def _evaluate(self, Gs, Gs_kwargs, num_gpus):
minibatch_size = num_gpus * self.minibatch_per_gpu
# Construct TensorFlow graph for each GPU.
result_expr = []
for gpu_idx in range(num_gpus):
with tf.device('/gpu:%d' % gpu_idx):
Gs_clone = Gs.clone()
# Generate images.
latents = tf.random_normal([self.minibatch_per_gpu] + Gs_clone.input_shape[1:])
labels = self._get_random_labels_tf(self.minibatch_per_gpu)
dlatents = Gs_clone.components.mapping.get_output_for(latents, labels, **Gs_kwargs)
images = Gs_clone.get_output_for(latents, None, **Gs_kwargs)
# Downsample to 256x256. The attribute classifiers were built for 256x256.
if images.shape[2] > 256:
factor = images.shape[2] // 256
images = tf.reshape(images, [-1, images.shape[1], images.shape[2] // factor, factor, images.shape[3] // factor, factor])
images = tf.reduce_mean(images, axis=[3, 5])
# Run classifier for each attribute.
result_dict = dict(latents=latents, dlatents=dlatents[:,-1])
for attrib_idx in self.attrib_indices:
classifier = misc.load_pkl(classifier_urls[attrib_idx])
logits = classifier.get_output_for(images, None)
predictions = tf.nn.softmax(tf.concat([logits, -logits], axis=1))
result_dict[attrib_idx] = predictions
result_expr.append(result_dict)
# Sampling loop.
results = []
for begin in range(0, self.num_samples, minibatch_size):
self._report_progress(begin, self.num_samples)
results += tflib.run(result_expr)
results = {key: np.concatenate([value[key] for value in results], axis=0) for key in results[0].keys()}
# Calculate conditional entropy for each attribute.
conditional_entropies = defaultdict(list)
for attrib_idx in self.attrib_indices:
# Prune the least confident samples.
pruned_indices = list(range(self.num_samples))
pruned_indices = sorted(pruned_indices, key=lambda i: -np.max(results[attrib_idx][i]))
pruned_indices = pruned_indices[:self.num_keep]
# Fit SVM to the remaining samples.
svm_targets = np.argmax(results[attrib_idx][pruned_indices], axis=1)
for space in ['latents', 'dlatents']:
svm_inputs = results[space][pruned_indices]
try:
svm = sklearn.svm.LinearSVC()
svm.fit(svm_inputs, svm_targets)
svm.score(svm_inputs, svm_targets)
svm_outputs = svm.predict(svm_inputs)
except:
svm_outputs = svm_targets # assume perfect prediction
# Calculate conditional entropy.
p = [[np.mean([case == (row, col) for case in zip(svm_outputs, svm_targets)]) for col in (0, 1)] for row in (0, 1)]
conditional_entropies[space].append(conditional_entropy(p))
def leave_one_out_cv(gram_matrix, labels, alg = 'SVM'):
"""
leave-one-out cross-validation
"""
scores = []
preds = []
loo = sklearn.cross_validation.LeaveOneOut(len(labels))
for train_index, test_index in loo:
X_train, X_test = gram_matrix[train_index][:,train_index], gram_matrix[test_index][:, train_index]
y_train, y_test = labels[train_index], labels[test_index]
if(alg == 'SVM'):
svm = sklearn.svm.SVC(kernel = 'precomputed')
svm.fit(X_train, y_train)
preds += svm.predict(X_test).tolist()
score = svm.score(X_test, y_test)
elif(alg == 'kNN'):
knn = sklearn.neighbors.KNeighborsClassifier()
knn.fit(X_train, y_train)
preds += knn.predict(X_test).tolist()
score = knn.score(X_test, y_test)
scores.append(score)
print "Mean accuracy: %f" %(np.mean(scores))
print "Stdv: %f" %(np.std(scores))
return preds, scores
def train(df_train, df_test):
X_train = df_train.drop('income', axis=1)
y_train = df_train['income']
X_test = df_train.drop('income', axis=1)
y_test = df_train['income']
start = time.time()
lr = LogisticRegression(penalty='l1', tol=0.01)
lr.fit(X_train, y_train)
start = cost_times(start, 'lr.fit')
score = lr.score(X_test, y_test)
start = cost_times(start, 'lr.score')
print("LR : ", score)
from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
start = cost_times(start, 'rfc.fit')
score = rfc.score(X_test, y_test)
start = cost_times(start, 'rfc.score')
print("RF : ", score)
from sklearn import svm
svm = svm.SVC()
svm.fit(X_train, y_train)
start = cost_times(start, 'svc.fit')
score = svm.score(X_test, y_test)
start = cost_times(start, 'svc.score')
print("SVM : ", score)
def k_fold_cv(gram_matrix, labels, folds = 10, alg = 'SVM', shuffle = True):
"""
K-fold cross-validation
"""
pdb.set_trace()
scores = []
preds = []
loo = sklearn.cross_validation.KFold(len(labels), folds, shuffle = shuffle, random_state = random.randint(0,100))
#loo = sklearn.cross_validation.LeaveOneOut(len(labels))
for train_index, test_index in loo:
X_train, X_test = gram_matrix[train_index][:,train_index], gram_matrix[test_index][:, train_index]
y_train, y_test = labels[train_index], labels[test_index]
if(alg == 'SVM'):
svm = sklearn.svm.SVC(kernel = 'precomputed')
svm.fit(X_train, y_train)
preds += svm.predict(X_test).tolist()
score = svm.score(X_test, y_test)
elif(alg == 'kNN'):
knn = sklearn.neighbors.KNeighborsClassifier()
knn.fit(X_train, y_train)
preds += knn.predict(X_test).tolist()
score = knn.score(X_test, y_test)
scores.append(score)
print "Mean accuracy: %f" %(np.mean(scores))
print "Stdv: %f" %(np.std(scores))
return preds, scores
def SVM(X_train, X_test, y_train, y_test):
filenames = [
'SVM1.sav', 'SVM2.sav', 'SVM3.sav', 'SVM4.sav', 'SVM5.sav', 'SVM7.sav',
'SVM6.sav', 'SVM8.sav', 'SVM9.sav'
]
c = [1, 1000, 1000000]
ker = ['linear', 'poly', 'rbf']
training_time, testing_time, max_accuracy = 0, 0, 0
for i in range(len(c)):
for j in range(len(ker)):
k = i * len(c) + j
filename = filenames[k]
if os.path.exists(filename):
svm = pickle.load(open(filename, 'rb'))
else:
t1 = time.time()
svm = OneVsRestClassifier(SVC(kernel=ker[j],
C=c[i])).fit(X_train, y_train)
t2 = time.time()
training_time = max(training_time, t2 - t1)
pickle.dump(svm, open(filename, 'wb'))
t1 = time.time()
accuracy = svm.score(X_test, y_test) * 100
t2 = time.time()
testing_time = max(testing_time, t2 - t1)
max_accuracy = max(accuracy, max_accuracy)
print('One VS Rest SVM accuracy with kernel={} and c={} is : {}%'.
