SCA - Actividad 3

import tensorflow as tf print(tf.__version__)

import numpy as np import matplotlib.pyplot as plt def plot_series(time, series, format="-", start=0, end=None): plt.plot(time[start:end], series[start:end], format) plt.xlabel("Time") plt.ylabel("Value") plt.grid(True)

!wget --no-check-certificate \ https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv \ -O /tmp/daily-min-temperatures.csv

import csv time_step = [] temps = [] with open('/tmp/daily-min-temperatures.csv') as csvfile: reader = csv.reader(csvfile, delimiter=',') next(reader) step=0 for row in reader: temps.append(float(row[1])) time_step.append(step) step = step + 1 series = np.array(temps) time = np.array(time_step) plt.figure(figsize=(10, 6)) plot_series(time, series)

## variables para la técnica de la ventana temporal split_time = 2500 window_size = 30 batch_size = 32 shuffle_buffer_size = 1000 ## Split del dataset en entrenamiento y validación time_t = time[:split_time] x_t = series[:split_time] time_v = time[split_time:] x_v = series[split_time:]

def windowed_dataset(series, window_size, batch_size, shuffle_buffer): series = tf.expand_dims(series, axis=-1) ds = tf.data.Dataset.from_tensor_slices(series) ds = ds.window(window_size + 1, shift=1, drop_remainder=True) ds = ds.flat_map(lambda w: w.batch(window_size + 1)) ds = ds.shuffle(shuffle_buffer) ds = ds.map(lambda w: (w[:-1], w[1:])) return ds.batch(batch_size).prefetch(1)

def model_forecast(model, series, window_size): ds = tf.data.Dataset.from_tensor_slices(series) ds = ds.window(window_size, drop_remainder=True) ds = ds.flat_map(lambda window: window.batch(window_size)) ds = ds.batch(32).prefetch(1) forecast = model.predict(ds, verbose=1) return forecast

tf.keras.backend.clear_session() tf.random.set_seed(51) np.random.seed(51) window_size = 64 batch_size = 256

train_set = windowed_dataset(x_t, window_size, batch_size, shuffle_buffer_size)

model = tf.keras.models.Sequential([ tf.keras.layers.Conv1D(filters=32, kernel_size=5, strides=1, padding="causal", activation="relu", input_shape=[None, 1]), tf.keras.layers.LSTM(64, return_sequences=True), tf.keras.layers.LSTM(64, return_sequences=True), tf.keras.layers.Dense(30), tf.keras.layers.Dense(10), tf.keras.layers.Dense(1), tf.keras.layers.Lambda(lambda x: x * 400) ])

## tu código para crear la variable lr_schedule aquí lr_schedule = tf.keras.callbacks.LearningRateScheduler(lambda epoch: 1e-8 * 10 * (epoch / 20), verbose=1)

model.compile(loss=tf.keras.losses.Huber(), optimizer=tf.keras.optimizers.SGD(lr=1e-8, momentum=0.9), metrics=["mae"])

history = model.fit(train_set, epochs=100, callbacks=[lr_schedule])

plt.semilogx(history.history["lr"], history.history["loss"]) plt.axis([1e-8, 1e-4, 0, 60])

tf.keras.backend.clear_session() tf.random.set_seed(51) np.random.seed(51) train_set = windowed_dataset(x_t, window_size=60, batch_size=100, shuffle_buffer=shuffle_buffer_size)

model = tf.keras.models.Sequential([ tf.keras.layers.Conv1D(filters=60, kernel_size=5, strides=1, padding="causal", activation="relu", input_shape=[None, 1]), tf.keras.layers.LSTM(64, return_sequences=True), tf.keras.layers.LSTM(64, return_sequences=True), tf.keras.layers.Dense(30), tf.keras.layers.Dense(10), tf.keras.layers.Dense(1), tf.keras.layers.Lambda(lambda x: x * 400) ])

model.compile(loss=tf.keras.losses.Huber(), optimizer=tf.keras.optimizers.SGD(lr=1e-5, momentum=0.9), metrics=["mae"])

history = model.fit(train_set,epochs=150)

rnn_forecast = model_forecast(model, x_v[..., np.newaxis], window_size) # rnn_forecast = rnn_forecast[split_time - window_size:-1, -1, 0]

plt.figure(figsize=(10, 6)) plot_series(time_v, x_v) plot_series(time_v[:-10], np.ravel(rnn_forecast))

tf.keras.metrics.mean_absolute_error(x_v, rnn_forecast).numpy()

import matplotlib.image as mpimg import matplotlib.pyplot as plt #----------------------------------------------------------- # Recuperar una lista de resultados de la lista de datos de entrenamiento y pruebas para cada epoch de entrenamiento #----------------------------------------------------------- loss=history.history['loss'] epochs=range(len(loss)) # Get number of epochs

#------------------------------------------------ # Pérdida de entrenamiento y validación por epoch #------------------------------------------------ plt.plot(epochs, loss, 'r') plt.title('Training loss') plt.xlabel("Epochs") plt.ylabel("Loss") plt.legend(["Loss"]) plt.figure()

#------------------------------------------------ # Pérdida de entrenamiento y validación por epoch con zoom #------------------------------------------------ zoomed_loss = loss[20:] zoomed_epochs = range(20,150) # ## tu código para el plot con zoom del ejercicio 8 aquí plt.plot(zoomed_epochs, zoomed_loss)