def eval_model(df, sets, motifs, alpha, nsample=1000, k=10, cutoff=0):
ret = select_sets(df, sets)
y = pd.DataFrame({"label":0}, index=df.index)
for label, rows in enumerate(ret):
y.loc[rows] = label + 1
y = y[y["label"] > 0]
y -= 1
clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=len(sets) > 2,
max_iter=20,
alpha=alpha,
C=1.0 / motifs.shape[0],
tol=1e-3)
accs = []
fractions = []
for i in np.arange(k):
idx = np.random.choice(range(y.shape[0]), nsample, replace=True)
y_pred = y.iloc[idx[:nsample * 0.8 + 1]]
X_pred = motifs.loc[y_pred.index].values
y_pred = y_pred.values.flatten()
y_test = y.iloc[idx[nsample * 0.8 + 1:]]
X_test = motifs.loc[y_test.index].values
y_test = y_test.values.flatten()
# train the model
clf.fit(X_pred, y_pred)
acc = clf.score(X_test, y_test)
fraction = clf.n_nonzero(percentage=True)
accs.append(acc)
fractions.append(fraction)
#print alpha, accs, fractions
return alpha, np.median(accs), np.median(fractions)
def eval_model(df, sets, motifs, alpha, nsample=1000, k=10, cutoff=0):
ret = select_sets(df, sets)
y = pd.DataFrame({"label": 0}, index=df.index)
for label, rows in enumerate(ret):
y.loc[rows] = label + 1
y = y[y["label"] > 0]
y -= 1
clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=len(sets) > 2,
max_iter=20,
alpha=alpha,
C=1.0 / motifs.shape[0],
tol=1e-3)
accs = []
fractions = []
for i in np.arange(k):
idx = np.random.choice(range(y.shape[0]), nsample, replace=True)
y_pred = y.iloc[idx[:nsample * 0.8 + 1]]
X_pred = motifs.loc[y_pred.index].values
y_pred = y_pred.values.flatten()
y_test = y.iloc[idx[nsample * 0.8 + 1:]]
X_test = motifs.loc[y_test.index].values
y_test = y_test.values.flatten()
# train the model
clf.fit(X_pred, y_pred)
acc = clf.score(X_test, y_test)
fraction = clf.n_nonzero(percentage=True)
accs.append(acc)
fractions.append(fraction)
#print alpha, accs, fractions
return alpha, np.median(accs), np.median(fractions)
one_over_n = 1. / float(n_samples)
ds = ColumnData(X)
coefs_ = np.zeros((n_features, n_classes))
fit( ds, y, one_over_n, n_samples, n_features, n_classes,coefs_,groups)
s = score (X,y,coefs_)
print "score = ", s
print '======================================================'
clf_max_iter=300
clf_tol = 1e-3
print "### Equivalent Lightning Cython Implementation ###"
light_clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=True,
max_iter=clf_max_iter,
alpha=0.5, # clf.alpha,
C=1.0 / X.shape[0],
tol=clf_tol,
permute=False,
verbose=3,
random_state=0).fit(X, y)
print "Acc:", light_clf.score(X, y)
print light_clf.coef_.T
import time
import numpy as np
from sklearn.datasets import fetch_20newsgroups_vectorized
from lightning.classification import CDClassifier
bunch = fetch_20newsgroups_vectorized(subset="all")
X = bunch.data
y = bunch.target
y[y >= 1] = 1
Cs = np.logspace(-3, 3, 20)
for warm_start in (True, False):
clf = CDClassifier(loss="squared_hinge",
tol=1e-3,
max_iter=100,
warm_start=warm_start)
scores = []
start = time.time()
for C in Cs:
clf.C = C
clf.fit(X, y)
scores.append(clf.score(X, y))
print "Total time", time.time() - start
print "Average accuracy", np.mean(scores)
# build model
# cross validation
for C in [1, 0.1, 0.01, 0.001, 0.0001]:
# create and fit a ridge regression model, testing each alpha
clf = LogisticRegression(
C=C, penalty='l1', tol=0.001
) # Inverse of regularization strength; must be a positive float. Like in support vector machines, smaller values specify stronger regularization.
clf.fit(X_train, y_train)
# Percentage of selected features
num = len(clf.coef_[0].nonzero()[0])
p = len(clf.coef_[0].nonzero()[0]) * 1.0 / len(X_train.columns)
print '%s = 0, %s = 1' % tuple(clf.classes_)
print 'C: ', C
print 'Prediction accuracy: ', clf.score(X_test, y_test)
print 'Features left (# / %): ', num, '/', p
if C == 1:
writer.write('%s = 0, %s = 1 \n' % tuple(clf.classes_))
writer.write('C: %s \n' % C)
writer.write('Accuracy: %s \n' % clf.score(X_test, y_test))
writer.write('Features left (#/%%): %s / %s \n' % (num, p))
# selected features
if p < 0.5:
idx = clf.coef_[0].nonzero()
ws = clf.coef_[0][idx].round(3).astype(str)
fs = X_train.columns[idx]
tmp = fs + ' (' + ws + ')'
print 'Selected features: %s' % ', '.join(tmp)
import time
import numpy as np
from sklearn.datasets import fetch_20newsgroups_vectorized
from lightning.classification import CDClassifier
bunch = fetch_20newsgroups_vectorized(subset="all")
X = bunch.data
y = bunch.target
y[y >= 1] = 1
Cs = np.logspace(-3, 3, 20)
for warm_start in (True, False):
clf = CDClassifier(loss="squared_hinge", tol=1e-3, max_iter=100,
warm_start=warm_start)
scores = []
start = time.time()
for C in Cs:
clf.C = C
clf.fit(X, y)
scores.append(clf.score(X, y))
print "Total time", time.time() - start
print "Average accuracy", np.mean(scores)
#Source
#http://contrib.scikit-learn.org/lightning/
from sklearn.datasets import fetch_20newsgroups_vectorized
from lightning.classification import CDClassifier
# Load News20 dataset from scikit-learn.
bunch = fetch_20newsgroups_vectorized(subset="all")
X = bunch.data
y = bunch.target
# Set classifier options.
clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=True,
max_iter=20,
alpha=1e-4,
C=1.0 / X.shape[0],
tol=1e-3)
# Train the model.
clf.fit(X, y)
# Accuracy
print(clf.score(X, y))
# Percentage of selected features
print(clf.n_nonzero(percentage=True))
texts = [ " ".join(text) for text in texts]
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(texts)
y_train = labels
clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=True,
max_iter=15,
alpha=1e-4,
C=1.0 / X_train.shape[0],
tol=1e-6, verbose=5)
mmclf = mmclf.LatentGroupClassifier(max_iter=15, C=1.0 / X_train.shape[0])
start = time()
clf.fit(X_train, y_train)
elapsed = time() - start
print "CDClassifier time", elapsed
print "CDClassifier score", clf.score(X_train, y_train)
start = time()
mmclf.fit(X_train, y_train)
elapsed = time() - start
print "LatentGroupClassifier time", elapsed
print "LatentGroupClassifier score", mmclf.score(X_train, y_train)
print "CDClassifier weights\n", clf.coef_.T
print "LatentGroupClassifier weights\n", mmclf.coefs_.T
print "features", vectorizer.vocabulary_
top_words = 30
print "==== Keywords ==== "
for m in xrange(clf.coefs_.shape[1]):
t = []
print 'Topic',m
for row in xrange(clf.coefs_.shape[0]):
if( clf.coefs_[row,m] >0):
t.append( dict_text[row])
for k in heapq.nlargest(top_words,t):
print k,
print
print "==== Lightning Cython Implementation (Row-wise sparsity) ====="
light_clf = CDClassifier(penalty="l1/l2",
loss="squared_hinge",
multiclass=True,
max_iter=clf.max_iter,
alpha=1e-4, # clf.alpha,
C=1.0 / X.shape[0],
tol=clf.tol,
permute=False,
verbose=3,
random_state=0).fit(X, y)
print "==========>> Accuracy :", light_clf.score(X, y)
print "Weight Matrix:"
print (light_clf.coef_.T)
import time
import numpy as np
from sklearn.datasets import fetch_20newsgroups_vectorized
from lightning.classification import CDClassifier
# Load News20 dataset from scikit-learn.
bunch = fetch_20newsgroups_vectorized(subset="all")
X = bunch.data
y = bunch.target
y[y >= 1] = 1
for shrinking in (True, False):
clf = CDClassifier(C=1.0, loss="squared_hinge", penalty="l1", tol=1e-3,
max_iter=1000, shrinking=shrinking, random_state=0)
start = time.time()
clf.fit(X, y)
print "Training time", time.time() - start
print "Accuracy", clf.score(X, y)