format(ker[j], c[i], accuracy))
return training_time, training_time, max_accuracy
def train_svm(train, labels_train, test, labels_test, dims):
if dims == 0:
#Train as is
new_train = train
new_test = test
else:
svd_t = skd.TruncatedSVD(n_components=dims)
pca = PCA(n_components=dims)
pca.fit(train)
pca_train = pca.transform(train)
inv_pca_train = pca.inverse_transform(pca_train)
#pca.fit(test);
#pca_test=pca.transform(test);
svd_t.fit(train)
new_train = svd_t.transform(train)
#new_train=svd.transform(train);
svd_t.fit(test)
new_test = svd_t.transform(test)
#new_test=svd.transform(test);
svm = SVC(decision_function_shape='ovo')
# svm=LinearSVC(max_iter=10000);
svm.fit(inv_pca_train, labels_train)
predicted = svm.predict(test)
ac = svm.score(test, labels_test)
print("Scoring ", ac)
#print("predicted", predicted.shape);
return ac
def train_model(self, X_train_cv, y_train, X_test_cv, y_test):
"""
This function will train_model & retun accuracy, f1_score.
:param X_train_cv, y_train, X_test_cv, y_test: Training data
:return: f1, accuracy
"""
svm = sklearn.svm.LinearSVC(C=0.1)
svm.fit(X_train_cv, y_train)
pred = svm.predict(X_test_cv)
f1 = sklearn.metrics.f1_score(pred, y_test, average='weighted')
accuracy = int(round(svm.score(X_test_cv, y_test) * 100))
return svm, f1, accuracy
def SVR_rbf(dates, prices, test_date, sl_df, forcastingDays):
svm = SVR(kernel='rbf', C=1e3, gamma=0.1)
sl_trainX, sl_trainY, sl_testX, sl_testY, sl_trainX_close, sl_trainY_close, sl_testX_close, sl_testY_close = create_sl_stock_preprocessed_Dataset(
sl_df)
X_train, X_test, y_train, y_test = train_test_split(sl_trainX,
sl_trainY,
test_size=0.33,
random_state=42)
X_train_close, X_test_close, y_train_close, y_test_close = train_test_split(
sl_trainX_close, sl_trainY_close, test_size=0.33, random_state=42)
df = sl_df[['close']]
forecast_out = int(
forcastingDays) # predicting forcastingDays days into future
df['Prediction'] = df[['close']].shift(-forecast_out)
X = np.array(df.drop(['Prediction'], 1))
X = preprocessing.scale(X)
X_forecast = X[-forecast_out:] # set X_forecast equal to last 30
X = X[:-forecast_out] # remove last forcastingDays from X
y = np.array(df['Prediction'])
y = y[:-forecast_out]
X_train_f, X_test_f, y_train_f, y_test_f = train_test_split(X,
y,
test_size=0.2)
svm.fit(X_train_f, y_train_f)
confidence = svm.score(X_test_f, y_test_f)
forecast_prediction = svm.predict(X_forecast)
svm.fit(sl_trainX, sl_trainY)
svm.fit(sl_trainX_close, sl_trainY_close)
svm_decision_boundary = svm.predict(sl_trainX)
predict_decision_boundary_close = svm.predict(sl_trainX_close)
svm_y_pred = svm.predict(X_test)
svm_reg_y_pred_close = svm.predict(X_test_close)
svm_test_score = mean_squared_error(y_test, svm_y_pred)
mean_squared_error_test_score_close = mean_squared_error(
y_test_close, svm_reg_y_pred_close)
svm_prediction = svm.predict(sl_testX)[0]
prediction_of_svm_close = svm.predict(sl_testX_close)[0]
return svm_decision_boundary, svm_prediction, svm_test_score, prediction_of_svm_close, forecast_prediction
def svm_inference(self, data, confidence, svm, norm=True, in_test=False):
print('\tPerforming SVM inference')
Nt = len(data)
print(Nt)
acc1 = 0
acc2 = 0
total1 = 0
total2 = 0
conf_new = np.zeros(confidence.shape)
cur_line = 0
for i in range(Nt):
word = data[i]
word_len = word.shape[0]
# print(word.shape)
Y = word[:, -1]
if in_test:
self.test_labels[cur_line:cur_line + word_len] = Y
# TODO: implemented iterative context inference
W_prime = np.zeros(
(word_len, self.dtr + self.n_classes * self.window_size * 2))
# W_prime : [X | extended context]
W_prime[:, :self.dtr] = word[:, :self.dtr]
W_prime[:, self.dtr:] = self.extend_context(
confidence[cur_line:(cur_line + word_len), :])
# y_hat = svm.predict(W_prime) # Predictions
conf = svm.decision_function(
W_prime) # Confidence measures of predictions
if norm:
conf = (1 + np.exp(
-1 * conf))**-1 # Sigmoid function --> Normalization
conf_new[cur_line:cur_line + word_len, :] = conf
cur_line += word_len
# Calculate accuracy rates
total1 += word_len
total2 += 1
subtask_acc = svm.score(W_prime, Y)
acc2 += subtask_acc
acc1 += subtask_acc * word_len
# print('\t\tShort-term accuracy: ' + str(subtask_acc))
return acc1 / total1, acc2 / total2, conf_new
def run(attrib_idx):
results = np.load("principal_directions/wspace_att_%d.npy" %
attrib_idx).item()
pruned_indices = list(range(results['latents'].shape[0]))
