def cvWithThreshold(X, y_current_tr, y_current_te, threshold, regularization='l2'):
out_dict = {}
scores = defaultdict(list)
fold=1
maxent = LogisticRegression(penalty=regularization)
for TrainIndices, TestIndices in cross_validation.StratifiedKFold(y_current_tr, n_folds=10, shuffle=False, random_state=None):
print('\r'+str(fold), end="")
fold+=1
TrainX_i = X[TrainIndices]
Trainy_i = y_current_tr[TrainIndices]
TestX_i = X[TestIndices]
Testy_i = y_current_te[TestIndices]
maxent.fit(TrainX_i,Trainy_i)
ypred_i, score=pred_for_threshold(maxent,TestX_i,Testy_i, threshold)
scores["F1"].append(score[0])
scores["Recall"].append(score[1])
scores["Accuracy"].append(score[2])
scores["Precision"].append(score[3])
#scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
print("\n--")
for key in sorted(scores.keys()):
currentmetric = np.array(scores[key])
out_dict[key] = (currentmetric.mean(),currentmetric.std())
print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
print("--")
return out_dict
def main():
scriptdir = os.path.dirname(os.path.realpath(__file__))
parser = argparse.ArgumentParser(description="Skeleton for features and classifier for CWI-2016--optimisation of threshhold")
parser.add_argument('--threshold',type=float,default=0.5)
parser.add_argument('--annotator',type=str,default="03")
parser.add_argument('--penalty',type=str,choices=["l1","l2"],default="l1")
args = parser.parse_args()
current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_"+args.annotator+".lbl.conll"
testfile = scriptdir+"/../data/cwi_testing/cwi_testing.txt.lbl.conll"
X__dict_train, y_train, v_train = feats_and_classify.collect_features(current_single_ann,vectorize=False)
X_dict_test, y_test, v_test = feats_and_classify.collect_features(testfile,vectorize=False)
featdicts = list([x for x in X__dict_train + X_dict_test])
vect = DictVectorizer()
X = vect.fit_transform(featdicts).toarray()
X_train=X[:len(y_train)]
X_test=X[len(y_train):]
maxent = LogisticRegression(penalty=args.penalty)
maxent.fit(X_train,y_train)
y_pred_proba = maxent.predict_proba(X_test)
ypred_i=["1" if pair[1]>=args.threshold else "0" for pair in y_pred_proba]
fout = open(args.annotator+".pred",mode="w")
print("\n".join(ypred_i),file=fout)
fout.close()
sys.exit(0)
def test_regularization_path(self):
# Check results using logistic path
num_samples = 10
num_feat = 5
X, y = make_classification(n_samples=num_samples, n_features=num_feat, n_informative=3,
n_classes=2, random_state=0, weights=[0.5, 0.5])
matrix = np.zeros((num_samples, num_feat + 2))
matrix[:,:-2] = X
matrix[:, -2] = np.ones(num_samples)
matrix[:, -1] = y
# Betas to test
logitfitL1 = LogisticRegressionL1()
lambda_grid = np.exp(-1 * np.linspace(1, 17, 200))
path = logitfitL1.fit(matrix, lambda_grid)
# Sklearn
cs = l1_min_c(X, y, loss='log') * np.logspace(0, 3)
# Computing regularization path using sklearn
clf = LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
coefs_ = []
for c in cs:
clf.set_params(C=c)
clf.fit(X, y)
coefs_.append(clf.coef_.ravel().copy())
skbetas = np.append(clf.intercept_[0], clf.coef_)
np.testing.assert_almost_equal(skbetas, logitfitL1.coef_, 1)
def mlogistic():
X = []
# 前三行作为输入样本
X.append("f**k you")
X.append("f**k you all")
X.append("hello everyone")
# 后两句作为测试样本
X.append("f**k me")
X.append("hello boy")
# y为样本标注
y = [1,1,0]
vectorizer = TfidfVectorizer()
# 取X的前三句作为输入做tfidf转换
X_train = vectorizer.fit_transform(X[:-2])
print X_train
# 取X的后两句用“上句生成”的tfidf做转换
X_test = vectorizer.transform(X[-2:])
print X_test
# 用逻辑回归模型做训练
classifier = LogisticRegression()
classifier.fit(X_train, y)
# 做测试样例的预测
predictions = classifier.predict(X_test)
print predictions
class LogReg:
def __init__(self):
self.load_data()
self.clf = LogisticRegression(class_weight = 'balanced')
self.train()
self.predict()
def load_data(self):
train_csv = './data/train.csv'
test_csv = './data/test.csv'
df_train = pd.read_csv(train_csv, header=0)
df_test = pd.read_csv(test_csv, header=0)
arr_train = df_train.values
arr_test = df_test.values
self.train_X = arr_train[0::,1::]
self.train_Y = arr_train[0::, 0]
self.test_X = arr_test[0::, 1::]
self.test_ID = arr_test[0::,0]
def train(self):
self.clf.fit(self.train_X, self.train_Y)
def predict(self):
self.test_Y = self.clf.predict_proba(self.test_X)
def get_training_accuracy(self):
return (self.clf.score(self.train_X, self.train_Y))
def store_result(self):
df_out = pd.DataFrame()
df_out['Id'] = self.test_ID
df_out['Action'] = self.test_Y[0::,1]
df_out.to_csv('./data/results/c1_result.csv',index=False)
def predictWithThreshold(datadir, threshold, penalty_type='l2'):
maxent = LogisticRegression(penalty=penalty_type)
scores = defaultdict(list)
for dir in sorted(os.listdir(datadir), reverse=True):
trainfeatures, trainlabels, vec = feats_and_classify.collect_features(datadir+dir+'/train.conll')
TrainIndices=np.array(range(len(trainfeatures)))
features, labels, vec = feats_and_classify.collect_features(datadir+dir+'/all.conll')
TestIndices=np.array(range(len(trainfeatures),len(features)))
# print('\r'+dir, end="")
# print(dir)
TrainX_i = features[TrainIndices]
Trainy_i = labels[TrainIndices]
TestX_i = features[TestIndices]
Testy_i = labels[TestIndices]
maxent.fit(TrainX_i,Trainy_i)
# print('Finished fitting')
ypred_i, score=pred_for_threshold(maxent,TestX_i,Testy_i, threshold)
# print('Predicting')
scores["F1"].append(score[0])
scores["Recall"].append(score[1])
scores["Accuracy"].append(score[2])
scores["Precision"].append(score[3])
#scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
print("\n--")
for key in sorted(scores.keys()):
currentmetric = np.array(scores[key])
print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
print("--")
def main():
classes = [
'chimp',
'corvette',
'tokyo',
'goldengatebridge'
]
images, labels = get_labels(classes)
std_features = get_standard_features(images)
k = 256
surf_features = get_visual_words(images, k)
tas_features = get_tas_features(images)
feature_dict = {
'Std': std_features,
'SURF': surf_features,
'TAS': tas_features
#'Zernike': zernike_features
}
best_features = log_classify(feature_dict, labels)
classifier = LogisticRegression()
classifier.fit(best_features, labels)
def test_logreg_cv_penalty():
