def test_variance_k_best_random_tree_k_fold(self):
# Feature Selection
samples, responses = open_model("models.obj")
samples = np.array(samples)
responses = np.array(responses)
FeatureSelection = True
if FeatureSelection:
selection = VarianceThreshold(threshold=0.00)
selection.fit(samples)
idxs = selection.get_support(indices=True)
samples = samples[:, idxs]
samples = preprocessing.scale(samples)
# Stratified cross-validation
scv = StratifiedKFold(responses, n_folds=10)
sum = 0
for i, (train, test) in enumerate(scv):
print('Case %d' % (i))
# Modeling
rdmForest = RandomForest_scikit()
# Train
init = time()
rdmForest.train(samples[train, :], responses[train])
# Test
a, confusionPre = rdmForest.test(samples[test, :], responses[test], True)
print('Time: %0.3fs' % (time() - init))
for idx, fila in enumerate(confusionPre):
for jdx, entrada in enumerate(fila):
if idx != jdx:
sum += entrada
print("Wrong Cases: "+str(sum))
print(' Full Case ')
rdmForest = RandomForest_scikit()
rdmForest.train(samples, responses)
rdmForest.test(samples, responses, True)
def upper(self):
model = FeatureSelectionScikit()
rdmForestPre = RandomForest_scikit()
rdmForest = RandomForest_scikit()
file = open("models.obj", 'r')
models = pickle.load(file)
samples = models[0]
responses = models[1]
'''
pca = decomposition.PCA()
X_digits = samples
y_digits = responses
pca.fit(X_digits)
plt.figure(1, figsize=(4, 3))
plt.clf()
plt.axes([.2, .2, .7, .7])
plt.plot(pca.explained_variance_, linewidth=2)
plt.axis('tight')
plt.xlabel('n_components')
plt.ylabel('explained_variance_')
plt.show()
'''
# Scaled data
#samplesScaled = preprocessing.scale(samples)
samplesScaled = samples
model.fit(samplesScaled, responses)
variablesImportance = model.importance()
mean = np.mean(variablesImportance)
std = np.std(variablesImportance)
fig1 = plt.figure(1, figsize=(4, 3))
ax1 = fig1.add_subplot(111)
ax1.plot(variablesImportance, linewidth=2)
basicPre = []
indices = []
minimo = min(variablesImportance)
for i, value in enumerate(variablesImportance):
if value > minimo:
basicPre.append(value)
indices.append(i)
print('Escogi %d' % (len(basicPre)))
fig2 = plt.figure(2, figsize=(4, 3))
ax2 = fig2.add_subplot(111)
ax2.plot(basicPre, linewidth=2)
newSample = []
for i, fila in enumerate(samplesScaled):
newSample.append([val for is_good, val in izip(indices, fila) if is_good])
t0 = time()
rdmForestPre.train(newSample, responses)
a, confusionPre = rdmForestPre.test(newSample, responses, True)
preTiempo = (time() - t0)
print("With Preprocessing %0.3fs" % (preTiempo))
sumPre = 0
for idx, fila in enumerate(confusionPre):
for jdx, entrada in enumerate(fila):
if idx != jdx:
sumPre += entrada
t0 = time()
rdmForest.train(samples, responses)
a, confusion = rdmForest.test(samples, responses, True)
Tiempo = time() - t0
print("Without Preprocessing %0.3fs" % (Tiempo))
print("Preprocessing/Without = %0.3fs" % (1.0 * preTiempo / Tiempo))
sum = 0
for idx, fila in enumerate(confusion):
for jdx, entrada in enumerate(fila):
if idx != jdx:
sum += entrada
print(str(sumPre), str(sum), float(1.0 * sumPre / sum))
plt.show()
