Related
i am very new in machine learning. I stumble on this source code on github that has no database, so i decided to use my own database. This code is to recognize speaker with MFCC and GMM-UBM. But when i try to run the code, i got this error "ValueError: Found array with 1 sample(s) (shape=(1, 13)) while a minimum of 2 is required". It seems like when the code is trying to fit the GMM on the 68th dataset, the MFCC shape of the data is broken. I assume there's something wrong on the feature extraction process.
Please help me! thank you very much.
Here's the code
import python_speech_features as psf
from sklearn.mixture import GaussianMixture
from sklearn.externals import joblib
from scipy.io import wavfile
from functools import reduce
import numpy as np
from os import listdir
from os.path import isfile, join
import os
import re
DATA_PATH = 'dataCoba'
# Make a list of speakers from the newdata/data folder. The format for the files in the folder is
# name_1,wav for training and name_2.wav for testing
substring = "_2"
onlyfiles = [f for f in listdir(DATA_PATH) if isfile(join(DATA_PATH, f))]
onlyfiles.sort()
onlyones = []
for filename in onlyfiles:
dups = re.search('[\w]+_2.wav', filename)
#dups = re.search('[\w].wav', filename)
if dups is None:
onlyones.append(''.join(filename.split('_')[0]))
print(onlyones)
SPEAKERS = onlyones
TOTAL_SPEAKERS = len(SPEAKERS)
MODEL_SPEAKERS = len(SPEAKERS)
print(len(SPEAKERS))
class SpeakerRecognition:
# Create a GMM and UBM model for each speaker. The GMM is modelled after the speaker and UBM for each speaker
# is modelled after all the other speakers. Likelihood Ratio test is used to verify speaker
def setGMMUBM(self, no_components):
self.GMM = []
self.UBM = []
for i in range(MODEL_SPEAKERS):
self.GMM.append(GaussianMixture(n_components= no_components, covariance_type= 'diag'))
self.UBM.append(GaussianMixture(n_components= no_components, covariance_type= 'diag'))
# Load in data from .wav files in data/
# Extract mfcc (first 13 coefficients) from each audio sample
def load_data(self):
#training
self.spk = [wavfile.read(DATA_PATH + '/' + (str(i).replace('.wav','')) + '_1.wav') for i in SPEAKERS]
self.spk_mfcc = [psf.mfcc(self.spk[i][1], self.spk[i][0]) for i in range(0, TOTAL_SPEAKERS)]
#testing
self.p_spk = [wavfile.read(DATA_PATH + '/' + (str(i).replace('.wav','')) + '_2.wav') for i in SPEAKERS]
self.p_spk_mfcc = [psf.mfcc(self.p_spk[i][1], self.p_spk[i][0]) for i in range(0, TOTAL_SPEAKERS)]
print(self.spk_mfcc)
for i in range(TOTAL_SPEAKERS):
self.spk_train_size.append(len(self.spk_mfcc[i]))
self.spk_start.append(len(self.total_mfcc))
print("Speaker Number(train) = ",i)
print ("self.spk_mfcc[i] = ", len(self.spk_mfcc[i]))
for mfcc in self.spk_mfcc[i]:
self.total_mfcc.append(mfcc)
self.speaker_label.append(i)
self.spk_end.append(len(self.total_mfcc))
print("self.total_mfcc = ", len(self.total_mfcc))
print("\n")
for i in range(TOTAL_SPEAKERS):
#print("self.p_spk_mfcc =", self.p_spk_mfcc)
self.spk_test_size.append(len(self.p_spk_mfcc[i]))
self.spk_start.append(len(self.p_total_mfcc))
print("Speaker Num(test) = ",i)
print("self.p_spk_mfcc = ",len(self.p_spk_mfcc[i]))
print("MFCC Shape = ",self.spk_mfcc[i].shape)
for mfcc in self.p_spk_mfcc[i]:
self.p_total_mfcc.append(mfcc)
self.p_speaker_label.append(i)
self.p_spk_end.append(len(self.p_total_mfcc))
print("self.total_mfcc = ", len(self.p_total_mfcc))
print("\n")