# Test that the correct penalty is passed to the final fit.
X, y = make_classification(n_samples=50, n_features=20, random_state=0)
lr_cv = LogisticRegressionCV(penalty="l1", Cs=[1.0], solver='liblinear')
lr_cv.fit(X, y)
lr = LogisticRegression(penalty="l1", C=1.0, solver='liblinear')
lr.fit(X, y)
assert_equal(np.count_nonzero(lr_cv.coef_), np.count_nonzero(lr.coef_))
def classify_logistic(train_features, train_labels, test_features):
global SAVE
clf = LogisticRegression()
clf.fit(train_features, train_labels)
if not TEST and SAVE:
save_pickle("logistic", clf)
return clf.predict(test_features)
def main():
scriptdir = os.path.dirname(os.path.realpath(__file__))
default_pool = scriptdir+"/../data/cwi_training/cwi_training.txt.lbl.conll"
parser = argparse.ArgumentParser(description="Skeleton for features and classifier for CWI-2016--optimisation of threshhold")
parser.add_argument('--iterations',type=int,default=5)
args = parser.parse_args()
all_feats = []
all_labels = defaultdict(list)
scores = defaultdict(list)
for idx in "01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 19 20".split(" "):
# for idx in "01".split(" "):
current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_"+idx+".lbl.conll"
f_current, labels_current, v_current = feats_and_classify.collect_features(current_single_ann,vectorize=False,generateFeatures=False)
for instance_index,l in enumerate(labels_current):
all_labels[instance_index].append(l)
current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_01.lbl.conll"
feats, labels_current, v_current = feats_and_classify.collect_features(current_single_ann,vectorize=True,generateFeatures=True)
for it in range(args.iterations):
for TrainIndices, TestIndices in cross_validation.KFold(n=feats.shape[0], n_folds=10, shuffle=True, random_state=None):
maxent = LogisticRegression(penalty='l2')
TrainX_i = feats[TrainIndices]
Trainy_i = [all_labels[x][random.randrange(0,20)] for x in TrainIndices]
TestX_i = feats[TestIndices]
Testy_i = [all_labels[x][random.randrange(0,20)] for x in TestIndices]
maxent.fit(TrainX_i,Trainy_i)
ypred_i = maxent.predict(TestX_i)
acc = accuracy_score(ypred_i, Testy_i)
pre = precision_score(ypred_i, Testy_i)
rec = recall_score(ypred_i, Testy_i)
# shared task uses f1 of *accuracy* and recall!
f1 = 2 * acc * rec / (acc + rec)
scores["Accuracy"].append(acc)
scores["F1"].append(f1)
scores["Precision"].append(pre)
scores["Recall"].append(rec)
#scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
print("--")
for key in sorted(scores.keys()):
currentmetric = np.array(scores[key])
print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
print("--")
sys.exit(0)
def my_module(rt, params, inputs, outputs):
# TODO : Fill your code here
X = pickle.load(open(inputs.X, 'r'))
Y = pickle.load(open(inputs.Y, 'r'))
model = LogisticRegression()
model.fit(X, Y)
pickle.dump(model, open(outputs.MODEL, 'w'))
print "Done"
def test_logreg_l1_sparse_data():
# Because liblinear penalizes the intercept and saga does not, we do not
# fit the intercept to make it possible to compare the coefficients of
# the two models at convergence.
rng = np.random.RandomState(42)
n_samples = 50
X, y = make_classification(n_samples=n_samples, n_features=20,
random_state=0)
X_noise = rng.normal(scale=0.1, size=(n_samples, 3))
X_constant = np.zeros(shape=(n_samples, 2))
X = np.concatenate((X, X_noise, X_constant), axis=1)
X[X < 1] = 0
X = sparse.csr_matrix(X)
lr_liblinear = LogisticRegression(penalty="l1", C=1.0, solver='liblinear',
fit_intercept=False,
tol=1e-10)
lr_liblinear.fit(X, y)
lr_saga = LogisticRegression(penalty="l1", C=1.0, solver='saga',
fit_intercept=False,
max_iter=1000, tol=1e-10)
lr_saga.fit(X, y)
assert_array_almost_equal(lr_saga.coef_, lr_liblinear.coef_)
# Noise and constant features should be regularized to zero by the l1
# penalty
assert_array_almost_equal(lr_liblinear.coef_[0, -5:], np.zeros(5))
assert_array_almost_equal(lr_saga.coef_[0, -5:], np.zeros(5))
# Check that solving on the sparse and dense data yield the same results
lr_saga_dense = LogisticRegression(penalty="l1", C=1.0, solver='saga',
fit_intercept=False,
max_iter=1000, tol=1e-10)
lr_saga_dense.fit(X.toarray(), y)
assert_array_almost_equal(lr_saga.coef_, lr_saga_dense.coef_)
def test_dtype_match():
# Disabled to unblock the 0.19.2 release. See:
# https://github.com/scikit-learn/scikit-learn/issues/11438
# Test that np.float32 input data is not cast to np.float64 when possible
raise SkipTest()
X_32 = np.array(X).astype(np.float32)
y_32 = np.array(Y1).astype(np.float32)
X_64 = np.array(X).astype(np.float64)
y_64 = np.array(Y1).astype(np.float64)
X_sparse_32 = sp.csr_matrix(X, dtype=np.float32)
for solver in ['newton-cg']:
for multi_class in ['ovr', 'multinomial']:
# Check type consistency
lr_32 = LogisticRegression(solver=solver, multi_class=multi_class)
lr_32.fit(X_32, y_32)
assert_equal(lr_32.coef_.dtype, X_32.dtype)
# check consistency with sparsity
lr_32_sparse = LogisticRegression(solver=solver,
multi_class=multi_class)
lr_32_sparse.fit(X_sparse_32, y_32)
assert_equal(lr_32_sparse.coef_.dtype, X_sparse_32.dtype)
# Check accuracy consistency
lr_64 = LogisticRegression(solver=solver, multi_class=multi_class)
lr_64.fit(X_64, y_64)
assert_equal(lr_64.coef_.dtype, X_64.dtype)
assert_almost_equal(lr_32.coef_, lr_64.coef_.astype(np.float32))
def test_dtype_match():
# Test that np.float32 input data is not cast to np.float64 when possible
X_32 = np.array(X).astype(np.float32)
y_32 = np.array(Y1).astype(np.float32)
X_64 = np.array(X).astype(np.float64)
y_64 = np.array(Y1).astype(np.float64)
X_sparse_32 = sp.csr_matrix(X, dtype=np.float32)
for solver in ['newton-cg']:
for multi_class in ['ovr', 'multinomial']:
# Check type consistency
lr_32 = LogisticRegression(solver=solver, multi_class=multi_class)
lr_32.fit(X_32, y_32)
assert_equal(lr_32.coef_.dtype, X_32.dtype)
# check consistency with sparsity
lr_32_sparse = LogisticRegression(solver=solver,
multi_class=multi_class)
lr_32_sparse.fit(X_sparse_32, y_32)
assert_equal(lr_32_sparse.coef_.dtype, X_sparse_32.dtype)
# Check accuracy consistency
lr_64 = LogisticRegression(solver=solver, multi_class=multi_class)
lr_64.fit(X_64, y_64)
assert_equal(lr_64.coef_.dtype, X_64.dtype)
assert_almost_equal(lr_32.coef_, lr_64.coef_.astype(np.float32))
def test_nnet(n_samples=200, n_features=7, distance=0.8, complete=False):
"""
:param complete: if True, all possible combinations will be checked, and quality is printed
"""
X, y = generate_sample(n_samples=n_samples, n_features=n_features, distance=distance)
nn_types = [
nnet.SimpleNeuralNetwork,
nnet.MLPClassifier,
nnet.SoftmaxNeuralNetwork,
nnet.RBFNeuralNetwork,
nnet.PairwiseNeuralNetwork,
nnet.PairwiseSoftplusNeuralNetwork,
]
if complete:
# checking all possible combinations
for loss in nnet.losses:
for NNType in nn_types:
for trainer in nnet.trainers:
nn = NNType(layers=[5], loss=loss, trainer=trainer, random_state=42, epochs=100)
nn.fit(X, y )
print(roc_auc_score(y, nn.predict_proba(X)[:, 1]), nn)
lr = LogisticRegression().fit(X, y)
print(lr, roc_auc_score(y, lr.predict_proba(X)[:, 1]))
assert 0 == 1, "Let's see and compare results"
else:
# checking combinations of losses, nn_types, trainers, most of them are used once during tests.
attempts = max(len(nnet.losses), len(nnet.trainers), len(nn_types))
losses_shift = numpy.random.randint(10)
trainers_shift = numpy.random.randint(10)
for attempt in range(attempts):
# each combination is tried 3 times. before raising exception
retry_attempts = 3
for retry_attempt in range(retry_attempts):
loss = list(nnet.losses.keys())[(attempt + losses_shift) % len(nnet.losses)]
trainer = list(nnet.trainers.keys())[(attempt + trainers_shift) % len(nnet.trainers)]
nn_type = nn_types[attempt % len(nn_types)]
nn = nn_type(layers=[5], loss=loss, trainer=trainer, random_state=42 + retry_attempt, epochs=200)
print(nn)
nn.fit(X, y)
quality = roc_auc_score(y, nn.predict_proba(X)[:, 1])
computed_loss = nn.compute_loss(X, y)
if quality > 0.8:
break
else:
print('attempt {} : {}'.format(retry_attempt, quality))
if retry_attempt == retry_attempts - 1:
raise RuntimeError('quality of model is too low: {} {}'.format(quality, nn))
def prepare(imageFolder):
print("preparing images...")