# pruned_indices = sorted(pruned_indices, key=lambda i: -np.max(results[attrib_idx][i]))
# keep = int(results['latents'].shape[0] * 0.95)
# print('Keeping: %d' % keep)
# pruned_indices = pruned_indices[:keep]
# Fit SVM to the remaining samples.
svm_targets = np.argmax(results[attrib_idx][pruned_indices], axis=1)
space = 'dlatents'
svm_inputs = results[space][pruned_indices]
svm = sklearn.svm.LinearSVC(C=1.0, dual=False, max_iter=10000)
svm.fit(svm_inputs, svm_targets)
svm.score(svm_inputs, svm_targets)
svm_outputs = svm.predict(svm_inputs)
w = svm.coef_[0]
np.save("principal_directions/direction_%d" % attrib_idx, w)
def svm_inference(self, data, confidence, svm, norm=True, in_test=False):
print('\tPerforming SVM inference')
Nt = len(data)
print(Nt)
acc1 = 0
acc2 = 0
total1 = 0
total2 = 0
conf_new = np.zeros(confidence.shape)
cur_line = 0
for i in range(Nt):
word = data[i]
word_len = word.shape[0]
# print(word.shape)
Y = word[:, -1]
if in_test:
self.test_labels[cur_line:cur_line+word_len] = Y
# TODO: implemented iterative context inference
W_prime = np.zeros((word_len, self.dtr + self.n_classes * self.window_size * 2))
# W_prime : [X | extended context]
W_prime[:, :self.dtr] = word[:, :self.dtr]
W_prime[:, self.dtr:] = self.extend_context(confidence[cur_line:(cur_line + word_len), :])
# y_hat = svm.predict(W_prime) # Predictions
conf = svm.decision_function(W_prime) # Confidence measures of predictions
if norm:
conf = (1 + np.exp(-1*conf))**-1 # Sigmoid function --> Normalization
conf_new[cur_line : cur_line+word_len, :] = conf
cur_line += word_len
# Calculate accuracy rates
total1 += word_len
total2 += 1
subtask_acc = svm.score(W_prime, Y)
acc2 += subtask_acc
acc1 += subtask_acc * word_len
# print('\t\tShort-term accuracy: ' + str(subtask_acc))
return acc1/total1, acc2/total2, conf_new
def train_svm(cls, train_x, train_y):
"""
train the binary SVM
:param cls: the class that this SVM is about
:param train_x: descriptors
:param train_y: corresponding labels
:return: the weight and bias of the SVM
"""
svm = sklearn.svm.LinearSVC(max_iter=1000)
svm.C = C[cls]
svm.fit(train_x, train_y)
error = 1 - svm.score(train_x, train_y)
print('Training Error for "{}" : {:.4f}'.format(cls, error))
w = svm.coef_
b = svm.intercept_
return w, b
def SVM(X_train, X_test, y_train, y_test, withpca, pca):
filenames = []
if withpca == 1:
filenames = [
'SVM1pca' + str(pca) + '.sav', 'SVM2pca' + str(pca) + '.sav',
'SVM3pca' + str(pca) + '.sav', 'SVM4pca' + str(pca) + '.sav',
'SVM5pca' + str(pca) + '.sav', 'SVM7pca' + str(pca) + '.sav',
'SVM6pca' + str(pca) + '.sav', 'SVM8pca' + str(pca) + '.sav',
'SVM9pca' + str(pca) + '.sav'
]
else:
filenames = [
'SVM1.sav', 'SVM2.sav', 'SVM3.sav', 'SVM4.sav', 'SVM5.sav',
'SVM7.sav', 'SVM6.sav', 'SVM8.sav', 'SVM9.sav'
]
c = [0.1, 1, 1000]
ker = ['linear', 'poly', 'rbf']
training_time, testing_time, max_accuracy = 0, 0, 0
max_model = None
for i in range(len(c)):
for j in range(len(ker)):
k = i * len(c) + j
filename = filenames[k]
if os.path.exists(filename):
svm = pickle.load(open(filename, 'rb'))
else:
t1 = time.time()
svm = OneVsRestClassifier(SVC(kernel=ker[j],
C=c[i])).fit(X_train, y_train)
t2 = time.time()
training_time = max(training_time, t2 - t1)
pickle.dump(svm, open(filename, 'wb'))
t1 = time.time()
accuracy = svm.score(X_test, y_test) * 100
t2 = time.time()
testing_time = max(testing_time, t2 - t1)
if accuracy > max_accuracy:
max_accuracy = accuracy
max_model = svm
max_accuracy = max(accuracy, max_accuracy)
# print('One VS Rest SVM accuracy with kernel={} and c={} is : {}%'.format(ker[j], c[i], accuracy))
y_pred = max_model.predict(X_test)
conf_mat = confusion_matrix(y_test, y_pred)
print("conf_mat of SVM ")
print(conf_mat)
return training_time, testing_time, max_accuracy
def SVM(request):
pk = request.user.id
student = Student.objects.get(user=pk)
df = pd.DataFrame(list(Student.objects.all().values()))
df = df.loc[df['user_id'] == pk]
df = df.drop(["user_id", "id", "Department_DS", "Department_SVM","Department_KNN" ,"DS_acc",
"SVM_acc" , "KNN_acc"], axis=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, shuffle=True)
svm = SVC(kernel="linear", C=0.025, random_state=101)
svm.fit(X_train, y_train)
y_pred = svm.predict(X_test)
Dep_pred = svm.predict(df)
accuracy = svm.score(X_test, y_test)
student.Department_SVM = list(Dep_pred)[0]
student.SVM_acc = format(accuracy * 100,".2f")
form = StudentObj(instance=student)
form = StudentObj(request.POST, instance=student)
if form.is_valid():
form.save()
return request
def svm_classifiation_score(self,
X,
y,
C=1.0,
kernel='rbf',
gamma='auto',
degree=3):
"""
Returns the classifiation score on the learnt encoding using a SVM with specified parameters.
The data X and the labels y are splitted into training and tesing sets.
