostly useful when you already have to compute the FFT for other purposes).
Note however that depending on what you compare there may be some (hopefully small) discrepancies. For example the use of non-linear amplifier and speakers would affect the relationship. Similarly ambient noises would add to the measured power by the decibel meter.

Not able to recreate same sound using FFT

I am trying to recreate musical note using top 10 frequencies returned by Fourier Transform (FFT). Resulting sound does not match the original sound. Not sure if I am not finding frequencies correctly or not generating sound from it correctly. The goal of this code is to match the original sound.
Here is my code:
import numpy as np
from scipy.io import wavfile
from scipy.fftpack import fft
import matplotlib.pyplot as plt
i_framerate = 44100
fs, data = wavfile.read('./Flute.nonvib.ff.A4.stereo.wav') # load the data
def findFrequencies(arr_data, i_framerate = 44100, i_top_n =5):
a = arr_data.T[0] # this is a two channel soundtrack, I get the first track
# b=[(ele/2**8.)*2-1 for ele in a] # this is 8-bit track, b is now normalized on [-1,1)
y = fft(a) # calculate fourier transform (complex numbers list)
xf = np.linspace(0,int(i_framerate/2.0),int((i_framerate/2.0))+1) /2 # Need to find out this last /2 part
yf = np.abs(y[:int((i_framerate//2.0))+1])
plt.plot(xf,yf)
yf_top_n = np.argsort(yf)[-i_top_n:][::-1]
amp_top_n = yf[yf_top_n] / np.max(yf[yf_top_n])
freq_top_n = xf[yf_top_n]
return freq_top_n, amp_top_n
def createSoundData(a_freq, a_amp, i_framerate=44100, i_time = 1, f_amp = 1000.0):
n_samples = i_time * i_framerate
x = np.linspace(0,i_time, n_samples)
y = np.zeros(n_samples)
for i in range(len(a_freq)):
y += np.sin(2 * np.pi * a_freq[i] * x)* f_amp * a_amp[i]
data2 = np.c_[y,y] # 2 Channel sound
return data2
top_freq , top_freq_amp = findFrequencies(data, i_framerate = 44100 , i_top_n = 200)
print('Frequencies: ',top_freq)
print('Amplitudes : ',top_freq_amp)
soundData = createSoundData(top_freq, top_freq_amp,i_time = 2, f_amp = 50 / len(top_freq))
wavfile.write('createsound_A4_v6.wav',i_framerate,soundData)
The top 10 spectral frequencies in a musical note are not the same as the center frequencies of the top 10 FFT result bin magnitudes. The actual frequency peaks can be between the FFT bins.
Not only can the frequency peak information be between FFT bins, but the phase information required to reproduce any note transients (attack, decay, etc.) can also be between bins. Spectral information that is between FFT bins is carried by a span (up to the full width) of the complex FFT result.

How to remove the noise from wave file

I have a sound file, I apply a high frequency filter
import wave
import scipy.io.wavfile as wav
import numpy as np
import scipy as sp
origAudio = wave.open('3734.wav','r')
frameRate = origAudio.getframerate()
nChannels = origAudio.getnchannels()
sampWidth = origAudio.getsampwidth()
nbframe=origAudio.getnframes()
da = np.fromstring(origAudio.readframes(frameRate), dtype=np.int16)
left, right = da[0::2], da[1::2]
b, a = signal.butter(2, 0.03,btype='highpass', analog=False)
left = signal.filtfilt(b, a, left)
hann = np.hanning(len(left))
l,f=np.fft.rfft(left*hann), np.fft.rfft(right)
plt.xscale('log')
plt.xlabel('frequency [Hz]')
plt.ylabel('|Magnitude|')
plt.plot(np.abs(l))
I obtain
However I want to remove the noise from the signal , abtain only the peaks.Thanks

Categories

Resources