def pca(dataset):
colors = ["r", "g", "b"]
labels = dataset[1]
label_names = dataset[2]
# Obtenemos el promedio de cada columna
(separated_data, tranposed, data) = common.separate_data(dataset)
means = data.mean(0)
std_data = data - means
# Obtenemos la matriz de covarianza
cov_mat = cov(std_data.T)
[values, vectors] = linalg.eig(cov_mat)
tuples = []
for i in xrange(len(values)):
tuples.append((values[i], vectors[i]))
sorted(tuples)
first_pc = tuples[0][1]
second_pc = tuples[1][1]
print(first_pc)
# Datos proyectados en distintas direcciones
projected_data_1 = [[], [], []]
projected_data_2 = [[], [], []]
for idx, row in enumerate(data):
projected_data_1[label_names.index(labels[idx])].append(dot(row, first_pc))
for idx, row in enumerate(data):
projected_data_2[label_names.index(labels[idx])].append(dot(row, second_pc))
label_names = ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]
# Ploteo con solo un PC
for i in xrange(len(colors) - 1):
for j in xrange(i + 1, len(colors)):
pyplot.plot(projected_data_1[i], zeros(len(projected_data_1[i])), "o" + colors[i])
pyplot.plot(projected_data_1[j], zeros(len(projected_data_1[j])), "o" + colors[j])
print("Clase " + colors[i] + ": " + label_names[i])
print("Clase " + colors[j] + ": " + label_names[j])
pyplot.show()
# Dos PC
for i in xrange(len(colors) - 1):
for j in xrange(i + 1, len(colors)):
pyplot.plot(projected_data_1[i], projected_data_2[i], "o" + colors[i])
pyplot.plot(projected_data_1[j], projected_data_2[j], "o" + colors[j])
print("Clase " + colors[i] + ": " + label_names[i])
print("Clase " + colors[j] + ": " + label_names[j])
pyplot.show()
# Igual que lo anterior, pero con 3 clases
for i in xrange(len(colors)):
pyplot.plot(projected_data_1[i], projected_data_2[i], "o" + colors[i])
print("Clase " + colors[i] + ": " + label_names[i])
pyplot.show()
def plot(dataset):
(separated_data, plot_data, numpy_data) = common.separate_data(dataset)
for i in xrange(0, 3): # Primer atributo = 1,2,3
for j in xrange(i + 1, 4): # Segundo atributo = 2,3,4
for k in xrange(0, len(plot_data)): # Para cada clase
pyplot.plot(plot_data[k][i], plot_data[k][j], 'o' + colors[k])
pyplot.xlabel(str(i + 1))
pyplot.ylabel(str(j + 1))
pyplot.show()
def plot(dataset):
(separated_data, plot_data, numpy_data) = common.separate_data(dataset)
for i in xrange(0, 3): # Primer atributo = 1,2,3
for j in xrange(i+1, 4): # Segundo atributo = 2,3,4
for k in xrange(0, len(plot_data)): # Para cada clase
pyplot.plot(plot_data[k][i], plot_data[k][j], 'o' + colors[k])
pyplot.xlabel(str(i+1))
pyplot.ylabel(str(j+1))
pyplot.show()
def fischer(dataset):
colors = ['r', 'g', 'b']
labels = dataset[1]
label_names = dataset[2]
# Obtenemos el promedio de cada columna
for i in xrange(len(label_names)): # Para cada clase de hace un one vs all
c1 = label_names[i]
new_labels = []
# Se crean nuevos labels para las clases: 0 y 1
for label in labels:
if label == c1:
new_labels.append(0)
else:
new_labels.append(1)
# Separacion de datos, nuevamente
(separated_data, tranposed, data) = common.separate_data((dataset[0], new_labels, [0, 1]))
#Calculo de medias
means = [ separated_data[0].mean(0), separated_data[1].mean(0) ]
# inicializamos las matrices de scatter
s1 = [[0,0,0,0], [0,0,0,0],[0,0,0,0],[0,0,0,0]]
s2 = [[0,0,0,0], [0,0,0,0],[0,0,0,0],[0,0,0,0]]
# Simplemente sacamos los scatters
for row in separated_data[0]:
m1 = array([row- means[0]])
m2 = array([row- means[0]]).transpose()
s1 = s1 + dot(m2, m1)
for row in separated_data[1]:
m1 = array([row- means[1]])
m2 = array([row- means[1]]).transpose()
s2 = s2 + dot(m2, m1)
# Within class scatter
sw = s1 + s2
inv_sw = inv(sw)
mean_diff = array([means[0]-means[1]]) # mu1 - mu2, es necesario llevarlo a un "doble arreglo" para multiplicar matrices
# Esta sera la direccion v optima
direction = dot(inv_sw, mean_diff.T)
p1 = [[],[]]
for idx, row in enumerate(data):
p1[[0, 1].index(new_labels[idx])].append(dot(row,direction))
# Ploteamos los datos proyectados
print('Rojo: ' + c1)
print('Azul: las otras')
pyplot.plot(p1[0], zeros(len(p1[0])), 'or')
pyplot.plot(p1[1], zeros(len(p1[1])), 'ob')
pyplot.show()
def pca(dataset):
colors = ['r', 'g', 'b']
labels = dataset[1]
label_names = dataset[2]
# Obtenemos el promedio de cada columna
(separated_data, tranposed, data) = common.separate_data(dataset)
means = data.mean(0)
std_data = data - means
# Obtenemos la matriz de covarianza
cov_mat = cov(std_data.T)
[values, vectors] = linalg.eig(cov_mat)
tuples = []
for i in xrange(len(values)):
tuples.append((values[i], vectors[i]))
sorted(tuples)
first_pc = tuples[0][1]
second_pc = tuples[1][1]
print(first_pc)
# Datos proyectados en distintas direcciones
projected_data_1 = [[], [], []]
projected_data_2 = [[], [], []]
for idx, row in enumerate(data):
projected_data_1[label_names.index(labels[idx])].append(
dot(row, first_pc))
for idx, row in enumerate(data):
projected_data_2[label_names.index(labels[idx])].append(
dot(row, second_pc))
label_names = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
# Ploteo con solo un PC
for i in xrange(len(colors) - 1):
for j in xrange(i + 1, len(colors)):
pyplot.plot(projected_data_1[i], zeros(len(projected_data_1[i])),
'o' + colors[i])
pyplot.plot(projected_data_1[j], zeros(len(projected_data_1[j])),
'o' + colors[j])
print('Clase ' + colors[i] + ": " + label_names[i])
print('Clase ' + colors[j] + ": " + label_names[j])
pyplot.show()
# Dos PC
for i in xrange(len(colors) - 1):
for j in xrange(i + 1, len(colors)):
pyplot.plot(projected_data_1[i], projected_data_2[i],
'o' + colors[i])
pyplot.plot(projected_data_1[j], projected_data_2[j],
'o' + colors[j])
print('Clase ' + colors[i] + ": " + label_names[i])
print('Clase ' + colors[j] + ": " + label_names[j])
pyplot.show()
# Igual que lo anterior, pero con 3 clases
for i in xrange(len(colors)):
pyplot.plot(projected_data_1[i], projected_data_2[i], 'o' + colors[i])
print('Clase ' + colors[i] + ": " + label_names[i])
pyplot.show()