def test_decision_function(self, data):
classes = np.array([-1., 1.])
raw_model = VW(loss_function='logistic')
raw_model.fit(data.x, data.y)
predictions = raw_model.predict(data.x)
class_indices = (predictions > 0).astype(np.int)
class_predictions = classes[class_indices]
model = VWClassifier()
model.fit(data.x, data.y)
assert np.allclose(class_predictions, model.predict(data.x))
def test_decision_function(self, data):
classes = np.array([-1., 1.])
raw_model = VW(loss_function='logistic')
raw_model.fit(data.x, data.y)
predictions = raw_model.predict(data.x)
class_indices = (predictions > 0).astype(np.int)
class_predictions = classes[class_indices]
model = VWClassifier()
model.fit(data.x, data.y)
assert np.allclose(class_predictions, model.predict(data.x))
def sanitycheck(self):
X, y = datasets.make_hastie_10_2(n_samples=1000, random_state=1)
X = X.astype(numpy.float32)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=256)
model = VWClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
score_train = model.score(X_train, y_train)
scoer_test = model.score(X_test, y_test)
return
# ----------------------------------------------------------------------------------------------------------------------
from vowpalwabbit.sklearn_vw import VWClassifier X = [[1, 2], [3, 4], [5, 6], [7, 8]] y = [-1, -1, 1, 1] model = VWClassifier(loss_function='logistic', l=0.01, l2=0.1) model.fit(X, y) print(model.predict(X)) print(model.score(X, y))
text_filename = os.listdir('D:/cadec/text')[i]
Ori_filename = os.listdir('D:/cadec/Ori')[i]
objects.append(
document('D:/cadec/text/' + text_filename,
'D:/cadec/Ori/' + Ori_filename, dic))
print(i)
sel = (len(objects))
x, y, l = transform(objects[:sel], dic)
train_cut = int(0.75 * (len(objects)))
test_cut = (len(objects))
x_train, y_train, l_train = transform(objects[:train_cut], dic)
x_test, y_test, l_test = transform(objects[train_cut:test_cut], dic)
x, y = clean(x, y)
x_train, y_train = clean(x_train, y_train)
x_test, y_test = clean(x_test, y_test)
print(x_test)
print(y_test)
print("completed")
vecx = DictVectorizer(sparse=True)
vecy = DictVectorizer(sparse=False)
train_len = (x_train)
test_len = (x_test)
clf = VWClassifier()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
print(len(y_pred))
print((y_pred))
print((y_test))
recall_str = classification_report(y_test, y_pred)
print(recall_str)
# from vowpalwabbit import pyvw
#
# vw = pyvw.vw(quiet=True)
# ex = vw.example('1 | a b c')
# vw.learn(ex)
# vw.predict(ex)
import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from vowpalwabbit.pyvw import vw
from vowpalwabbit.sklearn_vw import VWClassifier
# generate some data
X, y = datasets.make_hastie_10_2(n_samples=10000, random_state=1)
X = X.astype(np.float32)
# split train and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=256)
# build model
model = VWClassifier()
model.fit(X_train, y_train)
# predict model
y_pred = model.predict(X_test)
print(y_pred)
# evaluate model
model.score(X_train, y_train)
model.score(X_test, y_test)
