I am currently trying using librosa to perform stfft, such that the parameter resembles a stfft process from a different framework (Kaldi).
The audio file is fash-b-an251
Kaldi does it using a sample frequency of 16 KHz, window_size = 400 (25ms), hop_length=160 (10ms).
The spectrogram extracted from this looks like this:
I then tried to do the same using librosa:
import numpy as np
import sys
import librosa
import os
import scipy
import matplotlib.pyplot as plt
from matplotlib import cm
# Input parameter
# relative_path_to_file
if len(sys.argv) < 1:
print "Missing Arguments!"
print "python spectogram_librosa.py path_to_audio_file"
sys.exit()
path = sys.argv[1]
abs_path = os.path.abspath(path)
spectogram_dnn = "/home/user/dnn/spectogram"
if not os.path.exists(spectogram_dnn):
print "spectogram_dnn folder didn't exist!"
os.makedirs(spectogram_dnn)
print "Created!"
y,sr = librosa.load(abs_path,sr=16000)
D = librosa.logamplitude(np.abs(librosa.core.stft(y, win_length=400, hop_length=160, window=scipy.signal.hanning,center=False)), ref_power=np.max)
librosa.display.specshow(D,sr=16000,hop_length=160, x_axis='time', y_axis='log', cmap=cm.jet)
plt.colorbar(format='%+2.0f dB')
plt.title('Log power spectrogram')
plt.show()
raw_input()
sys.exit()
Which is basically taken from here:
In which i've modified the stfft function such that it fits my parameters..
Problems is that is creates an entirely different plot..
So.. What am I doing wrong in librosa?.. Why is this plot so much different, from the one created in kaldi.
Am I missing something?
It has to do with the Hz scale. The one in the first image is linear while the one in the second image is logarithmic. You can fix it by either changing the scale in either of the images to match the other.
Related
import wave
import numpy as np
from IPython.display import display, Audio
#sound 1
with wave.open('sound_file.wav', 'rb') as wf:
signal = np.frombuffer(wf.readframes(nframes = wf.getnframes()), 'int' + str(int(16 * wf.getsampwidth())))
display(Audio(data = signal, rate = wf.getframerate()))
#sound2
display(Audio('sound_file.wav'))
here the sound1 sounds different than sound2 so can anyone tell me what happens there.
As well as please state some usual practices of sound preprocessing that must be done after getting an np array from a sound file.
import time
# cv2.cvtColor takes a numpy ndarray as an argument
import numpy as nm
import pytesseract
# importing OpenCV
import cv2
from PIL import ImageGrab, Image
bboxes = [(1469, 1014, 1495, 1029)]
def imToString():
# Path of tesseract executable
pytesseract.pytesseract.tesseract_cmd = 'D:\Program Files (x86)\Tesseract-OCR' + chr(92) + 'tesseract.exe'
while (True):
for box in bboxes:
# ImageGrab-To capture the screen image in a loop.
# Bbox used to capture a specific area.
cap = ImageGrab.grab(bbox=box)
# Converted the image to monochrome for it to be easily
# read by the OCR and obtained the output String.
tesstr = pytesseract.image_to_string(
cv2.cvtColor(nm.array(cap), cv2.COLOR_BGR2GRAY), lang='eng', config='digits') # ,lang='eng')
cap.show()
#input()
time.sleep(5)
print(tesstr)
# Calling the function
imToString()
It captures an image like this:
It isn't always two digits it can be one or three digits too.
Pytesseract returns values like: asi and oli
So, which Image To Text (OCR) Algorithm should I use for this problem? And, how to use that? I need a very precise value in this example it's 53 so the output should be around 50.
I'm trying to run this machine learning tree algorithm code in IPython:
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
iris = load_iris()
X = iris.data[:, 2:] # petal length and width
y = iris.target
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
from sklearn.tree import export_graphviz
export_graphviz(tree_clf, out_file=image_path("iris_tree.dot"),
feature_names=iris.feature_names[2:],
class_names=iris.target_names,
rounded=True,
filled=True
)
But I get this error when run in IPython:
I'm unfamiliar with export_graphviz, does anyone have any idea how to correct this?
I guess you are following "Hands on Machine Learning with Scikit-Learn and TensorFlow" book by Aurelien Geron. I encountered with the same problem while trying out "Decision Trees" chapter. You can always refer to his GitHub notebooks . For your code, you may refer "decision tree" notebook.
Below I paste the code from notebook. Please do go ahead and have a look at the notebook also.
# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals
# Common imports
import numpy as np
import os
# to make this notebook's output stable across runs
np.random.seed(42)
# To plot pretty figures
%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "decision_trees"
def image_path(fig_id):
return os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID, fig_id)
def save_fig(fig_id, tight_layout=True):
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(image_path(fig_id) + ".png", format='png', dpi=300)
To get rid of all the mess simply remove image_path,
now out_file="iris_tree.dot", after running that command a file will be saved in your folder named iris_tree. Open that file in Microsoft Word and copy all of its content. Now open your browser and type "webgraphviz" and then click on the first link. Then delete whatever is written in white space and paste your code which is copied from iris_tree. Then click "generate graph". Scroll down and your graph is ready.
I know you might have got what you were looking for. But in case you don't, all you need to do is just replace:
out_file=image_path("iris_tree.dot")
with:
out_file="iris_tree.dot"
This will create the .dot file in the same directory in which your current script is.
You can also give the absolute path to where you want to save the .dot file as:
out_file="/home/cipher/iris_tree.dot"
you must correct
out_file=image_path("iris_tree.dot"),
in below code line:
out_file="C:/Users/VIDA/Desktop/python/iris_tree.dot",
You can directly type instead of using the webgraphviz, if you are using sklearn version 0.20.
import graphviz
with open ("iris_tree.dot") as f:
dot_graph = f.read()
display (graphviz.Source(dot_graph))
With sklearn 0.22 you have to change again. See sklearn users guide.
