预测温度

wget https://s3.amazonaws.com/keras-datasets/jena_climate_2009_2016.csv.zip
unzip jena_climate_2009_2016.csv.zip

这份数据大概就这样：

预备数据

import os
import matplotlib.pyplot as plt
import numpy as np
# 这份数据是 每10分钟记载一次 一共是14个物理量
fname = os.path.join("jena_climate_2009_2016.csv")
if __name__ == '__main__':
    with open(fname) as f:
        data = f.read()
    lines = data.split("n")
    header = lines[0].split(",")
    lines = lines[1:]
    print(header)
    print(len(lines))
    # 放弃了 date time 这一项
    temperature = np.zeros((len(lines),))
    raw_data = np.zeros((len(lines), len(header) - 1))
    for i, line in enumerate(lines):
        values = [float(x) for x in line.split(",")[1:]]
        temperature[i] = values[1]
        raw_data[i, :] = values[:]
    plt.plot(range(len(temperature)), temperature)
    # 时刻跨度为8年的温度曲线改变
    plt.show()
    # 看下前10天的数据
    plt.plot(range(1440), temperature[:1440])
    plt.show()

能够看出来这8年的温度改变曲线是差不多的

再看下头几天的温度曲线

预备练习集

# 创建3个数据集
# 每6个数据点保存一个，这个很好理解，因为数据是10分钟收集一次 2个10分钟之间 温度的改变其实很小 因此没必要保留这么多数据
sampling_rate = 6
# 给定曩昔5天的数据
sequence_length = 120
delay = sampling_rate * (sequence_length + 24 - 1)
batch_size = 256
train_dataset = keras.utils.timeseries_dataset_from_array(
    raw_data[:-delay],
    targets=temperature[delay:],
    sampling_rate=sampling_rate,
    sequence_length=sequence_length,
    shuffle=True,
    batch_size=batch_size,
    start_index=0,
    end_index=num_train_samples)
val_dataset = keras.utils.timeseries_dataset_from_array(
    raw_data[:-delay],
    targets=temperature[delay:],
    sampling_rate=sampling_rate,
    sequence_length=sequence_length,
    shuffle=True,
    batch_size=batch_size,
    start_index=num_train_samples,
    end_index=num_train_samples + num_val_samples)
test_dataset = keras.utils.timeseries_dataset_from_array(
    raw_data[:-delay],
    targets=temperature[delay:],
    sampling_rate=sampling_rate,
    sequence_length=sequence_length,
    shuffle=True,
    batch_size=batch_size,
    start_index=num_train_samples + num_val_samples)

能够看下这个输出

for samples, targets in train_dataset:
    print("samples shape:", samples.shape)
    print("targets shape:", targets.shape)
    break

sample便是包含256个样本的批量，每个样本是接连120小时的数据， targets 是对应的256个方针温度的数组

留意这儿因为shuffle是true。所以sample[0] 和 sample[1] 不一定在时刻上是接连挨近的

根据LSTM的简单模型

有一种专门处理 因果联系和顺序联系都很重要的序列 的神经网络架构 RNN

其间LSTM 是应用规模最广的

这儿用LSTM 来处理上述的使命

inputs = keras.Input(shape=(sequence_length, raw_data.shape[-1]))
x = layers.LSTM(16)(inputs)
outputs = layers.Dense(1)(x)
model = keras.Model(inputs, outputs)
callbacks = [
    keras.callbacks.ModelCheckpoint("jena_lstm.keras", save_best_only=True)
]
model.compile(optimizer="rmsprop", loss="mse", metrics=["mae"])
history = model.fit(train_dataset, epochs=10, validation_data=val_dataset, callbacks=callbacks)
loss = history.history["mae"]
val_loss = history.history["val_mae"]
epochs = range(1, len(loss) + 1)
plt.figure()
plt.plot(epochs, loss, "bo", label="Training MAE")
plt.plot(epochs, val_loss, "b", label="Validation MAE")
plt.title("Training and validation MAE")
plt.legend()
plt.show()
model = keras.models.load_model("jena_lstm.keras")
print(f"Test MAE: {model.evaluate(test_dataset)[1]:.2f}")

测试的mae为

换一种写法

使用dropout正则化 总是需要更长时刻才能完全收敛，所以这儿 模型的练习书调整为本来的5倍

inputs = keras.Input(shape=(sequence_length, raw_data.shape[-1]))
# 正则化
x = layers.LSTM(32, recurrent_dropout=0.25)(inputs)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(1)(x)
model = keras.Model(inputs, outputs)
callbacks = [
    keras.callbacks.ModelCheckpoint("jena_lstm_dropout.keras", save_best_only=True)
]
model.compile(optimizer="rmsprop", loss="mse", metrics=["mae"])
history = model.fit(train_dataset, epochs=50, validation_data=val_dataset, callbacks=callbacks)

总结

如果顺序对数据很重要，特别是关于时刻序列数据，那么循环神经网络RNN是一种很合适的办法