class PerceptronClassifier(AbstractSKLearnClassifier):
def __init__(self):
AbstractSKLearnClassifier.__init__(self)
self.model = False
def set_label_encoder(self, labels):
AbstractSKLearnClassifier.set_label_encoder(self, labels)
def return_label_encoding(self, labels):
return AbstractSKLearnClassifier.return_label_encoding(self, labels)
def train_classifier(self, trainvectors, labels, alpha='1.0', iterations=10, jobs=1, v=2):
iterations = int(iterations)
jobs = int(jobs)
if alpha == 'search':
paramsearch = GridSearchCV(estimator=Perceptron(), param_grid=dict(alpha=numpy.linspace(0,2,20)[1:],n_iter=[iterations]), n_jobs=jobs)
paramsearch.fit(trainvectors,labels)
alpha = paramsearch.best_estimator_.alpha
else:
alpha = float(alpha)
self.model = Perceptron(alpha=alpha,n_iter=iterations,n_jobs=jobs)
self.model.fit(trainvectors, labels)
def return_classifier(self):
return self.model
def return_model_insights(self,vocab=False):
model_insights = []
return model_insights
class ClassificationPLA(ClassficationBase.ClassificationBase):
def __init__(self, isTrain, isOutlierRemoval=0):
super(ClassificationPLA, self).__init__(isTrain, isOutlierRemoval)
# data preprocessing
self.dataPreprocessing()
# PLA object
self.clf = Perceptron()
def dataPreprocessing(self):
# deal with unbalanced data
self.dealingUnbalancedData()
# Standardization
#self.Standardization()
def training(self):
# train the K Nearest Neighbors model
self.clf.fit(self.X_train, self.y_train.ravel())
def predict(self):
# predict the test data
self.y_pred = self.clf.predict(self.X_test)
# print the error rate
self.y_pred = self.y_pred.reshape((self.y_pred.shape[0], 1))
err = 1 - np.sum(self.y_test == self.y_pred) * 1.0 / self.y_pred.shape[0]
print "Error rate: {}".format(err)
def PERCEPTRON(data_train, data_train_vectors, data_test_vectors, **kwargs):
# Implementing classification model- using Perceptron
clf_p = Perceptron()
clf_p.fit(data_train_vectors, data_train.target)
y_pred = clf_p.predict(data_test_vectors)
return y_pred
def run(self):
"""
Пуск задачи
"""
train_data = pd.read_csv(self.param.get('train'))
test_data = pd.read_csv(self.param.get('test'))
X_train = train_data[['1', '2']]
y_train = train_data['0']
X_test = test_data[['1', '2']]
y_test = test_data['0']
if self.param.get('scale') is True:
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
perceptron = Perceptron(random_state=241)
perceptron.fit(X_train, y_train)
predictions = perceptron.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
with self.output().open('w') as output:
output.write(str(accuracy))
def percep(X_tr, y_tr, X_te):
clf = Perceptron(n_iter = 1000)
X_tr_aug = add_dummy_feature(X_tr)
X_te_aug = add_dummy_feature(X_te)
clf.fit(X_tr_aug, y_tr)
y_pred = clf.predict(X_te_aug)
return y_pred
def perceptron_histo():
"Interprétation des images comme histogrammes de couleurs et classification via le Perceptron"
alphas = np.arange(0.01,1.01,0.1)
best=np.zeros(4)
_, data, target, _ = utils.chargementHistogrammesImages(mer,ailleurs,1,-1)
X_train,X_test,Y_train,Y_test=train_test_split(data,target,test_size=0.3,random_state=random.seed())
for iterations in range(1,5):
for a in alphas:
start_time = time.time()
p = Perceptron(alpha=a, n_iter=iterations, random_state=random.seed(), n_jobs=-1)
x1=np.array(X_train)
x2=np.array(X_test)
p.fit(X=x1, y=Y_train)
score = p.score(x2,Y_test)
end_time = time.time()
if score>best[0]:
best[0] = score
best[1] = a
best[2] = iterations
best[3] = end_time-start_time
print("| Perceptron simple | V.Histo | alpha={:1.2f} iterations={:1.0f} | {:10.3f}ms | {:1.3f} |".format(best[1],best[2],best[3]*1000,best[0]))
def Perceptron_1(train_predictors,test_predictors,train_target,test_target):
clf = Perceptron()
clf.fit(train_predictors,train_target)
predicted = clf.predict(test_predictors)
accuracy = accuracy_score(test_target, predicted)
print "Accuracy for Linear Model Perceptron: "+str(accuracy)
return accuracy,predicted
def perceptron_vecteur():
"Interprétation des images comme vecteurs de pixels et classification via le Perceptron"
alphas = np.arange(0.01,1.01,0.1)
best=np.zeros(5)
for npix in range(50,200,50):
_, data, target, _ = utils.chargementVecteursImages(mer,ailleurs,1,-1,npix)
X_train,X_test,Y_train,Y_test=train_test_split(data,target,test_size=0.3,random_state=random.seed())
for iterations in range(1,5):
for a in alphas:
start_time = time.time()
p = Perceptron(alpha=a, n_iter=iterations, random_state=random.seed(), n_jobs=-1)
#X_train, etc, sont des tableaux à 3 dimensiosn par défaut, (93,1,30000) par exemple, qu'il faut remmener en 2 dimensions
x1=np.array(X_train)
x1 = np.reshape(x1, (x1.shape[0],x1.shape[2]))
x2=np.array(X_test)
x2 = np.reshape(x2, (x2.shape[0],x2.shape[2]))
p.fit(X=x1, y=Y_train)
score = p.score(x2,Y_test)
end_time = time.time()
if score>best[0]:
best[0] = score
best[1] = a
best[2] = iterations
best[3] = end_time-start_time
best[4] = npix
print("| Perceptron simple | V.Pix {:4.0f} | alpha={:1.2f} iterations={:1.0f} | {:10.3f}ms | {:1.3f} |".format(best[4],best[1],best[2],best[3]*1000,best[0]))
def t1():
from sklearn.linear_model import Perceptron
X = np.array([[1, 2], [3, 4], [5, 6]])
y = np.array([0, 1, 0])
clf = Perceptron()
clf.fit(X, y)
predictions = clf.predict(X)
print(predictions)
def perceptron(kf,data,label,k): for train, test in kf: X_train, X_test, y_train, y_test = data[train,:], data[test,:], label[train], label[test] log = Perceptron(penalty="l2", alpha=0.003) logit = log.fit(X_train,y_train) y_pred = logit.predict(X_test) scores = cross_validation.cross_val_score(log, data, label, cv=k) return scores.mean()
def main():
iris = load_iris()
X = iris.data[:, (2, 3)] # 花弁の長さ、花弁の幅
y = (iris.target == 0.).astype(np.int32)
perceptron_classifier = Perceptron(random_state=42)
perceptron_classifier.fit(X, y)
y_prediction = perceptron_classifier.predict([[2, 0.5]])
print(y_prediction)
def classify_perceptron():
print "perceptron"
(X_train, y_train), (X_test, y_test) = util.load_all_feat()
print "original X_train shape", X_train.shape
clf = Perceptron()
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
print "accuracy score:", accuracy_score(y_test, pred)
def train_data_perceptron( tup, penalty ): df, features, label = tup percep = Perceptron( penalty = penalty, fit_intercept = True, eta0 = ETA, n_iter = CYCLES, n_jobs = 2 ) percep.fit( df[features], df[label] ) return percep
def solve(train_set_x, train_set_y, test_set_x, test_set_y):
clf = Perceptron(random_state=241)
clf.fit(X=train_set_x, y=train_set_y)
prediction = clf.predict(test_set_x)
accuracy = accuracy_score(test_set_y, prediction)
return accuracy
def get_accuracy(_data_train_features, _data_train_labels, _data_test_features, _data_test_labels):
# Обучите персептрон со стандартными параметрами и random_state=241.
clf = Perceptron(random_state=241, shuffle=True)
clf.fit(_data_train_features, numpy.ravel(_data_train_labels))
# Подсчитайте качество (долю правильно классифицированных объектов, accuracy)
# полученного классификатора на тестовой выборке.
predictions = clf.predict(_data_test_features)
score = accuracy_score(_data_test_labels, predictions)
return score
def neural_net(train, test): y = [] xTrain, yTrain = loadData(train) xTest, yTest = loadData(test) nN = Perceptron() nN.fit(xTrain, yTrain) y = nN.predict(xTest) testError = 1 - nN.score(xTest, yTest) print 'Test error: ' , testError return y
def test():
X = np.array([[1, 2], [3, 4], [5, 6]])
y = np.array([0, 1, 0])
clf = Perceptron()
clf.fit(X, y)
predictions = clf.predict(X)
print("Predictions: %s" % predictions)
print("Accuracy: %s" % accuracy_score(y, predictions))
def perceptron(trainingData,trainingLabels):
"""
Implements a linear perceptron model as the
machine learning algorithm.
