def first_set(min_sup):
""" Database bbp2 """
print("-- Database: bbp2 --")
train_labels = load_labels("train_bbp2.gt")
test_labels = load_labels("test_bbp2.gt")
# Run graph mining to get matrices
train_matrix, test_matrix, num_freq = graph_mining(
os_join(DATA_PATH, "train_bbp2.gsp"),
os_join(DATA_PATH, "test_bbp2.gsp"),
len(train_labels) * min_sup)
# Train RandomForrestClassifier with matrices and labels
try:
score = run_random_forest(train_matrix, train_labels, test_matrix,
test_labels)
except Exception as e:
print(str(e))
return str(e)
print("Accuracy of classifier: " + str(score))
return score, num_freq
def second_set(min_sup):
""" Database molecules """
print("-- Database: molecules --")
train_labels = load_labels("train_molecules.groundTruth", sep=" ")
test_labels = load_labels("test_molecules.groundTruth", sep=" ")
# Run graph mining to get matrices
train_matrix, test_matrix, num_freq = graph_mining(
os_join(DATA_PATH, "train_molecules.gsp"),
os_join(DATA_PATH, "test_molecules.gsp"),
len(train_labels) * min_sup)
# Train RandomForrestClassifier with matrices and labels
try:
score = run_random_forest(train_matrix, train_labels, test_matrix,
test_labels)
except Exception as e:
print(str(e))
return str(e)
print("Accuracy of classifier: " + str(score))
return score, num_freq
from ada_boost import run_ada_boost
from data import get_data_frame, split_train_test
from decision_tree import run_decision_tree
from knn import run_knn
from linear_regression import run_linear_regression
from logistic_regression import run_logistic_regression
from naive_bayes import run_gaussianNB, run_multinomialNB, run_bernoulliNB
from neural_network import run_neural_network
from random_forest import run_random_forest
from svm import run_svm
if __name__ == "__main__":
data = get_data_frame()
X_train, X_test, y_train, y_test = split_train_test(data)
# Uncomment the algorithms to run as you wish
# be careful with knn it is too slow.
#run_gaussianNB(X_train, X_test, y_train, y_test)
#run_multinomialNB(X_train, X_test, y_train, y_test)
#run_bernoulliNB(X_train, X_test, y_train, y_test)
#run_knn(X_train, X_test, y_train, y_test)
#run_linear_regression(X_train, X_test, y_train, y_test)
#run_logistic_regression(X_train, X_test, y_train, y_test)
#run_svm(X_train, X_test, y_train, y_test)
#run_decision_tree(X_train, X_test, y_train, y_test)
run_random_forest(X_train, X_test, y_train, y_test)
#run_neural_network(X_train, X_test, y_train, y_test)
#run_ada_boost(X_train, X_test, y_train, y_test)
from data_preprocessor import get_data
if __name__ == '__main__':
x_train, x_test, y_train, y_test = get_data(True)
print(
"\n-------------------------------------\nAccuracies with top 5 features:\n-------------------------------------"
)
run_decision_tree(x_train, x_test, y_train, y_test)
run_k_nearest_neighbour(x_train, x_test, y_train, y_test)
run_logistic_regression(x_train, x_test, y_train, y_test)
run_naive_bayes(x_train, x_test, y_train, y_test)
run_neural_network(x_train, x_test, y_train, y_test)
run_perceptron(x_train, x_test, y_train, y_test)
run_random_forest(x_train, x_test, y_train, y_test)
run_svm(x_train, x_test, y_train, y_test)
run_xg_boost(x_train, x_test, y_train, y_test)
print(
"\n-------------------------------------\nAccuracy with Voting in top 5 features:\n-------------------------------------"
)
run_voting(x_train, x_test, y_train, y_test)
x_train, x_test, y_train, y_test = get_data()
print(
"\n-------------------------------------\nAccuracies with all 22 features:\n-------------------------------------"
)
run_decision_tree(x_train, x_test, y_train, y_test)
run_k_nearest_neighbour(x_train, x_test, y_train, y_test)
df_movie = fill_nan(df_movie)
df_movie = df_movie.drop(columns="imdb_score")
print(df_movie["director_name"].head())
col_mask = print(df_movie.isna().any(axis=0))
print(col_mask)
# return the processed dataset.
return df_movie
if __name__ == "__main__":
# df_movie, df_standard = data_prepocessing()
# df_knn = df_movie
# df_knn = df_knn.reset_index()
# df_knn["class"] = df_knn.apply(classify, axis=1)
# classes = list(df_knn["class"])
# amazing = classes==['AMAZING']
# print(amazing)
# df_knn = df_knn.drop(columns="imdbRating")
df_movie = load_metadata_dataset()
#run_knn(df_movie)
#run_logistic_regression(df_movie)
classifier=run_random_forest(df_movie)
run(classifier)