inputData = []
outputData = []
for file in os.listdir(imageFolder):
if (len(file) == 8):
inputData += getInputFromPic(Image.open(imageFolder + file).convert("L"), file)
outputData += getOutputFromFileName(file)
print("training model...")
model = LogisticRegression()
model.fit(inputData, outputData)
return model
def test_liblinear_decision_function_zero():
# Test negative prediction when decision_function values are zero.
# Liblinear predicts the positive class when decision_function values
# are zero. This is a test to verify that we do not do the same.
# See Issue: https://github.com/scikit-learn/scikit-learn/issues/3600
# and the PR https://github.com/scikit-learn/scikit-learn/pull/3623
X, y = make_classification(n_samples=5, n_features=5, random_state=0)
clf = LogisticRegression(fit_intercept=False)
clf.fit(X, y)
# Dummy data such that the decision function becomes zero.
X = np.zeros((5, 5))
assert_array_equal(clf.predict(X), np.zeros(5))
def fit_model_2(self, lol = .07, toWrite = False):
model = LogisticRegression(C = lol, penalty = 'l1', tol = 1e-6)
for data in self.cv_data:
X_train, X_test, Y_train, Y_test = data
X_train,Y_train = self.balance_data(X_train,Y_train)
model.fit(X_train,Y_train)
pred = model.predict_proba(X_test)[:,1]
print("Model 2 Score: %f" % (logloss(Y_test,pred),))
if toWrite:
f2 = open('model2/model.pkl','w')
pickle.dump(model,f2)
f2.close()
def test_logistic_regression_solvers():
X, y = make_classification(n_features=10, n_informative=5, random_state=0)
clf_n = LogisticRegression(solver='newton-cg', fit_intercept=False)
clf_n.fit(X, y)
clf_lbf = LogisticRegression(solver='lbfgs', fit_intercept=False)
clf_lbf.fit(X, y)
clf_lib = LogisticRegression(fit_intercept=False)
clf_lib.fit(X, y)
assert_array_almost_equal(clf_n.coef_, clf_lib.coef_, decimal=3)
assert_array_almost_equal(clf_lib.coef_, clf_lbf.coef_, decimal=3)
assert_array_almost_equal(clf_n.coef_, clf_lbf.coef_, decimal=3)
def test_logistic_regression_solvers_multiclass():
X, y = make_classification(n_samples=20, n_features=20, n_informative=10, n_classes=3, random_state=0)
clf_n = LogisticRegression(solver="newton-cg", fit_intercept=False)
clf_n.fit(X, y)
clf_lbf = LogisticRegression(solver="lbfgs", fit_intercept=False)
clf_lbf.fit(X, y)
clf_lib = LogisticRegression(fit_intercept=False)
clf_lib.fit(X, y)
assert_array_almost_equal(clf_n.coef_, clf_lib.coef_, decimal=4)
assert_array_almost_equal(clf_lib.coef_, clf_lbf.coef_, decimal=4)
assert_array_almost_equal(clf_n.coef_, clf_lbf.coef_, decimal=4)
def test_max_iter():
# Test that the maximum number of iteration is reached
X, y_bin = iris.data, iris.target.copy()
y_bin[y_bin == 2] = 0
solvers = ["newton-cg", "liblinear", "sag"]
# old scipy doesn't have maxiter
if sp_version >= (0, 12):
solvers.append("lbfgs")
for max_iter in range(1, 5):
for solver in solvers:
lr = LogisticRegression(max_iter=max_iter, tol=1e-15, random_state=0, solver=solver)
lr.fit(X, y_bin)
assert_equal(lr.n_iter_[0], max_iter)
def test_inconsistent_input():
# Test that an exception is raised on inconsistent input
rng = np.random.RandomState(0)
X_ = rng.random_sample((5, 10))
y_ = np.ones(X_.shape[0])
y_[0] = 0
clf = LogisticRegression(random_state=0)
# Wrong dimensions for training data
y_wrong = y_[:-1]
assert_raises(ValueError, clf.fit, X, y_wrong)
# Wrong dimensions for test data
assert_raises(ValueError, clf.fit(X_, y_).predict, rng.random_sample((3, 12)))
def clazzify(train_mat, test_mat, true_train_labels):
"""
"""
# learn
logging.info('learning...')
model = LogisticRegression(random_state=17, penalty='l1')
model.fit(train_mat, true_train_labels)
logging.info('finished learning.')
# test
logging.info('testing')
predicted_test_labels = model.predict(test_mat)
logging.info('finished testing')
return predicted_test_labels, model
def test_multinomial_binary_probabilities():
# Test multinomial LR gives expected probabilities based on the
# decision function, for a binary problem.
X, y = make_classification()
clf = LogisticRegression(multi_class='multinomial', solver='saga')
clf.fit(X, y)
decision = clf.decision_function(X)
proba = clf.predict_proba(X)
expected_proba_class_1 = (np.exp(decision) /
(np.exp(decision) + np.exp(-decision)))
expected_proba = np.c_[1-expected_proba_class_1, expected_proba_class_1]
assert_almost_equal(proba, expected_proba)
def generate_submission():
global alg, predictions, submission
# The columns we'll use to predict the target
# Initialize the algorithm class
alg = LogisticRegression(random_state=1)
# Train the algorithm using all the training data
alg.fit(train[predictors], train["Survived"])
# Make predictions using the test set.
predictions = alg.predict(test[predictors])
# Create a new dataframe with only the columns Kaggle wants from the dataset.
submission = pandas.DataFrame({
"PassengerId": test["PassengerId"],
"Survived": predictions
})
submission.to_csv("kaggle.csv", index=False)
print("kaggele.csv is generated")
def test_scikit_learn_exploded_data(self):
# Check results with scikit learn
betas = [0.001, 0.07, 0.4]
matrix = create_random_observations(200, 2, betas)
new_matrix = explode_matrix(matrix)
X = new_matrix[:,:-2]
y = new_matrix[:, -1]
lib = LogisticRegression(fit_intercept=True)
lib.fit(X, y)
path = self.logitfitL1.fit(new_matrix, self.lambda_grid)
skbetas = np.append(lib.intercept_[0], lib.coef_)
np.testing.assert_almost_equal(skbetas, self.logitfitL1.coef_, 2)
def test_predict_iris():
"""Test logistic regression with the iris dataset"""
n_samples, n_features = iris.data.shape
target = iris.target_names[iris.target]
clf = LogisticRegression(C=len(iris.data)).fit(iris.data, target)
assert_array_equal(np.unique(target), clf.classes_)
pred = clf.predict(iris.data)
assert_greater(np.mean(pred == target), .95)
probabilities = clf.predict_proba(iris.data)
assert_array_almost_equal(probabilities.sum(axis=1), np.ones(n_samples))
pred = iris.target_names[probabilities.argmax(axis=1)]
assert_greater(np.mean(pred == target), .95)
def test_max_iter():
# Test that the maximum number of iteration is reached
X, y_bin = iris.data, iris.target.copy()
y_bin[y_bin == 2] = 0
solvers = ['newton-cg', 'liblinear', 'sag', 'saga', 'lbfgs']
for max_iter in range(1, 5):
for solver in solvers:
for multi_class in ['ovr', 'multinomial']:
if solver == 'liblinear' and multi_class == 'multinomial':
continue
lr = LogisticRegression(max_iter=max_iter, tol=1e-15,
multi_class=multi_class,
random_state=0, solver=solver)
lr.fit(X, y_bin)
assert_equal(lr.n_iter_[0], max_iter)
def test_nnet(n_samples=200, n_features=5, distance=0.5, complete=False):
X, y = make_blobs(
n_samples=n_samples,
n_features=5,
centers=[numpy.ones(n_features) * distance, -numpy.ones(n_features) * distance],
)
nn_types = [
nnet.SimpleNeuralNetwork,
nnet.MultiLayerNetwork,
nnet.SoftmaxNeuralNetwork,
nnet.RBFNeuralNetwork,
nnet.PairwiseNeuralNetwork,
nnet.PairwiseSoftplusNeuralNetwork,
]
if complete:
# checking all possible combinations
for loss in nnet.losses:
for NNType in nn_types:
for trainer in nnet.trainers:
nn = NNType(layers=[5], loss=loss, trainer=trainer, random_state=42)
nn.fit(X, y, epochs=100)
print(roc_auc_score(y, nn.predict_proba(X)[:, 1]), nn)
lr = LogisticRegression().fit(X, y)
print(lr, roc_auc_score(y, lr.predict_proba(X)[:, 1]))
assert 0 == 1, "Let's see and compare results"
else:
# checking combinations of losses, nn_types, trainers, most of them are used once during tests.
attempts = max(len(nnet.losses), len(nnet.trainers), len(nn_types))
attempts = 4
losses_shift = numpy.random.randint(10)
trainers_shift = numpy.random.randint(10)
for attempt in range(attempts):
loss = nnet.losses.keys()[(attempt + losses_shift) % len(nnet.losses)]
trainer = nnet.trainers.keys()[(attempt + trainers_shift) % len(nnet.trainers)]
nn_type = nn_types[attempt % len(nn_types)]
nn = nn_type(layers=[5], loss=loss, trainer=trainer, random_state=42)
print(nn)
nn.fit(X, y, epochs=200)
assert roc_auc_score(y, nn.predict_proba(X)[:, 1]) > 0.8, "quality of model is too low: {}".format(nn)
class mentoryWEB:
def __init__(self, file):
self.vect = TfidfVectorizer(max_df=0.25, stop_words=None, max_features=2500, ngram_range=(1,2), use_idf=True, norm='l2')
df = pd.read_csv(file, delimiter='\t', header=None)
X_train_raw, y_train = df[1], df[0]
X_train = self.vect.fit_transform(X_train_raw)
self.clf = LogisticRegression(penalty='l2', C=10)
self.clf.fit(X_train, y_train)
def test(self, string):
X_test = self.vect.transform([string])
prediction = self.clf.predict(X_test)
return prediction[0]
def test_logistic_regression_sample_weights():
X, y = make_classification(n_samples=20,
n_features=5,
n_informative=3,
n_classes=2,
random_state=0)
sample_weight = y + 1
for LR in [LogisticRegression, LogisticRegressionCV]:
# Test that passing sample_weight as ones is the same as
# not passing them at all (default None)
for solver in ['lbfgs', 'liblinear']:
clf_sw_none = LR(solver=solver,
fit_intercept=False,
random_state=42)
clf_sw_none.fit(X, y)
clf_sw_ones = LR(solver=solver,
fit_intercept=False,
random_state=42)
clf_sw_ones.fit(X, y, sample_weight=np.ones(y.shape[0]))
assert_array_almost_equal(clf_sw_none.coef_,
clf_sw_ones.coef_,
decimal=4)
# Test that sample weights work the same with the lbfgs,
# newton-cg, and 'sag' solvers
clf_sw_lbfgs = LR(solver='lbfgs', fit_intercept=False, random_state=42)
clf_sw_lbfgs.fit(X, y, sample_weight=sample_weight)
clf_sw_n = LR(solver='newton-cg', fit_intercept=False, random_state=42)
clf_sw_n.fit(X, y, sample_weight=sample_weight)
clf_sw_sag = LR(solver='sag',
fit_intercept=False,
tol=1e-10,
random_state=42)
# ignore convergence warning due to small dataset
with ignore_warnings():
clf_sw_sag.fit(X, y, sample_weight=sample_weight)
clf_sw_liblinear = LR(solver='liblinear',
fit_intercept=False,
random_state=42)
clf_sw_liblinear.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(clf_sw_lbfgs.coef_,
clf_sw_n.coef_,
decimal=4)
assert_array_almost_equal(clf_sw_lbfgs.coef_,
clf_sw_sag.coef_,
decimal=4)
assert_array_almost_equal(clf_sw_lbfgs.coef_,
clf_sw_liblinear.coef_,
decimal=4)
# Test that passing class_weight as [1,2] is the same as
# passing class weight = [1,1] but adjusting sample weights
# to be 2 for all instances of class 2
for solver in ['lbfgs', 'liblinear']:
clf_cw_12 = LR(solver=solver,
fit_intercept=False,
class_weight={
0: 1,
1: 2
},
random_state=42)
clf_cw_12.fit(X, y)
clf_sw_12 = LR(solver=solver, fit_intercept=False, random_state=42)
clf_sw_12.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(clf_cw_12.coef_,
clf_sw_12.coef_,
decimal=4)
# Test the above for l1 penalty and l2 penalty with dual=True.
# since the patched liblinear code is different.
clf_cw = LogisticRegression(solver="liblinear",
fit_intercept=False,
class_weight={
0: 1,
1: 2
},
penalty="l1",
tol=1e-5,
random_state=42)
clf_cw.fit(X, y)
clf_sw = LogisticRegression(solver="liblinear",
fit_intercept=False,
penalty="l1",
tol=1e-5,
random_state=42)
clf_sw.fit(X, y, sample_weight)
assert_array_almost_equal(clf_cw.coef_, clf_sw.coef_, decimal=4)
clf_cw = LogisticRegression(solver="liblinear",
fit_intercept=False,
class_weight={
0: 1,
1: 2
},
penalty="l2",
dual=True,
random_state=42)
clf_cw.fit(X, y)
clf_sw = LogisticRegression(solver="liblinear",
fit_intercept=False,
penalty="l2",
dual=True,
random_state=42)
clf_sw.fit(X, y, sample_weight)
assert_array_almost_equal(clf_cw.coef_, clf_sw.coef_, decimal=4)
def test_logistic_regression_class_weights():
# Multinomial case: remove 90% of class 0
X = iris.data[45:, :]
y = iris.target[45:]
solvers = ("lbfgs", "newton-cg")
class_weight_dict = _compute_class_weight_dictionary(y)
for solver in solvers:
clf1 = LogisticRegression(solver=solver,
multi_class="multinomial",
class_weight="balanced")
clf2 = LogisticRegression(solver=solver,
multi_class="multinomial",
class_weight=class_weight_dict)
clf1.fit(X, y)
clf2.fit(X, y)
assert_array_almost_equal(clf1.coef_, clf2.coef_, decimal=4)
# Binary case: remove 90% of class 0 and 100% of class 2
X = iris.data[45:100, :]
y = iris.target[45:100]
solvers = ("lbfgs", "newton-cg", "liblinear")
class_weight_dict = _compute_class_weight_dictionary(y)
for solver in solvers:
clf1 = LogisticRegression(solver=solver,
multi_class="ovr",
class_weight="balanced")
clf2 = LogisticRegression(solver=solver,
multi_class="ovr",
class_weight=class_weight_dict)
clf1.fit(X, y)
clf2.fit(X, y)
assert_array_almost_equal(clf1.coef_, clf2.coef_, decimal=6)
def test_logistic_regression_multinomial():
# Tests for the multinomial option in logistic regression
# Some basic attributes of Logistic Regression
n_samples, n_features, n_classes = 50, 20, 3
X, y = make_classification(n_samples=n_samples,
n_features=n_features,
n_informative=10,
n_classes=n_classes,
random_state=0)
# 'lbfgs' is used as a referenced
solver = 'lbfgs'
ref_i = LogisticRegression(solver=solver, multi_class='multinomial')
ref_w = LogisticRegression(solver=solver,
multi_class='multinomial',
fit_intercept=False)
ref_i.fit(X, y)
ref_w.fit(X, y)
assert_array_equal(ref_i.coef_.shape, (n_classes, n_features))
assert_array_equal(ref_w.coef_.shape, (n_classes, n_features))
for solver in ['sag', 'newton-cg']:
clf_i = LogisticRegression(solver=solver,
multi_class='multinomial',
random_state=42,
max_iter=1000,
tol=1e-6)
clf_w = LogisticRegression(solver=solver,
multi_class='multinomial',
random_state=42,
max_iter=1000,
tol=1e-6,
fit_intercept=False)
clf_i.fit(X, y)
clf_w.fit(X, y)
assert_array_equal(clf_i.coef_.shape, (n_classes, n_features))
assert_array_equal(clf_w.coef_.shape, (n_classes, n_features))
# Compare solutions between lbfgs and the other solvers
assert_almost_equal(ref_i.coef_, clf_i.coef_, decimal=3)
assert_almost_equal(ref_w.coef_, clf_w.coef_, decimal=3)
assert_almost_equal(ref_i.intercept_, clf_i.intercept_, decimal=3)
# Test that the path give almost the same results. However since in this
# case we take the average of the coefs after fitting across all the
# folds, it need not be exactly the same.
for solver in ['lbfgs', 'newton-cg', 'sag']:
clf_path = LogisticRegressionCV(solver=solver,
max_iter=2000,
tol=1e-6,
multi_class='multinomial',
Cs=[1.])