"""
from sklearn.linear_model import Perceptron
clf = Perceptron()
clf.fit(trainingData,trainingLabels)
print "Perceptron has been generated with a training set size of",len(trainingLabels)
return clf
def test_perceptron_correctness():
y_bin = y.copy()
y_bin[y != 1] = -1
clf1 = MyPerceptron(n_iter=2)
clf1.fit(X, y_bin)
clf2 = Perceptron(n_iter=2)
clf2.fit(X, y_bin)
assert_array_almost_equal(clf1.w, clf2.coef_.ravel())
def linear_train(features_train, target_train): data_f = pandas.read_csv(features_train, header=None, sep=';') features = data_f.iloc[:, 1:] features = scale(features) data_t = pandas.read_csv(target_train, header=None, sep=';') target = data_t.iloc[:, 1] perc = Perceptron(random_state=242) perc.fit(features, target) return perc
def neural_net():
Xtrain,ytrain,Xtest,ytest = getSplitData()
Xtrain, Xtest = getScaledData(Xtrain, Xtest)
ntest = Xtest.shape[0]
#Your code here
clf = Perceptron()
clf.fit(Xtrain, ytrain)
yPredict = clf.predict(Xtest)
#print "parameter: n_neighbors = ",n
print "neural_net classification accuracy: ", accuracy_score(ytest,yPredict)
def train(im_features, image_classes): # Train the Perceptron clf = Perceptron(n_iter=100, eta0=0.1) clf.fit(im_features, np.array(image_classes)) n_folds = 10 kFoldScore = evaluate_cross_validation(clf, im_features, np.array(image_classes), n_folds) #print 'SVM Score:',clf.score(im_features, np.array(image_classes)) #print 'SVM Score:', kFoldScore return clf
def neural_net(train, test):
y = []
trainY, trainX = loadData(train)
testY, testX = loadData(test)
neuralNet = Perceptron()
neuralNet.fit(trainX, trainY)
y = neuralNet.predict(testX)
testError = 1 - neuralNet.score(testX, testY)
print 'Test error: ' + str(testError)
return y
class DrunkLearningOnline(DrunkLearningBatch):
"""drunk_learning class for online learning"""
def __init__(self):
super(DrunkLearningOnline, self).__init__()
self.clf = Perceptron()
self.filename = 'modelPerceptron.pkl'
def partial_fit(self, X, y):
X = np.array([X])
y = np.array(y)
self.clf.partial_fit(X, y, [0, 1])
joblib.dump(self.clf, self.filename, compress=9)
def main():
start = time.time()
print "Reading train data and its features from: " + train_file
data = cu.get_dataframe(train_file)
global fea
fea = features.extract_features(feature_names,data)
percep = Perceptron(penalty=None, alpha=0.0001, fit_intercept=False, n_iter=5, shuffle=False, verbose=1, eta0=1.0, n_jobs=-1, seed=0, class_weight="auto", warm_start=False)
X = []
for i in data["OwnerUndeletedAnswerCountAtPostTime"]:
X.append([i])
# Must be array type object. Strings must be converted to
# to integer values, otherwise fit method raises ValueError
global y
y = []
print "Collecting statuses"
for element in data["OpenStatus"]:
for index, status in enumerate(ques_status):
if element == status:
y.append(index)
print "Fitting"
percep.fit(fea, y)
'''Make sure you have the up to date version of sklearn; v0.12 has the
predict_proba method; http://scikit-learn.org/0.11/install.html '''
print "Reading test data and features"
test_data = cu.get_dataframe(test_file)
test_fea = features.extract_features(feature_names,test_data)
print "Making predictions"
global probs
#probs = percep.predict_proba(test_fea) # only available for binary classification
probs = percep.predict(test_fea)
# shape of probs is [n_samples]
# convert probs to shape [n_samples,n_classes]
probs = np.resize(probs, (len(probs) / 5, 5))
#if is_full_train_set == 0:
# print("Calculating priors and updating posteriors")
# new_priors = cu.get_priors(full_train_file)
# old_priors = cu.get_priors(train_file)
# probs = cu.cap_and_update_priors(old_priors, probs, new_priors, 0.001)
print "writing submission to " + submission_file
cu.write_submission(submission_file, probs)
finish = time.time()
print "completed in %0.4f seconds" % (finish-start)
def test_model(training_data, testing_data, word2vec_model):
v = DictVectorizer()
train_features, train_labels = build_features(training_data, word2vec_model, v, 'train')
test_features, test_labels = build_features(testing_data, word2vec_model, v)
# create the perceptron model
model = Perceptron(n_iter = 5)
# fit the model to the training data
model.fit(train_features, train_labels)
# get the accuracy on the testing data
accuracy = model.score(test_features, test_labels)
return accuracy
def __test_perceptron(self, normalized):
clf = Perceptron()
X_train = self.train_data.iloc[:, 1:]
y_train = self.train_data.iloc[:, 0]
X_test = self.test_data.iloc[:, 1:]
y_test = self.test_data.iloc[:, 0]
if normalized:
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
return accuracy_score(y_test, predictions)
def __init__(self, zmq_sub_string, channel):
self.classes = ["pos", "neg"]
self.re_emoticons = re.compile(r":\)|:\(")
self.vec = HashingVectorizer(n_features=2 ** 20, non_negative=True)
self.clf = Perceptron()
self.count = {
"train": {
"pos": 0,
"neg": 0,
},
"test": {
"pos": 0,
"neg": 0,
}
}
self.train = 1
self.eval_count = {
"pos": {"tp": 0, "fp": 0, "fn": 0},
"neg": {"tp": 0, "fp": 0, "fn": 0},
}
super(StreamingLearner, self).__init__(zmq_sub_string, channel)
def runTrial(numberOfTestPoints, iterationLimit, showChart = False):
x1, y1, x2, y2, points = generatePoints(numberOfTestPoints)
pclf = Perceptron()
clf = SVC(C = 1000, kernel = 'linear')
sample = np.array(points)
X = np.c_[sample[:,1], sample[:,2]]
y = sample[:,3]
#print(y)
pclf.fit(X,y)
clf.fit(X,y)
iterations, w = train(points, iterationLimit)
#print("weights ", w)
#print("coefficients", pclf.coef_)
errorProb = findErrorProbability(x1,y1,x2,y2,w, 50000, clf, pclf)
if showChart:
if iterations == iterationLimit:
print( "No solution found in " + str(iterations) + " iterations!")
