def test(clf):
global labels, pres, recall, f1score
y_pred = clf.predict(docs_test)
p, r, f1, s = precision_recall_fscore_support(y_test, y_pred)
labels.append(str(clf))
res[0].append(np.mean(p))
res[1].append(np.mean(r))
res[2].append(np.mean(f1))
res[3].append(np.mean(y_pred == y_test))
conf_arr = stat.confusion_matrix(y_test, y_pred)
norm_conf = []
for i in conf_arr:
a = 0
tmp_arr = []
a = sum(i,0)
for j in i:
tmp_arr.append(float(j)/float(a))
norm_conf.append(tmp_arr)
return conf_arr, norm_conf
def test(clf):
global labels, res
y_pred = clf.predict(docs_test)
p, r, f1, s = precision_recall_fscore_support(y_test, y_pred)
labels.append(str(clf))
res[0].append(np.mean(p))
res[1].append(np.mean(r))
res[2].append(np.mean(f1))
res[3].append(np.mean(y_pred == y_test))
conf_arr = stat.confusion_matrix(y_test, y_pred)
norm_conf = []
for z in conf_arr:
a = sum(z, 0)
norm_conf.append([float(k)/float(a) for k in z])
plt.clf()
fig = plt.figure()
ax = fig.add_subplot(111)
plt.title('Confusion Matrix for %s' % str(clf))
ares = ax.imshow(array(norm_conf), cmap=cm.jet, interpolation='nearest', vmin=0, vmax=1.0)
for i, cas in enumerate(conf_arr):
for j, c in enumerate(cas):
if c>0:
plt.text(j-.2, i+.2, c, fontsize=14)
cb = fig.colorbar(ares)
savefig("plots/gridsearch/confusion_matrix_%s.png" % str(clf), format="png")
def test(clf):
global labels, pres, recall, f1score
y_pred = clf.predict(docs_test)
p, r, f1, s = precision_recall_fscore_support(y_test, y_pred)
labels.append(str(clf))
res[0].append(np.mean(p))
res[1].append(np.mean(r))
res[2].append(np.mean(f1))
res[3].append(np.mean(y_pred == y_test))
conf_arr = stat.confusion_matrix(y_test, y_pred)
norm_conf = []
for i in conf_arr:
a = 0
tmp_arr = []
a = sum(i, 0)
for j in i:
tmp_arr.append(float(j) / float(a))
norm_conf.append(tmp_arr)
return conf_arr, norm_conf
def test(clf):
global labels, res
y_pred = clf.predict(docs_test)
p, r, f1, s = precision_recall_fscore_support(y_test, y_pred)
labels.append(str(clf))
res[0].append(np.mean(p))
res[1].append(np.mean(r))
res[2].append(np.mean(f1))
res[3].append(np.mean(y_pred == y_test))
conf_arr = stat.confusion_matrix(y_test, y_pred)
norm_conf = []
for z in conf_arr:
a = sum(z, 0)
norm_conf.append([float(k) / float(a) for k in z])
plt.clf()
fig = plt.figure()
ax = fig.add_subplot(111)
plt.title('Confusion Matrix for %s' % str(clf))
ares = ax.imshow(array(norm_conf),
cmap=cm.jet,
interpolation='nearest',
vmin=0,
vmax=1.0)
for i, cas in enumerate(conf_arr):
for j, c in enumerate(cas):
if c > 0:
plt.text(j - .2, i + .2, c, fontsize=14)
cb = fig.colorbar(ares)
savefig("plots/gridsearch/confusion_matrix_%s.png" % str(clf),
format="png")
vect_options = {
'ngram_range': (1,1),
'sublinear_tf': True,
'preprocessor': pr.remove_noise,
'use_idf': False,
'stop_words': None
}
default_options = {
'C': 1.0
}
clf = SVM(docs_train, y_train, default_options=default_options, vect_options=vect_options)
y_predicted = clf.predict(docs_test)
conf_arr = s.confusion_matrix(y_test, y_predicted)
norm_conf = []
for i in conf_arr:
a = 0
tmp_arr = []
a = sum(i,0)
for j in i:
tmp_arr.append(float(j)/float(a))
norm_conf.append(tmp_arr)
plt.clf()
fig = plt.figure()
ax = fig.add_subplot(111)
res = ax.imshow(array(norm_conf), cmap=cm.jet, interpolation='nearest')
for i, cas in enumerate(conf_arr):
