import numpy as np import pandas as pd import tensorflow as tf import matplotlib.cm as cm import matplotlib.pyplot as plt import matplotlib matplotlib.rcParams['text.usetex'] = True from sklearn.preprocessing import KBinsDiscretizer from sklearn.model_selection import StratifiedGroupKFold, StratifiedShuffleSplit, GridSearchCV, train_test_split from sklearn.metrics import mean_squared_error, mean_absolute_error from sklearn.preprocessing import MinMaxScaler from xgboost import XGBRegressor import keras from keras import layers import ray from ray import tune from ray.tune.schedulers import ASHAScheduler # from ray import tune # import ray # from keras.callbacks import TensorBoard # from keras.models import Sequential # from keras.callbacks import EarlyStopping # from keras.layers import Dense, BatchNormalization, Dropout # from kerastuner.tuners import RandomSearch, Hyperband, GridSearch from datetime import datetime import enlighten import logging import zipfile import random import joblib import pickle import time import json import os def get_seed(): return random.randint(0, 2**32 - 1) class eNoseTrainer: def __init__(self, loader, test_size=0.2, debug=False): self.ledger = pd.DataFrame(columns=["node", "ts", "Dataset", "Samples", "Target", "Train Size", "Train Ratio", "Model", "Params", "Ratio", "Train mse", "mse", "mae", "rmse"]) self.loader = loader self.name = self.loader.label_file self.state = dict() os.makedirs(self.name, exist_ok=True) self.start = int(time.time()) log_format = '%(asctime)s | %(levelname)-8s | %(name)-15s | %(message)s' date_format = '%Y-%m-%d %H:%M:%S' logging.basicConfig(format=log_format, datefmt=date_format) target_log = '{}/load-{}.log'.format(self.name, self.start) fh = logging.FileHandler(target_log) self.debug = debug self.logger = logging.getLogger("eNoseTrainer") if self.debug: self.logger.setLevel(logging.DEBUG) fh.setLevel(logging.DEBUG) else: self.logger.setLevel(logging.INFO) fh.setLevel(logging.INFO) self.logger.addHandler(fh) self.ratio = test_size self.loader.stats() self.loadCheckPoint() def loadCheckPoint(self): if not os.path.isfile('{}/Simulaciones.xlsx'.format(self.name)): self.saveCheckPoint() with pd.ExcelFile('{}/Simulaciones.xlsx'.format(self.name)) as xls: self.ledger = pd.read_excel(xls, sheet_name='Historial') self.trained = self.ledger.shape[0] # with open('{}/vars.pickle'.format(self.name), 'rb') as pfile: # self.ratio, self.state = pickle.load(pfile) def saveCheckPoint(self): with pd.ExcelWriter('{}/Simulaciones.xlsx'.format(self.name), engine='xlsxwriter') as xls: self.ledger.to_excel(xls, sheet_name='Historial', index=False) # with open('{}/vars.pickle'.format(self.name), 'wb') as pfile: # pickle.dump((self.ratio, self.state), pfile, protocol=pickle.HIGHEST_PROTOCOL) self.trained = self.ledger.shape[0] def wrap_and_save(self): self.logger.info("{:=^60}".format(' Saving Summary and Wrap the output in a ZipFile ')) with zipfile.ZipFile('{}-{}.zip'.format(self.name, self.start), 'w', zipfile.ZIP_DEFLATED) as zipf: for root, dirs, files in os.walk(self.name): for file in files: zipf.write(os.path.join(root, file)) def row_exists(self, dataset, model): search_result = self.ledger[(self.ledger["Dataset"]==dataset) & (self.ledger["Target"]==self.loader.target) & (self.ledger["Model"]==model) & (self.ledger["Ratio"]==self.ratio)].shape[0] > 0 self.logger.debug(f'Looking for {dataset}, {model}, {self.loader.target}, {self.ratio} => {search_result} {self.ledger.shape}') return search_result def model_A(self, hp): model = Sequential() model.add(Dense(units=hp.Int('units_input', min_value=48, max_value=56, step=8), input_dim=self.nvars, activation='relu')) model.add(BatchNormalization()) model.add(Dropout(rate=hp.Float('dropout_input', min_value=0.1, max_value=0.1, step=0.1))) model.add(Dense(units=hp.Int('units_hidden', min_value=32, max_value=48, step=8), activation='relu')) model.add(BatchNormalization()) model.add(Dropout(rate=hp.Float('dropout_hidden', min_value=0.4, max_value=0.4, step=0.1))) model.add(Dense(1, activation='sigmoid')) model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy', AUC()]) return model def train_and_score_model_keras(self, X_train, X_test, Y_train, Y_test, seed, label): # set_random_seed(seed) ntrials = 6 tuner = RandomSearch( self.get_model_train_keras, objective='val_loss', #val_loss # seed=seed, max_trials=ntrials, # executions_per_trial=1, # Número de ejecuciones por cada configuración directory=self.name, project_name='{}-{}'.format(label,seed)) self.logger.info("{:~^60}".format(' {}-{} '.format(label,seed))) search_dir = "{}/keras-tuner-{}/".format(self.name,label) os.makedirs(search_dir, exist_ok=True) search_callback = TensorBoard(log_dir=search_dir) early_stopping_search = EarlyStopping(monitor='val_loss', patience=13, min_delta=0.005, start_from_epoch=7, restore_best_weights=True) tuner.search(X_train, Y_train, epochs=150, batch_size=10, validation_data=(X_test, Y_test), callbacks=[early_stopping_search, search_callback]) best_hps = tuner.get_best_hyperparameters(num_trials=1)[0] self.trained += 1 self.bar.update() return mse, mae, rmse, optimized_model, model_params def get_model_train(self): return [ XGBRegressor(objective='reg:squarederror'), ] def get_tunable_params(self, model): if isinstance(model, XGBRegressor): return { 'tree_method': ["hist"], "n_estimators": [100, 128, 150], 'max_depth': [6, 7, 8], 'subsample': [0.5, 0.6, 0.7], 'multi_strategy': ['one_output_per_tree', 'multi_output_tree'] } elif isinstance(model, RandomForestClassifier): return { "n_estimators": [50, 100, 200], "max_depth": [5, 10, 15], "max_features": [2, 5, 10] #['n', 'max_depth', 'max_features', 'max_leaf_nodes', 'max_samples', 'min_impurity_decrease', 'min_samples_leaf', 'min_samples_split', 'min_weight_fraction_leaf', 'monotonic_cst', 'n_estimators', 'n_jobs', 'oob_score', 'random_state', 'verbose', 'warm_start'] } else: return {} def search_best_conv1D_v1(self, X_train_orig, X_test_orig, Y_train_orig, Y_test_orig, epochs=30, nsamples=0.1): ray.init(ignore_reinit_error=True) X_train_ref = ray.put(X_train_orig) Y_train_ref = ray.put(Y_train_orig) X_test_ref = ray.put(X_test_orig) Y_test_ref = ray.put(Y_test_orig) def build_model_conv1D(config, input_shape, output_dim): model = keras.Sequential([ layers.Conv1D(filters=config['filters'], kernel_size=config['kernel_size'], stride=config['kernel_size']//2, activation='relu', input_shape=input_shape), layers.MaxPooling1D(pool_size=config['pool_size']), layers.Conv1D(filters=config['filters'] * 