My dataset is :enter image description here. First seven columns are for input metric. And the last five columns are for outputs. Output is an array of 5 numbers consist of zero or one. I am using Keras functional API for that. Whenever I try to to resample my data with individual columns, I got shape issues in merging, even if I I try to slice the rows.
Basically there's no "easy" approach to doing this. The only logical way is to maybe use Label Powerset over your design matrix, and resample based on the created column off that - though in that scenario it might be easier to "handcraft" such a transformation.
Here is one approach
import numpy as np
from sklearn.datasets import make_multilabel_classification
from sklearn.datasets import make_classification
from imblearn.over_sampling import RandomOverSampler
import pandas as pd
X0, y = make_classification()
_, X1 = make_multilabel_classification(n_classes=5, random_state=0)
# transform X1 by creating a powerset...
df_x1 = pd.DataFrame(X1, columns=[f'c{x}' for x in range(X1.shape[1])])
df_x1 = pd.merge(df_x1, df_x1.drop_duplicates().reset_index()).rename(columns={"index":"dummy"})
print(df_x1['dummy'].value_counts()) # shows imbalance
df_x1 = df_x1.reset_index() # so that we know which rows are resampled
df_y1 = df_x1['dummy']
df_x1 = df_x1[[x for x in df_x1.columns if x != 'dummy']]
ros = RandomOverSampler()
X_sample, _ = ros.fit_resample(df_x1, df_y1) # this is the resampled index
X = np.hstack([X0, X1])
X_res, y_res = X[X_sample['index'], :], y[X_sample['index']]
Where the secret sauce really is this bit:
df_x1 = pd.merge(df_x1, df_x1.drop_duplicates().reset_index()).rename(columns={"index":"dummy"})
Which re-indexes based on the selected 5 columns
df_x1 = df_x1.reset_index()
Which is then used in the RandomOverSampler, and would guarantee the 5 columns would be balanced.
Finally, we can select the indices of the sampling, to generate a dataset and labels which has been successfully resampled across both X0, X1, y
X = np.hstack([X0, X1])
X_res, y_res = X[X_sample['index'], :], y[X_sample['index']]
Related
I have a final project in my first degree and I want to build a Neural Network that gonna take the first 13 mfcc coeffs of a wav file and return who talked in the audio file from a banch of talkers.
I want you to notice that:
My audio files are text independent, therefore they have different length and words
I have trained the machine on about 35 audio files of 10 speaker ( the first speaker had about 15, the second 10, and the third and fourth about 5 each )
I defined :
X=mfcc(sound_voice)
Y=zero_array + 1 in the i_th position ( where i_th position is 0 for the first speaker, 1 for the second, 2 for the third... )
And than trained the machine, and than checked the output of the machine for some files...
So that’s what I did... but unfortunately it’s look like the results are completely random...
Can you help me understand why?
This is my code in python -
from sklearn.neural_network import MLPClassifier
import python_speech_features
import scipy.io.wavfile as wav
import numpy as np
from os import listdir
from os.path import isfile, join
from random import shuffle
import matplotlib.pyplot as plt
from tqdm import tqdm
winner = [] # this array count how much Bingo we had when we test the NN
for TestNum in tqdm(range(5)): # in every round we build NN with X,Y that out of them we check 50 after we build the NN
X = []
Y = []
onlyfiles = [f for f in listdir("FinalAudios/") if isfile(join("FinalAudios/", f))] # Files in dir
names = [] # names of the speakers
for file in onlyfiles: # for each wav sound
# UNESSECERY TO UNDERSTAND THE CODE
if " " not in file.split("_")[0]:
names.append(file.split("_")[0])
else:
names.append(file.split("_")[0].split(" ")[0])
names = list(dict.fromkeys(names)) # names of speakers
vector_names = [] # vector for each name
i = 0
vector_for_each_name = [0] * len(names)
for name in names:
vector_for_each_name[i] += 1
vector_names.append(np.array(vector_for_each_name))
vector_for_each_name[i] -= 1
i += 1
for f in onlyfiles:
if " " not in f.split("_")[0]:
