def search(clf, params_list):
results = []
for params in params_list:
sc = SentimentClassifier(clf=clf)
ev = Evaluator()
sc._pipeline.set_params(**params)
sc.fit(X_train, y_train)
y_pred = sc.predict(X_dev)
ev.evaluate(y_dev, y_pred)
results.append({'acc': ev.accuracy(), 'f1': ev.macro_f1(), **params})
results_df = pd.DataFrame(results)
print(results_df.sort_values(['acc', 'f1'], ascending=False))
X, y = X1 + X2, y1 + y2
# load development corpus (for evaluation)
reader = InterTASSReader('TASS/InterTASS/TASS2017_T1_development.xml')
Xdev, y_true = list(reader.X()), list(reader.y())
# create model and evaluator instances
# train model
model_type = opts['-m']
if model_type == 'clf':
model = models[model_type](clf=opts['-c'])
else:
model = models[model_type]() # baseline
evaluator = Evaluator()
N = len(X)
for i in reversed(range(8)):
n = int(N / 2**i)
this_X = X[:n]
this_y = y[:n]
# train, test and evaluate
model.fit(this_X, this_y)
y_pred = model.predict(Xdev)
evaluator.evaluate(y_true, y_pred)
# print this data point:
acc = evaluator.accuracy()
f1 = evaluator.macro_f1()
print('n={}, acc={:2.2f}, f1={:2.2f}'.format(n, acc, f1))