print( "Iterations: " + str(iterations) + ' | Weights: ' + str(w))
# plot points above(green) and below(blue) the target function.
green_x = []
green_y = []
blue_x = []
blue_y = []
for x in points:
if x[3] == 1:
green_x.append(x[1])
green_y.append(x[2])
else:
blue_x.append(x[1])
blue_y.append(x[2])
pylab.plot(green_x, green_y, 'go')
pylab.plot(blue_x, blue_y, 'bo')
# plot target function(black) and hypothesis function(red) lines
x = np.array( [-1,1] )
slope = (y2-y1)/(x2-x1)
intercept = y2 - slope * x2
pylab.plot(x, slope*x + intercept, 'k--')
pylab.plot( x, -w[1]/w[2] * x - w[0] / w[2] , 'r' ) # this will throw an error if w[2] == 0
pylab.ylim([-1,1])
pylab.xlim([-1,1])
pylab.show()
return iterations, w, errorProb
def __init__(self, isTrain, isOutlierRemoval=0):
super(ClassificationPLA, self).__init__(isTrain, isOutlierRemoval)
# data preprocessing
self.dataPreprocessing()
# PLA object
self.clf = Perceptron()
tuned_param_knn = [{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}]
models = {
'dt': {
'name': 'Decision Tree ',
'estimator': DecisionTreeClassifier(),
'param': tuned_param_dt,
},
'nb': {
'name': 'Gaussian Naive Bayes',
'estimator': GaussianNB(),
'param': tuned_param_nb
},
'lp': {
'name': 'Linear Perceptron ',
'estimator': Perceptron(),
'param': tuned_param_lp,
},
'svc': {
'name': 'Support Vector ',
'estimator': SVC(),
'param': tuned_param_svc
},
'knn': {
'name': 'K Nearest Neighbor ',
'estimator': KNeighborsClassifier(),
'param': tuned_param_knn
}
}
scores = ['precision', 'recall']
# Gaussian Naive Bayes gaussian = GaussianNB() scores = cross_val_score(gaussian, X_train, Y_train, cv=10) acc_gaussian = round(scores.mean() * 100, 2) acc_gaussian # In[ ]: # Perceptron (a single layer neural net) perceptron = Perceptron() scores = cross_val_score(perceptron, X_train, Y_train, cv=10) acc_perceptron = round(scores.mean() * 100, 2) acc_perceptron # In[ ]: # Neural Network (a multi layer neural net) neural_net = MLPClassifier() scores = cross_val_score(neural_net, X_train, Y_train, cv=10) acc_neural_net = round(scores.mean() * 100, 2) acc_neural_net
def IncreasingFIT():
global total_vect_time
classifiers = {
'SGD': SGDClassifier(),
'Perceptron': Perceptron(),
'NB Multinomial': MultinomialNB(alpha=0.01),
'Passive-Aggressive': PassiveAggressiveClassifier(),
}
Vocubularysave = []
if os.path.exists("VocubularySave.v"):
Vocubularysave = joblib.load("VocubularySave.v")
VocubularyList = []
for numV in Vocubularysave:
VocubularyList.append(numV['name'])
vectorizer = CountVectorizer(stop_words=None, vocabulary=VocubularyList)
transformer = TfidfTransformer()
count = vectorizer.fit_transform(xtest)
X_test = transformer.fit_transform(count)
for i in range(TrainDataSize):
tick = time.time()
# X_train = vectorizer.transform(xtrain[i])
count = vectorizer.fit_transform(xtrain[i])
X_train = transformer.fit_transform(count)
total_vect_time += time.time() - tick
for cls_name, cls_useless in partial_fit_classifiers.items():
cls = classifiers[cls_name]
tick = time.time()
# update estimator with examples in the current mini-batch
# 使用当前最小批次中的示例更新估算器
# print(X_train)
cls.partial_fit(X_train, ytrain[i], classes=all_classes)
# if i % printjumpsize == 0:
if i == (TrainDataSize - 1):
# accumulate test accuracy stats
# 累积测试准确度统计
cls_stats[cls_name]['total_fit_time'] += time.time() - tick
cls_stats[cls_name]['n_train'] += X_train.shape[0]
cls_stats[cls_name]['n_train_pos'] += sum(ytrain[i])
tick = time.time()
# 测试准确性函数
cls_stats[cls_name]['accuracy'] = cls.score(X_test, ytest)
cls_stats[cls_name]['prediction_time'] = time.time() - tick
acc_history = (cls_stats[cls_name]['accuracy'],
cls_stats[cls_name]['n_train'])
cls_stats[cls_name]['accuracy_history'].append(acc_history)
run_history = (cls_stats[cls_name]['accuracy'],
total_vect_time +
cls_stats[cls_name]['total_fit_time'])
cls_stats[cls_name]['runtime_history'].append(run_history)
# accumulate test accuracy stats
# 累积测试准确度统计
if T == 0:
print(progress(cls_name, cls_stats[cls_name]))
if T != 0:
AccuracyAverage[cls_name]['total_fit_time'] += time.time(
) - tick
AccuracyAverage[cls_name]['n_train'] += X_train.shape[0]
AccuracyAverage[cls_name]['n_train_pos'] += sum(ytrain[i])
tick = time.time()
# 测试准确性函数
AccuracyAverage[cls_name]['accuracy'] += cls.score(
X_test, ytest)
RecordOneAccuracy[cls_name]['accuracy'] += cls.score(
X_test, ytest)
acc_history = (AccuracyAverage[cls_name]['accuracy'],
AccuracyAverage[cls_name]['n_train'])
AccuracyAverage[cls_name]['accuracy_history'].append(
acc_history)
run_history += (
AccuracyAverage[cls_name]['accuracy'],
total_vect_time +
AccuracyAverage[cls_name]['total_fit_time'])
AccuracyAverage[cls_name]['runtime_history'].append(
run_history)
recordAccuracy.append(RecordOneAccuracy)
print(progress2(cls_name, AccuracyAverage[cls_name], T))
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import SGDClassifier, Perceptron
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.linear_model import LogisticRegression
heldout = [0.95, 0.90, 0.75, 0.50, 0.01]
rounds = 20
digits = datasets.load_digits()
X, y = digits.data, digits.target
classifiers = [("SGD", SGDClassifier(max_iter=100, tol=1e-3)),
("ASGD", SGDClassifier(average=True, max_iter=100, tol=1e-3)),
("Perceptron", Perceptron(tol=1e-3)),
("Passive-Aggressive I",
PassiveAggressiveClassifier(loss='hinge', C=1.0, tol=1e-4)),
("Passive-Aggressive II",
PassiveAggressiveClassifier(loss='squared_hinge',
C=1.0,
tol=1e-4)),
("SAG",
LogisticRegression(solver='sag', tol=1e-1,
C=1.e4 / X.shape[0]))]
xx = 1. - np.array(heldout)
for name, clf in classifiers:
print("training %s" % name)
rng = np.random.RandomState(42)
def main():
# Number of hiddens
n = 10
# Instance of Read class to read in data
trainData, testData, train, test = Read().read()
# Ensure that both the training and testing dataframes have the same columns.
# If we're adding any new columns through this, make all values in that column = 0.
trainData, testData = trainData.align(testData,
join='outer',
fill_value=0,
axis=1)
# Run the training and testing data through an Sklearns model.
model = SVC()
model_GNB = GaussianNB()
model_Bern = BernoulliNB()
model_MNB = MultinomialNB()
model_MLP = MLPClassifier(hidden_layer_sizes=(n, n),
activation='logistic',
max_iter=2000)
testScore = 0
targetLabels = train['Survived'].values
testLabels = test['Survived'].values
trainData, testData = dropData(trainData, testData)
# just uncomment the data you want to use
trainFeatures = trainData
testFeatures = testData
# trainFeatures = train[["Pclass", "Age", "Sex", "Fare"]].values
# testFeatures = test[["Pclass", "Age", "Sex", "Fare"]].values
print(trainFeatures.shape)
print(trainFeatures)
# 3 hidden layers (n, n, n)
model_Perceptron = Perceptron(n_iter_no_change=10)
model.fit(trainFeatures, targetLabels)
model_GNB.fit(trainFeatures, targetLabels)
model_Bern.fit(trainFeatures, targetLabels)
model_MNB.fit(trainFeatures, targetLabels)
model_MLP.fit(trainFeatures, targetLabels)
model_Perceptron.fit(trainFeatures, targetLabels)