# Gaussian Mixture Model is made of a number of Gaussian distribution components.
# To model data, a suitable number o gaussian components have to be selected.
# There is no method for finding this. It is done by trial and error. This runs
# the program for different values of component and records accuracy for each one
[![This is the error when i run the code][1]][1]
def find_best_params(self):
best_no_components = 1
maxacc = 0
for i in range(100, 256):
self.setGMMUBM(i)
self.fit_model()
_, acc, _ = self.predict()
print("Accuracy for n = {} is {}".format(i, acc))
if acc > maxacc:
maxacc = acc
best_no_components = i
return best_no_components
# Fit the GMM UBM models with training data
# fit = N buah data * dimensi data
def fit_model(self):
for i in range(MODEL_SPEAKERS):
print("Fit start for {}".format(i))
self.GMM[i].fit(self.spk_mfcc[i])
print(self.spk_mfcc[i].shape)
self.UBM[i].fit(self.total_mfcc[:self.spk_start[i]] + self.total_mfcc[self.spk_end[i]:])
print("Fit end for {}".format(i))
joblib.dump(self.UBM[i], 'dumps/new/ubm' + str(i) + '.pkl')
joblib.dump(self.GMM[i], 'dumps/new/gmm' + str(i) + '.pkl')
def model(self, no_components = 244):
self.setGMMUBM(no_components)
self.fit_model()
# Predict the output for each model for each speaker and produce confusion matrix
def load_model(self):
for i in range(0, MODEL_SPEAKERS):
self.GMM.append(joblib.load('dumps/new/gmm' + str(i) + '.pkl'))
self.UBM.append(joblib.load('dumps/new/ubm' + str(i) + '.pkl'))
def predict(self):
avg_accuracy = 0
confusion = [[ 0 for y in range(MODEL_SPEAKERS) ] for x in range(TOTAL_SPEAKERS)]
for i in range(TOTAL_SPEAKERS):
for j in range(MODEL_SPEAKERS):
x = self.GMM[j].score_samples(self.p_spk_mfcc[i]) - self.UBM[j].score_samples(self.p_spk_mfcc[i])
for score in x :
if score > 0:
confusion[i][j] += 1
confusion_diag = [confusion[i][i] for i in range(MODEL_SPEAKERS)]
diag_sum = 0
for item in confusion_diag:
diag_sum += item
remain_sum = 0
for i in range(MODEL_SPEAKERS):
for j in range(MODEL_SPEAKERS):
if i != j:
remain_sum += confusion[i][j]
spk_accuracy = 0
for i in range(MODEL_SPEAKERS):
best_guess, _ = max(enumerate(confusion[i]), key=lambda p: p[1])
print("For Accent {}, best guess is {}".format(SPEAKERS[i], SPEAKERS[best_guess]))
if i == best_guess:
spk_accuracy += 1
#print(MODEL_SPEAKERS)
spk_accuracy /= MODEL_SPEAKERS
avg_accuracy = diag_sum/(remain_sum+diag_sum)
return confusion, avg_accuracy, spk_accuracy
def __init__(self):
self.test_spk = []
self.test_mfcc = []
# Speaker data and corresponding mfcc
self.spk = []
self.spk_mfcc = []
self.p_spk = []
self.p_spk_mfcc = []
# Holds all the training mfccs of all speakers and
# speaker_label is the speaker label for the corresponding mfcc
self.total_mfcc = []
self.speaker_label = []
self.spk_train_size = [] # Index upto which is training data for that speaker.