f_speaker = f.split("_")[0]
else:
f_speaker = f.split("_")[0].split(" ")[0]
(rate, sig) = wav.read("FinalAudios/" + f) # read the file
try:
mfcc_feat = python_speech_features.mfcc(sig, rate, winlen=0.2, nfft=512) # mfcc coeffs
for index in range(len(mfcc_feat)): # adding each mfcc coeff to X, meaning if there is 50000 coeffs than
# X will be [first coeff, second .... 50000'th coeff] and Y will be [f_speaker_vector] * 50000
X.append(np.array(mfcc_feat[index]))
Y.append(np.array(vector_names[names.index(f_speaker)]))
except IndexError:
pass
Z = list(zip(X, Y))
shuffle(Z) # WE SHUFFLE X,Y TO PERFORM RANDOM ON THE TEST LEVEL
X, Y = zip(*Z)
X = list(X)
Y = list(Y)
X = np.asarray(X)
Y = np.asarray(Y)
Y_test = Y[:50] # CHOOSE 50 FOR TEST, OTHERS FOR TRAIN
X_test = X[:50]
X = X[50:]
Y = Y[50:]
clf = MLPClassifier(solver='lbfgs', alpha=1e-2, hidden_layer_sizes=(5, 3), random_state=2) # create the NN
clf.fit(X, Y) # Train it
for sample in range(len(X_test)): # add 1 to winner array if we correct and 0 if not, than in the end it plot it
if list(clf.predict([X[sample]])[0]) == list(Y_test[sample]):
winner.append(1)
else:
winner.append(0)
# plot winner
plot_x = []
plot_y = []
for i in range(1, len(winner)):
plot_y.append(sum(winner[0:i])*1.0/len(winner[0:i]))
plot_x.append(i)
plt.plot(plot_x, plot_y)
plt.xlabel('x - axis')
# naming the y axis
plt.ylabel('y - axis')
# giving a title to my graph
plt.title('My first graph!')
# function to show the plot
plt.show()
This is my zip file that contains the code and the audio file : https://ufile.io/eggjm1gw
You have a number of issues in your code and it will be close to impossible to get it right in one go, but let's give it a try. There are two major issues:
Currently you're trying to teach your neural network with very few training examples, as few as a single one per speaker (!). It's impossible for any machine learning algorithm to learn anything.
To make matters worse, what you do is that you feed to the ANN only MFCC for the first 25 ms of each recording (25 comes from winlen parameter of python_speech_features). In each of these recordings, first 25 ms will be close to identical. Even if you had 10k recordings per speaker, with this approach you'd not get anywhere.
I will give you concrete advise, but won't do all the coding - it's your homework after all.
Use all MFCC, not just first 25 ms. Many of these should be skipped, simply because there's no voice activity. Normally there should be VOD (Voice Activity Detector) telling you which ones to take, but in this exercise I'd skip it for starter (you need to learn basics first).
Don't use dictionaries. Not only it won't fly with more than one MFCC vector per speaker, but also it's very inefficient data structure for your task. Use numpy arrays, they're much faster and memory efficient. There's a ton of tutorials, including scikit-learn that demonstrate how to use numpy in this context. In essence, you create two arrays: one with training data, second with labels. Example: if omersk speaker "produces" 50000 MFCC vectors, you will get (50000, 13) training array. Corresponding label array would be 50000 with single constant value (id) that corresponds to the speaker (say, omersk is 0, lucas is 1 and so on). I'd consider taking longer windows (perhaps 200 ms, experiment!) to reduce the variance.
Don't forget to split your data for training, validation and test. You will have more than enough data. Also, for this exercise I'd watch for not feeding too much of data for any single speaker - ot taking steps to make sure algorithm is not biased.
Later, when you make prediction, you will again compute MFCCs for the speaker. With 10 sec recording, 200 ms window and 100 ms overlap, you'll get 99 MFCC vectors, shape (99, 13). The model should run on each of the 99 vectors, for each producing probability. When you sum it (and normalise, to make it nice) and take top value, you'll get the most likely speaker.
There's a dozen of other things that typically would be taken into account, but in this case (homework) I'd focus on getting the basics right.