# Let's test a few different models ..
# Now do support vector machine
trainScore = model.score(trainFeatures, targetLabels) * 100
testScore = model.score(testFeatures, testLabels) * 100
print("Support vector results:\n", "Train: ", trainScore, "%", "Test: ",
testScore, "%\n\n")
# Now do Gaussian Naive Bayes
trainScore = model_GNB.score(trainFeatures, targetLabels) * 100
testScore = model_GNB.score(testFeatures, testLabels) * 100
print("Gaussian NB results:\n", "Train: ", trainScore, "%", "Test: ",
testScore, "%\n\n")
# Now do Bernoulli Naive Bayes
# trainScore = model_Bern.score(trainFeatures, targetLabels)*100
# testScore = model_Bern.score(testFeatures, testLabels)*100
# print("Bernoulli NB results:\n", "Train: ", trainScore, "%", "Test: ", testScore, "%")
# Now do Multinomial Naive Bayes
# trainScore = model_MNB.score(trainFeatures, targetLabels)*100
# testScore = model_MNB.score(testFeatures, testLabels)*100
# print("Multinomial NB results:\n", "Train: ", trainScore, "%", "Test: ", testScore, "%")
# Now do MLP
trainScore = model_MLP.score(trainFeatures, targetLabels) * 100
testScore = model_MLP.score(testFeatures, testLabels) * 100
print("Multi-Layer Perceptron results:\n", "Train: ", trainScore, "%",
"Test: ", testScore, "%\n\n")
# Now do Perceptron
trainScore = model_Perceptron.score(trainFeatures, targetLabels) * 100
testScore = model_Perceptron.score(testFeatures, testLabels) * 100
print("Perceptron Learning Algorithm results:\n", "Train: ", trainScore,
"%", "Test: ", testScore, "%\n\n\n\n")
# Some PCA magic, reduce down to n parameters
""" Everything below this point is using PCA for dimensionality reduction in the data
"""
numComp = 2
pca = PCA(n_components=numComp)
pca.fit(trainFeatures)
trainFeatures = pca.transform(trainFeatures)
testFeatures = pca.transform(testFeatures)
print(trainFeatures.shape)
model.fit(trainFeatures, targetLabels)
model_GNB.fit(trainFeatures, targetLabels)
model_Bern.fit(trainFeatures, targetLabels)
# Now do support vector machine
trainScore = model.score(trainFeatures, targetLabels) * 100
testScore = model.score(testFeatures, testLabels) * 100
print("(PCA) Support vector results:\n", "Train: ", trainScore, "%",
"Test: ", testScore, "%\n\n")
# Now do Gaussian Naive Bayes
trainScore = model_GNB.score(trainFeatures, targetLabels) * 100
testScore = model_GNB.score(testFeatures, testLabels) * 100
print("(PCA) Gaussian NB results:\n", "Train: ", trainScore, "%", "Test: ",
testScore, "%\n\n")
# Now do Bernoulli Naive Bayes
# trainScore = model_Bern.score(trainFeatures, targetLabels)*100
# testScore = model_Bern.score(testFeatures, testLabels)*100
# print("Bernoulli NB results:\n", "Train: ", trainScore, "%", "Test: ", testScore, "%")
model_MLP.fit(trainFeatures, targetLabels)
trainScore = model_MLP.score(trainFeatures, targetLabels) * 100
testScore = model_MLP.score(testFeatures, testLabels) * 100
print("(PCA) Multi-Layer Perceptron results:\n", "Train: ", trainScore,
"%", "Test: ", testScore, "%\n\n")
model_Perceptron.fit(trainFeatures, targetLabels)
trainScore = model_Perceptron.score(trainFeatures, targetLabels) * 100
testScore = model_Perceptron.score(testFeatures, testLabels) * 100
print("(PCA) Perceptron Learning Algorithm results:\n", "Train: ",
trainScore, "%", "Test: ", testScore, "%\n\n\n")
# fig = plt.figure(figsize = (8,8))
# ax = fig.add_subplot(1,1,1)
# ax.set_title("n="+str(numComp)+" PCA")
# colors = itertools.cycle(['r', 'g', 'b'])
# plt.scatter(trainFeatures[:, 0], trainFeatures[:, 1], alpha = 0.5)
# print(trainFeatures)
# plt.show()
plot(trainFeatures, targetLabels, "PCA", "MLP", numComp)
print(np.shape(class_labels))
#print(class_labels)
# In[251]:
def calcul_accuracy(real_label, pre_label):
cnt = 0
for i in range(len(real_label)):
if real_label[i] == pre_label[i]:
cnt += 1
return cnt / len(real_label)
#perceptron on the first two features
perceptron = Perceptron(max_iter=1000, tol=0.0001, random_state=None)
perceptron.fit(
feature_2, class_labels
) #fit(X, y[, coef_init, intercept_init, ...]) Fit linear model with Stochastic Gradient Descent.
print("feature_2's final Weight:")
#print(perceptron.intercept_) #不懂
final_wei1 = perceptron.coef_
print(final_wei1)
label_train_pred1 = perceptron.predict(
feature_2) #Predict class labels for samples in X.
#print(label_train_pred1)
mean_ar = perceptron.score(feature_2, class_labels)
#print(mean_ar)
mean_accuracy1 = calcul_accuracy(
class_labels, label_train_pred1
import numpy as np from sklearn.linear_model import Perceptron X = [[0, 0.1], [0.1, 0.9], [0.02, 0], [0.9, 0], [1, 0.9]] y = [0, 0, 0, 0, 1] per_clf = Perceptron(random_state=42) per_clf.fit(X, y) #y_pred = per_clf.predict([[2, 0.5]]) y_pred = per_clf.predict([[0.12, 0], [1, 0], [0, 1], [0.9, 0.9], [1, 1]]) print(y_pred) # output expected to be [0 0 0 1 1]
def test_multiclass(data):
data['target'] = lb.fit_transform(data['target'])
print('Classes: {}'.format(list(lb.classes_)))
X = data.loc[:, data.columns != 'target']
y = data['target']
print('Arvore de decisao - GINI')
dt = DecisionTreeClassifier()
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('Arvore de decisao - Entropy')
dt = DecisionTreeClassifier(criterion='entropy')
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('SVM - Um contra todos')
dt = LinearSVC()
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('SVM - Crammer-Singer')
dt = LinearSVC(multi_class='crammer_singer')
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('Perceptron')
dt = Perceptron()
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('Random Forest - GINI')
dt = RandomForestClassifier()
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('Random Forest - Entropy')
dt = RandomForestClassifier(criterion='entropy')
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
print('------------------------------')
print('Naive Bayes')
dt = BernoulliNB()
scores = cross_validate(dt,
X,
y=y,
cv=10,
scoring={
'acc': 'accuracy',
'rec': make_scorer(multiclass_recall),
'f1': 'f1_weighted'
},
return_train_score=False)
print('Acurácia: {:.2f} (+/- {:.2f})'.format(scores['test_acc'].mean(),
scores['test_acc'].std()))
print('Cobertura: {:.2f} (+/- {:.2f})'.format(scores['test_rec'].mean(),
scores['test_rec'].std()))
print('F-score: {:.2f} (+/- {:.2f})'.format(scores['test_f1'].mean(),
scores['test_f1'].std()))
# 建立正規化物件
sc = StandardScaler()
# 利用現有資料計算正規化所需的平均值與標準差
# 不執行此指令則之後的動作都無法操作
sc.fit(X_train)
# 查平均值與標準差，回傳陣列[平均值，標準差]
sc.mean_
# 利用sc.fit算出來的平均值與標準差來正規化訓練集與測試集
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
# 模型訓練
ppn = Perceptron(max_iter=40, eta0=0.01, random_state=0)
ppn.fit(X_train_std, y_train)
# 預測
y_pred = ppn.predict(X_test_std)
print(accuracy_score(y_test, y_pred))
# 繪圖
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
pdr.plot_decision_regions(X=X_combined_std,
y=y_combined,
classifier=ppn,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
self.model = model
def FIT(self, X_train, y_train):
self.model.fit(X_train, y_train)
def predict(self, X_test, y_test):
y_pred = self.model.predict(X_test_std)
print(y_pred)
print(f"Number of Misclassified Examples by {self.model} are {sum(y_pred!=y_test)}")
print(f"Accuracy of {self.model} using Accuracy_score function is {accuracy_score(y_test, y_pred)}")
print(f"Accuracy of {self.model} using Score is {self.model.score(X_test_std, y_test)}")
percp = Perceptron(eta0=0.1, random_state=1)
Logic = LogisticRegression(C=100.0, random_state=1, solver='lbfgs', multi_class='ovr')
Logic2 = LogisticRegression(C=100.0, random_state=1, solver='lbfgs', multi_class='multinomial',)