"""
H = self.encode(X)
H_train, H_test, Y_train, Y_test = train_test_split(H,
y,
test_size=0.1)
svm = svm.SVC(C=C,
kernel=kernel,
gamma=gamma,
degree=degree,
cache_size=600)
svm.fit(H_train, Y_train)
return svm.score(H_test, Y_test)
def chapter_13():
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = \
train_test_split(cancer.data, cancer.target, stratify=cancer.target, random_state=66)
if 0: # Cross validation
tree = DecisionTreeClassifier(criterion='entropy',
max_depth=3,
random_state=0)
scores = cross_val_score(tree, cancer.data, cancer.target, cv=5)
print("Cross validation scores :{}".format(scores))
print("Cross validation scores(mean):{:.5}".format(scores.mean()))
if 0: # Grid search ex
best_score = 0
best_param = {}
for gamma in [0.001, 0.01, 0.1, 1, 10, 100]:
for C in [0.001, 0.01, 0.1, 1, 10, 100]:
svm = SVC(gamma=gamma, C=C)
svm.fit(X_train, y_train)
score = svm.score(X_test, y_test)
if score > best_score:
best_score = score
best_param = {'C': C, 'gamma': gamma}
print("Best score:{:.2f}".format(best_score))
print("Parameters in best score:{}".format(best_param))
if 0:
param_grid = {
'C': [10**i for i in range(-3, 2)],
'gamma': [10**i for i in range(-3, 2)]
}
grid_search = GridSearchCV(SVC(), param_grid, cv=5)
grid_search.fit(X_train, y_train)
print("Test set score:{:.2f}".format(grid_search.score(X_test,
y_test)))
print("Best parameters:{}".format(grid_search.best_params_))
print("Best cross-validation score:{:.2f}".format(
grid_search.best_score_))
if 0:
model = SVC(gamma=0.001, C=1)
model.fit(X_train, y_train)
print("train:", clf.__class__.__name__, model.score(X_train, y_train))
print("test :", clf.__class__.__name__, model.score(X_test, y_test))
pred_svc = model.predict(X_test)
confusion_m = confusion_matrix(y_test, pred_svc)
print("Confution matrix:\n{}".format(confusion_m))
print("Precision score: {:.3f}".format(
precision_score(y_true=y_test, y_pred=pred_svc)))
print("Recall score : {:.3f}".format(
recall_score(y_true=y_test, y_pred=pred_svc)))
print("F1 score : {:.3f}".format(
f1_score(y_true=y_test, y_pred=pred_svc)))
if 0:
model = LogisticRegression()
lrmodelfit = model.fit(X_train, y_train)
prob_result = pd.DataFrame(lrmodelfit.predict_proba(X_test))
prob_result.columns = ["malignant", "benign"]
for threhold, flg in zip([0.4, 0.3, 0.15, 0.05],
["flg_04", "flg_03", "flg_015", "flg_005"]):
prob_result[flg] = prob_result["benign"].map(
lambda x: 1 if x > threhold else 0)
print(prob_result.head(15))
fig, ax = plt.subplots()
for flg in ["flg_04", "flg_03", "flg_015", "flg_005"]:
confusion_m = confusion_matrix(y_test, prob_result[flg])
print("◆ThreholdFlg:", flg)
print("Confution matrix:\n{}".format(confusion_m))
fpr = (confusion_m[0, 1]) / (confusion_m[0, 0] + confusion_m[0, 1])
tpr = (confusion_m[1, 1]) / (confusion_m[1, 0] + confusion_m[1, 1])
plt.scatter(fpr, tpr)
plt.xlabel("fpr")
plt.ylabel("tpr")
ax.annotate(flg, (fpr, tpr))
# plt.show()
if 0:
X = cancer.data
y = cancer.target
y = label_binarize(y, classes=[0, 1])
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=.5,
random_state=0)
classifier = OneVsRestClassifier(
SVC(kernel='linear', probability=True, random_state=0))
y_score = classifier.fit(X_train, y_train).decision_function(X_test)
# fpr:偽陽性率、tpr:真陽性率を計算
fpr, tpr, _ = roc_curve(y_test, y_score)
roc_auc = auc(fpr, tpr)
plt.plot(fpr,
tpr,
color='red',
lw=2,
label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='black', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="best")
plt.show()
if 0: # jack-knife
random.seed(0)
norm_random_sample_data = random.randn(1000)
mean_array = np.array([])
for i in range(0, len(norm_random_sample_data)):
ind = np.ones(1000, dtype=bool)
extract_num = [i]
ind[i] = False
mean_array = np.append(mean_array,
norm_random_sample_data[ind].mean())
x = (mean_array - mean_array.mean())**2
print(np.sqrt(x.sum() * 999 / 1000))
mean_array_boot = np.array([])
for i in range(0, len(norm_random_sample_data)):
mean_array_boot = \
np.append(mean_array_boot, random.choice(norm_random_sample_data, 500, replace=True).mean())
x = (mean_array_boot - mean_array_boot.mean())**2
print(np.sqrt(x.sum() / 1000))
if 0: # Bagging
bagging = BaggingClassifier(KNeighborsClassifier(),
max_samples=0.5,
max_features=0.5)
clf = bagging
clf.fit(X_train, y_train)
print("train:", clf.__class__.__name__, clf.score(X_train, y_train))
print("test:", clf.__class__.__name__, clf.score(X_test, y_test))
if 0: # Boosting
clf = AdaBoostClassifier(learning_rate=1.0)
clf.fit(X_train, y_train)
print("train:", clf.__class__.__name__, clf.score(X_train, y_train))
print("test:", clf.__class__.__name__,
clf.score(X_test, y_test)) # 若干、オーバーフィッティングしている
score_list = []
for r in np.arange(0.00001, 2, 0.01):
clf = AdaBoostClassifier(learning_rate=r)
clf.fit(X_train, y_train)
score_list.append([r, clf.score(X_test, y_test)])
score_list_df = pd.DataFrame(score_list)
score_list_df.columns = ["r", "score"]
plt.plot(score_list_df.r, score_list_df.score)
plt.xlabel("learning rate")
plt.ylabel("test score")
plt.grid(True)
plt.show()
if 1: # Random forest
f_model = RandomForestClassifier(random_state=0)
clf = f_model.fit(X_train, y_train)
print("train:", clf.__class__.__name__, clf.score(X_train, y_train))
print("test:", clf.__class__.__name__, clf.score(X_test, y_test))
importances = f_model.feature_importances_
indi = np.argsort(importances)[::-1]
label = cancer.feature_names
plt.bar(range(X_train.shape[1]), importances[indi])
plt.xticks(range(X_train.shape[1]), label[indi], rotation=90)
plt.grid(True)
plt.tight_layout()
plt.show()
df['Size'] = df['Size'].apply(lambda x: x.strip('M'))
df[df['Size'] == 'Varies with device'] = 0
df['Size'] = df['Size'].astype(float)
#take specific attributes
features = ['Size','Type', 'Price', 'Content Rating', 'Genres']