2, kernel_size=config['kernel_size'], stride=config['kernel_size']//2, activation='relu'), layers.MaxPooling1D(pool_size=config['pool_size']), layers.Flatten(), layers.Dense(config['dense_units'], activation='relu'), layers.Dropout(config['dropout']), layers.Dense(output_dim) ]) model.compile(optimizer=keras.optimizers.Adam(learning_rate=config['lr']), loss='mse') return model def train_model_conv1D(config): X_trainc1D = ray.get(X_train_ref) Y_trainc1D = ray.get(Y_train_ref) X_testc1D = ray.get(X_test_ref) Y_testc1D = ray.get(Y_test_ref) input_shape = X_trainc1D.shape[1:] output_dim = Y_trainc1D.shape[1] model = build_model_conv1D(config, input_shape, output_dim) early_stopping = keras.callbacks.EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True) model.fit( X_trainc1D, Y_trainc1D, validation_data=(X_testc1D, Y_testc1D), epochs=config['epochs'], batch_size=config['batch_size'], verbose=0, callbacks=[early_stopping] ) Y_pred = model.predict(X_testc1D) mse = mean_squared_error(Y_testc1D, Y_pred) tune.report({'mse': mse}) config_space = { 'filters': tune.choice([16, 32, 64]), 'kernel_size': tune.choice([3, 5, 7]), 'pool_size': tune.choice([2, 3]), 'dense_units': tune.choice([32, 64, 128]), 'dropout': tune.choice([0.1, 0.2, 0.3]), 'lr': tune.choice([0.001, 0.0005, 0.0001]), 'batch_size': tune.choice([16, 32, 64]), 'epochs': epochs } total_space = (3*3*2*3*3*3*3) scheduler = ASHAScheduler(metric='mse', mode='min', max_t=epochs, grace_period=5, reduction_factor=2) # analysis = tune.run(train_model, config=config_space, num_samples=num_samples, scheduler=scheduler) analysis = tune.run( tune.with_parameters(train_model_conv1D), config=config_space, num_samples=int(nsamples*total_space), scheduler=scheduler, max_concurrent_trials=8 ) best_config = analysis.get_best_config(metric='mse', mode='min') best_model = build_model_conv1D(best_config, X_train_orig.shape[1:], Y_train_orig.shape[1]) ray.internal.free([X_train_ref, Y_train_ref, X_test_ref, Y_test_ref]) ray.shutdown() return best_model, best_config def train_and_score_model(self, model, X_train, X_test, Y_train, Y_test): param_dist = self.get_tunable_params(model) cv = StratifiedShuffleSplit(n_splits=int(1/(2*self.ratio))+1, test_size=self.ratio, random_state=get_seed()) grid_search = GridSearchCV(estimator=model, param_grid=param_dist, scoring='neg_mean_squared_error', cv=cv, verbose=2, n_jobs=-1) grid_search.fit(X_train, Y_train) optimized_model = grid_search.best_estimator_ model_params = grid_search.best_params_ y_aux = optimized_model.predict(X_train) tmse = mean_squared_error(Y_train, y_aux) y_pred = optimized_model.predict(X_test) mse = mean_squared_error(Y_test, y_pred) mae = mean_absolute_error(Y_test, y_pred) rmse = np.sqrt(mse) return tmse, mse, mae, rmse, optimized_model, model_params def gen_plots(self, dataset, model_id, target=None): if isinstance(target, list): self.loader.target_list=target if isinstance(target, str): self.loader.target_list= list(target) if dataset.endswith("-conv3"): self.loader.smooth = 'conv3' else: self.loader.smooth = None self.loader.reset() if not self.row_exists(dataset, model_id): self.logger.error(f'No se encuentra la simulacion {dataset}, {model_id}') return model_file = '{}/{}/{}/{}'.format(self.name, self.loader.target, dataset, model_id ) if not os.path.isfile(model_file): self.logger.error('No se encuentra el modelo') return trained_model = joblib.load(model_file) pics_folder = '{}/{}/{}/plots'.format(self.name, self.loader.target, dataset) os.makedirs(pics_folder, exist_ok=True) df = self.loader.scaled_data Y_samples = np.zeros((len(df), len(self.loader.target_list))) for i, sample in enumerate(df): Y_samples[i] = np.array([[df[sample]['label'][key] for key in self.loader.target_list]]) self.logger.debug(f"Y_samples.shape: {Y_samples.shape}") target_scaler = MinMaxScaler() Y_samples = target_scaler.fit_transform(Y_samples) cmapx = cm.get_cmap('winter', len(self.loader.source_channels)) cmapy = cm.get_cmap('prism', Y_samples.shape[1]) for measurament, (r, l) in self.loader.dataset['range'].items(): # df[measurament]['data'].plot(figsize=(12, 6), title=f"{measurament} Prediction") plt.figure(figsize=(12, 6)) plt.title(f"[{dataset}] {model_id}. Sample {measurament}") plt.xlabel("Sensor Readings") plt.vlines(x=r, ymin=0, ymax=1, colors='blue', linestyle='dashed') plt.vlines(x=l, ymin=0, ymax=1, colors='blue', linestyle='dashed') Y_value = np.zeros((1, len(self.loader.target_list))) Y_value[0] = np.array([[df[measurament]['label'][key] for key in self.loader.target_list]]) self.logger.debug(f"Y_value.shape: {Y_value.shape}") self.logger.debug(f"Y_value: {Y_value}") Y_scaled = target_scaler.transform(Y_value).reshape(1, -1) self.logger.debug(f"Y_scaled.shape: {Y_scaled.shape}") self.logger.debug(f"Y_scaled: {Y_scaled}") y_pred = trained_model.predict(df[measurament]['data'].to_numpy()) self.logger.debug(f"y_pred.shape: {y_pred.shape}") # self.logger.debug(f"y_pred: {Y_scaled}") if y_pred.ndim == 2: plt.ylabel("Target dashed / Pred solid") for i, channel_name in enumerate(df[measurament]['data'].columns): plt.plot(df[measurament]['data'][channel_name], linestyle = 'dotted', color=cmapx(i), alpha=0.2) for i in range(y_pred.shape[1]): self.logger.debug(f"Y_scaled[0][i]: {Y_scaled[0][i]}") plt.axhline(y=Y_scaled[0][i], xmin=0, xmax=df[measurament]['data'].shape[0], color=cmapy(i), linestyle='dashed') plt.plot(y_pred[:, i], color=cmapy(i), linestyle='solid') else: plt.ylabel("Samples dotted / Target dashed / Pred solid") for i, channel_name in enumerate(df[measurament]['data'].columns): plt.plot(df[measurament]['data'][channel_name], linestyle = 'dotted', color=cmapx(i)) plt.plot(y_pred, color=cmapy(0), linestyle='solid') plt.axhline(y=Y_scaled, xmin=0, xmax=df[measurament]['data'].shape[0], color=cmapy(i), linestyle='dashed') filename = os.path.join(pics_folder, f"{measurament}_{model_id}.png") plt.savefig(filename, format='png') self.logger.info(f"Saved plot as {filename}") plt.close() def fit(self): windows = [32, 64, 128] total_train_queue = 2*int(1/self.ratio)*(len(self.get_model_train())+len(windows)) self.logger.info("{:=^60}".format(f'Begin Fit {total_train_queue} Models')) self.trained = 0 manager = enlighten.get_manager() self.bar = manager.counter(total=total_train_queue, count=self.trained, desc='Tunning', unit='Models', format='{desc}{desc_pad}{percentage:3.0f}%|{bar}| {count:{len_total}d}/{total:d} [{elapsed}<{eta}, {rate:.2f}{unit_pad}{unit}/s]' ) discretizer = KBinsDiscretizer(n_bins=200, encode='ordinal', strategy='uniform') gss = StratifiedGroupKFold(n_splits=int(1/self.ratio), shuffle=True, random_state=get_seed()) node = os.uname()[1] self.loader.smooth = None self.loader.reset() X_xboost, Y_xboost, G_xboost = self.loader.load_dataset_xboost() # self.logger.debug(f"X_xboost: {X_xboost.shape}") self.logger.debug(f"Y_xboost: {Y_xboost.shape}") # self.logger.debug(f"G_xboost: {G_xboost.shape}") Y_discrete = discretizer.fit_transform(Y_xboost) if Y_discrete.ndim == 2: Y_discrete = np.sum(Y_discrete, axis=1) # self.logger.debug(f"Y_discrete: {Y_discrete.shape}") dataset = 'Tabular' for i, (train_index, test_index) in enumerate(gss.split(X_xboost, Y_discrete, G_xboost)): self.logger.info("{:=^60}".format(f'CV {i+1}/{int(1/self.ratio)} {dataset}')) os.makedirs('{}/{}/{}'.format(self.name, self.loader.target, dataset), exist_ok=True) X_train, X_test = X_xboost[train_index], X_xboost[test_index] Y_train, Y_test = Y_xboost[train_index], Y_xboost[test_index] # self.logger.debug(f"X_train: {X_train.shape}") # self.logger.debug(f"X_test: {X_test.shape}") self.logger.debug(f"Y_train: {Y_train.shape}") self.logger.debug(f"Y_test: {Y_test.shape}") for model in self.get_model_train(): model_id = "{}_{}".format(type(model).__name__, i) self.trained += 1 if self.row_exists(dataset, model_id): self.bar.update() continue model_file = '{}/{}/{}/{}'.format(self.name, self.loader.target, dataset, model_id ) tmse, mse, mae, rmse, optimized_model, model_params = self.train_and_score_model(model, X_train, X_test, Y_train, Y_test) ts = datetime.now().strftime("%d/%m/%Y %H:%M:%S") joblib.dump(optimized_model, model_file) newrow = pd.DataFrame( [{"node": node, "ts": ts, "Dataset": dataset, "Samples": Y_xboost.shape[0], "Target": self.loader.target, "Train Size": Y_train.shape[0], "Train Ratio": Y_train.shape[0]/Y_xboost.shape[0], "Ratio": self.ratio, "Model": model_id, "Params": json.dumps(model_params), "Train mse": tmse, "mse": mse, "mae": mae, "rmse": rmse }] ) self.ledger = pd.concat([self.ledger, newrow], ignore_index=True) self.bar.update() self.saveCheckPoint() self.loader.smooth = 'conv3' self.loader.reset() X_xboost, Y_xboost, G_xboost = self.loader.load_dataset_xboost() # self.logger.debug(f"X_xboost: {X_xboost.shape}") self.logger.debug(f"Y_xboost: {Y_xboost.shape}") # self.logger.debug(f"G_xboost: {G_xboost.shape}") Y_discrete = discretizer.fit_transform(Y_xboost) if Y_discrete.ndim == 2: Y_discrete = np.sum(Y_discrete, axis=1) dataset = 'Tabular-conv3' for i, (train_index, test_index) in enumerate(gss.split(X_xboost, Y_discrete, G_xboost)): self.logger.info("{:=^60}".format(f'CV {i+1}/{int(1/self.ratio)} {dataset}')) os.makedirs('{}/{}/{}'.format(self.name, self.loader.target, dataset), exist_ok=True) X_train, X_test = X_xboost[train_index], X_xboost[test_index] Y_train, Y_test = Y_xboost[train_index], Y_xboost[test_index] # self.logger.debug(f"X_train: {X_train.shape}") # self.logger.debug(f"X_test: {X_test.shape}") self.logger.debug(f"Y_train: {Y_train.shape}") self.logger.debug(f"Y_test: {Y_test.shape}") for model in self.get_model_train(): model_id = "{}_{}".format(type(model).