def run():
logging.config.fileConfig("logging_config.ini")
print("Processing data")
df_data: pd.DataFrame = dh.read_data(paths.total_dataset_location)
data_dict: dict = dh.split_original_data(df_data, 0.1)
df_train_data: pd.DataFrame = data_dict["train_data"]
df_test_data: pd.DataFrame = data_dict["test_data"]
train_samples: np.ndarray = dh.df_as_array(df_train_data)
test_samples: np.ndarray = dh.df_as_array(df_test_data)
mean_predictions = calculate_all_means(df_train_data)
# initialize variables needed for training
k = 100
bu = np.zeros(paths.num_users)
bm = np.zeros(paths.num_movies)
user_features = np.zeros((paths.num_users, k))
movie_features = np.zeros((k, paths.num_movies))
train(k, mean_predictions, user_features, movie_features, bu, bm,
train_samples, test_samples)
print("Calculating predictions and writing file")
prediction_matrix = final_predictions(mean_predictions, user_features,
movie_features, bu, bm)
dh.write_submission(prediction_matrix)
def cross_validation():
df_data: pd.DataFrame = dh.read_data(paths.total_dataset_location)
data_dict: dict = dh.split_original_data(df_data, 0.2)
df_train_data: pd.DataFrame = data_dict["train_data"]
df_test_data: pd.DataFrame = data_dict["test_data"]
A: np.ndarray = fill_averages(df_train_data)
U, Vh = perform_svd(A)
min_k = 2
max_k = 50
print("Starting cross validation")
ks = []
errs = []
# Winning K = 10
for k in range(min_k, max_k + 1):
prediction_matrix = make_predictions(k, U, Vh)
err = calc_rmse(df_test_data, prediction_matrix)
print("K = {0}, RMSE = {1}".format(k, err))
ks.append(k)
errs.append(err)
plt.plot(ks, errs)
plt.show()
def run():
logging.config.fileConfig("logging_config.ini")
print("Processing data")
df_data: pd.DataFrame = dh.read_data(paths.total_dataset_location)
data_dict: dict = dh.split_original_data(df_data, 0.1)
df_train_data: pd.DataFrame = data_dict["train_data"]
df_test_data: pd.DataFrame = data_dict["test_data"]
train(df_train_data, df_test_data)
def run():
logging.config.fileConfig("logging_config.ini")
print("Processing data")
df_data: pd.DataFrame = dh.read_data(paths.total_dataset_location)
data_dict: dict = dh.split_original_data(df_data, 0.1)
df_train_data: pd.DataFrame = data_dict["train_data"]
df_test_data: pd.DataFrame = data_dict["test_data"]
# cross_validation(df_train_data, df_test_data)
# assign the best result from cross validation to K
K = 10
train(K, df_train_data, df_test_data)
def run():
logging.config.fileConfig("logging_config.ini")
print("Processing data")
df_data: pd.DataFrame = dh.read_data(paths.total_dataset_location)
data_dict: dict = dh.split_original_data(df_data, 0.1)
df_train_data: pd.DataFrame = data_dict["train_data"]
df_test_data: pd.DataFrame = data_dict["test_data"]
print("Calculating initialization data")
mean_predictions = calculate_all_means(df_train_data)
train_samples: np.ndarray = dh.df_as_array(df_train_data)
# Perform either cross validation or a single run using best result
# cross_validation(df_train_data, train_samples, df_test_data, mean_predictions)
k = 10
execute_approach(k, df_train_data, train_samples, df_test_data, mean_predictions)