m1 = Model(percp)
m2 = Model(Logic)
m3 = Model(Logic2)
m1.FIT(X_train_std, y_train)
m2.FIT(X_train_std, y_train)
m3.FIT(X_train_std, y_train)
m1.predict(X_test_std, y_test)
m2.predict(X_test_std, y_test)
m3.predict(X_test_std, y_test)
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0, shuffle=True)
ppn.fit(X_train_std, y_train)
y_pred = ppn.predict(X_test_std)
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
from sklearn.datasets import load_files
from sklearn.model_selection import train_test_split
from sklearn import metrics
#
languages_data_folder = sys.argv[1] #this line is the cause of 90% of my stress in this class today
dataset = load_files(languages_data_folder)
docs_train, docs_test, y_train, y_test = train_test_split(dataset.data, dataset.target, test_size=0.5)
vectorizer = TfidfVectorizer(ngram_range=(1, 3), analyzer='char', use_idf=False)
# this is the thing that gets rid of small, common words because they're not super duper useful
clf = Pipeline([ ('vec', vectorizer), ('clf', Perceptron(tol=1e-3)), ]) #This is equivalent to one millitolerance
clf.fit(docs_train, y_train)
y_predicted = clf.predict(docs_test)
print(metrics.classification_report(y_test, y_predicted, target_names=dataset.target_names))
#this is the confusing confusion matrix
centimeter = metrics.confusion_matrix(y_test, y_predicted)
print(centimeter)
sentences = [
u'Pikachu squirtle togepi',
print("accuracy: %0.3f" % score)
totalPredictions.append(predictions)
return name, score, train_time, test_time
results = []
#Main Code
#Classifiers
clf1 = LogisticRegression()
clf2 = PassiveAggressiveClassifier()
clf3 = MultinomialNB(alpha=.01)
clf4 = BernoulliNB(alpha=.01)
clf5 = NearestCentroid()
clf6 = RidgeClassifier(tol=1e-2, solver="sag")
clf7 = Perceptron(n_iter=50)
clf8 = SGDClassifier(loss='hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="l2",n_jobs=-1)
clf9 = SGDClassifier(loss='hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="l1",n_jobs=-1)
clf10 = SGDClassifier(loss='hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="elasticnet",n_jobs=-1)
clf11 = SGDClassifier(loss='log',alpha=.0001, n_iter=50,shuffle=True,penalty="l2",n_jobs=-1)
clf12 = SGDClassifier(loss='log',alpha=.0001, n_iter=50,shuffle=True,penalty="l1",n_jobs=-1)
clf13 = SGDClassifier(loss='log',alpha=.0001, n_iter=50,shuffle=True,penalty="elasticnet",n_jobs=-1)
clf14 = SGDClassifier(loss='modified_huber',alpha=.0001, n_iter=50,shuffle=True,penalty="l2",n_jobs=-1)
clf15 = SGDClassifier(loss='modified_huber',alpha=.0001, n_iter=50,shuffle=True,penalty="l1",n_jobs=-1)
clf16 = SGDClassifier(loss='modified_huber',alpha=.0001, n_iter=50,shuffle=True,penalty="elasticnet",n_jobs=-1)
clf17 = SGDClassifier(loss='squared_hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="l2",n_jobs=-1)
clf18 = SGDClassifier(loss='squared_hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="l1",n_jobs=-1)
clf19 = SGDClassifier(loss='squared_hinge',alpha=.0001, n_iter=50,shuffle=True,penalty="elasticnet",n_jobs=-1)
clf20 = SGDClassifier(loss='perceptron',alpha=.0001, n_iter=50,shuffle=True,penalty="l2",n_jobs=-1)
clf21 = SGDClassifier(loss='perceptron',alpha=.0001, n_iter=50,shuffle=True,penalty="l1",n_jobs=-1)
clf22 = SGDClassifier(loss='perceptron',alpha=.0001, n_iter=50,shuffle=True,penalty="elasticnet",n_jobs=-1)
def test_predict_proba():
X = np.random.randn(5, 5)
y = np.array([0, 1, 0, 0, 0])
clf1 = Perceptron()
clf1.fit(X, y)
DESKNN([clf1, clf1, clf1])
test_hy = hy[:8678, :]
X_train, X_test, y_train, y_test = train_test_split(hy, data, train_size=0.80, test_size=0.20, random_state=1234)
nb = MultinomialNB()
nb = nb.fit(X=X_train, y=y_train)
y_pred = nb.predict(X_test)
print("Bow + Tf-idf ---> " + str(accuracy_score(y_test, y_pred) * 100) + "%")
# -------------------------------------PERCEPTRON-------------------------------------
bow_vectorizer = CountVectorizer()
bow = bow_vectorizer.fit_transform(res)
train_bow = bow[8678:, :]
test_bow = bow[:8678, :]
X_train, X_test, y_train, y_test = train_test_split(bow, data, test_size=0.20, train_size=0.80, random_state=1234)
per = Perceptron(tol=1e-3, random_state=0)
per = per.fit(X=X_train, y=y_train)
y_pred = per.predict(X_test)
print("----------------------------------------------------------------------------------")
print("__________PERCEPTRON__________")
print("BagOfWords -----> " + str(accuracy_score(y_test, y_pred) * 100) + "%")
tfidf_vectorizer = TfidfVectorizer()
tfidf = tfidf_vectorizer.fit_transform(res)
train_tfidf = tfidf[8678:, :]
test_tfidf = tfidf[:8678, :]
X_train, X_test, y_train, y_test = train_test_split(tfidf, data, test_size=0.20, train_size=0.80, random_state=1234)
per = Perceptron(tol=1e-3, random_state=0)
per = per.fit(X=X_train, y=y_train)
y_pred = per.predict(X_test)
def CheckingClassifer(ClassiferName):
if ClassiferName == "Perceptron":
# Running the Perceptron Classifier and computing the Test accuracy and CV accuracy
print(
"--------------------------------perceptron---------------------------------------------------"
)
start_time = time.time()
eta_P = input("Please Insert the value of learning Rate : \n")
pip_perce = make_pipeline(
StandardScaler(), PCA(n_components=2),
Perceptron(penalty=None,
alpha=0.0001,
fit_intercept=True,
max_iter=50,
tol=None,
shuffle=True,
verbose=0,
eta0=float(eta_P),
n_jobs=None,
random_state=0,
early_stopping=False,
validation_fraction=0.1,
n_iter_no_change=5,
class_weight=None,
warm_start=False))
pip_perce.fit(X, y)
y_pred = pip_perce.predict(Xtest)
print("Test Accuracy : ", metrics.accuracy_score(
ytest, y_pred)) # Computing the Test accuracy
print("The Running Time To compute the Test Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
K3 = StratifiedKFold(n_splits=10, random_state=1,
shuffle=True).split(T, P)
scores1 = []
for K, (train_index, test_index) in enumerate(K3):
pip_perce.fit(T[train_index], P[train_index])
score = pip_perce.score(T[test_index], P[test_index])
scores1.append(score)
print(
" The accuracy of Cross validation Perceptron : " +
str(sum(scores1) / len(scores1))) # Computing The CV Accuracy
print("The Running Time To compute the CV Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
print(
"-----------------------------------------------------------------------------------"
)
elif ClassiferName == "SVM":
# Running the Support Vector Machine (SVM) Classifier and computing the Test accuracy and CV accuracy
print(
"--------------------------------SVM---------------------------------------------------"
)
start_time = time.time()
C_SVM = input("Please Inuput the value of C : \n")
pip_SV = make_pipeline(
StandardScaler(), PCA(n_components=2),
LinearSVC(random_state=0, tol=1e-5, C=float(C_SVM)))
pip_SV.fit(X, y)
y_pred = pip_SV.predict(Xtest)
print("Test Accuracy: ", metrics.accuracy_score(
ytest, y_pred)) # Computing The test accuracy
print("The Running Time To compute the Test Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
K3 = StratifiedKFold(n_splits=10, random_state=1,
shuffle=True).split(T, P)
scores2 = []
for K, (train_index, test_index) in enumerate(K3):
pip_SV.fit(T[train_index], P[train_index])
score = pip_SV.score(T[test_index], P[test_index])
scores2.append(score)
print(
" The accuracy of Cross validation SVM : " +
str(sum(scores2) / len(scores2))) # Computing The CV accuracy
print("The Running Time To compute the CV Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
scores = []
elif ClassiferName == "DecisionTree":
# Running the Decision Tree algorithm (DT) Classifier and computing the Test accuracy and CV accuracy
print(