clf_path.fit(X, y)
assert_array_almost_equal(clf_path.coef_, ref_i.coef_, decimal=3)
assert_almost_equal(clf_path.intercept_, ref_i.intercept_, decimal=3)
label=[
"en clinton test",
"en trump test",
"fr macron test",
"fr lepen test",
"it referendum test",
"ca indipendencia test",
"es indipendencia test",
]
clfs = {
"NB" : GaussianNB(),
"SVM": SVC(kernel="linear"),
"LR" : LogisticRegression()
}
for i in range(0,len(training)):
for key, clf in clfs.items():
print(key,label[i])
tweets_training=training[i]
tweets_test=test[i]
stance_training=numpy.array(feature_manager.get_stance(tweets_training))
stance_test=numpy.array(feature_manager.get_stance(tweets_test))
def test_multinomial_validation():
for solver in ['lbfgs', 'newton-cg', 'sag']:
lr = LogisticRegression(C=-1, solver=solver, multi_class='multinomial')
assert_raises(ValueError, lr.fit, [[0, 1], [1, 0]], [0, 1])
def test_liblinear_dual_random_state():
# random_state is relevant for liblinear solver only if dual=True
X, y = make_classification(n_samples=20, random_state=0)
lr1 = LogisticRegression(random_state=0, dual=True, max_iter=1, tol=1e-15)
lr1.fit(X, y)
lr2 = LogisticRegression(random_state=0, dual=True, max_iter=1, tol=1e-15)
lr2.fit(X, y)
lr3 = LogisticRegression(random_state=8, dual=True, max_iter=1, tol=1e-15)
lr3.fit(X, y)
# same result for same random state
assert_array_almost_equal(lr1.coef_, lr2.coef_)
# different results for different random states
msg = "Arrays are not almost equal to 6 decimals"
assert_raise_message(AssertionError, msg, assert_array_almost_equal,
lr1.coef_, lr3.coef_)
def gbdt_lr_train(libsvmFileName):
# load样本数据
X_all, y_all = load_svmlight_file(libsvmFileName)
# 训练/测试数据分割
X_train, X_test, y_train, y_test = train_test_split(X_all,
y_all,
test_size=0.3,
random_state=42)
# 定义GBDT模型
gbdt = GradientBoostingClassifier(n_estimators=40,
max_depth=3,
verbose=0,
max_features=0.5)
# 训练学习
gbdt.fit(X_train, y_train)
# 预测及AUC评测
y_pred_gbdt = gbdt.predict_proba(X_test.toarray())[:, 1]
gbdt_auc = roc_auc_score(y_test, y_pred_gbdt)
print('gbdt auc: %.5f' % gbdt_auc)
# lr对原始特征样本模型训练
lr = LogisticRegression()
lr.fit(X_train, y_train) # 预测及AUC评测
y_pred_test = lr.predict_proba(X_test)[:, 1]
lr_test_auc = roc_auc_score(y_test, y_pred_test)
print('基于原有特征的LR AUC: %.5f' % lr_test_auc)
# GBDT编码原有特征
X_train_leaves = gbdt.apply(X_train)[:, :, 0]
X_test_leaves = gbdt.apply(X_test)[:, :, 0]
# 对所有特征进行ont-hot编码
(train_rows, cols) = X_train_leaves.shape
gbdtenc = OneHotEncoder()
X_trans = gbdtenc.fit_transform(
np.concatenate((X_train_leaves, X_test_leaves), axis=0))
# 定义LR模型
lr = LogisticRegression()
# lr对gbdt特征编码后的样本模型训练
lr.fit(X_trans[:train_rows, :], y_train)
# 预测及AUC评测
y_pred_gbdtlr1 = lr.predict_proba(X_trans[train_rows:, :])[:, 1]
gbdt_lr_auc1 = roc_auc_score(y_test, y_pred_gbdtlr1)
print('基于GBDT特征编码后的LR AUC: %.5f' % gbdt_lr_auc1)
# 定义LR模型
lr = LogisticRegression(n_jobs=-1)
# 组合特征
X_train_ext = hstack([X_trans[:train_rows, :], X_train])
X_test_ext = hstack([X_trans[train_rows:, :], X_test])
print(X_train_ext.shape)
# lr对组合特征的样本模型训练
lr.fit(X_train_ext, y_train)
# 预测及AUC评测
y_pred_gbdtlr2 = lr.predict_proba(X_test_ext)[:, 1]
gbdt_lr_auc2 = roc_auc_score(y_test, y_pred_gbdtlr2)
print('基于组合特征的LR AUC: %.5f' % gbdt_lr_auc2)
from sklearn.naive_bayes import GaussianNB
from sklearn.lda import LDA
from sklearn.qda import QDA
h = .02 # step size in the mesh
from pyearth.earth import Earth
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
np.random.seed(1)
# Combine Earth with LogisticRegression in a pipeline to do classification
earth_classifier = Pipeline([('earth', Earth(max_degree=3, penalty=1.5)),
('logistic', LogisticRegression())])
names = [
"Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
"Random Forest", "Naive Bayes", "LDA", "QDA", "Earth"
]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
GaussianNB(),
LDA(),
QDA(), earth_classifier
]
im = mh.imread(fname, as_grey=True)
haralicks.append(texture(im))
sobels.append(edginess_sobel(im))
# Files are named like building00.jpg, scene23.jpg...
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralicks = np.array(haralicks)
sobels = np.array(sobels)
labels = np.array(labels)
# We use logistic regression because it is very fast.
# Feel free to experiment with other classifiers
scores = cross_validation.cross_val_score(LogisticRegression(),
haralicks,
labels,
cv=5)
print('Accuracy (5 fold x-val) with Logistic Regrssion [std features]: {}%'.
