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)
#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))