X = df[features]
y = df['Rating'].astype(int)
#spite for train and test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 10)
svm = svm.SVR()
svm.fit(X_train, y_train)
accuracy = svm.score(X_test,y_test)
print('Accuracy: ' + str(np.round(accuracy*100, 2)) + '%')
window = tk.Tk()
window.title('Predict Rate App')
window.geometry('800x350')
window.configure(background='gray')
def calculate_number():
df['Size'] = size_entry.get()
df['Type'] = type_entry.get()
X_test = [(x, np.empty((0, 2), dtype=np.int)) for x in x_test]
print len(x_test)
for i in range(len(test_labels)):
test_labels = test_labels.astype(int)
"""
print len(test_labels)
pbl = GraphCRF(inference_method='ad3')
svm = NSlackSSVM(pbl, C=1,n_jobs = 1,verbose = 1)
start = time()
print len(X_valid)
print len(valid_Y)
svm.fit(X_valid, valid_Y)
print "fit finished"
time_svm = time() - start
print X_test[i][0].shape
print svm.score(X_valid,valid_Y)
print svm.score(X_test,test_Y)
y_pred = np.vstack(svm.predict(np.array(X_valid)))
print("Score with pystruct crf svm: %f (took %f seconds)"
% (np.mean(y_pred == valid_Y), time_svm))
y_predt = np.vstack(svm.predict(np.array(X_test)))
print("Score with pystruct crf svm: %f (took %f seconds)"
% (np.mean(y_predt == test_Y), time_svm))
#we throw away void superpixels and flatten everything
#y_pred, y_true = np.hstack(y_pred), np.hstack(valid_Y)
#y_pred = y_pred[y_true != 255]
#y_true = y_true[y_true != 255]
#print("Score on test set: %f" % np.mean(y_true == y_pred))
knn = neighbors.KNeighborsClassifier(n_neighbors = 100)
knn.fit(x_train,y_train)
prediction = knn.predict(x_test)
print("knn score:", knn.score(x_test,y_test))
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, prediction))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, prediction))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, prediction)))
#%% svm
from sklearn import svm
svm = svm.SVC(random_state=1)
svm.fit(x_train,y_train)
prediction_svm = svm.predict(x_test)
print("svm accuary: ",svm.score(x_test,y_test))
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, prediction_svm))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, prediction_svm))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, prediction_svm)))
#%% rf classification
from sklearn import ensemble
rf= ensemble.RandomForestClassifier(n_estimators=10,random_state=1)
rf.fit(x_train,y_train)
prediction_rf = rf.predict(x_test)
print("rf accuracy: ",rf.score(x_test,y_test))
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, prediction_rf))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, prediction_rf))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, prediction_rf)))
print('\n Testing set Accuracy:' + str(100 * np.mean((predicted_label == test_label).astype(float))) + '%')
print(confusion_matrix(test_label, predicted_label, labels = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]))
stop_time_LR = time.time() - start_time_LR
print("Time taken for Logistic Regression {}.seconds\n".format(str(stop_time_LR)))
# Code for SVM
print("Learning SVM Using Linear Kernel")
svm = SVC(kernel = 'linear')
#train_label = train_label.flatten()
indexes = np.random.randint(50000, size = 10000)
sample_data = train_data[indexes, :]
sample_label = train_label[indexes, :]
svm.fit(sample_data, sample_label.flatten())
traning_accuracy = svm.score(train_data, train_label)
traning_accuracy = str(100*traning_accuracy)
print("Traning data Accuracy for Linear Kernel: {}%\n".format(traning_accuracy))
validation_accuracy = svm.score(validation_data, validation_label)
validation_accuracy = str(100*validation_accuracy)
print("Validation data Accuracy for Linear Kernel: {}%\n".format(validation_accuracy))
test_accuracy = svm.score(test_data, test_label)
test_accuracy = str(100*test_accuracy)
print("Test data Accuracy for Linear Kernel: {}%\n".format(test_accuracy))
time_linear_kernel = time.time() - start_time_linear_kernel
print("Time taken for SVM using Linear Kernel {}.seconds\n\n\n".format(str(time_linear_kernel)))
print("SVM with radial basis function with value of gamma setting to 1 ")
start_time_rbf = time.time()
X = scaler.transform(X)
#split dataset into train and test data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.1,
random_state=1,
stratify=y)
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, stratify=y)
# Create SVM classifier
svm.fit(X_train, y_train)
score_vals = dict()
score_vals['bins'] = biin
score_vals['score'] = svm.score(X_test, y_test)
scores.append(score_vals)
print(score_vals)
# calculate best run parameters
print(scores)
scores_list = [record['score'] for record in scores]
# best_run = [record for record in scores if record['score'] == np.max(scores)]
best_run = [
record for record in scores if record['score'] == np.max(scores_list)
]
print(best_run)
# save best trained model
biin = best_run[0]['bins']
print('Running to save the best model for bin = {}'.format(biin))
# Sample 3.3: Bagging
import pandas as pd
from sklearn import svm
from sklearn.model_selection import train_test_split
from sklearn.ensemble import BaggingClassifier
from sklearn.linear_model import LogisticRegression
data = pd.read_csv('wifi.txt', header=None)
X = data.values[:, :-1]
y = data.values[:, -1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
bagging = BaggingClassifier()
svm = svm.SVC()
logreg = LogisticRegression()
bagging.fit(X_train, y_train)
svm.fit(X_train, y_train)
logreg.fit(X_train, y_train)
print("Bagging Accuracy: %.2f%s" % (bagging.score(X_test, y_test) * 100, '%'))
print("SVM Accuracy: %.2f%s" % (svm.score(X_test, y_test) * 100, '%'))
print("LogReg Accuracy: %.2f%s" % (logreg.score(X_test, y_test) * 100, '%'))
def score(test_data, test_labels):
global svm
return svm.score(test_data, test_labels)
def main():