self.p_total_mfcc = []
self.p_speaker_label = []
#print(self.p_speaker_label)
self.spk_test_size = []
# Since the length of all the audio files are different, spk_start and spk_end hold
self.spk_start = []
self.spk_end = []
self.p_spk_start = []
self.p_spk_end = []
self.GMM = []
self.UBM = []
self.load_data()
self.cepstral_mean_subtraction()
# Cepstral Mean Subtraction (Feature Normalization step)
def cepstral_mean_subtraction(self):
for i, speaker_mfcc in enumerate(self.spk_mfcc):
average = reduce(lambda acc, ele: acc + ele, speaker_mfcc)
average = list(map(lambda x: x/len(speaker_mfcc), average))
for j, feature_vector in enumerate(speaker_mfcc):
for k, feature in enumerate(feature_vector):
self.spk_mfcc[i][j][k] -= average[k]
for i, speaker_mfcc in enumerate(self.p_spk_mfcc):
average = reduce(lambda acc, ele: acc + ele, speaker_mfcc)
average = list(map(lambda x: x / len(speaker_mfcc), average))
for j, feature_vector in enumerate(speaker_mfcc):
for k, feature in enumerate(feature_vector):
self.p_spk_mfcc[i][j][k] -= average[k]
#TBD : Ten fold validation
def ten_fold():
#fold_size = 0.1 * self.n
fold_offset = 0.0
accuracy_per_fold = 0
average_accuracy = 0
for i in range(0, 10):
print("Fold start is {} and fold end is {} ".format( fold_offset, fold_offset + fold_size))
#accuracy = self.execute(int(fold_offset), int(fold_offset + fold_size))
#print("Accuracy is of test {} is : {} ".format(i, accuracy))
#average_accuracy += accuracy
#fold_offset += fold_size
average_accuracy /= 10.0
print("Average accuracy " + str(100 * average_accuracy))
return average_accuracy
# Final result is a confusion matrix which represents the accuracy of the fit of the model
if __name__ == '__main__':
SR = SpeakerRecognition()
#SR.load_model()
SR.setGMMUBM(no_components=13)
#SR.find_best_params()
SR.fit_model()
confusion, mfcc_accuracy, spk_accuracy = SR.predict()
print("Confusion Matrix")
print(np.matrix(confusion))
print("Accuracy in predicting speakers : {}".format(spk_accuracy))
print("Accuracy in testing for MFCC : {}".format(mfcc_accuracy))
I want to find these three Prestige measures for an existing graph using python:
Degree Prestige
Proximity Prestige
Rank Prestige
Can I use networkx for this purpose? If not, then which library can I use and how can I do it. Any links or references are appreciated.
Yes, you can but you to implement the measures by yourself as far as I know.
For instance, consider the Degree prestige defined as the number of incoming links to a node divided by the total possible number of incoming links.
In this case you could just calculate it as:
n_nodes = 10
d = nx.gnp_random_graph(n_nodes, 0.5, directed=True)
degree_prestige = dict((v,len(d.in_edges(v))/(n_nodes-1)) for v in d.nodes_iter())
Same for the other measures which can be easily implemented used the functions defined by networkx.
n_nodes = 5
d = nx.gnp_random_graph(n_nodes, 0.5, directed=True)
degree_prestige = dict((v,len(d.in_edges(v))/(n_nodes-1)) for v in d.nodes())
print("DEGREE PRESTIGE :\n")
for i in degree_prestige:
print(i, " : ", degree_prestige[i])
distance = []
temp_dis = 0
n = 0
for dest in d.nodes:
temp_dis = 0
n = 0
for src in d.nodes:
if (nx.has_path(d,src,dest) == True):
temp_dis = temp_dis + nx.shortest_path_length(d,source = src,target = dest)
n = n + 1
if temp_dis == 0:
distance.append([dest, 0])
else:
distance.append([dest, temp_dis/(n - 1)])
print("\nPROXIMITY PRESTIGE :\n")
for i in distance:
print(str(i[0]) + " : " + str(i[1]))
prominance = np.random.randint(1, 4, size=n_nodes)
print("\nASSUME PROMINANCE :\n")
print(prominance)
rank_prestige = np.zeros([n_nodes], dtype = int)
path_matrix = np.zeros([n_nodes, n_nodes], dtype = int)
i = 0
j = 0
for src in d.nodes:
for dest in d.nodes:
if d.has_edge(dest, src):
path_matrix[i][j] = 1
j = j+1
j = 0
i = i+1
for i in range(n_nodes):
pr_i = 0
for j in range(n_nodes):
pr_i = pr_i + path_matrix[i][j] * prominance[j]
rank_prestige[i] = pr_i
print("\nRANK PRESTIGE :\n")
print(rank_prestige)
I want to use FCBF technique from github https://github.com/shiralkarprashant/FCBF
The problem i faced is that i am working on Python 3 ad the module is implemented for python 2 users . I got the following error that describes that name 'xrange' is not defined because i work on python3
i think to solve the issue just by changing range by xrange
from FCBF_module import FCBF, FCBFK, FCBFiP, get_i
from sklearn.datasets import load_digits
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
import time
from sklearn.grid_search import GridSearchCV
classifiers = [('DecisionTree', DecisionTreeClassifier(), {'max_depth' : [5, 10, 15]}),
('LogisticRegression', LogisticRegression(), {'C' : [0.1, 1, 10]})]
n_features = dataCAD.shape[1]
npieces = get_i(n_features)
The module code contains just one xrange occurence i tried to change it by range but it does not solve the problem:
# -*- coding: utf-8 -*-
import numpy as np
def count_vals(x):
vals = np.unique(x)
occ = np.zeros(shape = vals.shape)
for i in range(vals.size):
occ[i] = np.sum(x == vals[i])
return occ
def entropy(x):
n = float(x.shape[0])
ocurrence = count_vals(x)
px = ocurrence / n
return -1* np.sum(px*np.log2(px))
def symmetricalUncertain(x,y):
n = float(y.shape[0])
vals = np.unique(y)