"--------------------------------DT---------------------------------------------------"
)
start_time = time.time()
Max_depth = input("Please Insert the Depth of the Tree : \n")
pip_DT = make_pipeline(
StandardScaler(), PCA(n_components=2),
DecisionTreeClassifier(random_state=0,
max_depth=int(Max_depth)))
pip_DT.fit(X, y)
y_pred = pip_DT.predict(Xtest)
print("Test Accuracy : ", metrics.accuracy_score(
ytest, y_pred)) # Computing The test accuracy
print("The Running Time To compute the Test Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
K0 = StratifiedKFold(n_splits=10, random_state=1,
shuffle=True).split(T, P)
scores3 = []
for K, (train_index, test_index) in enumerate(K0):
pip_DT.fit(T[train_index], P[train_index])
score = pip_DT.score(T[test_index], P[test_index])
scores3.append(score)
print(
" The accuracy of Cross validation DT : " +
str(sum(scores3) / len(scores3))) # Computing The CV accuracy
print("The Running Time To compute the CV Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
elif ClassiferName == "KNN":
# Running the k-nearest neighbors algorithm (k-NN) Classifier and computing the Test accuracy and CV accuracy
print(
"--------------------------------KNN---------------------------------------------------"
)
start_time = time.time()
N_of_neg = input("Please insert the number of neigbours : \n")
pip_KNN = make_pipeline(
StandardScaler(), PCA(n_components=2),
KNeighborsClassifier(n_neighbors=int(N_of_neg)))
pip_KNN.fit(X, y)
y_pred = pip_KNN.predict(Xtest)
print("Test Accuracy: ", metrics.accuracy_score(
ytest, y_pred)) # Computing the Test accuracy
print("The Running Time To compute the Test Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
K1 = StratifiedKFold(n_splits=10, random_state=1,
shuffle=True).split(T, P)
scores4 = []
for K, (train_index, test_index) in enumerate(K1):
pip_KNN.fit(T[train_index], P[train_index])
score = pip_KNN.score(T[test_index], P[test_index])
scores4.append(score)
print(" The accuracy of Cross validation KNN : " +
str(sum(scores4) / len(scores4))) #Computing the CV Accuracy
print("--- %s seconds ---" % (time.time() - start_time))
elif ClassiferName == "LG":
#Running the Logestic Regression Classifier and computing the Test accuracy and CV accuracy
print(
"--------------------------------LG---------------------------------------------------"
)
start_time = time.time()
C_LG = input("Please Insert C value :\n")
pip_LG = make_pipeline(
StandardScaler(), PCA(n_components=2),
LogisticRegression(penalty='l2',
dual=False,
tol=0.0001,
C=float(C_LG),
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
random_state=None,
max_iter=500,
solver='liblinear'))
pip_LG.fit(X, y)
y_pred = pip_LG.predict(Xtest)
print("Test Accuracy :",
metrics.accuracy_score(ytest,
y_pred)) #Comuting the test accuracy
print("The Running Time To compute the Test Accuracy :")
print("--- %s seconds ---" % (time.time() - start_time))
start_time = time.time()
kflod = StratifiedKFold(n_splits=10, random_state=1,
shuffle=True).split(T, P)
scores5 = []
for K, (train_index, test_index) in enumerate(kflod):
pip_LG.fit(T[train_index], P[train_index])
score = pip_LG.score(T[test_index], P[test_index])
scores5.append(score)
print(" The accuracy of Cross validation LG : " +
str(sum(scores5) / len(scores5))) #Computing The CV Accuracy
print("--- %s seconds ---" % (time.time() - start_time))
print(
"----------------------------------------------------------------------"
)
X = np.array(cancer.ix[:, 0:28].values)
#ouoput label
y = np.array(cancer.ix[:, 29].values)
#creating empty dictionary to append all classifiers
dictOfClassifiers = {}
knn = KNeighborsClassifier(n_neighbors=7, weights='uniform')
dictOfClassifiers.update({knn: "K nearest neighbour"})
svm = SVC(kernel="rbf", C=1)
dictOfClassifiers.update({svm: "SVM"})
lr = LogisticRegression(C=1, max_iter=100)
dictOfClassifiers.update({lr: "Logistic Regression"})
dt = DecisionTreeClassifier(criterion='entropy', max_depth=4)
dictOfClassifiers.update({dt: "Decision Tree"})
nb = GaussianNB()
dictOfClassifiers.update({nb: "Naive Bayes"})
p = Perceptron(eta0=1, alpha=0.0001)
dictOfClassifiers.update({p: "Perceptron"})
ann = MLPClassifier(hidden_layer_sizes=(3, 5),
activation='relu',
alpha=1,
max_iter=2000,
learning_rate='adaptive')
dictOfClassifiers.update({ann: "Neural Network"})
dnn = MLPClassifier(hidden_layer_sizes=(10, 10),
activation='relu',
alpha=1,
max_iter=2000,
learning_rate='adaptive')
dictOfClassifiers.update({dnn: "Deep Learning"})
rfc = RandomForestClassifier(max_depth=14,
n_estimators=19,
# In[ ]: # Gaussian Naive Bayes gaussian = GaussianNB() gaussian.fit(X_train, Y_train) Y_pred = gaussian.predict(X_test) acc_gaussian = round(gaussian.score(X_train, Y_train) * 100, 2) acc_gaussian # In[ ]: # Perceptron perceptron = Perceptron() perceptron.fit(X_train, Y_train) Y_pred = perceptron.predict(X_test) acc_perceptron = round(perceptron.score(X_train, Y_train) * 100, 2) acc_perceptron # In[ ]: # Linear SVC linear_svc = LinearSVC() linear_svc.fit(X_train, Y_train) Y_pred = linear_svc.predict(X_test) acc_linear_svc = round(linear_svc.score(X_train, Y_train) * 100, 2) acc_linear_svc
test_stats = {'n_test': 0, 'n_test_pos': 0}
tick = time.time()
parsing_time = time.time() - tick
tick = time.time()
# 数据集文本向量化 (哈希技巧) -------------------------------------------------------
# vectorizer = HashingVectorizer(decode_error='ignore', n_features=2 ** 18,
# alternate_sign=False)
# X_test = vectorizer.transform(xtest)
# 这里有一些支持`partial_fit`方法的分类器
# 新创建分类器容器
partial_fit_classifiers = {
'SGD': SGDClassifier(),
'Perceptron': Perceptron(),
'NB Multinomial': MultinomialNB(alpha=0.01),
'Passive-Aggressive': PassiveAggressiveClassifier(),
}
# 载入旧的分类器容器
# end 数据集文本向量化 (哈希技巧) -------------------------------------------------------
vectorizing_time = time.time() - tick
test_stats['n_test'] += len(ytest)
test_stats['n_test_pos'] += sum(ytest)
def progress(cls_name, stats):
"""Report progress information, return a string.报告进度信息，返回一个字符串。"""
duration = time.time() - stats['t0']
micro avg 0.84 0.84 0.84 16262
macro avg 0.77 0.81 0.79 16262
weighted avg 0.85 0.84 0.84 16262
"""
from sklearn import metrics
fpr, tpr, thresholds = metrics.roc_curve(y_test, predicted, pos_label=1)
print("AUC :", metrics.auc(fpr, tpr))
"""
AUC : 0.803154835157
"""
from sklearn.linear_model import Perceptron
classifier5 = Perceptron(eta0=0.5, max_iter=75)
mlp = classifier5.fit(x_train, y_train)
print("Training accuracy: ", mlp.score(x_train, y_train))
predicted = mlp.predict(x_test)
print("Testing Accuracy score: ", accuracy_score(y_test, predicted))
print("Confusion Matrix: ")
print(confusion_matrix(y_test, predicted))
print("\nClassification Report: ")
print(classification_report(y_test, predicted))
"""
Training accuracy: 0.5
Testing Accuracy score: 0.23637928914
Confusion Matrix:
y = y.reshape(-1, 1)
for idx, row in enumerate(tokens):
for v in row:
if v in feature_dict:
X[idx, feature_dict[v]] += 1
return X, y
if __name__ == '__main__':
train_labels, train_tokens, train_vocab = convert_data(train_text)
index_dir = {key: value for (value, key) in enumerate(train_vocab)}
inversed_index_dir = {value: key for (key, value) in index_dir.items()}
train_X, train_y = lists_to_arrays(train_labels, train_tokens, index_dir)
# train perceptron
perceptron = Perceptron(tol=1e-3, random_state=42)
perceptron.fit(train_X, train_y)
#print(perceptron.score(train_X,train_y))
# train logistic regression
lr = LogisticRegression(random_state=42, tol=1e-4)
lr.fit(train_X, train_y)