mnist = fetch_openml(name='mnist_784')
echantillon = np.random.randint(70000, size=5000)
data = mnist.data[echantillon]
target = mnist.target[echantillon]
xtrain, xtest, ytrain, ytest = train_test_split(data,
target,
train_size=0.7)
classifier = svm.SVC(kernel='linear')
classifier.fit(xtrain, ytrain)
error = 1 - classifier.score(xtest, ytest)
print(f"Score SVM linéaire : {error}")
kernels = []
print("Modification du kernel : ")
for kernel in ['linear', 'poly', 'rbf', 'sigmoid']:
classifier = svm.SVC(kernel=kernel)
start_training = time.time()
classifier.fit(xtrain, ytrain)
final_training = time.time() - start_training
start_prediction = time.time()
ypred = classifier.predict(xtest)
final_prediction = time.time() - start_prediction
error = metrics.zero_one_loss(ytest, ypred)
kernels.append((kernel, final_training, final_prediction, error))
print(f"\t {kernels[-1]}")
kernels_liste = list(zip(*kernels))
plot_fig(kernels_liste)
tol = []
print("Evolution de la tolérance : ")
for tolerance in np.linspace(0.1, 1.0, num=5):
svm = svm.SVC(C=tolerance)
start_training = time.time()
svm.fit(xtrain, ytrain)
final_training = time.time() - start_training
start_prediction = time.time()
ypred = svm.predict(xtest)
final_prediction = time.time() - start_prediction
error = metrics.zero_one_loss(ytest, ypred)
error_training = svm.score(xtrain, ytrain)
tol.append((tolerance, final_training, final_prediction, error,
error_training))
print(f"\t {tol[-1]}")
tol_list = list(zip(*tol))
plot_fig(tol_list)
plt.figure(figsize=(19, 9))
plt.plot(tol_list[0], tol_list[3], 'x-', color='blue') # erreur de test
plt.plot(tol_list[0], tol_list[-1], 'x-',
color='orange') # erreur d'entrainement
plt.grid(True)
plt.show()
best_kernel = 'rbf'
best_tolerance = 1.0
best_svm = svm.SVC(kernel=best_kernel, C=best_tolerance)
start_training = time.time()
best_svm.fit(xtrain, ytrain)
best_final_entrainement = time.time() - start_training
start_prediction = time.time()
ypred = best_svm.predict(xtest)
best_final_prediction = time.time() - start_prediction
cross_val = model_selection.cross_val_score(best_svm, data, target, cv=10)
meilleure_erreur = 1 - np.mean(cross_val)
print(f"Durée de l'entraînement : {best_final_entrainement}")
print(f"Durée de la prédiction : {best_final_prediction}")
print(f"Erreur : {meilleure_erreur}")
cm = confusion_matrix(ytest, ypred)
df_cm = pd.DataFrame(cm, columns=np.unique(ytest), index=np.unique(ytest))
df_cm.index.name = 'Valeur réelle'
df_cm.columns.name = 'Valeur prédite'
plt.figure(figsize=(16, 9))
sn.heatmap(df_cm, cmap="Blues", annot=True)
plt.show()
print('Accuracy of GNB classifier on training set: {:.2f}'.format(
gnb.score(X_train, Y_train)))
print('Accuracy of GNB classifier on test set: {:.2f}'.format(
gnb.score(X_test, Y_test)))
def svc_param_selection(X, y, nfolds):
from sklearn import svm
import numpy as np
GridSearchCV = sklearn.model_selection.GridSearchCV
Cs = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
# gammas = [0.001, 0.01, 0.1, 1]
kernels = ['linear', 'rbf']
param_grid = {'C': Cs, 'kernel': kernels}
grid_search = GridSearchCV(svm.SVC(), param_grid, cv=nfolds)
grid_search.fit(X, y)
return grid_search.best_params_
# Learning
params = svc_param_selection(X_train, Y_train, 3)
print params
svm = SVC(**params)
# svm = SVC()
svm.fit(X_train, Y_train)
print('Accuracy of SVM classifier on training set: {:.2f}'.format(
svm.score(X_train, Y_train)))
print('Accuracy of SVM classifier on test set: {:.2f}'.format(
svm.score(X_test, Y_test)))
#svm, X1, Y1, cv=bs)#, score_func=metrics.f1_score)
#print 'score: %f +- %f' % (scores.mean(), scores.std())
#pred_Y = svm.predict(test_X)
#print metrics.precision_score(test_Y, pred_Y)
#print metrics.recall_score(test_Y, pred_Y)
#print metrics.f1_score(test_Y, pred_Y)
#pred_Y = svm.predict(X1)
#print metrics.precision_score(Y1, pred_Y)
#print metrics.recall_score(Y1, pred_Y)
#print metrics.f1_score(Y1, pred_Y)
alpha_arr = []
for label in np.unique(labels):
n = np.sum(labels == label)
alpha_arr.append(n / float(labels.shape[0]))
alpha_arr = np.array(alpha_arr)
alpha = np.max(alpha_arr)
print alpha
bs = cross_validation.Bootstrap(data.shape[0], 3)
for train_indices, test_indices in bs:
svm.fit(data[train_indices], labels[train_indices])
score = svm.score(data[test_indices], labels[test_indices])
print score, (score - alpha) / (1 - alpha)
#pred = svm.predict(data[test_indices])
# Splitting data
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=44, shuffle=True
)
# ----------------------------------------------------
# Applying LogisticRegression Model
svm = svm.SVC()
svm.fit(X_train, y_train)
# Calculating Details
print("svm Train Score is : ", svm.score(X_train, y_train))
print("svm Test Score is : ", svm.score(X_test, y_test))
print("svm Classes are : ", svm.classes_)
print("----------------------------------------------------")
# Calculating Prediction
y_pred = svm.predict(X_test)
print("Predicted Value for svm is : ", y_pred[:10])
# ----------------------------------------------------
# Calculating Confusion Matrix
CM = confusion_matrix(y_test, y_pred)
print("Confusion Matrix is : \n", CM)
# drawing confusion matrix
sns.heatmap(CM, center=True)
#One fight at a time
le = LabelEncoder()
cat = ['genre','certificate', 'distributor']
for col in cat:
train[col] = le.fit_transform(train[col])
test[col] = le.fit_transform(test[col])
#no shirts, no shoes
train_X = train.drop(['year','oscar', 'movie_name', 'actor_name', 'href'], axis=1)
test_X = test.drop(['year','oscar', 'movie_name', 'actor_name', 'href'], axis = 1)
train_Y = train['oscar']
#Fights will go on as long as they want to
svm =svm.SVC(kernel='rbf',C=1).fit(train_X,train_Y)
svm.score(train_X, train_Y)
#If this is your first night at Fight Club, you have to fight.