# Computing Entropy for the feature x.
Hx = entropy(x)
# Computing Entropy for the feature y.
Hy = entropy(y)
#Computing Joint entropy between x and y.
partial = np.zeros(shape = (vals.shape[0]))
for i in range(vals.shape[0]):
partial[i] = entropy(x[y == vals[i]])
partial[np.isnan(partial)==1] = 0
py = count_vals(y).astype(dtype = 'float64') / n
Hxy = np.sum(py[py > 0]*partial)
IG = Hx-Hxy
return 2*IG/(Hx+Hy)
def suGroup(x, n):
m = x.shape[0]
x = np.reshape(x, (n,m/n)).T
m = x.shape[1]
SU_matrix = np.zeros(shape = (m,m))
for j in range(m-1):
x2 = x[:,j+1::]
y = x[:,j]
temp = np.apply_along_axis(symmetricalUncertain, 0, x2, y)
for k in range(temp.shape[0]):
SU_matrix[j,j+1::] = temp
SU_matrix[j+1::,j] = temp
return 1/float(m-1)*np.sum(SU_matrix, axis = 1)
def isprime(a):
return all(a % i for i in xrange(2, a))
"""
get
"""
def get_i(a):
if isprime(a):
a -= 1
return filter(lambda x: a % x == 0, range(2,a))
"""
FCBF - Fast Correlation Based Filter
L. Yu and H. Liu. Feature Selection for High‐Dimensional Data: A Fast Correlation‐Based Filter Solution.
In Proceedings of The Twentieth International Conference on Machine Leaning (ICML‐03), 856‐863.
Washington, D.C., August 21‐24, 2003.
"""
class FCBF:
idx_sel = []
def __init__(self, th = 0.01):
'''
Parameters
---------------
th = The initial threshold
'''
self.th = th
def fit(self, x, y):
'''
This function executes FCBF algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.idx_sel = []
"""
First Stage: Computing the SU for each feature with the response.
"""
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
SU_list = SU_vec[SU_vec > self.th]
SU_list[::-1].sort()
m = x[:,SU_vec > self.th].shape
x_sorted = np.zeros(shape = m)
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = 0
x_sorted[:,i] = x[:,ind].copy()
self.idx_sel.append(ind)
"""
Second Stage: Identify relationships between feature to remove redundancy.
"""
j = 0
while True:
"""
Stopping Criteria:The search finishes
"""
if j >= x_sorted.shape[1]: break
y = x_sorted[:,j].copy()
x_list = x_sorted[:,j+1:].copy()
if x_list.shape[1] == 0: break
SU_list_2 = SU_list[j+1:]
SU_x = np.apply_along_axis(symmetricalUncertain, 0,
x_list, y)
comp_SU = SU_x >= SU_list_2
to_remove = np.where(comp_SU)[0] + j + 1
if to_remove.size > 0:
x_sorted = np.delete(x_sorted, to_remove, axis = 1)
SU_list = np.delete(SU_list, to_remove, axis = 0)
to_remove.sort()
for r in reversed(to_remove):
self.idx_sel.remove(self.idx_sel[r])
j = j + 1
def fit_transform(self, x, y):
'''
This function fits the feature selection
algorithm and returns the resulting subset.
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.fit(x, y)
return x[:,self.idx_sel]
def transform(self, x):
'''
This function applies the selection
to the vector x.
Parameters
---------------
x = dataset [NxM]
'''
return x[:, self.idx_sel]
"""
FCBF# - Fast Correlation Based Filter
B. Senliol, G. Gulgezen, et al. Fast Correlation Based Filter (FCBF) with a Different Search Strategy.
In Computer and Information Sciences (ISCIS ‘08) 23rd International Symposium on, pages 1‐4.
