第六章代码小修改

Author: sunjiaxin111

chapter6/inspect_jena_weather_dataset.py

@@ -1,9 +1,10 @@
 import os
+
 import numpy as np
-from matplotlib import pyplot as plt
-from keras.models import Sequential
 from keras import layers
+from keras.models import Sequential
 from keras.optimizers import RMSprop
+from matplotlib import pyplot as plt
 
 data_dir = ''
 fname = os.path.join(data_dir, 'jena_climate_2009_2016.csv')
@@ -149,14 +150,9 @@ def generator(data, lookback, delay, min_index, max_index, shuffle=False, batch_
                               validation_steps=val_steps)
 '''
 '''
-# 使用一个正则化后多层的GRU模型
+# 使用一个双向的GRU模型
 model = Sequential()
-model.add(layers.GRU(32,
-          dropout=0.1,
-          recurrent_dropout=0.5,
-          return_sequences=True,
-          input_shape=(None, float_data.shape[-1])))
-model.add(layers.GRU(64, activation='relu', dropout=0.1, recurrent_dropout=0.5))
+model.add(layers.Bidirectional(layers.GRU(32), input_shape=(None, float_data.shape[-1])))
 model.add(layers.Dense(1))
 
 model.compile(optimizer=RMSprop(), loss='mae')
@@ -166,9 +162,14 @@ def generator(data, lookback, delay, min_index, max_index, shuffle=False, batch_
                               validation_steps=val_steps)
 '''
 
-# 使用一个双向的GRU模型
+# 使用一个正则化后多层的GRU模型
 model = Sequential()
-model.add(layers.Bidirectional(layers.GRU(32), input_shape=(None, float_data.shape[-1])))
+model.add(layers.GRU(32,
+                     dropout=0.1,
+                     recurrent_dropout=0.5,
+                     return_sequences=True,
+                     input_shape=(None, float_data.shape[-1])))
+model.add(layers.GRU(64, activation='relu', dropout=0.1, recurrent_dropout=0.5))
 model.add(layers.Dense(1))
 
 model.compile(optimizer=RMSprop(), loss='mae')

chapter6/temperature_forecast_conv1d_gru.py

@@ -0,0 +1,160 @@
+import os
+
+import numpy as np
+from keras import layers
+from keras.models import Sequential
+from keras.optimizers import RMSprop
+from matplotlib import pyplot as plt
+
+data_dir = ''
+fname = os.path.join(data_dir, 'jena_climate_2009_2016.csv')
+
+f = open(fname)
+data = f.read()
+f.close()
+
+lines = data.split('\n')
+header = lines[0].split(',')
+lines = lines[1:]
+
+print(header)
+print(len(lines))
+
+# 解析数据
+float_data = np.zeros((len(lines), len(header) - 1))
+for i, line in enumerate(lines):
+    values = [float(x) for x in line.split(',')[1:]]
+    float_data[i, :] = values
+
+# 画出温度序列
+temp = float_data[:, 1]  # 温度序列
+plt.plot(range(len(temp)), temp)
+plt.show()
+
+# 画出前10天的温度序列
+plt.plot(range(1440), temp[:1440])
+plt.show()
+
+# 把前200000个序列作为训练数据,正规化
+mean = float_data[:200000].mean(axis=0)
+float_data -= mean
+std = float_data[:200000].std(axis=0)
+float_data /= std
+
+
+# 定义一个生成序列样本和目标序列的生成器
+# data：正则化后的原始数据
+# lookback：往前看多少步
+# delay：往后看第多少步
+# min_index和max_index：限制序列的选择区间
+# shuffle：是否打乱数据
+# batch_size：每个样本多少数据
+# step：多少一个周期，设置为6表示一小时一个数据点
+def generator(data, lookback, delay, min_index, max_index, shuffle=False, batch_size=128, step=6):
+    if max_index is None:
+        max_index = len(data) - delay - 1
+    i = min_index + lookback
+    while 1:
+        if shuffle:
+            rows = np.random.randint(min_index + lookback, max_index, size=batch_size)
+        else:
+            if i + batch_size >= max_index:
+                i = min_index + lookback
+            rows = np.arange(i, min(i + batch_size, max_index))
+            i += len(rows)
+
+        samples = np.zeros((len(rows), lookback // step, data.shape[-1]))
+        targets = np.zeros((len(rows),))
+        for j, row in enumerate(rows):
+            indices = range(rows[j] - lookback, rows[j], step)
+            samples[j] = data[indices]
+            targets[j] = data[rows[j] + delay][1]
+        yield samples, targets
+
+
+# 准备训练、验证和测试数据生成器
+lookback = 720
+step = 3
+delay = 144
+batch_size = 128
+
+train_gen = generator(float_data,
+                      lookback=lookback,
+                      delay=delay,
+                      min_index=0,
+                      max_index=200000,
+                      shuffle=True,
+                      step=step,
+                      batch_size=batch_size)
+val_gen = generator(float_data,
+                    lookback=lookback,
+                    delay=delay,
+                    min_index=200001,
+                    max_index=300000,
+                    shuffle=True,
+                    step=step,
+                    batch_size=batch_size)
+test_gen = generator(float_data,
+                     lookback=lookback,
+                     delay=delay,
+                     min_index=300001,
+                     max_index=None,
+                     shuffle=True,
+                     step=step,
+                     batch_size=batch_size)
+
+# 看到所有验证数据需要生成的次数
+val_steps = (300000 - 200001 - lookback) // batch_size
+
+# 看到所有测试数据需要生成的次数
+test_steps = (len(float_data) - 300001 - lookback) // batch_size
+
+'''
+# 使用一个一维卷积层和GRU层结合的模型
+model = Sequential()
+model.add(layers.Conv1D(32, 5, activation='relu',
+                        input_shape=(None, float_data.shape[-1])))
+model.add(layers.MaxPooling1D(3))
+model.add(layers.Conv1D(32, 5, activation='relu'))
+model.add(layers.GRU(32, dropout=0.1, recurrent_dropout=0.5))
+model.add(layers.Dense(1))
+
+model.compile(optimizer=RMSprop(), loss='mae')
+history = model.fit_generator(train_gen, steps_per_epoch=500,
+                              epochs=40,
+                              validation_data=val_gen,
+                              validation_steps=val_steps)
+'''
+
+# 使用简单一维卷积层的模型
+model = Sequential()
+model.add(layers.Conv1D(32, 5, activation='relu',
+                        input_shape=(None, float_data.shape[-1])))
+model.add(layers.MaxPooling1D(3))
+model.add(layers.Conv1D(32, 5, activation='relu'))
+model.add(layers.MaxPooling1D(3))
+model.add(layers.Conv1D(32, 5, activation='relu'))
+model.add(layers.GlobalMaxPool1D())
+model.add(layers.Dense(1))
+
+model.compile(optimizer=RMSprop(), loss='mae')
+history = model.fit_generator(train_gen, steps_per_epoch=500,
+                              epochs=40,
+                              validation_data=val_gen,
+                              validation_steps=val_steps)
+
+# 画出训练过程中损失函数值的变化曲线
+loss = history.history['loss']
+val_loss = history.history['val_loss']
+
+epochs = range(1, len(loss) + 1)
+
+plt.figure()
+
+plt.plot(epochs, loss, 'bo', label='Training loss')
+plt.plot(epochs, val_loss, 'b', label='Validation loss')
+plt.title('Training and validation loss')
+plt.legend()
+
+plt.show()
+print('end')