format(0.1 * round(1000 * scores.mean())))
haralick_plus_sobel = np.hstack([np.atleast_2d(sobels).T, haralicks])
scores = cross_validation.cross_val_score(LogisticRegression(),
haralick_plus_sobel,
labels,
cv=5).mean()
print(
'Accuracy (5 fold x-val) with Logistic Regrssion [std features + sobel]: {}%'
.format(0.1 * round(1000 * scores.mean())))
y_test = []
accuracy_meta_train = []
for temp in range(2708):
y.append(LABEL[labels[temp]])
y = np.array(y)
class_label = [0, 1, 2, 3, 4, 5, 6]
combination = list(combinations(class_label, 2))
for i in range(len(combination)):
print('Cross_Validation: ', i + 1)
test_label = list(combination[i])
train_label = [n for n in class_label if n not in test_label]
print('Cross_Validation {} Train_Label_List {}: '.format(
i + 1, train_label))
print('Cross_Validation {} Test_Label_List {}: '.format(i + 1, test_label))
classifier = LogisticRegression()
for j in range(50):
labels_local = labels.copy()
select_class = random.sample(train_label, 2)
print('Cross_Validation {} ITERATION {} Train_Label: {}'.format(
i + 1, j + 1, select_class))
class1_idx = []
class2_idx = []
for k in range(2708):
if (labels_local[k] == LABEL2[select_class[0]]):
class1_idx.append(k)
labels_local[k] = LABEL2[select_class[0]]
elif (labels_local[k] == LABEL2[select_class[1]]):
class2_idx.append(k)
labels_local[k] = LABEL2[select_class[1]]
from sklearn.datasets.samples_generator import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.linear_model.logistic import LogisticRegression
from sklearn import metrics
if __name__ == '__main__':
# X为样本特征, y为样本类别输出
X, y = make_classification(n_samples=80000)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
X_train, X_train_lr, y_train, y_train_lr = train_test_split(X_train,
y_train,
test_size=0.5)
grd = GradientBoostingClassifier(n_estimators=10)
grd_enc = OneHotEncoder()
grd_lm = LogisticRegression()
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
'''
使用训练好的GBDT模型构建特征，然后将特征经过one-hot编码作为新的特征输入到LR模型训练。
'''
grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
# 用训练好的LR模型多X_test做预测
y_pred_grd_lm = grd_lm.predict_proba(
grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
# 根据预测结果输出
fpr_grd_lm, tpr_grd_lm, _ = metrics.roc_curve(y_test, y_pred_grd_lm)
print(grd.apply(X_train)[:, :, :].shape)
def classify(train_data, train_label):
train_label = train_label.ravel() #将多维数据降成一维
# LSTM_AC, LSTM_f1 = Lstm_models()
# GRU_AC, GRU_f1 = GRU_models()
NLSTM_AC, NLSTM_f1 = Nestlstm_models()
lgbmModel = LGBMClassifier(max_depth=5,
num_leaves=25,
learning_rate=0.007,
n_estimators=1000,
min_child_samples=80,
subsample=0.8,
colsample_bytree=1,
reg_alpha=0,
reg_lambda=0,
random_state=np.random.randint(10e6))
lgbmModel.fit(train_data, train_label)
lgbm_pre = lgbmModel.predict(test_data)
lgbm_AC = accuracy_score(test_label, lgbm_pre)
lgbm_f1 = f1_score(test_label, lgbm_pre, average='macro')
AdaBoostModel = AdaBoostClassifier(base_estimator=None,
n_estimators=50,
learning_rate=1,
algorithm='SAMME.R',
random_state=None)
AdaBoostModel.fit(train_data, train_label)
AdaBoost_pre = AdaBoostModel.predict(test_data)
AdaBoost_AC = accuracy_score(test_label, AdaBoost_pre)
AdaBoost_f1 = f1_score(test_label, AdaBoost_pre, average='macro')
rfc1 = RandomForestClassifier(n_estimators=40,
max_depth=None,
min_samples_split=2,
random_state=2) #随机森林分类器
rfc1.fit(train_data, train_label)
RF_pre = rfc1.predict(test_data)
RF_AC = accuracy_score(test_label, RF_pre)
RF_f1 = f1_score(test_label, RF_pre, average='macro')
clf = SVC(kernel='rbf', C=9, gamma=0.1)
clf.set_params(kernel='rbf',
probability=True).fit(train_data,
train_label) #set_params：设置SVC函数的参数
clf.predict(train_data)
test_pre = clf.predict(test_data)
SVM_AC = accuracy_score(test_label, test_pre)
SVM_f1 = f1_score(test_label, test_pre, average='macro')
# decision tree
dtc = DecisionTreeClassifier()
dtc.fit(train_data, train_label)
dt_pre = dtc.predict(test_data)
DT_AC = accuracy_score(test_label, dt_pre)
DT_f1 = f1_score(test_label, dt_pre, average='macro')
MLP = MLPClassifier(solver='lbfgs',
alpha=1e-4,
hidden_layer_sizes=(100, 3),
random_state=1)
MLP.fit(train_data, train_label)
MLP_predict = MLP.predict(test_data)
MLP_AC = accuracy_score(test_label, MLP_predict)
MLP_f1 = f1_score(test_label, MLP_predict, average='macro')
# KNN
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(train_data, train_label)
knn_predict = knn.predict(test_data)
KNN_AC = accuracy_score(test_label, knn_predict)
KNN_f1 = f1_score(test_label, knn_predict, average='macro')
# LogisticRegression
classifier = LogisticRegression()
classifier.fit(train_data, train_label)
lg_predict = classifier.predict(test_data)
LG_AC = accuracy_score(test_label, lg_predict)
LG_f1 = f1_score(test_label, lg_predict, average='macro')
#
# print("===== Diagnosis original=======")
# print('Original Accuracy:')
# print(RF_AC, SVM_AC, DT_AC, NB_AC, MLP_AC, KNN_AC, LG_AC)
# print('F1-score')
# print(RF_f1, SVM_f1, DT_f1, NB_f1, MLP_f1, KNN_f1, LG_f1)
# Main.py按照original.py, Ensemble.py, vae_od.py顺序执行，结果依次存入下面文件
# file_name1 = "./temp_result/Diagnosis_"+str(select_number)+"Level"+str(level_num)+"_Accuracy_result.txt"
# file_name2 = "./temp_result/Diagnosis_"+str(select_number)+"Level"+str(level_num)+"_f1_score_result.txt"
# with open(file_name1, "a") as f:
# f.writelines([str(RF_AC), ' ', str(SVM_AC), ' ', str(DT_AC), ' ', str(NB_AC), ' ', str(MLP_AC), ' ', str(KNN_AC), ' ', str(LG_AC), '\n'])
# with open(file_name2, "a") as f:
# f.writelines([str(RF_f1), ' ', str(SVM_f1), ' ', str(DT_f1), ' ', str(NB_f1), ' ', str(MLP_f1), ' ', str(KNN_f1), ' ', str(LG_f1), '\n'])
# return NLSTM_AC,LSTM_AC ,GRU_AC,lgbm_AC,AdaBoost_AC,RF_AC, SVM_AC, DT_AC, MLP_AC, KNN_AC, LG_AC,NLSTM_f1,LSTM_f1,GRU_f1,lgbm_f1,AdaBoost_f1,RF_f1,SVM_f1,DT_f1,MLP_f1,KNN_f1,LG_f1
return NLSTM_AC, lgbm_AC, AdaBoost_AC, RF_AC, SVM_AC, DT_AC, MLP_AC, KNN_AC, LG_AC, NLSTM_f1, lgbm_f1, AdaBoost_f1, RF_f1, SVM_f1, DT_f1, MLP_f1, KNN_f1, LG_f1
def initialize_with_logistic_regression(self, zs, xs, initialize=False):
from sklearn.linear_model.logistic import LogisticRegression
if not hasattr(self, '_lr'):
self._lr = LogisticRegression(verbose=False,
multi_class="multinomial",
solver="lbfgs",
warm_start=True,
max_iter=10)
lr = self._lr
# Make the covariates
K, D = self.num_states, self.covariate_dim
# Split zs into prevs and nexts
zps = zs[:-1] if isinstance(zs, np.ndarray) else np.concatenate(
[z[:-1] for z in zs], axis=0)
zns = zs[1:] if isinstance(zs, np.ndarray) else np.concatenate(
[z[1:] for z in zs], axis=0)
xps = xs[:-1] if isinstance(xs, np.ndarray) else np.concatenate(
[x[:-1] for x in xs], axis=0)
assert zps.shape[0] == xps.shape[0]
assert zps.ndim == 1 and zps.dtype == np.int32 and zps.min(
) >= 0 and zps.max() < K
assert zns.ndim == 1 and zns.dtype == np.int32 and zns.min(
) >= 0 and zns.max() < K
assert xps.ndim == 2 and xps.shape[1] == D
used = np.bincount(zns, minlength=K) > 0
K_used = np.sum(used)
lr_X = np.column_stack((one_hot(zps, K), xps))
lr_y = zns
# The logistic regression solver fails if we only have one class represented
# In this case, set the regression weights to zero and set logpi to have
# high probability of the visited class
if K_used == 1:
self.W = np.zeros((D, K))
self.log_pi = np.zeros((K, K))
self.log_pi[:, used] = 3.0
else:
lr.fit(lr_X, lr_y)
# Now convert the logistic regression into weights
if K_used > 2:
self.W = np.zeros((D, K))
self.W[:, used] = lr.coef_[:, K:].T
self.logpi = np.zeros((K, K))
self.logpi[:, used] = lr.coef_[:, :K].T
self.logpi[:, used] += lr.intercept_[None, :]
self.logpi[:, ~used] += -100.