Istanbul, October 27‐29, 2008.
"""
class FCBFK(FCBF):
idx_sel = []
def __init__(self, k = 10):
'''
Parameters
---------------
k = Number of features to include in the
subset.
'''
self.k = k
def fit(self, x, y):
'''
This function executes FCBFK algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
self.idx_sel = []
"""
First Stage: Computing the SU for each feature with the response.
"""
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
SU_list = SU_vec[SU_vec > 0]
SU_list[::-1].sort()
m = x[:,SU_vec > 0].shape
x_sorted = np.zeros(shape = m)
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = 0
x_sorted[:,i] = x[:,ind].copy()
self.idx_sel.append(ind)
"""
Second Stage: Identify relationships between features to remove redundancy with stopping
criteria (features in x_best == k).
"""
j = 0
while True:
y = x_sorted[:,j].copy()
SU_list_2 = SU_list[j+1:]
x_list = x_sorted[:,j+1:].copy()
"""
Stopping Criteria:The search finishes
"""
if x_list.shape[1] == 0: break
SU_x = np.apply_along_axis(symmetricalUncertain, 0,
x_list, y)
comp_SU = SU_x >= SU_list_2
to_remove = np.where(comp_SU)[0] + j + 1
if to_remove.size > 0 and x.shape[1] > self.k:
for i in reversed(to_remove):
x_sorted = np.delete(x_sorted, i, axis = 1)
SU_list = np.delete(SU_list, i, axis = 0)
self.idx_sel.remove(self.idx_sel[i])
if x_sorted.shape[1] == self.k: break
if x_list.shape[1] == 1 or x_sorted.shape[1] == self.k:
break
j = j + 1
if len(self.idx_sel) > self.k:
self.idx_sel = self.idx_sel[:self.k]
"""
FCBFiP - Fast Correlation Based Filter in Pieces
"""
class FCBFiP(FCBF):
idx_sel = []
def __init__(self, k = 10, npieces = 2):
'''
Parameters
---------------
k = Number of features to include in the
subset.
npieces = Number of pieces to divide the
feature space.
'''
self.k = k
self.npieces = npieces
def fit(self, x, y):
'''
This function executes FCBF algorithm and saves indexes
of selected features in self.idx_sel
Parameters
---------------
x = dataset [NxM]
y = label [Nx1]
'''
"""
First Stage: Computing the SU for each feature with the response. We sort the
features. When we have a prime number of features we remove the last one from the
sorted features list.
"""
m = x.shape
nfeaturesPieces = int(m[1] / float(self.npieces))
SU_vec = np.apply_along_axis(symmetricalUncertain, 0, x, y)
x_sorted = np.zeros(shape = m, dtype = 'float64')
idx_sorted = np.zeros(shape = m[1], dtype = 'int64')
for i in range(m[1]):
ind = np.argmax(SU_vec)
SU_vec[ind] = -1
idx_sorted[i]= ind
x_sorted[:,i] = x[:,ind].copy()
if isprime(m[1]):
x_sorted = np.delete(x_sorted, m[1]-1, axis = 1 )
ind_prime = idx_sorted[m[1]-1]
idx_sorted = np.delete(idx_sorted, m[1]-1)
#m = x_sorted.shape
"""
Second Stage: Identify relationships between features into its vecinity
to remove redundancy with stopping criteria (features in x_best == k).
"""
x_2d = np.reshape(x_sorted.T, (self.npieces, nfeaturesPieces*m[0])).T
SU_x = np.apply_along_axis(suGroup, 0, x_2d, nfeaturesPieces)
SU_x = np.reshape(SU_x.T, (self.npieces*nfeaturesPieces,))
idx_sorted2 = np.zeros(shape = idx_sorted.shape, dtype = 'int64')
SU_x[np.isnan(SU_x)] = 1
for i in range(idx_sorted.shape[0]):
ind = np.argmin(SU_x)
idx_sorted2[i] = idx_sorted[ind]
SU_x[ind] = 10
"""
Scoring step
"""
self.scores = np.zeros(shape = m[1], dtype = 'int64')
for i in range(m[1]):
if i in idx_sorted:
self.scores[i] = np.argwhere(i == idx_sorted) + np.argwhere(i == idx_sorted2)
if isprime(m[1]):
self.scores[ind_prime] = 2*m[1]
self.set_k(self.k)
def set_k(self, k):
self.k = k
scores_temp = -1*self.scores
self.idx_sel = np.zeros(shape = self.k, dtype = 'int64')
for i in range(self.k):
ind = np.argmax(scores_temp)
scores_temp[ind] = -100000000
self.idx_sel[i] = ind
Try using 2to3 package for python to automatically convert the files. Worked for me!