EDIT: I decided to take a stab at creating the model with your idea at heart, but basics fixed. It's not exactly clean Python, all because it's adapted from Jupyter Notebook I was running.
import python_speech_features
import scipy.io.wavfile as wav
import numpy as np
import glob
import os
from collections import defaultdict
from sklearn.neural_network import MLPClassifier
from sklearn import preprocessing
from sklearn.model_selection import cross_validate
from sklearn.ensemble import RandomForestClassifier
audio_files_path = glob.glob('audio/*.wav')
win_len = 0.04 # in seconds
step = win_len / 2
nfft = 2048
mfccs_all_speakers = []
names = []
data = []
for path in audio_files_path:
fs, audio = wav.read(path)
if audio.size > 0:
mfcc = python_speech_features.mfcc(audio, samplerate=fs, winlen=win_len,
winstep=step, nfft=nfft, appendEnergy=False)
filename = os.path.splitext(os.path.basename(path))[0]
speaker = filename[:filename.find('_')]
data.append({'filename': filename,
'speaker': speaker,
'samples': mfcc.shape[0],
'mfcc': mfcc})
else:
print(f'Skipping {path} due to 0 file size')
speaker_sample_size = defaultdict(int)
for entry in data:
speaker_sample_size[entry['speaker']] += entry['samples']
person_with_fewest_samples = min(speaker_sample_size, key=speaker_sample_size.get)
print(person_with_fewest_samples)
max_accepted_samples = int(speaker_sample_size[person_with_fewest_samples] * 0.8)
print(max_accepted_samples)
training_idx = []
test_idx = []
accumulated_size = defaultdict(int)
for entry in data:
if entry['speaker'] not in accumulated_size:
training_idx.append(entry['filename'])
accumulated_size[entry['speaker']] += entry['samples']
elif accumulated_size[entry['speaker']] < max_accepted_samples:
accumulated_size[entry['speaker']] += entry['samples']
training_idx.append(entry['filename'])
X_train = []
label_train = []
X_test = []
label_test = []
for entry in data:
if entry['filename'] in training_idx:
X_train.append(entry['mfcc'])
label_train.extend([entry['speaker']] * entry['mfcc'].shape[0])
else:
X_test.append(entry['mfcc'])
label_test.extend([entry['speaker']] * entry['mfcc'].shape[0])
X_train = np.concatenate(X_train, axis=0)
X_test = np.concatenate(X_test, axis=0)
assert (X_train.shape[0] == len(label_train))
assert (X_test.shape[0] == len(label_test))
print(f'Training: {X_train.shape}')
print(f'Testing: {X_test.shape}')
le = preprocessing.LabelEncoder()
y_train = le.fit_transform(label_train)
y_test = le.transform(label_test)
clf = MLPClassifier(solver='lbfgs', alpha=1e-2, hidden_layer_sizes=(5, 3), random_state=42, max_iter=1000)
cv_results = cross_validate(clf, X_train, y_train, cv=4)
print(cv_results)
{'fit_time': array([3.33842635, 4.25872731, 4.73704267, 5.9454329 ]),
'score_time': array([0.00125694, 0.00073504, 0.00074005, 0.00078583]),
'test_score': array([0.40380048, 0.52969121, 0.48448687, 0.46043165])}
The test_score isn't stellar. There's a lot to improve (for starter, choice of algorithm), but the basics are there. Notice for starter how I get the training samples. It's not random, I only consider recordings as whole. You can't put samples from a given recording to both training and test, as test is supposed to be novel.
What was not working in your code? I'd say a lot. You were taking 200ms samples and yet very short fft. python_speech_features likely complained to you that the fft is should be longer than the frame you're processing.
I leave to you testing the model. It won't be good, but it's a starter.
I am working on a PCA example with Scikit-Learn and SVD in the following dataset. I thought I should get the same PCA components with both methods at the end however, what I find is that the signs get reversed. I followed different resources but correctly I assume. Did not quite understand why getting this sign reversal. Below is what I have done. Xpca and Xsvd should be same I thought.
Useful links 1, 2
import pandas as pd
data = pd.read_csv("http://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data", header=None)
data.columns = ["V"+str(i) for i in range(1, len(data.columns)+1)] # rename column names to be similar to R naming convention
data.V1 = data.V1.astype(str)
X = data.loc[:, "V2":] # independent variables data
y = data.V1 # dependent variable data
# Using Scikit-Learn
from sklearn.preprocessing import scale
from sklearn.decomposition import PCA
standardisedX = scale(X)
standardisedX = pd.DataFrame(standardisedX, index=X.index, columns=X.columns)
pca = PCA().fit(standardisedX)
Xpca = pd.DataFrame(pca.transform(standardisedX))
# Using SVD
U, S, V = np.linalg.svd(standardisedX, full_matrices=False, compute_uv=True)
Xsvd = pd.DataFrame(U.dot(np.diag(S)))
I'm learning about clustering and KMeans and such, so my knowldge is very basic on the topic. What I have below is a bit of a self study on how it works. Basically, if 'a' shows up in any of the columns, 'Binary' will equal 1. Essentially I am trying to teach it a pattern. I learned the following from a tutorial using the Titanic dataset, but I've adapted to my own data.
