def load_rf_data(cur_path): data_folder = "data\\titanic" processed_data_folder = os.path.join(cur_path, data_folder) # Note: Not using test.csv as it does not provide whether or not the passenger survived; therefore we cannot assess # how well the model performed. data_file_path = os.path.join(processed_data_folder, "train.csv") data = DataProcessor(data_file_path, processed_data_folder) try: #Try to load data data.load_processed_data() except FileNotFoundError: #No data found, so process it # 10% test, 10% validation, 80% training samples from data splits = (0.1, 0.1, 0.8) # Only use certain columns use_cols = ( # 0, #PassengerID 1, # Survived 2, # Pclass # 3, #Name 4, # Sex 5, # Age 6, # SibSp 7, # Parch # 8, #Ticket 9, # Fare # 10, #Cabin 11, # Embarked ) # Mark features as categorical (so we can one-hot-encode them later) # categorical_cols = () categorical_cols = (2, # Pclass 4, # Sex 11 # Embarked ) # Convert certain columns to float values (so we can use numpy arrays) converters = {4: lambda sex: {'male': 0.0, 'female': 1.0}[sex], 11: lambda embarked: {'S': 0.0, 'C': 1.0, 'Q': 2.0}[embarked]} data.process_data(splits=splits, use_cols=use_cols, categorical_cols=categorical_cols, converters=converters, filter_missing=True) return data
import sys from data_processing import DataProcessor from matplotlib import pyplot cur_path = os.path.dirname(__file__) data_folder = "data\\titanic" processed_data_folder = os.path.join(cur_path, data_folder) # Note: Not using test.csv as it does not provide whether or not the passenger survived; therefore we cannot assess # how well the model performed. data_file_path = os.path.join(processed_data_folder, "train.csv") data_processor = DataProcessor(data_file_path, processed_data_folder, "ffnn_processed.npz") # Load data try: # Try to load data data_processor.load_processed_data() except FileNotFoundError: # No data found, so process it # 20% test, 20% validation, 60% training samples from data splits = (0.2, 0.2, 0.6) # Only use certain columns use_cols = ( # 0, #PassengerID 1, # Survived 2, # Pclass # 3, #Name 4, # Sex 5, # Age 6, # SibSp 7, # Parch # 8, #Ticket