#print(lr.score(train_X, train_y))
print('Top words for LR:')
for coef in lr.coef_:
print([inversed_index_dir[x] for x in np.argsort(coef)[::-1][:10]])
print("Top words for Perceptron:")
for coef in perceptron.coef_:
print([inversed_index_dir[x] for x in np.argsort(coef)[::-1][:10]])
metrics.classification_report(y_test,
pred,
target_names=target_names))
if opts.print_cm:
print("confusion matrix:")
print(metrics.confusion_matrix(y_test, pred))
print()
clf_descr = str(clf).split('(')[0]
return clf_descr, score, train_time, test_time
results = []
for clf, name in ((RidgeClassifier(tol=1e-2, solver="lsqr"),
"Ridge Classifier"), (Perceptron(n_iter=50), "Perceptron"),
(PassiveAggressiveClassifier(n_iter=50),
"Passive-Aggressive"),
(KNeighborsClassifier(n_neighbors=10), "kNN"),
(RandomForestClassifier(n_estimators=100), "Random forest")):
print('=' * 80)
print(name)
results.append(benchmark(clf))
for penalty in ["l2", "l1"]:
print('=' * 80)
print("%s penalty" % penalty.upper())
# Train Liblinear model
results.append(benchmark(LinearSVC(penalty=penalty, dual=False, tol=1e-3)))
# Train SGD model
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
X_test, y_test = X[test_id, :], y[test_id]
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],alpha=0.8, c=cmap(idx), marker=markers[idx], label=cl)
if test_id:
X_test, y_test = X[test_id, :], y[test_id]
plt.scatter(X_test[:,0],X_test[:, 1], c='', s=55, alpha=0.1, linewidths=1, marker='o', label='test set')
if __name__ == '__main__':
iris = datasets.load_iris()
iris_X = iris.data[:, [2, 3]]#取数据的2，3列特征
iris_y = iris.target
X_train, X_test, y_train, y_test = train_test_split(iris_X, iris_y, test_size=0.3, random_state=0)#划分数据集，分为训练集和测试集
sc = StandardScaler()#特征缩放
sc.fit(X_train)#训练得每个特征得样本均值和标准差
X_train_sc = sc.transform(X_train)#对训练数据做标准化处理，即特征缩放
X_test_sc = sc.transform(X_test)#测试集与训练集同步
ppn = Perceptron(n_iter=50, eta0=0.1, random_state=0)#感知器模型，迭代次数50，学习速率为0.1每次迭代初始化重排训练集
ppn.fit(X_train_sc, y_train)#训练
y_yred = ppn.predict(X_test_sc)#用测试集进行预测
X_combined_std = np.vstack((X_train_sc, X_test_sc))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined_std, y=y_combined, classifier=ppn, test_id=range(105, 150))
plt.show()
def run(self):
names = ['DNA_TO_CLASSIFY', 'attribute', 'sequence']
data = pd.read_csv(self.file_name, names = names)
print('Build our dataset using custom pandas dataframe')
clases = data.loc[:,'DNA_TO_CLASSIFY']
sequence = list(data.loc[:, 'sequence'])
dic = {}
for i, seq in enumerate(sequence):
nucleotides = list(seq)
nucleotides = [char for char in nucleotides if char != '\t']
nucleotides.append(clases[i])
dic[i] = nucleotides
print('Convert Dict object into dataframe')
df = pd.DataFrame(dic)
print('transpose dataframe into correct format')
df = df.transpose()
df.rename(columns = {XXX__Length of sample__XX:'XXXXX__Sample DNA Name___XXXXX'}, inplace = True)
print('Encoding')
numerical_df = pd.get_dummies(df)
numerical_df.drop('helitron_not-helitron', axis = 1, inplace = True)
print(numerical_df)
numerical_df.rename(columns = {'XXX__Fill_XXXX':'XXX__Fill__XXX'}, inplace = True)
#Importing different classifier from sklearn
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.metrics import classification_report, accuracy_score
from sklearn.model_selection import train_test_split
X = numerical_df.drop(['heli'], axis = 1).values
y = numerical_df['heli'].values
#define a seed for reproducibility
seed = 1
print('Splitting data into training and testing data')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = seed)
print(X_test[0])
# Define scoring method
scoring = 'accuracy'
print('Model building to train')
names = ['MultinomialNB', 'BernoulliNB', 'Perceptron', 'SGDClassifier', 'PassiveAggressiveClassifier']
Classifiers = [
MultinomialNB(),
BernoulliNB(),
Perceptron(),
SGDClassifier(),
PassiveAggressiveClassifier(),
]
models = zip(names, Classifiers)
from sklearn.model_selection import KFold, cross_val_score
names = []
result = []
for name, model in models:
kfold = KFold(n_splits = 5, random_state = 1)
cv_results = cross_val_score(model, X_train, y_train, cv = kfold, scoring = 'accuracy', verbose=2, n_jobs=-1)
result.append(cv_results)
names.append(name)
msg = "{0}: {1} ({2})".format(name, cv_results.mean(), cv_results.std())
print(msg)
models = zip(names, Classifiers)
for name, model in models:
print("Training with: "+name)
model.partial_fit(X_train, y_train, classes=np.unique(y_train))
y_pred = model.predict(X_test)
print('Exporting')
joblib.dump(model, "Models/"+name + ".pkl")
print(name)
print(accuracy_score(y_test, y_pred))
print(classification_report(y_test, y_pred))
score.append(lr.score(x_test,y_test))
print(' Logistic Regression ')
print(cross_val_score(lr,x_train,y_train,cv=3))
print(f1(y_test,y_lr,average='micro'))
#LDA
lda = LinearDiscriminantAnalysis(solver='svd')
lda.fit(x_train,y_train)
y_lda = lda.predict(x_test)
score.append(lda.score(x_test,y_test))
print(' Linear Discriminant Analysis ')
print(cross_val_score(lda,x_train,y_train,cv=3))
print(f1(y_test,y_lda,average='micro'))
#Perceptron
per = Perceptron(penalty='l1',alpha=0.001)
per.fit(x_train,y_train)
y_per = per.predict(x_test)
score.append(per.score(x_test,y_test))
print(' Perceptron Classifier ')
print(cross_val_score(per,x_train,y_train,cv=3))
print(f1(y_test,y_per,average='micro'))
#SVM
svm = SVC(C=100,kernel='poly',degree=4,coef0 = 0)
svm.fit(x_train,y_train)
y_svm = svm.predict(x_test)
score.append(svm.score(x_test,y_test))
print(' Support Vector Machine ')
print(f1(y_test,y_svm,average='micro'))
print(cross_val_score(svm,x_train,y_train,cv=3))
'''
Multi Layer Perceptron
단층 Perceptron은 XOR 분류를 하지 못함. 하지만 층(Layer)를 늘리면 가능. 이를 MLP라고 함
'''
import numpy as np
from sklearn.linear_model import Perceptron
feature = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
label = np.array([0, 1, 1, 0])
ml = Perceptron(max_iter=1000).fit(feature, label)
print(ml.predict(feature))
print()
# 다층 신경망 사용
from sklearn.neural_network import MLPClassifier
# ml2 = MLPClassifier(hidden_layer_sizes=50, verbose=2).fit(feature, label) #verbose 진행과정 프린트(Iteration 반복횟수, loss = 실제값과 예측값 차이),
ml2 = MLPClassifier(
hidden_layer_sizes=(10, 10, 10),
learning_rate_init=0.01,
max_iter=100,
random_state=1,
verbose=1).fit(
feature,
label) # hidden_layer_sizes=(10, 10, 10) 노드가 10개인 히든레이어를 3개를 준 것
print(ml2.predict(feature))
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
X = [[181, 80, 44], [177, 70, 43], [160, 60, 38], [154, 54, 37], [166, 65, 40],
[190, 90, 47], [175, 64, 39], [177, 70, 40], [159, 55, 37], [171, 75, 42],
[181, 85, 43]]
Y = [
'male', 'male', 'female', 'female', 'male', 'male', 'female', 'female',
'female', 'male', 'male'
]
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.4)
clf_tree = tree.DecisionTreeClassifier()
clf_linear = Perceptron()
clf_log = LogisticRegression()
clf_knn = KNeighborsClassifier(n_neighbors=2)
clf_svm = SVC()
clf_tree = clf_tree.fit(X_train, y_train)
clf_linear = clf_linear.fit(X_train, y_train)
clf_log = clf_log.fit(X_train, y_train)
clf_knn = clf_knn.fit(X_train, y_train)
clf_svm = clf_svm.fit(X_train, y_train)
y_pred1 = clf_tree.predict(X_test)
y_pred2 = clf_linear.predict(X_test)
y_pred3 = clf_log.predict(X_test)
y_pred4 = clf_knn.predict(X_test)
y_pred5 = clf_svm.predict(X_test)
#New Code For PAN
pan_train='/home/namrita/Downloads/AIdata/pan13-author-profiling-training-corpus-2013-01-09/en'
pan_temp='/home/namrita/Downloads/AIdata/pantemp'
# pan_test='/home/namrita/Downloads/AIdata/pan13-author-profiling-test-corpus2-2013-04-29/en'
print ('Reading database ...')