import pandas as pd
import numpy as np
from sklearn.cluster import KMeans
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import MinMaxScaler
import seaborn as sns
import matplotlib.pyplot as plt
my constructed data
dataset = [
[0,'x','f','g'],[1,'a','c','b'],[1,'d','k','a'],[0,'y','v','w'],
[0,'q','w','e'],[1,'c','a','l'],[0,'t','x','j'],[1,'w','o','a'],
[0,'z','m','n'],[1,'z','x','a'],[0,'f','g','h'],[1,'h','a','c'],
[1,'a','r','e'],[0,'g','c','c']
]
df = pd.DataFrame(dataset, columns=['Binary','Col1','Col2','Col3'])
df.head()
df:
Binary Col1 Col2 Col3
------------------------
1 a b c
0 x t v
0 s q w
1 n m a
1 u a r
Encode non binary to binary:
labelEncoder = LabelEncoder()
labelEncoder.fit(df['Col1'])
df['Col1'] = labelEncoder.transform(df['Col1'])
labelEncoder.fit(df['Col2'])
df['Col2'] = labelEncoder.transform(df['Col2'])
labelEncoder.fit(df['Col3'])
df['Col3'] = labelEncoder.transform(df['Col3'])
Set clusters to two, because its either 1 or 0?
X = np.array(df.drop(['Binary'], 1).astype(float))
y = np.array(df['Binary'])
kmeans = KMeans(n_clusters=2)
kmeans.fit(X)
Test it:
correct = 0
for i in range(len(X)):
predict_me = np.array(X[i].astype(float))
predict_me = predict_me.reshape(-1, len(predict_me))
prediction = kmeans.predict(predict_me)
if prediction[0] == y[i]:
correct += 1
The result:
print(f'{round(correct/len(X) * 100)}% Accuracy')
>>> 71%
How can I get it more accurate to the point where it 99.99% knows that 'a' means binary column is 1? More data?
K-means does not even try to predict this value. Because it is an unsupervised method. Because it is not a prediction algorithm; it is a structure discovery task. Don't mistake clustering for classification.
The cluster numbers have no meaning. They are 0 and 1 because these are the first two integers. K-means is randomized. Run it a few times and you will also score just 29% sometimes.
Also, k-means is designed for continuous input. You can apply it on binary encoded data, but the results will be pretty poor.
I am having a training data set consisting of 144 feedback with 72 positive and 72 negative respectively. there are two target labels positive and negative respectively. Consider the following code segment :
import pandas as pd
feedback_data = pd.read_csv('output.csv')
print(feedback_data)
data target
0 facilitates good student teacher communication. positive
1 lectures are very lengthy. negative
2 the teacher is very good at interaction. positive
3 good at clearing the concepts. positive
4 good at clearing the concepts. positive
5 good at teaching. positive
6 does not shows test copies. negative
7 good subjective knowledge. positive
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(binary = True)
cv.fit(feedback_data)
X = cv.transform(feedback_data)
X_test = cv.transform(feedback_data_test)
from sklearn import svm
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
target = [1 if i<72 else 0 for i in range(144)]
# the below line gives error
X_train, X_val, y_train, y_val = train_test_split(X, target, train_size = 0.50)
I do not understand what the problem is. Please help.
You are not using the count vectorizer right. This what you have now:
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(binary = True)
cv.fit(df)
X = cv.transform(df)
X
<2x2 sparse matrix of type '<class 'numpy.int64'>'
with 2 stored elements in Compressed Sparse Row format>
So you see that you don't achieve what you want. you do not transform each line correctly. You don't even train the count vectorizer right because you use the entire DataFrame and not just the corpus of comments.
To solve the issue we need to make sure that the Count is well done:
if you do this (Use the right corpus):
cv = CountVectorizer(binary = True)
cv.fit(df['data'].values)
X = cv.transform(df)
X
<2x23 sparse matrix of type '<class 'numpy.int64'>'
with 0 stored elements in Compressed Sparse Row format>
you see that we are coming close to what we want. We just have to transform it right (transform each line):
cv = CountVectorizer(binary = True)
cv.fit(df['data'].values)
X = df['data'].apply(lambda x: cv.transform([x])).values
X
array([<1x23 sparse matrix of type '<class 'numpy.int64'>'
with 5 stored elements in Compressed Sparse Row format>,
...