https://docs.python.org/2/library/2to3.html
This is the voted perceptron algorithm:
#this is a pseudo code
#m is the number of examples
initialize k = 0, w1 := 0, c1 := 0
repeat for T epochs:
for i = 1 to i = m (this is one epoch)
if (x[i],y[i]) is classified correctly then
c[k] = c[k] + 1
otherwise:
w[k+1] = w[k] + y[i]x[i]
c[k+1]=1
k = k+1
The algorithm is reported at http://curtis.ml.cmu.edu/w/courses/index.php/Voted_Perceptron
I want to make a voted perceptron dual form. This is my pseudocode:
#m is the number of examples
Initialize k = 0, a1 := 0, c1 := 0
Repeat for T epochs:
for i = 1 to i = m
if (x[i], y[i]) is classified correctly then
c[k] = c[k] + 1
otherwise
k = k + 1
a[k][i] = a[k][i]+1
c[k] = 1
The output is the following list: (a_1, c1),(a_2,c2),...,(a_k,ck) where each a_i is a vector
Is it correct ? Must i add the bias ?
Here i report my python implementation of this voted dual perceptron:
class Perceptron(object):
def __init__(self, kernel = linear_kernel, epochs = 50):
self.kernel = kernel
self.epochs = epochs
def summation(self, a, y, x, xi, b):
s = 0
for j in range(0, len(x)):
s += (a[j]*y[j]*(self.kernel(x[j], xi))) + b
return s
def maxNorm(self, x):
v = np.linalg.norm(x[0])
for i in range(1, len(x)):
if (np.linalg.norm(x[i]) > v):
v = np.linalg.norm(x[i])
return v
def training(self, x, y):
k = 0
a = np.zeros(len(x), dtype=np.int)
alfa = []
alfa.append(a.copy())
print(alfa)
b = 0
bias = []
bias.append(0)
c = []
c.append(0)
for _ in range(self.epochs):
for i in range(len(y)):
if (y[i] * self.summation(a, y, x, x[i], b))<=0:
a[i] = a[i] + 1
alfa.append(a.copy())
b = b + (y[i]*(self.maxNorm(x)**2))
bias.append(b)
c.append(1)
k = k+1
else:
c[k] += 1
self.alfa = alfa
self.b = bias
self.c = c
print("b: ",len(self.b))
print("c: ",len(self.c))
def predict(self,xTest, yTest, xTrain, yTrain):
print("a: ",self.alfa)
print("\nc:", self.c)
print(yTest)
print(yTrain)
SumFin=0
Err = np.zeros(len(xTest))
nErr = 0
yPredict = []
for i in range(len(xTest)):
for j in range(len(self.c)):
print(self.c[j]*(np.sign(self.summation(self.alfa[i], yTrain, xTrain, xTest[i], self.b[i]))))
SumFin += (self.c[j]*(np.sign(self.summation(self.alfa[i], yTrain, xTrain, xTest[i], self.b[i]))))
yPredict.append(np.sign(SumFin))
for i in range(len(yTest)):
print("i = ",i," | yTest = ",yTest[i]," | yPredict = ",yPredict[i])
if(yTest[i] != yPredict[i]):
nErr += 1
Err[i] += 1
print("Error rate: ", ((100*nErr)/len(xTest)), "%")
self.Err = Err
I don't think this code work because if i predict the training set i get 75% of error rate.
Can anyone help me? Thanks
Training:
Voted Perceptron Training Algorithm
def voted_perceptron(x, target=y, nb_epoch=1):
k = v = c = 0
V = C = []
for epoch in nb_epoch:
for i in range(len(x)):
y_pred = sign(v*k)
if y_pred == y:
c += 1
v += y[i]*x[i]
c = 1
k += 1
V.append(v)
C.append(c)
return V,C
Prediction:
Voted Perceptron Prediction Algorithm
def vp_predict(V, C, X):
predictions = []
for x in X:
s = 0
for w,c in zip(V,C):
s = s + c*sign(np.dot(w,x))
predictions.append(sign(s))
return predictions
i'm beginner in machine learning and i'm trying to implement my first Naive Bayes by myself for better understanding. So, i have dataset from http://archive.ics.uci.edu/ml/datasets/Adult (american census data, classes are '<=50k' and '>50k').