I have a sklearn with the version of 0.20.1, and I got the example to work through the line below.
export_graphviz(
tree_clf,
out_file = "iris_tree.dot",
feature_names = iris.feature_names[2:])
I am using python 3x in Jupyter notebook, what I want to do is to plot some of the R plots in a shell in jupyter notebook. However, the problem is that when I do so, the plot is drawn on another window rather than in the shell. However, when I close it the jupyter notebook gives me an error a "Dead Kernel"
My code is:
# To fit a restricted VAR model we will have to call the function from R
# Call function from R
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri
pandas2ri.activate()
# Calling packages
import pandas as pd, numpy as np
# Test for serial correlation
MTS = importr("MTS", lib_loc = "C:/Users/Rami Chehab/Documents/R/win-library/3.3")
RMTSmq=MTS.mq
# Create data
df = pd.DataFrame(np.random.random((108, 2)), columns=['Number1','Number2'])
# Test for data
RMTSmq(df, adj=4)
After I close the program I am getting this
Can someone help me? I wish if I may plot the graph inside jupyter notebook if possible.
Thank you
I would like to thank my great friend Sarunas for his wild idea. In particular, he informed me that there is a way out through "instead of showing the picture (in the window) you could try to write it as png or another image format? Then open it with some photo viewer? "
That is exactly what I have done!
Consider for example that I would like to show a figure from R say the plot of sin(x) from x=-pi till 2pi
import rpy2.robjects as ro
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
grdevices.png(file="Rami1.png", width=512, height=512)
p = ro.r('curve(sin, -pi, 2*pi)')
grdevices.dev_off()
print()
from IPython.display import Image
Image("Rami1.png")
The output is
This is another answer for the above question using precisely the arguments raised in the above question. Rather the flavour
import rpy2.robjects as ro, pandas as pd, numpy as np
from rpy2.robjects.packages import importr
# Call function from R
import rpy2.robjects as robjects
from rpy2.robjects import r
from rpy2.robjects.numpy2ri import numpy2ri
from rpy2.robjects.packages import importr
# To plot drawings in R
grdevices = importr('grDevices')
# Save the figure as Rami1.png
grdevices.png(file="Rami1.png", width=512, height=512)
# We are interested in finding if there is any serial correlation in the Multivariate residuals
# Since there is a fitting VAR it will be cumbersome to create this function here therefore consider
# that residauls resi as follow
resi = pd.DataFrame(np.random.random((108, 2)), columns=['Number1','Number2'])
# firt take the values of the dataframe to numpy
resi1=np.array(resi, dtype=float)
# Taking the variable from Python to R
r_resi = numpy2ri(resi1)
# Creating this variable in R (from python)
r.assign("resi", r_resi)
# Calling libraries in R for mq to function which is MTS
r('library("MTS")')
# Calling a function in R (from python)
p = ro.r('result <-mq(resi,adj=4)')
grdevices.dev_off()
from IPython.display import Image
Image("Rami1.png")
I'm having trouble with sklearn.mixture.dpgmm. The main issue is that it is not returning correct covariances for synthetic data (2 separated 2D gaussians), where it really should have no issue. In particular, when I do dpgmm._get_covars(), the covariance matrices have diagonal elements that are always exactly 1.0 too large, regardless of the input data distributions. This seems like a bug, as gmm works perfectly (when limiting to known exact number of groups)
Another issue is that dpgmm.weights_ makes no sense, they sum to one but the values appear meaningless.
Does anyone have a solution to this or see something clearly wrong with my example?
Here is the exact script I'm running:
import itertools
import numpy as np
from scipy import linalg
import matplotlib.pyplot as plt
import matplotlib as mpl
import pdb
from sklearn import mixture
# Generate 2D random sample, two gaussians each with 10000 points
rsamp1 = np.random.multivariate_normal(np.array([5.0,5.0]),np.array([[1.0,-0.2],[-0.2,1.0]]),10000)
rsamp2 = np.random.multivariate_normal(np.array([0.0,0.0]),np.array([[0.2,-0.0],[-0.0,3.0]]),10000)
X = np.concatenate((rsamp1,rsamp2),axis=0)
# Fit a mixture of Gaussians with EM using 2
gmm = mixture.GMM(n_components=2, covariance_type='full',n_iter=10000)
gmm.fit(X)
# Fit a Dirichlet process mixture of Gaussians using 10 components
dpgmm = mixture.DPGMM(n_components=10, covariance_type='full',min_covar=0.5,tol=0.00001,n_iter = 1000000)
dpgmm.fit(X)
print("Groups With data in them")
print(np.unique(dpgmm.predict(X)))
##print the input and output covars as example, should be very similar
correct_c0 = np.array([[1.0,-0.2],[-0.2,1.0]])
print "Input covar"
print correct_c0
covars = dpgmm._get_covars()
c0 = np.round(covars[0],decimals=1)
print "Output Covar"
print c0
print("Output Variances Too Big by 1.0")
According to the dpgmm docs this Class is Deprecated in version 0.18 and will be removed in version 0.20
You should use BayesianGaussianMixture Class instead, with parameter weight_concentration_prior_type set with option "dirichlet_process"
Hope it helps
instead of writing
from sklearn.mixture import GMM
gmm = GMM(2, covariance_type='full', random_state=0)
you should write:
from sklearn.mixture import BayesianGaussianMixture
gmm = BayesianGaussianMixture(2, covariance_type='full', random_state=0)