pred_svm = svm.predict_proba(test_X)[:,1]
svm_prediction = pd.DataFrame(pred_svm, test['movie_name'])
X = data.values[:, :-1]
y = data.values[:, -1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
svm = svm.SVC(probability=True)
logreg = LogisticRegression()
tree = tree.DecisionTreeClassifier()
svm.fit(X_train, y_train)
logreg.fit(X_train, y_train)
tree.fit(X_train, y_train)
print("SVM Accuracy: %.2f%s" %
(svm.score(X_test, y_test) * 100, '%'))
print("LogReg Accuracy: %.2f%s" %
(logreg.score(X_test, y_test) * 100, '%'))
print("Tree Accuracy: %.2f%s" %
(tree.score(X_test, y_test) * 100, '%'))
w = [1, 1, 1]
ensemble = VotingClassifier(
estimators=[('svm', svm),
('logreg', logreg),
('tree', tree)],
voting='hard', weights=w)
ensemble.fit(X_train, y_train)
print("Ensemble Accuracy: %.2f%s" %
(ensemble.score(X_test, y_test) * 100, '%'))
def _evaluate(self, Gs, Gs_kwargs, num_gpus):
minibatch_size = num_gpus * self.minibatch_per_gpu
inception = misc.load_pkl(
'https://drive.google.com/uc?id=1MzTY44rLToO5APn8TZmfR7_ENSe5aZUn'
) # inception_v3_features.pkl
real_activations = np.empty(
[self.num_images, inception.output_shape[1]], dtype=np.float32)
fake_activations = np.empty(
[self.num_images, inception.output_shape[1]], dtype=np.float32)
# Construct TensorFlow graph.
self._configure(self.minibatch_per_gpu, hole_range=self.hole_range)
real_img_expr = []
fake_img_expr = []
real_result_expr = []
fake_result_expr = []
for gpu_idx in range(num_gpus):
with tf.device('/gpu:%d' % gpu_idx):
Gs_clone = Gs.clone()
inception_clone = inception.clone()
latents = tf.random_normal([self.minibatch_per_gpu] +
Gs_clone.input_shape[1:])
reals, labels = self._get_minibatch_tf()
reals_tf = tflib.convert_images_from_uint8(reals)
masks = self._get_random_masks_tf()
fakes = Gs_clone.get_output_for(latents, labels, reals_tf,
masks, **Gs_kwargs)
fakes = tflib.convert_images_to_uint8(fakes[:, :3])
reals = tflib.convert_images_to_uint8(reals_tf[:, :3])
real_img_expr.append(reals)
fake_img_expr.append(fakes)
real_result_expr.append(inception_clone.get_output_for(reals))
fake_result_expr.append(inception_clone.get_output_for(fakes))
for begin in tqdm(range(0, self.num_images, minibatch_size)):
self._report_progress(begin, self.num_images)
end = min(begin + minibatch_size, self.num_images)
real_results, fake_results = tflib.run(
[real_result_expr, fake_result_expr])
real_activations[begin:end] = np.concatenate(real_results,
axis=0)[:end - begin]
fake_activations[begin:end] = np.concatenate(fake_results,
axis=0)[:end - begin]
# Calculate FID conviniently.
mu_real = np.mean(real_activations, axis=0)
sigma_real = np.cov(real_activations, rowvar=False)
mu_fake = np.mean(fake_activations, axis=0)
sigma_fake = np.cov(fake_activations, rowvar=False)
m = np.square(mu_fake - mu_real).sum()
s, _ = scipy.linalg.sqrtm(np.dot(sigma_fake, sigma_real), disp=False)
dist = m + np.trace(sigma_fake + sigma_real - 2 * s)
self._report_result(np.real(dist), suffix='-FID')
svm = sklearn.svm.LinearSVC(dual=False)
svm_inputs = np.concatenate([real_activations, fake_activations])
svm_targets = np.array([1] * real_activations.shape[0] +
[0] * fake_activations.shape[0])
svm.fit(svm_inputs, svm_targets)
self._report_result(1 - svm.score(svm_inputs, svm_targets),
suffix='-U')
real_outputs = svm.decision_function(real_activations)
fake_outputs = svm.decision_function(fake_activations)
self._report_result(np.mean(fake_outputs > real_outputs), suffix='-P')
#%%
svm = sklearn.svm.SVR()
Cs = numpy.logspace(0, 2, 8)
gammas = numpy.logspace(-6, -4, 10)
accuracies = numpy.zeros((8, 10))
for i, c in enumerate(Cs):
for j, gamma in enumerate(gammas):
svm = sklearn.svm.SVR(C = c, gamma = gamma)
svm.fit(trainingx[:1000], trainingy[:1000])
accuracies[i, j] = svm.score(testingx, testingy)
print i, j
plt.imshow(accuracies, interpolation = 'NONE')
plt.xticks(range(10), ['{:2.2e}'.format(v) for v in gammas])
plt.yticks(range(8), ['{:2.1e}'.format(v) for v in Cs])
plt.gcf().set_size_inches((10, 10))
plt.colorbar()
plt.show()
#%%
svm = sklearn.svm.SVR(C = 5.0, gamma = 1e-5)
svm.fit(trainingx[:1000], trainingy[:1000])
print svm.score(testingx, testingy)
df.drop(['scan_date', 'dod', 'Measure.volume', 'Braak_Lewy', 'Braak_NFT', 'Braak_AB'], axis=1, inplace=True)
X_train, X_test, y_train, y_test = train_test_split(df.drop('Group', axis=1), df['Group'], test_size=0.30, random_state=101)
#logistic regression model
lr=LogisticRegression()
lr.fit(X_train, y_train)
y_pred = lr.predict(X_test)
print("LR Training:", lr.score(X_train, y_train))
print("LR Test:", lr.score(X_test, y_test))
print(classification_report(y_test, y_pred))
#SVM model
svm = svm.SVC(kernel='linear')
svm.fit(X_train, y_train)
y_pred = svm.predict(X_test)
print("SVM Training:", svm.score(X_train, y_train))
print("SVM Test:", svm.score(X_test, y_test))
print(classification_report(y_test, y_pred))
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.neighbors import KNeighborsClassifier
# Define the classifiers
classifiers = [LogisticRegression(), LinearSVC(), SVC(), KNeighborsClassifier()]
# Fit the classifiers
for c in classifiers:
c.fit(X_train, y_train)
# Plot the classifiers
from sklearn import svm
#Don't forget to change this value AND also The filename on the second to last line!
experiment_number = 10
print "Loading datasets..."
