def performance_for_features(feat_idxs):
# train classifier
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(f_train_norm[:, feat_idxs], c_train)
# predict and evaluate performance
prediction = knn.predict(f_test_norm[:, feat_idxs])
return performance(prediction, c_test)
X_train = X_train[:, s_clean]
# Paso 3-Training: Normalizacion
# > Training: 211 x 387
X_train, a, b = normalize(X_train)
# Paso 4-Training: SFS
# > Training: 211 x 40
s_sfs = sfs(X_train, d_train, n_features=40, method="fisher", show=True)
X_train = X_train[:, s_sfs]
# Paso 5-Training: PCA
# > Training: 211 x 10
X_train, _, A, Xm, _ = pca(X_train, n_components=10)
# *** DEFINCION DE DATOS PARA EL TESTING ***
X_test = X_test[:, s_clean] # Paso 2: clean
X_test = X_test * a + b # Paso 3: normalizacion
X_test = X_test[:, s_sfs] # Paso 4: SFS
X_test = np.matmul(X_test - Xm, A) # Paso 5: PCA
# *** ENTRENAMIENTO CON DATOS DE TRAINING Y PRUEBA CON DATOS DE TESTING ***
knn = KNN(n_neighbors=1)
knn.fit(X_train, d_train)
Y_pred = knn.predict(X_test)
accuracy = performance(Y_pred, d_test)
print("Accuracy = " + str(accuracy))
# Leemos los datos.
mat1 = loadmat('DATOS1.mat')
mat2 = loadmat('DATOS2.mat')
# Cantidad de features.
N_FEATURES = 15
# Obtenemos X,Y
X, Y = mat2["X"], mat2["Y"].squeeze()
# Selección de features
selected_feats = sfs(X, Y, n_features=N_FEATURES, method="fisher", show=False)
# Separamos los datos de entrenamiento y testing.
Xtrain, Ytrain = mat1["Xtrain"], mat1["Ytrain"].squeeze()
Xtest, Ytest = mat1["Xtest"], mat1["Ytest"].squeeze()
# Se definen Xtrain_new,Xtest_new con las features seleccionadas.
Xtrain_new, Xtest_new = Xtrain[:, selected_feats], Xtest[:, selected_feats]
# Se define el modelo y se entrena.
knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(Xtrain_new, Ytrain)
# Se obtiene la predicción
Ypred_new = knn.predict(Xtest_new)
# Computamos el accuracy.
result = performance(Ypred_new, Ytest)
print(result)
(c) Solución proporcionada por:
Germán Leandro Contreras Sagredo, Daniel Vives
Santiago de Chile, 04 de Abril de 2019
Universidad Católica de Chile
'''
# Librerías a utilizar
from scipy.io import loadmat # Lectura de archivos.
from sklearn.neighbors import KNeighborsClassifier # Modelo KNN
from pybalu.performance_eval import performance # Cómputo del accuracy.
# Leemos los datos.
mat = loadmat('DATOS1.mat')
# Separamos los datos de entrenamiento y testing.
Xtrain, Ytrain = mat["Xtrain"], mat["Ytrain"].squeeze()
Xtest, Ytest = mat["Xtest"], mat["Ytest"].squeeze()
# Se define el modelo y se entrena.
knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(Xtrain, Ytrain)
# Se obtiene la predicción
Ypred = knn.predict(Xtest)
# Computamos el accuracy.
result = performance(Ypred, Ytest)
print(result)