__name__, i) self.trained += 1 if self.row_exists(dataset, model_id): self.bar.update() continue model_file = '{}/{}/{}/{}'.format(self.name, self.loader.target, dataset, model_id ) tmse, mse, mae, rmse, optimized_model, model_params = self.train_and_score_model(model, X_train, X_test, Y_train, Y_test) ts = datetime.now().strftime("%d/%m/%Y %H:%M:%S") joblib.dump(optimized_model, model_file) newrow = pd.DataFrame( [{"node": node, "ts": ts, "Dataset": dataset, "Samples": Y_xboost.shape[0], "Target": self.loader.target, "Train Size": Y_train.shape[0], "Train Ratio": Y_train.shape[0]/Y_xboost.shape[0], "Ratio": self.ratio, "Model": model_id, "Params": json.dumps(model_params), "Train mse": tmse, "mse": mse, "mae": mae, "rmse": rmse }] ) self.ledger = pd.concat([self.ledger, newrow], ignore_index=True) self.bar.update() self.saveCheckPoint() sample_size = 50000 self.loader.smooth = None self.loader.reset() for window in windows: X_conv1d, Y_conv1d, G_conv1d = self.loader.load_dataset_window(window) self.logger.debug(f"X_conv1d: {X_conv1d.shape}") self.logger.debug(f"Y_conv1d: {Y_conv1d.shape}") self.logger.debug(f"G_conv1d: {G_conv1d.shape}") Y_discrete = discretizer.fit_transform(Y_conv1d) if Y_discrete.ndim == 2: Y_discrete = np.sum(Y_discrete, axis=1) dataset = f'Conv1d-base-w{window}' for i, (train_index, test_index) in enumerate(gss.split(X_conv1d, Y_discrete, G_conv1d)): self.logger.info("{:=^60}".format(f'CV {i+1}/{int(1/self.ratio)} {dataset}')) os.makedirs('{}/{}/{}-w{}'.format(self.name, self.loader.target, dataset, window), exist_ok=True) X_train, X_test = X_conv1d[train_index], X_conv1d[test_index] Y_train, Y_test = Y_conv1d[train_index], Y_conv1d[test_index] G_train, G_test = G_conv1d[train_index], G_conv1d[test_index] # self.logger.debug(f"X_train: {X_train.shape}") # self.logger.debug(f"X_test: {X_test.shape}") model_id = "Conv1d-base_{}".format(i) self.trained += 1 if self.row_exists(dataset, model_id): self.bar.update() continue model_file = '{}/{}/{}-w{}/{}'.format(self.name, self.loader.target, dataset, window, model_id ) X_train_sample, _, Y_train_sample, _ = train_test_split(X_train, Y_train, stratify=G_train, train_size=0.8*sample_size / len(X_train), random_state=get_seed()) X_test_sample, _, Y_test_sample, _ = train_test_split(X_test, Y_test, stratify=G_test, train_size=0.2*sample_size / len(X_test), random_state=get_seed()) self.logger.debug(f"Y_train_sample: {Y_train_sample.shape}") self.logger.debug(f"Y_test_sample: {Y_test_sample.shape}") optimized_model, model_params = self.search_best_conv1D_v1(X_train_sample, X_test_sample, Y_train_sample, Y_test_sample) self.logger.info(f"Training Model {model_id} with {model_params}")) optimized_model.fit(X_train, Y_train, epochs=model_params['epochs'], batch_size=model_params['batch_size'], verbose=1) Y_train_pred = optimized_model.predict(X_train) Y_test_pred = optimized_model.predict(X_test) mse_train = mean_squared_error(Y_train, Y_train_pred) mae_test = mean_absolute_error(Y_test, Y_test_pred) mse_test = mean_squared_error(Y_test, Y_test_pred) rmse_test = np.sqrt(mse_test) ts = datetime.now().strftime("%d/%m/%Y %H:%M:%S") optimized_model.save(model_file) optimized_model.save_weights(f"{model_file}.weights.h5") newrow = pd.DataFrame( [{"node": node, "ts": ts, "Dataset": dataset, "Samples": Y_xboost.shape[0], "Target": self.loader.target, "Train Size": Y_train.shape[0], "Train Ratio": Y_train.shape[0]/Y_xboost.shape[0], "Ratio": self.ratio, "Model": model_id, "Params": json.dumps(model_params), "Train mse": mse_train, "mse": mse_test, "mae": mae_test, "rmse": rmse_test }] ) self.ledger = pd.concat([self.ledger, newrow], ignore_index=True) self.bar.update() self.saveCheckPoint() self.loader.smooth = 'conv3' self.loader.reset() for window in windows: X_conv1d, Y_conv1d, G_conv1d = self.loader.load_dataset_window(window) self.logger.debug(f"X_conv1d: {X_conv1d.shape}") self.logger.debug(f"Y_conv1d: {Y_conv1d.shape}") self.logger.debug(f"G_conv1d: {G_conv1d.shape}") Y_discrete = discretizer.fit_transform(Y_conv1d) if Y_discrete.ndim == 2: Y_discrete = np.sum(Y_discrete, axis=1) dataset = f'Conv1d-base-w{window}-conv3' for i, (train_index, test_index) in enumerate(gss.split(X_conv1d, Y_discrete, G_conv1d)): self.logger.info("{:=^60}".format(f'CV {i+1}/{int(1/self.ratio)} {dataset}')) os.makedirs('{}/{}/{}-w{}'.format(self.name, self.loader.target, dataset, window), exist_ok=True) X_train, X_test = X_conv1d[train_index], X_conv1d[test_index] Y_train, Y_test = Y_conv1d[train_index], Y_conv1d[test_index] G_train, G_test = G_conv1d[train_index], G_conv1d[test_index] # self.logger.debug(f"X_train: {X_train.shape}") # self.logger.debug(f"X_test: {X_test.shape}") self.logger.debug(f"Y_train: {Y_train.shape}") self.logger.debug(f"Y_test: {Y_test.shape}") model_id = "Conv1d-base_{}".format(i) self.trained += 1 if self.row_exists(dataset, model_id): self.bar.update() continue X_train_sample, _, Y_train_sample, _ = train_test_split(X_train, Y_train, stratify=G_train, train_size=0.8*sample_size / len(X_train), random_state=get_seed()) X_test_sample, _, Y_test_sample, _ = train_test_split(X_test, Y_test, stratify=G_test, train_size=0.2*sample_size / len(X_test), random_state=get_seed()) self.logger.debug(f"Y_train_sample: {Y_train_sample.shape}") self.logger.debug(f"Y_test_sample: {Y_test_sample.shape}") optimized_model, model_params = self.search_best_conv1D_v1(X_train_sample, X_test_sample, Y_train_sample, Y_test_sample) optimized_model.fit(X_train, Y_train, epochs=model_params['epochs'], batch_size=model_params['batch_size'], verbose=1) Y_train_pred = optimized_model.predict(X_train) Y_test_pred = optimized_model.predict(X_test) mse_train = mean_squared_error(Y_train, Y_train_pred) mae_test = mean_absolute_error(Y_test, Y_test_pred) mse_test = mean_squared_error(Y_test, Y_test_pred) rmse_test = np.sqrt(mse_test) ts = datetime.now().strftime("%d/%m/%Y %H:%M:%S") optimized_model.save(model_file) optimized_model.save_weights(f"{model_file}.weights.h5") newrow = pd.DataFrame( [{"node": node, "ts": ts, "Dataset": dataset, "Samples": Y_xboost.shape[0], "Target": self.loader.target, "Train Size": Y_train.shape[0], "Train Ratio": Y_train.shape[0]/Y_xboost.shape[0], "Ratio": self.ratio, "Model": model_id, "Params": json.dumps(model_params), "Train mse": tmse, "mse": mse, "mae": mae, "rmse": rmse }] ) self.ledger = pd.concat([self.ledger, newrow], ignore_index=True) self.bar.update() self.saveCheckPoint() self.bar.close()