elif K_used == 2:
# LogisticRegression object only represents one
# set of weights for binary problems
self.W = np.zeros((D, K))
self.W[:, 1] = lr.coef_[0, K:]
self.logpi = np.zeros((K, K))
self.logpi[:, 1] = lr.coef_[0, :K].T
self.logpi[:, 1] += lr.intercept_
def test_logistic_regression_solvers_multiclass():
X, y = make_classification(n_samples=20,
n_features=20,
n_informative=10,
n_classes=3,
random_state=0)
tol = 1e-6
ncg = LogisticRegression(solver='newton-cg', fit_intercept=False, tol=tol)
lbf = LogisticRegression(solver='lbfgs', fit_intercept=False, tol=tol)
lib = LogisticRegression(fit_intercept=False, tol=tol)
sag = LogisticRegression(solver='sag',
fit_intercept=False,
tol=tol,
max_iter=1000,
random_state=42)
ncg.fit(X, y)
lbf.fit(X, y)
sag.fit(X, y)
lib.fit(X, y)
assert_array_almost_equal(ncg.coef_, lib.coef_, decimal=4)
assert_array_almost_equal(lib.coef_, lbf.coef_, decimal=4)
assert_array_almost_equal(ncg.coef_, lbf.coef_, decimal=4)
assert_array_almost_equal(sag.coef_, lib.coef_, decimal=4)
assert_array_almost_equal(sag.coef_, ncg.coef_, decimal=4)
assert_array_almost_equal(sag.coef_, lbf.coef_, decimal=4)
def test_logistic_regression_solvers():
X, y = make_classification(n_features=10, n_informative=5, random_state=0)
ncg = LogisticRegression(solver='newton-cg', fit_intercept=False)
lbf = LogisticRegression(solver='lbfgs', fit_intercept=False)
lib = LogisticRegression(fit_intercept=False)
sag = LogisticRegression(solver='sag',
fit_intercept=False,
random_state=42)
ncg.fit(X, y)
lbf.fit(X, y)
sag.fit(X, y)
lib.fit(X, y)
assert_array_almost_equal(ncg.coef_, lib.coef_, decimal=3)
assert_array_almost_equal(lib.coef_, lbf.coef_, decimal=3)
assert_array_almost_equal(ncg.coef_, lbf.coef_, decimal=3)
assert_array_almost_equal(sag.coef_, lib.coef_, decimal=3)
assert_array_almost_equal(sag.coef_, ncg.coef_, decimal=3)
assert_array_almost_equal(sag.coef_, lbf.coef_, decimal=3)
# TAKE THE TRAINSET AND THE TARGET FROM DATASET
trainset=get_trainset(dataset)
targets=get_target_dataset(dataset)
# DELETING THE STATISTICS OF THE USERS CONTENTS
trainset_without_stats=drop_stats(trainset)
# STANDARDIZE DATASET
trainset_without_stats=StandardScale_dataset(trainset_without_stats)
# TRAINING WITHOUT STATISTICS OF THE USERS CONTENTS
x_train, x_test, y_train, y_test = train_test_split(trainset_without_stats, targets, test_size = 0.2, random_state = 12345)
lr = LogisticRegression(solver='lbfgs')
lr.fit(x_train, y_train)
predictions = lr.predict(x_test)
print("\nPERFORMANCE WITHOUT THE STATISTICS OF THE USERS CONTENTS: ")
print("\nCONFUSION MATRIX:")
print(confusion_matrix(y_test, predictions))
print("\nCLASSIFICATION REPORT:")
print(classification_report(y_test, predictions))
# CLASSIFICATION OF ONLY PUBLIC PROFILES
dataset_publics=drop_NaN_entries(dataset)
trainset_publics=get_trainset(dataset_publics)
targets_publics=get_target_dataset(dataset_publics)
for i in range(50): #set range to contain number of csv files
new = pd.read_csv(path + file + str(i + 1) + ".csv")
raw = pd.concat([raw, new])
raw = raw[['content', 'troll']]
#these can be played with, currently set to ignore words in more than half or less than 100
vectorizer = TfidfVectorizer(min_df=100, max_df=0.5)
c = vectorizer.fit_transform(raw['content'])
dictionary = vectorizer.get_feature_names()
return c, raw['troll'], dictionary
X, y, dictionary = load_data("tweet_data_batch")
X_train, X_test, y_train, y_test = train_test_split(X, y, shuffle=True)
model1 = LogisticRegression(
max_iter=400, n_jobs=-1
) #increased arbitariy to 400 since default iterations reach limit
'''
scores_clf_svc_cv1 = cross_val_score(model1,X,y,cv=5)
print("LogReg Accuracy: %0.2f (+/- %0.2f)" % (scores_clf_svc_cv1.mean(), scores_clf_svc_cv1.std() * 2)) # print accuracy
'''
model1.fit(X_train, y_train)
print("LogReg Accuracy:\n", model1.score(X_test, y_test))
predic1 = model1.predict(X_test)
print("LogReg matrix:", metrics.confusion_matrix(y_test, predic1))
model2 = Perceptron()
'''
scores_clf_svc_cv2 = cross_val_score(model2,X,y,cv=5)
print("Perceptron Accuracy: %0.2f (+/- %0.2f)" % (scores_clf_svc_cv2.mean(), scores_clf_svc_cv2.std() * 2)) # print accuracy
'''
def tokenize_porter(text):
return [porter.stem(word) for word in text.split()]
stop = stopwords.words("english")
vectorizer = TfidfVectorizer(stop_words="english", ngram_range=(1, 1))
X = vectorizer.fit_transform(movie["review"])
print(vectorizer.get_feature_names)
#print(vectorizer.get_feature_names())
train_x, test_x, train_y, test_y = train_test_split(X,
movie["sentiment"],
test_size=0.2,
random_state=42)
print(train_x.shape, train_y.shape)
clf = LogisticRegression()
clf.fit(train_x, train_y)
#predict result
print(clf.predict(test_x))
#crossval score
scores = cross_val_score(clf, test_x, test_y, cv=5)
acc = scores.mean()
print("Accuracy: %0.2f percent" % (acc * 100))
def test_nan():
# Test proper NaN handling.
# Regression test for Issue #252: fit used to go into an infinite loop.
Xnan = np.array(X, dtype=np.float64)
Xnan[0, 1] = np.nan
LogisticRegression(random_state=0).fit(Xnan, Y1)
#对测试集进行预测 from sklearn.model_selection import train_test_split x_data=data[:,:-1] y_data=data[:,-1] prediction_list=[] for i in range(5): x_train, x_val, y_train, y_val = train_test_split(data[:,:-1], data[:,-1], test_size=0.2) x_train_new,x_test_new =PCA_Reduction(x_train,x_test) print(x_test_new.shape) clf = SVC(kernel='linear',verbose=1) clf.fit(x_train_new, y_train) y_predition_test=clf.predict(x_test_new) prediction_list.append(y_predition_test) classifier=LogisticRegression() classifier.fit(x_train_new,y_train) y_predict=classifier.predict(x_test_new) prediction_list.append(y_predict) dtree=RandomForestClassifier(criterion='gini',max_depth=120,min_impurity_decrease=0) dtree.fit(x_train_new,y_train) pred=dtree.predict(x_test_new) prediction_list.append(pred) print(prediction_list) prediction_result=np.array(prediction_list).T print(prediction_result.shape) test_result=[] for x in prediction_result:
def test_logreg_intercept_scaling_zero():
# Test that intercept_scaling is ignored when fit_intercept is False
clf = LogisticRegression(fit_intercept=False)
clf.fit(X, Y1)
assert_equal(clf.intercept_, 0.)
def test_logreg_predict_proba_multinomial():
X, y = make_classification(n_samples=10, n_features=20, random_state=0,
n_classes=3, n_informative=10)
# Predicted probabilities using the true-entropy loss should give a
# smaller loss than those using the ovr method.
clf_multi = LogisticRegression(multi_class="multinomial", solver="lbfgs")
clf_multi.fit(X, y)
clf_multi_loss = log_loss(y, clf_multi.predict_proba(X))
clf_ovr = LogisticRegression(multi_class="ovr", solver="lbfgs")
clf_ovr.fit(X, y)
clf_ovr_loss = log_loss(y, clf_ovr.predict_proba(X))
assert_greater(clf_ovr_loss, clf_multi_loss)
