def cross_validation(k,
X,
y,
random_forest=False,
use_confidence=False,
num_of_trees=1):
accuracies = []
y_pred = []
y_true = []
predictors = get_predictors()
emotion_values = get_emotion_values()
X_splits = np.array_split(X, k)
y_splits = np.array_split(y, k)
for i in range(k):
X_train, X_test, y_train, y_test = get_train_test_split(
X_splits, y_splits, i)
emotion_predictor = EmotionPredictor(predictors, random_forest,
use_confidence, num_of_trees)
emotion_predictor.fit(emotion_values, X_train, y_train)
predictions = emotion_predictor.predict(X_test)
y_pred = y_pred + predictions
# print(y_test)
# print(y_true)
for elem in y_test:
y_true.append(elem)
# y_true = y_true + y_test
correct = sum([
1 for i, prediction in enumerate(predictions)
if prediction == y_test[i]
])
accuracy = float(correct * 100) / len(y_test)
accuracies.append(accuracy)
print("Accuracy for round {0} is {1:.2f}".format(i + 1, accuracy))
print(
"Cross Validation accuracy has a mean of {0:.2f} and a std of {1:.2f}".
format(np.mean(accuracies), np.std(accuracies)))
print(" prec, rec, f1")
for emotion_number in emotion_values:
print("Emotion {0}: {1:.2f}, {2:.2f}, {3:.2f}".format(
emotion_number, get_precision(y_true, y_pred, emotion_number),
get_recall(y_true, y_pred, emotion_number),
get_f1_score(y_true, y_pred, emotion_number)))
plt.figure()
cfm = confusion_matrix(y_true, y_pred) / k
plot_confusion_matrix(cfm, classes=["1", "2", "3", "4", "5", "6"])
plt.show()
import pickle
from emotion_predictor import EmotionPredictor
from util import get_clean_data, get_predictors, get_emotion_values
X, y = get_clean_data()
predictors = get_predictors()
emotion_values = get_emotion_values()
emotion_predictor = EmotionPredictor(predictors, random_forest=True, use_confidence=True, num_of_trees=200)
emotion_predictor.fit(emotion_values, X, y)
with open('emotion_predictor.pickle', 'wb') as f:
pickle.dump(emotion_predictor, f, pickle.HIGHEST_PROTOCOL)