Clasificacion de Audio

# Importar librerias
import pandas as pd # Pandas
import numpy as np # Numpy
import matplotlib.pyplot as plt

from sklearn import preprocessing # para preprocesar los datos
from sklearn import tree # Decision tree
from sklearn.ensemble import AdaBoostClassifier # Ensamble de clasificadores usando AdaBoost
from sklearn.model_selection import cross_val_score # Para realizar crossvalidation
from sklearn.metrics import confusion_matrix, classification_report # Confusion Matrix y reporte de clasificacion
from sklearn.svm import SVC # Clasificador support vector machine

import IPython.display as ipd # Para reproducir audio en el Jupyter Notebook
print('Banana')
ipd.display(ipd.Audio('./Data/Audio/Banana/Track70.wav'))
print('Chair')
ipd.display(ipd.Audio('./Data/Audio/Chair/Track106.wav'))
print('Goodbye')
ipd.display(ipd.Audio('./Data/Audio/Goodbye/Track54.wav'))
print('Hello')
ipd.display(ipd.Audio('./Data/Audio/Hello/Track32.wav'))
print('IceCream')
ipd.display(ipd.Audio('./Data/Audio/IceCream/Track91.wav'))

# Caracteristicas extraidas
train    = pd.read_csv("Data/data-model.csv") # datos de entrenamiento
test     = pd.read_csv("Data/validation.csv") #datos de prueba

train.sample(10) #Tomar aleatoriamente 10 elementos de tabla

x = train[["meanfreq","sd","median","Q25","Q75","IQR","skew","kurt","sp.ent","sfm","mode","centroid",
           "peakf","meanfun","minfun","maxfun","meandom","mindom","maxdom","dfrange","modindx"]]
y = train["class"]

# Definir los algoritmos de machine learning
clh = tree.DecisionTreeClassifier(max_depth  = 7)
clf = AdaBoostClassifier(base_estimator= clh,n_estimators=10) # Adaboost

# Entrenar el adaBoost
clf.fit(x,y)

#  Aplicar el modelo a los datos
y_tree_pred = clf.predict(x)

# Valor medio del desempeño con cross validation
print('Desempeño Promedio en el set de entrenamiento = ')
print(np.mean(cross_val_score(clf, x, y, cv=8)))

# Ver la matriz de confusion
cm = confusion_matrix(y, y_tree_pred)
print(cm)

#Reporte de clasificacion
print(classification_report(y,y_tree_pred))

test_x = test[["meanfreq","sd","median","Q25","Q75","IQR","skew","kurt","sp.ent","sfm","mode",
               "centroid","peakf","meanfun","minfun","maxfun","meandom","mindom","maxdom","dfrange","modindx"]]
print('Desempeño promedio en el set de pruebas = ')
print(clf.score(test_x,test["class"]))

# función para graficar mejor la matriz de confusion
def plot_confusion_matrix(cm,
                          target_names,
                          title='Confusion matrix',
                          cmap=None,
                          normalize=True):
    """
    given a sklearn confusion matrix (cm), make a nice plot

    Arguments
    ---------
    cm:           confusion matrix from sklearn.metrics.confusion_matrix

    target_names: given classification classes such as [0, 1, 2]
                  the class names, for example: ['high', 'medium', 'low']

    title:        the text to display at the top of the matrix

    cmap:         the gradient of the values displayed from matplotlib.pyplot.cm
                  see http://matplotlib.org/examples/color/colormaps_reference.html
                  plt.get_cmap('jet') or plt.cm.Blues

    normalize:    If False, plot the raw numbers
                  If True, plot the proportions

    Usage
    -----
    plot_confusion_matrix(cm           = cm,                  # confusion matrix created by
                                                              # sklearn.metrics.confusion_matrix
                          normalize    = True,                # show proportions
                          target_names = y_labels_vals,       # list of names of the classes
                          title        = best_estimator_name) # title of graph

    Citiation
    ---------
    http://scikit-learn.org/stable/auto_examples/model_selection/plot_confusion_matrix.html

    """
    import matplotlib.pyplot as plt
    import numpy as np
    import itertools

    accuracy = np.trace(cm) / float(np.sum(cm))
    misclass = 1 - accuracy

    if cmap is None:
        cmap = plt.get_cmap('Blues')

    plt.figure(figsize=(8, 6))
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()

    if target_names is not None:
        tick_marks = np.arange(len(target_names))
        plt.xticks(tick_marks, target_names, rotation=45)
        plt.yticks(tick_marks, target_names)

    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]


    thresh = cm.max() / 1.5 if normalize else cm.max() / 2
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        if normalize:
            plt.text(j, i, "{:0.4f}".format(cm[i, j]),
                     horizontalalignment="center",
                     color="white" if cm[i, j] > thresh else "black")
        else:
            plt.text(j, i, "{:,}".format(cm[i, j]),
                     horizontalalignment="center",
                     color="white" if cm[i, j] > thresh else "black")


    plt.tight_layout()
    plt.ylabel('Clase Verdadera')
    plt.xlabel('Prediccion de clase\n accuracy={:0.4f}; misclass={:0.4f}'.format(accuracy, misclass))
    plt.show()

plot_confusion_matrix(cm           = cm,
                      normalize    = False,
                      target_names = ['Banana', 'chair', 'Goodby', 'Hello','Icecream'],
                      title        = "Confusion Matrix")

# Configurar el clasificador SVC
svcfit = SVC(C=0.01, kernel='linear')
x =  preprocessing.scale(x) # Escalar los datos

# Entrenar el modelo
svcfit.fit(x, y)

# Predicion con el modelo
y_svc_pred =svcfit.predict(x)

# Valor medio del desempeño con cross validation
print('Desempeño Promedio en el set de entrenamiento = ')
print(np.mean(cross_val_score(svcfit, x, y, cv=8)))

# Matriz de confusion
cm = confusion_matrix(y,y_svc_pred)
print(cm)

#Reporte de clasificacion
print(classification_report(y,y_svc_pred))

test_x     =  preprocessing.scale(test_x)
print('Desempeño Promedio en el set de test = ')
print(svcfit.score(test_x,test["class"]))

plot_confusion_matrix(cm           = cm,
                      normalize    = False,
                      target_names = ['Banana', 'chair', 'Goodby', 'Hello','Icecream'],
                      title        = "Confusion Matrix")