#train_samples = pickle.load(open("Models/SC/trainset%d.pkl"%experiment_number,'rb'))
#train_samples = pickle.load(open("Models/AutoE/trainset%d.pkl"%experiment_number,'rb'))
train_samples = pickle.load(open("Models/RBM/trainset%d.pkl"%experiment_number,'rb'))
train_outputs = pickle.load(open("Models/train_outputs.pkl",'rb'))[:1000]
#valid_samples = pickle.load(open("Models/SC/validset%d.pkl"%experiment_number,'rb'))
#valid_samples = pickle.load(open("Models/AutoE/validset%d.pkl"%experiment_number,'rb'))
valid_samples = pickle.load(open("Models/RBM/validset%d.pkl"%experiment_number,'rb'))
valid_outputs = pickle.load(open("Models/valid_outputs.pkl",'rb'))[:1000]
print "Training the svm"
svm = svm.SVC() # Default uses RBF
svm.fit(train_samples, train_outputs)
print "Predicting..."
train_score = svm.score(train_samples,train_outputs)
valid_score = svm.score(valid_samples,valid_outputs)
print "Training accuracy: %.3f, validation accuracy¸: %.3f"%(train_score, valid_score)
#Save the output to file.
with open("Outputs/RBM_param_tests.txt", "a") as myfile:
myfile.write("Experiment %d, training accuracy: %.3f, validation accuracy: %.3f \n"%(experiment_number,train_score, valid_score))
"""#> **SVM**"""
from sklearn import svm
svm = svm.SVC(C=1000)
svm.get_params
svm.fit(X_train,y_train)
y_svm = svm.predict(X_test)
svm.score(X_train,y_train)
svm.score(X_test,y_test)
generate_model_report(y_test,y_svm)
from yellowbrick.classifier.rocauc import roc_auc
roc_auc(svm, X_train, y_train, X_test=X_test, y_test=y_test, classes=["Low_damage","Medium_damage","High_damage"])
# from sklearn.model_selection import GridSearchCV
# parameters={"C":[1,10,100,500,1000],'gamma':['auto','scale']}
# sv = GridSearchCV(svm, parameters,scoring= 'f1',
# cv=5)
# sv.fit(X_train,y_train)
# params = sv.best_params_
# svm2 = svm.SVC()
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
for svm, title, ax in zip(models, titles, sub.flatten()):
Z = svm.predict(np.c_[xx.ravel(), yy.ravel()])
plot_contours(ax, svm, xx, yy, cmap=plt.cm.brg, alpha=0.8)
#Z = Z.reshape(xx.shape)
#plt.figure(1, figsize=(4, 3))
#plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
#ax.scatter(X_train[:, 0], X_train[:, 1], c=Y_train, cmap=plt.cm.brg, s=20, edgecolors='k')
ax.scatter(X_test[:, 0],
X_test[:, 1],
c=Y_test,
cmap=plt.cm.brg,
s=20,
edgecolors='k',
marker='D')
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xlabel('Sepal length')
ax.set_ylabel('Sepal width')
ax.set_xticks(())
ax.set_yticks(())
ax.set_title(title + ' \n traning error: ' +
str(round(100 * (1 - svm.score(X_train, Y_train)), 2)) + '%'
' \n test error: ' +
str(round(100 * (1 - svm.score(X_test, Y_test)), 2)) + '%')
plt.show()
svm.fit(X_train, y_train)
predictions = svm.predict(X_test)
# KNN
knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
predictions = knn.predict(X_test)
plt.title("KNN Predictions vs Actual")
plt.scatter(y_test, predictions)
plt.xlabel("Actual Values")
plt.ylabel("Predictions")
plt.show()
# Adapted from https://towardsdatascience.com/solving-a-simple-classification-problem-with-python-fruits-lovers-edition-d20ab6b071d2
print('Accuracy of Logistic regression classifier on training set: {:.2f}'
.format(lm.score(X_train, y_train)))
print('Accuracy of Logistic regression classifier on test set: {:.2f}'
.format(lm.score(X_test, y_test)))
print('Accuracy of SVM classifier on training set: {:.2f}'
.format(svm.score(X_train, y_train)))
print('Accuracy of SVM classifier on test set: {:.2f}'
.format(svm.score(X_test, y_test)))
print('Accuracy of K-NN classifier on training set: {:.2f}'
.format(knn.score(X_train, y_train)))
print('Accuracy of K-NN classifier on test set: {:.2f}'
.format(knn.score(X_test, y_test)))
cv = CountVectorizer(token_pattern=r"(?u)\b\w+\b")
X = cv.fit_transform(split_corpus).toarray()
#构造标签向量，垃圾标签为0，正常标签为1
y = [0] * 5000 + [1] * 5000
#将特征集 分为训练集和测试集
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.4, random_state = 0)
#使用SVM训练分类模型
svm = svm.SVC(kernel='rbf', gamma=0.7, C = 1.0)
svm.fit(X_train, y_train)
#SVM分类性能
y_pred_svm = svm.predict(X_test)
print("SVM accuracy:\n",svm.score(X_test, y_test))
print("SVM report:\n",metrics.classification_report(y_test, y_pred_svm))
print("SVM matrix:\n",metrics.confusion_matrix(y_test, y_pred_svm))
#使用朴素贝叶斯训练分类模型，给出分类效果
gnb = GaussianNB()
gnb.fit(X_train,y_train)
y_pred = gnb.predict(X_test)
#朴素贝叶斯模型分类效果
print("naive_bayes accuracy:\n",gnb.score(X_test, y_test))
print("naive_bayes report:\n",metrics.classification_report(y_test, y_pred))
print("naive_bayes matrix:\n",metrics.confusion_matrix(y_test, y_pred))