<1x23 sparse matrix of type '<class 'numpy.int64'>'
with 3 stored elements in Compressed Sparse Row format>], dtype=object)
We have a more suitable X! Now we just need to check if we can split:
target = [1 if i<72 else 0 for i in range(8)] # The dataset is here of size 8
# the below line gives error
X_train, X_val, y_train, y_val = train_test_split(X, target, train_size = 0.50)
And it works!
You need to be sure you understand what CountVectorizer do to use it the right way
I am getting different shapes for my PCA using sklearn. Why isn't my transformation resulting in an array of the same dimensions like the docs say?
fit_transform(X, y=None)
Fit the model with X and apply the dimensionality reduction on X.
Parameters:
X : array-like, shape (n_samples, n_features)
Training data, where n_samples is the number of samples and n_features is the number of features.
Returns:
X_new : array-like, shape (n_samples, n_components)
Check this out with the iris dataset which is (150, 4) where I'm making 4 PCs:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn import decomposition
import seaborn as sns; sns.set_style("whitegrid", {'axes.grid' : False})
%matplotlib inline
np.random.seed(0)
# Iris dataset
DF_data = pd.DataFrame(load_iris().data,
index = ["iris_%d" % i for i in range(load_iris().data.shape[0])],
columns = load_iris().feature_names)
Se_targets = pd.Series(load_iris().target,
index = ["iris_%d" % i for i in range(load_iris().data.shape[0])],
name = "Species")
# Scaling mean = 0, var = 1
DF_standard = pd.DataFrame(StandardScaler().fit_transform(DF_data),
index = DF_data.index,
columns = DF_data.columns)
# Sklearn for Principal Componenet Analysis
# Dims
m = DF_standard.shape[1]
K = m
# PCA (How I tend to set it up)
M_PCA = decomposition.PCA()
A_components = M_PCA.fit_transform(DF_standard)
#DF_standard.shape, A_components.shape
#((150, 4), (150, 4))
but then when I use the same exact approach on my actual dataset (76, 1989) as in 76 samples and 1989 attributes/dimensions I get a (76, 76) array instead of (76, 1989)
DF_centered = normalize(DF_mydata, method="center", axis=0)
m = DF_centered.shape[1]
# print(m)
# 1989
M_PCA = decomposition.PCA(n_components=m)
A_components = M_PCA.fit_transform(DF_centered)
DF_centered.shape, A_components.shape
# ((76, 1989), (76, 76))
normalize is just a wrapper I made that subtracts the mean from each dimension.
(Note: this answer is adapted from my answer on Cross Validated here: Why are there only n−1 principal components for n data points if the number of dimensions is larger or equal than n?)
PCA (as most typically run) creates a new coordinate system by:
shifting the origin to the centroid of your data,
squeezes and/or stretches the axes to make them equal in length, and
rotates your axes into a new orientation.
(For more details, see this excellent CV thread: Making sense of principal component analysis, eigenvectors & eigenvalues.) However, step 3 rotates your axes in a very specific way. Your new X1 (now called "PC1", i.e., the first principal component) is oriented in your data's direction of maximal variation. The second principal component is oriented in the direction of the next greatest amount of variation that is orthogonal to the first principal component. The remaining principal components are formed likewise.
With this in mind, let's examine a simple example (suggested by #amoeba in a comment). Here is a data matrix with two points in a three dimensional space:
X = [ 1 1 1
2 2 2 ]
Let's view these points in a (pseudo) three dimensional scatterplot:
So let's follow the steps listed above. (1) The origin of the new coordinate system will be located at (1.5,1.5,1.5). (2) The axes are already equal. (3) The first principal component will go diagonally from what used to be (0,0,0) to what was originally (3,3,3), which is the direction of greatest variation for these data. Now, the second principal component must be orthogonal to the first, and should go in the direction of the greatest remaining variation. But what direction is that? Is it from (0,0,3) to (3,3,0), or from (0,3,0) to (3,0,3), or something else? There is no remaining variation, so there cannot be any more principal components.
With N=2 data, we can fit (at most) N−1=1 principal components.