UrbanSoundClassifier.py

import librosa
import librosa.display
import os
import pandas as pd
import glob
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten

precedeString_Train = '.../Documents/UrbanSoundClassifier/train'
precedeString_Val = '.../Documents/UrbanSoundClassifier/validate'

#setup train
data, sampling_rate = librosa.load(precedeString_Train + '/Train/6999.wav')
plt.figure(figsize=(12,4))
librosa.display.waveplot(data,sr=sampling_rate)

train = pd.read_csv(precedeString_Train + '/train.csv')

print(train.Class.value_counts(normalize=True)) #distribution of data

def parser_Train(row):    #load files and extract features
    file_name = precedeString_Train + '/Train/' + str(row.ID) + '.wav'
    try:
      X, sample_rate = librosa.load(file_name,res_type='kaiser_fast') 
      mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40).T,axis=0) #MFCCS feature used to analyze data
    except Exception as e:
      print("Error encountered while parsing file: ", file_name)
      return None, None
    feature = mfccs
    label = row.Class
    print(file_name)
    return [feature,label]
        
temp = train.apply(parser_Train, axis=1)
temp.columns = ['feature', 'label']

X = np.array(temp.feature.tolist())
y = np.array(temp.label.tolist())

lb = LabelEncoder()
y = np_utils.to_categorical(lb.fit_transform(y))

#setup validation set

validate = pd.read_csv(precedeString_Val + '/validate.csv')
def parser_Val(row):    #load files and extract features
    file_name = precedeString_Val + '/Validate/' + str(row.ID) + '.wav'
    try:
      # here kaiser_fast is a technique used for faster extraction
      val_X, sample_rate = librosa.load(file_name,res_type='kaiser_fast') 
      # we extract mfcc feature from data
      mfccs = np.mean(librosa.feature.mfcc(y=val_X, sr=sample_rate, n_mfcc=40).T,axis=0) 
    except Exception as e:
      print("Error encountered while parsing file: ", file_name)
      return None, None
    feature = mfccs
    label = row.Class
    print(file_name)
    return [feature,label]
temp_Val = validate.apply(parser_Val, axis=1)
temp_Val.columns = ['feature', 'label']
val_X = np.array(temp_Val.feature.tolist())
val_Y = np.array(temp_Val.label.tolist())
lb2 = LabelEncoder()
val_Y = np_utils.to_categorical(lb2.fit_transform(val_Y))

#training
num_labels = y.shape[1]
filter_size = 2

model = Sequential()

model.add(Dense(256, input_shape = (40,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_labels))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
model.fit(X, y, batch_size=32, epochs=40, validation_data=(val_X, val_Y))

#testing
file_name = ".../Documents/UrbanSoundClassifier/test/Test/5.wav"
test_X, sample_rate = librosa.load(file_name,res_type='kaiser_fast')
mfccs = np.mean(librosa.feature.mfcc(y=test_X, sr=sample_rate, n_mfcc=40).T,axis=0)
test_X = np.array(mfccs)
print(model.predict(test_X)) #########ERROR##########

Data can be found here: https://drive.google.com/drive/u/0/folders/0By0bAi7hOBAFUHVXd1JCN3MwTEU

File test.csv that contained in your link doesn't include class column, where can I find validate dataset?