Here is my python code:
#!/usr/bin/python
import sys
import csv
words_stats = {} # {'word': {'class1': cnt, 'class2': cnt'}}
words_cnt = 0
targets_stats = {} # {'class1': 3234, 'class2': 884} how many words in each class
class_stats = {} # {'class1': 7896, 'class2': 3034} how many lines in each class
items_cnt = 0
def train(dataset, targets):
global words_stats, words_cnt, targets_stats, items_cnt, class_stats
num = len(dataset)
for item in xrange(num):
class_stats[targets[item]] = class_stats.get(targets[item], 0) + 1
for i in xrange(len(dataset[item])):
word = dataset[item][i]
if not words_stats.has_key(word):
words_stats[word] = {}
tgt = targets[item]
cnt = words_stats[word].get(tgt, 0)
words_stats[word][tgt] = cnt + 1
targets_stats[tgt] = targets_stats.get(tgt, 0) + 1
words_cnt += 1
items_cnt = num
def classify(doc, tgt_set):
global words_stats, words_cnt, targets_stats, items_cnt
probs = {} #the probability itself P(c|W) = P(W|c) * P(c) / P(W)
pc = {} #probability of the class in document set P(c)
pwc = {} #probability of the word set in particular class. P(W|c)
pw = 1 #probability of the word set in documet set
for word in doc:
if word not in words_stats:
continue #dirty, very dirty
pw = pw * float(sum(words_stats[word].values())) / words_cnt
for tgt in tgt_set:
pc[tgt] = class_stats[tgt] / float(items_cnt)
for word in doc:
if word not in words_stats:
continue #dirty, very dirty
tgt_wrd_cnt = words_stats[word].get(tgt, 0)
pwc[tgt] = pwc.get(tgt, 1) * float(tgt_wrd_cnt) / targets_stats[tgt]
probs[tgt] = (pwc[tgt] * pc[tgt]) / pw
l = sorted(probs.items(), key = lambda i: i[1], reverse=True)
print probs
return l[0][0]
def check_results(dataset, targets):
num = len(dataset)
tgt_set = set(targets)
correct = 0
incorrect = 0
for item in xrange(num):
res = classify(dataset[item], tgt_set)
if res == targets[item]:
correct = correct + 1
else:
incorrect = incorrect + 1
print 'correct:', float(correct) / num, ' incorrect:', float(incorrect) / num
def load_data(fil):
data = []
tgts = []
reader = csv.reader(fil)
for line in reader:
d = [x.strip() for x in line]
if '?' in d:
continue
if not len(d):
continue
data.append(d[:-1])
tgts.append(d[-1:][0])
return data, tgts
if __name__ == '__main__':
if len(sys.argv) < 3:
print './program train_data.txt test_data.txt'
sys.exit(1)
filename = sys.argv[1]
fil = open(filename, 'r')
data, tgt = load_data(fil)
train(data, tgt)
test_file = open(sys.argv[2], 'r')
test_data, test_tgt = load_data(test_file)
check_results(test_data, tgt)
it gives ~61% of correct results. when i print probabilities i get the following:
{'<=50K': 0.07371606889800396, '>50K': 15.325378327213354}
but in case of correct classifier i expect to see sum of both probabilities equal to 1.
At first i thought the problem is in float underflow and tried to make all calculations in logarithms, but results were similiar.
i understand that omitting some words is gonna affect accuracy, but the probabilities are sooo wrong.
What do i do wrong or don't understand?
for your convinience i've uploaded dataset and python script here:
https://dl.dropboxusercontent.com/u/36180992/adult.tar.gz
Thank you for your help.
Naive Bayes doesn't compute a probability directly, rather it computes a "raw score" that is relatively compared to the other scores for each label in order to classify an instance. This score can easily be converted to a "probability" in the range of [0, 1]:
total = sum(probs.itervalues())
for label, score in probs.iteritems():
probs[label] = score / total
However, keep in mind this still doesn't represent a true probability, as mentioned in this answer:
naive Bayes tends to predict probabilities that are almost always either very close to zero or very close to one.