# Predicted probabilities using the soft-max function should give a
# smaller loss than those using the logistic function.
clf_multi_loss = log_loss(y, clf_multi.predict_proba(X))
clf_wrong_loss = log_loss(y, clf_multi._predict_proba_lr(X))
assert_greater(clf_wrong_loss, clf_multi_loss)
predict_me = np.array(X[i].astype(float))
predict_me = predict_me.reshape(-1, len(predict_me))
prediction = clf.predict(predict_me)
if prediction == y[i]:
correct += 1
print (float(correct)/float(len(X)))
'''
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn import decomposition
from sklearn.pipeline import Pipeline
logistic = LogisticRegression()
pca = decomposition.PCA()
pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])
X = np.array(df.drop('survived', 1))
X = preprocessing.scale(X)
print X.shape
y = np.array(df['survived'])
print y.shape
clf = pca.fit_transform(X, y)
plt.figure(1, figsize=(5, 5))
plt.clf()
plt.axes([.2, .2, .7, .7])
plt.plot(pca.explained_variance_, linewidth=2)
plt.axis('tight')
plt.xlabel('n_components')
def crossval(features, labels, vec):
maxent = LogisticRegression(penalty='l1')
#maxent = SGDClassifier(penalty='l1')
#maxent = Perceptron(penalty='l1')
maxent.fit(
features, labels
) # only needed for feature inspection, crossvalidation calls fit(), too
coeffcounter = Counter(vec.feature_names_)
negfeats = set(vec.feature_names_)
posfeats = set(vec.feature_names_)
scores = defaultdict(list)
TotalCoeffCounter = Counter()
for TrainIndices, TestIndices in cross_validation.KFold(
n=features.shape[0], n_folds=10, shuffle=False, random_state=None):
TrainX_i = features[TrainIndices]
Trainy_i = labels[TrainIndices]
TestX_i = features[TestIndices]
Testy_i = labels[TestIndices]
maxent.fit(TrainX_i, Trainy_i)
ypred_i = maxent.predict(TestX_i)
coeffs_i = list(maxent.coef_[0])
coeffcounter_i = Counter(vec.feature_names_)
for value, name in zip(coeffs_i, vec.feature_names_):
coeffcounter_i[name] = value
acc = accuracy_score(ypred_i, Testy_i)
pre = precision_score(ypred_i, Testy_i)
rec = recall_score(ypred_i, Testy_i)
# shared task uses f1 of *accuracy* and recall!
f1 = 2 * acc * rec / (acc + rec)
scores["Accuracy"].append(acc)
scores["F1"].append(f1)
scores["Precision"].append(pre)
scores["Recall"].append(rec)
posfeats = posfeats.intersection(
set([key for (key, value) in coeffcounter.most_common()[:20]]))
negfeats = negfeats.intersection(
set([key for (key, value) in coeffcounter.most_common()[-20:]]))
print("Pervasive positive: ", posfeats)
print("Pervasive negative: ", negfeats)
#scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
print("--")
for key in sorted(scores.keys()):
currentmetric = np.array(scores[key])
print("%s : %0.2f (+/- %0.2f)" %
(key, currentmetric.mean(), currentmetric.std()))
print("--")
maxent.fit(features, labels) # fit on everything
coeffs_total = list(maxent.coef_[0])
for value, name in zip(coeffs_total, vec.feature_names_):
TotalCoeffCounter[name] = value
for (key, value) in TotalCoeffCounter.most_common()[:20]:
print(key, value)
print("---")
for (key, value) in TotalCoeffCounter.most_common()[-20:]:
print(key, value)
print("lowest coeff:", coeffcounter.most_common()[-1])
print("highest coeff", coeffcounter.most_common()[0])
clf = SVC() clf.fit(X_train, y_train) print "使用支持向量分类算法分类结果：" print clf.score(X_test, y_test) #支持向量分类 #nusvm clf = NuSVC() clf.fit(X_train, y_train) print "使用支持向量分类算法分类结果：" print clf.score(X_test, y_test) #核支持向量分类 clf = GaussianNB() clf.fit(X_train, y_train) print "使用朴素贝叶斯分类算法分类结果：" print clf.score(X_test, y_test) #朴素贝叶斯分类 classifier = LogisticRegression() classifier.fit(X_train, y_train) print "使用逻辑回归算法分类结果：" print classifier.score(X_test, y_test) #逻辑回归 classifier = tree.DecisionTreeClassifier() classifier.fit(X_train, y_train) print "使用决策树算法分类结果：" print classifier.score(X_test, y_test) classifier = GradientBoostingClassifier(n_estimators=200) classifier.fit(X_train, y_train) print "使用GBDT算法分类结果：" print classifier.score(X_test, y_test)
# +
# calculate train/test data number
N = len(digits)
N_train = int(N*0.8)
N_test = N - N_train
# split train/test data
x_train = digits[:N_train, :]
y_train = dig_label[:N_train]
x_test = digits[N_train:, :]
y_test = dig_label[N_train:]
# do logistic regression
lr=LogisticRegression()
lr.fit(x_train,y_train)
pred_train = lr.predict(x_train)
pred_test = lr.predict(x_test)
# calculate train/test accuracy
acc_train = accuracy_score(y_train, pred_train)
acc_test = accuracy_score(y_test, pred_test)
print("accuracy train = %f, accuracy_test = %f" % (acc_train, acc_test))
# +
# do PCA with 'n_components=40'
pca = decomposition.PCA(n_components=40)
pca.fit(x_train)
def test_predict_3_classes():
check_predictions(LogisticRegression(C=10), X, Y2)
check_predictions(LogisticRegression(C=10), X_sp, Y2)
for k in range(5):
train_texts = np.concatenate((texts[:i], texts[i + 200:]), axis=0)
train_labels = np.concatenate((labels[:i], labels[i + 200:]), axis=0)
test_texts = texts[i:i + 200]
test_labels = labels[i:i + 200]
# 贝叶斯
text_clf = Pipeline([('tfidf', TfidfVectorizer(max_features=2000)),
('clf', MultinomialNB())])
text_clf = text_clf.fit(train_texts, train_labels)
predicted = text_clf.predict(test_texts)
t1 += np.mean(predicted == test_labels)
print("MultinomialNB准确率为：", np.mean(predicted == test_labels))
# LogisticRegression
text_clf = Pipeline([('tfidf', TfidfVectorizer(max_features=2000)),
('clf', LogisticRegression())])
text_clf = text_clf.fit(train_texts, train_labels)
predicted = text_clf.predict(test_texts)
t2 += np.mean(predicted == test_labels)
print("LogisticRegression准确率为：", np.mean(predicted == test_labels))
# SVM
text_clf = Pipeline([('tfidf', TfidfVectorizer(max_features=2000)),
('clf', NuSVC())])
text_clf = text_clf.fit(train_texts, train_labels)
predicted = text_clf.predict(test_texts)
t3 += np.mean(predicted == test_labels)
print("SVC准确率为：", np.mean(predicted == test_labels))
text_clf = Pipeline([('tfidf', TfidfVectorizer(max_features=2000)),
('clf', LinearSVC())])
def test_n_iter():
# Test that self.n_iter_ has the correct format.
X, y = iris.data, iris.target
y_bin = y.copy()
y_bin[y_bin == 2] = 0
n_Cs = 4
n_cv_fold = 2
for solver in ['newton-cg', 'liblinear', 'sag', 'saga', 'lbfgs']:
# OvR case
n_classes = 1 if solver == 'liblinear' else np.unique(y).shape[0]
clf = LogisticRegression(tol=1e-2, multi_class='ovr',
solver=solver, C=1.,
random_state=42, max_iter=100)
clf.fit(X, y)
assert_equal(clf.n_iter_.shape, (n_classes,))
n_classes = np.unique(y).shape[0]
clf = LogisticRegressionCV(tol=1e-2, multi_class='ovr',
solver=solver, Cs=n_Cs, cv=n_cv_fold,
random_state=42, max_iter=100)
clf.fit(X, y)
assert_equal(clf.n_iter_.shape, (n_classes, n_cv_fold, n_Cs))
clf.fit(X, y_bin)
assert_equal(clf.n_iter_.shape, (1, n_cv_fold, n_Cs))
# multinomial case
n_classes = 1
if solver in ('liblinear', 'sag', 'saga'):
break
clf = LogisticRegression(tol=1e-2, multi_class='multinomial',
solver=solver, C=1.,
random_state=42, max_iter=100)
clf.fit(X, y)
assert_equal(clf.n_iter_.shape, (n_classes,))
clf = LogisticRegressionCV(tol=1e-2, multi_class='multinomial',
solver=solver, Cs=n_Cs, cv=n_cv_fold,
random_state=42, max_iter=100)
clf.fit(X, y)
assert_equal(clf.n_iter_.shape, (n_classes, n_cv_fold, n_Cs))
clf.fit(X, y_bin)
assert_equal(clf.n_iter_.shape, (1, n_cv_fold, n_Cs))
def getPipeline():
return Pipeline([('vect',
TfidfVectorizer(stop_words='english',
sublinear_tf=True)),
('clf', LogisticRegression())])
