def linear_reg(algo={},tmp={},testset={},X=None,Y=None):
Xtrain, Ytrain, Xtest, Ytest = getSample(X=X, Y=Y,ratio=0.6)
#lm.LinearRegression
print "linear_reg"
reg = lm.Ridge(alpha=0.25)
#reg=lm.Lasso(alpha=0.0005)
pred=reg.fit(Xtrain, Ytrain).predict(Xtest)
#print algo.keys()
#print reg.coef_
#print reg.intercept_
RMSE2(pred=pred, test=Ytest)
MAE(pred=pred, test=Ytest)
ClassifyError(pred=pred, test=Ytest)
print "LogisticRegression"
logreg=lm.LogisticRegression(penalty="l2",C=2);
pred=logreg.fit(Xtrain,Ytrain).predict(Xtest)
RMSE2(pred=pred, test=Ytest)
MAE(pred=pred, test=Ytest)
ClassifyError(pred=pred, test=Ytest)
def test_weight():
"""
Test class weights
"""
clf = svm.SVC()
# we give a small weights to class 1
clf.fit(X, Y, {1: 0.1})
# so all predicted values belong to class 2
assert_array_almost_equal(clf.predict(X), [2] * 6)
X_, y_ = test_dataset_classif(n_samples=200, n_features=100, param=[5, 1],
seed=0)
for clf in (linear_model.LogisticRegression(), svm.LinearSVC(), svm.SVC()):
clf.fit(X_[: 180], y_[: 180], class_weight={0: 5})
y_pred = clf.predict(X_[180:])
assert np.sum(y_pred == y_[180:]) >= 11
iris = datasets.load_iris()
X = iris.data
y = iris.target
X = X[y != 2]
y = y[y != 2]
X -= np.mean(X, 0)
################################################################################
# Demo path functions
alphas = np.logspace(2, -4, 100)
print "Computing regularization path ..."
start = datetime.now()
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
coefs_ = [clf.fit(X, y, C=1.0/alpha).coef_.ravel().copy() for alpha in alphas]
print "This took ", datetime.now() - start
coefs_ = np.array(coefs_)
pl.plot(-np.log10(alphas), coefs_)
ymin, ymax = pl.ylim()
pl.xlabel('-log(alpha)')
pl.ylabel('Coefficients')
pl.title('Logistic Regression Path')
pl.axis('tight')
pl.show()
from scikits.learn import datasets, neighbors, linear_model
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:.9 * n_samples]
y_train = y_digits[:.9 * n_samples]
X_test = X_digits[.9 * n_samples:]
y_test = y_digits[.9 * n_samples:]
knn = neighbors.NeighborsClassifier()
logistic = linear_model.LogisticRegression()
print 'KNN score:', knn.fit(X_train, y_train).score(X_test, y_test)
print 'LogisticRegression score:', logistic.fit(X_train,
y_train).score(X_test, y_test)
from scikits.learn import linear_model
# this is our test set, it's just a straight line with some
# gaussian noise
xmin, xmax = -5, 5
n_samples = 100
np.random.seed(0)
X = np.random.normal(size=n_samples)
y = (X > 0).astype(np.float)
X[X > 0] *= 4
X += .3 * np.random.normal(size=n_samples)
X = X[:, np.newaxis]
# run the classifier
clf = linear_model.LogisticRegression(C=1e5)
clf.fit(X, y)
# and plot the result
pl.figure(1, figsize=(4, 3))
pl.clf()
pl.scatter(X.ravel(), y, color='black', zorder=20)
X_test = np.linspace(-5, 10, 300)
def model(x):
return 1 / (1 + np.exp(-x))
loss = model(X_test * clf.coef_ + clf.intercept_).ravel()
pl.plot(X_test, loss, color='blue', linewidth=3)
