plt.plot(x,avg_values,label="average")
plt.xlabel('Feature Index')
plt.xticks(x,x)
plt.ylabel('Accuracy [%]')
plt.title('Subset of Features Excluding Feature X')
plt.legend()
plt.grid()
plt.savefig("subset_excluding_feature")
exit(0)
config = Config()
dataloader = Dataloader(config,generate_tfidf=False,feature_flag=True)
x_train, y_train = dataloader.get_train_dataloader()
# model = KNeighborsClassifier(n_neighbors=1001,weights='distance')
# scores = cross_val_score(model, x_train[:,[0,1,2,5,6,8,9]], y_train, cv=10)
knn_cv_dict = {
'model_name': 'KNN',
'k_list': [1,3,5,7,9,11,13,15,17,19,21,25,31,41,51,61,71,91,121,151,181,211,251,301,351,401,501,601,801,1001]
}
svm_cv_dict = {
'model_name': 'SVM',
'c_list': [0.5,1,2,4],
'kernel_list': ['linear', 'poly', 'rbf', 'sigmoid']
}
decision_tree_cv_dict = {
from dataloader import Dataloader
from config import Config
TEST_SIZE = 0.15
RANDOM_STATE = 42
if __name__ == "__main__":
# words_list, y = create_data_list(input_file)
config = Config()
dataloader = Dataloader(config)
# word1 = create_word2vec(words_list)
# x_data = create_tfidf(words_list)
# X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(dataloader.all, dataloader.all_labels, test_size=TEST_SIZE, random_state=RANDOM_STATE)
x_train, y_train = dataloader.get_train_dataloader()
x_test, y_test = dataloader.get_test_dataloader()
print("Results with common sarcstic words: ")
training.bernoulli_model(x_train, x_test, y_train, y_test)
training.KNN_model(x_train, x_test, y_train, y_test)
training.SVM_model(x_train, x_test, y_train, y_test)
x_train_tfidf, y_train_tfidf = dataloader.get_train_dataloader(tfidf=True)
x_test_tfidf, y_test_tfidf = dataloader.get_test_dataloader(tfidf=True)
print()
print("Results with common sarcstic words + TF-IDF: ")
training.bernoulli_model(x_train_tfidf, x_test_tfidf, y_train_tfidf, y_test_tfidf)
training.KNN_model(x_train_tfidf, x_test_tfidf, y_train_tfidf, y_test_tfidf)
training.SVM_model(x_train_tfidf, x_test_tfidf, y_train_tfidf, y_test_tfidf)
