print("************* Learning Models Comparison ***************")
# Here I load temporary dummy data
iris = load_iris()
X = iris.data
y = iris.target
print("-----------------------------------------------")
print("Grid search of best C parameter for Linear SVM:\n")
C_range = np.logspace(-2, 10, 13)
# If we have used cross-validation, we could also choose the model
# with the max accuracy, min training time
scores_timed = []
for C in C_range:
model = LinearSVMClassifier(C=C)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=42)
train_data = TrainData(X_train, y_train.tolist())
t = time.time()
model.train(train_data)
t = time.time() - t
test_data = TrainData(X_test, y_test.tolist())
scores_timed.append([C, model.score(test_data), t])
scores_timed = np.array(scores_timed)
best_linear_C = scores_timed[np.argmax(scores_timed[:, 1])][0]
print("The best parameter is C=%.2f with a score of %.2f"
% (best_linear_C, scores_timed[np.argmax(scores_timed[:, 1])][1]))
X = []
Y = []
for w in data:
l = data[w]
if len(l) < 8:
continue
l.sort(key=lambda tup: tup[0])
for x in l[-50:]:
X.append(x[1])
Y.append(w)
X = np.asarray(X)
train_data = TrainData(X, Y)
print(X.shape)
# End of sanitize
# Export model
model = LinearSVMClassifier()
model.fit(train_data)
with open(filename_models, 'wb') as f:
pickle.dump(model, f)
for name, model in models:
t2 = time.time()
print("------------ %s -------------" % name)
m = model()
m.fit(train_data)
print("In", m.scores(train_data))
print("Cv", m.cross_validation_scores(train_data, 4))
print("ok (%f s)" % (time.time() - t2))
the wind direction for an observer facing toward the bar is
typically from the left and slightly behind the observer."""
words = np.array(word_tokenize(text))
ambiguous_data = feature_extractor.extract_features(np.array(words), "bar")
print("Shape of the matrix of features:", ambiguous_data.data.shape)
print("Done,", time.time() - t, "s")
print(ambiguous_data.data)
print(ambiguous_data.targets)
print(ambiguous_data.words)
# Learning model
print("************************* Learning model *************************")
print("-- SVM with Linear Kernel (default parameters")
t = time.time()
model = LinearSVMClassifier()
model.train(train_data)
labels = model.predict(ambiguous_data)
print(labels)
print("Done,", time.time() - t, "s\n\n")
print("-- SVM with RBF Kernel (default parameters")
t = time.time()
model = RbfSVMClassifier()
model.train(train_data)
labels = model.predict(ambiguous_data)
print(labels)
print("Done,", time.time() - t, "s\n\n")
print("-- Naive Bayes Classifier")
t = time.time()