k,g,y_train = read_pan(pan_train)
# print (y_train)
# k_t, test_y, a_t = read_pan(pan_test)
print('Extracting asset')
train_x,f_names,chi,transformer=feature_extraction2(givenlabel,k)
# print ('Writing database ...')
# writeTrainToTxt(train_x,'feature.txt')
# # writeTrainToTxt(y_train,'y.txt')
# print ('written')
train_X, test_X, train_y, test_y = train_test_split(train_x, y_train, train_size=0.80)
print ('Mission successful')
# print(len(X_train))
# test_x,_,_,_=feature_extraction2(givenlabel,k_t)
# train_x=train_x.toarray().astype(np.float)
# print (train_x.dtype)
# train_x,f_names,chi,transformer=feature_extraction(givenlabel,k)
# print(simple_classify(RandomForestClassifier(),test_X,test_y,train_X,train_y))
print(simple_classify(RidgeClassifier(),test_X,test_y,train_X,train_y))
print(simple_classify(Perceptron(),test_X,test_y,train_X,train_y))
print(simple_classify(PassiveAggressiveClassifier(),test_X,test_y,train_X,train_y))
print(simple_classify(RandomForestClassifier(),test_X,test_y,train_X,train_y))
print(simple_classify(KNeighborsClassifier(),test_X,test_y,train_X,train_y))
print(simple_classify(MultinomialNB(),test_X,test_y,train_X,k))
def get_model_from_name(model_name, training_params=None):
# For Keras
epochs = 250
if 'is_test_suite' in sys.argv:
print(
'Heard that this is the test suite. Limiting epochs to 10, which will increase training speed dramatically at the expense of model accuracy'
)
epochs = 10
all_model_params = {
'LogisticRegression': {
'n_jobs': -2
},
'RandomForestClassifier': {
'n_jobs': -2
},
'ExtraTreesClassifier': {
'n_jobs': -1
},
'AdaBoostClassifier': {
'n_estimators': 10
},
'SGDClassifier': {
'n_jobs': -1
},
'Perceptron': {
'n_jobs': -1
},
'LinearRegression': {
'n_jobs': -2
},
'RandomForestRegressor': {
'n_jobs': -2
},
'ExtraTreesRegressor': {
'n_jobs': -1
},
'MiniBatchKMeans': {
'n_clusters': 8
},
'GradientBoostingRegressor': {
'presort': False
},
'SGDRegressor': {
'shuffle': False
},
'PassiveAggressiveRegressor': {
'shuffle': False
},
'AdaBoostRegressor': {
'n_estimators': 10
},
'XGBRegressor': {
'nthread': -1,
'n_estimators': 200
},
'XGBClassifier': {
'nthread': -1,
'n_estimators': 200
},
'LGBMRegressor': {},
'LGBMClassifier': {},
'DeepLearningRegressor': {
'epochs': epochs,
'batch_size': 50,
'verbose': 2
},
'DeepLearningClassifier': {
'epochs': epochs,
'batch_size': 50,
'verbose': 2
}
}
model_params = all_model_params.get(model_name, None)
if model_params is None:
model_params = {}
if training_params is not None:
print('Now using the model training_params that you passed in:')
print(training_params)
# Overwrite our stock params with what the user passes in (i.e., if the user wants 10,000 trees, we will let them do it)
model_params.update(training_params)
print(
'After overwriting our defaults with your values, here are the final params that will be used to initialize the model:'
)
print(model_params)
model_map = {
# Classifiers
'LogisticRegression': LogisticRegression(),
'RandomForestClassifier': RandomForestClassifier(),
'RidgeClassifier': RidgeClassifier(),
'GradientBoostingClassifier': GradientBoostingClassifier(),
'ExtraTreesClassifier': ExtraTreesClassifier(),
'AdaBoostClassifier': AdaBoostClassifier(),
'SGDClassifier': SGDClassifier(),
'Perceptron': Perceptron(),
'PassiveAggressiveClassifier': PassiveAggressiveClassifier(),
# Regressors
# 'DeepLearningRegressor': KerasRegressor(build_fn=make_deep_learning_model, epochs=10, batch_size=10, **training_params, verbose=1),
'LinearRegression': LinearRegression(),
'RandomForestRegressor': RandomForestRegressor(),
'Ridge': Ridge(),
'ExtraTreesRegressor': ExtraTreesRegressor(),
'AdaBoostRegressor': AdaBoostRegressor(),
'RANSACRegressor': RANSACRegressor(),
'GradientBoostingRegressor': GradientBoostingRegressor(),
'Lasso': Lasso(),
'ElasticNet': ElasticNet(),
'LassoLars': LassoLars(),
'OrthogonalMatchingPursuit': OrthogonalMatchingPursuit(),
'BayesianRidge': BayesianRidge(),
'ARDRegression': ARDRegression(),
'SGDRegressor': SGDRegressor(),
'PassiveAggressiveRegressor': PassiveAggressiveRegressor(),
# Clustering
'MiniBatchKMeans': MiniBatchKMeans()
}
if xgb_installed:
model_map['XGBClassifier'] = xgb.XGBClassifier()
model_map['XGBRegressor'] = xgb.XGBRegressor()
if lgb_installed:
model_map['LGBMRegressor'] = lgb.LGBMRegressor()
model_map['LGBMClassifier'] = lgb.LGBMClassifier()
if keras_installed:
model_map['DeepLearningClassifier'] = KerasClassifier(
build_fn=make_deep_learning_classifier)
model_map['DeepLearningRegressor'] = KerasRegressor(
build_fn=make_deep_learning_model)
model_without_params = model_map[model_name]
model_with_params = model_without_params.set_params(**model_params)
return model_with_params
y= iris.target
#spliting the dataset
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
#Feature scaling: standarization
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train) #estimates the parameters: mean and standard deviation for EACH FEATURE DIMENSION from the training data
X_train_std=sc.transform(X_train)
X_test_std=sc.transform(X_test)
#Perceptron
from sklearn.linear_model import Perceptron
ppn = Perceptron(n_iter = 40, eta0 = 0.1, random_state = 0) #random_state=0 gives the system...
#... reproducibility of the initial shuffling of the training dataset after each epoch
ppn.fit(X_train_std, y_train) #initializing the model
y_pred = ppn.predict(X_test_std)
n_y_pred = y_pred.size
print(n_y_pred)
n_misclassification = (y_test != y_pred).sum()
print('Misclassified samples: %d' % n_misclassification)
#from the previous, the missclassification error can be calculated as:
misclassification_error = n_misclassification / n_y_pred
print('Misclassificication error: %.2f' % misclassification_error)
#Therefore the accuracy in two forms:
