本文展示了如何使用循环神经网络去估计一个向量序列,我们会使用到LSTM的网络。我在网上找的
大多数用到LSTM的例子都是用来解决自然语言处理方面问题的,还没有找到相关的例子可以用在预测连续
值序列上,所以写下了本文。
所以本文的任务是基于历史观察数据去预测一系列连续的实数。传统的神经网络做不到这一点,但是循环神经
网络可以解决该问题,因为他们能够存储历史信息来预测未来事件。
在下面的一个例子中我们将尝试预测一组函数sin、cos和x*sin(x).
首先让我们建立一个模型lstm_model, 这个模型是一系列不同时间步的lstm单元的堆叠,后接一个深层网络。
- def lstm_model(time_steps, rnn_layers, dense_layers=None):
- """
- Creates a deep model based on:
- * stacked lstm cells
- * an optional dense layers
- :param time_steps: the number of time steps the model will be looking at.
- :param rnn_layers: list of int or dict
- * list of int: the steps used to instantiate the `BasicLSTMCell` cell
- * list of dict: [{steps: int, keep_prob: int}, ...]
- :param dense_layers: list of nodes for each layer
- :return: the model definition
- """
- def lstm_cells(layers):
- if isinstance(layers[0], dict):
- return [tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.BasicLSTMCell(layer['steps'],
- state_is_tuple=True),
- layer['keep_prob'])
- if layer.get('keep_prob') else tf.nn.rnn_cell.BasicLSTMCell(layer['steps'],
- state_is_tuple=True)
- for layer in layers]
- return [tf.nn.rnn_cell.BasicLSTMCell(steps, state_is_tuple=True) for steps in layers]
- def dnn_layers(input_layers, layers):
- if layers and isinstance(layers, dict):
- return learn.ops.dnn(input_layers,
- layers['layers'],
- activation=layers.get('activation'),
- dropout=layers.get('dropout'))
- elif layers:
- return learn.ops.dnn(input_layers, layers)
- else:
- return input_layers
- def _lstm_model(X, y):
- stacked_lstm = tf.nn.rnn_cell.MultiRNNCell(lstm_cells(rnn_layers), state_is_tuple=True)
- x_ = learn.ops.split_squeeze(1, time_steps, X)
- output, layers = tf.nn.rnn(stacked_lstm, x_, dtype=dtypes.float32)
- output = dnn_layers(output[-1], dense_layers)
- return learn.models.linear_regression(output, y)
- return _lstm_model
所以我们的模型接收的数据维度应该是这样的:(batch size,time steps of the first lstm cell, num_features)
下一步要做的就是把我们的数据重整成模型可以接收的格式。
- def rnn_data(data, time_steps, labels=False):
- """
- creates new data frame based on previous observation
- * example:
- l = [1, 2, 3, 4, 5]
- time_steps = 2
- -> labels == False [[1, 2], [2, 3], [3, 4]]
- -> labels == True [2, 3, 4, 5]
- """
- rnn_df = []
- for i in range(len(data) - time_steps):
- if labels:
- try:
- rnn_df.append(data.iloc[i + time_steps].as_matrix())
- except AttributeError:
- rnn_df.append(data.iloc[i + time_steps])
- else:
- data_ = data.iloc[i: i + time_steps].as_matrix()
- rnn_df.append(data_ if len(data_.shape) > 1 else [[i] for i in data_])
- return np.array(rnn_df)
- def split_data(data, val_size=0.1, test_size=0.1):
- """
- splits data to training, validation and testing parts
- """
- ntest = int(round(len(data) * (1 - test_size)))
- nval = int(round(len(data.iloc[:ntest]) * (1 - val_size)))
- df_train, df_val, df_test = data.iloc[:nval], data.iloc[nval:ntest], data.iloc[ntest:]
- return df_train, df_val, df_test
- def prepare_data(data, time_steps, labels=False, val_size=0.1, test_size=0.1):
- """
- Given the number of `time_steps` and some data,
- prepares training, validation and test data for an lstm cell.
- """
- df_train, df_val, df_test = split_data(data, val_size, test_size)
- return (rnn_data(df_train, time_steps, labels=labels),
- rnn_data(df_val, time_steps, labels=labels),
- rnn_data(df_test, time_steps, labels=labels))
- def generate_data(fct, x, time_steps, seperate=False):
- """generates data with based on a function fct"""
- data = fct(x)
- if not isinstance(data, pd.DataFrame):
- data = pd.DataFrame(data)
- train_x, val_x, test_x = prepare_data(data['a'] if seperate else data, time_steps)
- train_y, val_y, test_y = prepare_data(data['b'] if seperate else data, time_steps, labels=True)
- return dict(train=train_x, val=val_x, test=test_x), dict(train=train_y, val=val_y, test=test_y)
是10个time steps的单元,那么每做一次预测,我们都需要输入10个历史数据点。我们想要预测的
数值应该和数据点里的第10个相关。
首先定义超参数
- LOG_DIR = './ops_logs'
- TIMESTEPS = 5
- RNN_LAYERS = [{'steps': TIMESTEPS}, {'steps': TIMESTEPS, 'keep_prob': 0.5}]
- DENSE_LAYERS = [2]
- TRAINING_STEPS = 130000
- BATCH_SIZE = 100
- PRINT_STEPS = TRAINING_STEPS / 100
现在可以建立一个回归模型
- regressor = learn.TensorFlowEstimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),
- n_classes=0,
- verbose=1,
- steps=TRAINING_STEPS,
- optimizer='Adagrad',
- learning_rate=0.03,
- batch_size=BATCH_SIZE)
预测sin函数
- X, y = generate_data(np.sin, np.linspace(0, 100, 10000), TIMESTEPS, seperate=False)
- # create a lstm instance and validation monitor
- validation_monitor = learn.monitors.ValidationMonitor(X['val'], y['val'],
- every_n_steps=PRINT_STEPS,
- early_stopping_rounds=1000)
- regressor.fit(X['train'], y['train'], validation_monitor, logdir=LOG_DIR)
- # > last training steps
- # Step #9700, epoch #119, avg. train loss: 0.00082, avg. val loss: 0.00084
- # Step #9800, epoch #120, avg. train loss: 0.00083, avg. val loss: 0.00082
- # Step #9900, epoch #122, avg. train loss: 0.00082, avg. val loss: 0.00082
- # Step #10000, epoch #123, avg. train loss: 0.00081, avg. val loss: 0.00081
- mse = mean_squared_error(regressor.predict(X['test']), y['test'])
- print ("Error: {}".format(mse))
- # 0.000776
- def sin_cos(x):
- return pd.DataFrame(dict(a=np.sin(x), b=np.cos(x)), index=x)
- X, y = generate_data(sin_cos, np.linspace(0, 100, 10000), TIMESTEPS, seperate=False)
- # create a lstm instance and validation monitor
- validation_monitor = learn.monitors.ValidationMonitor(X['val'], y['val'],
- every_n_steps=PRINT_STEPS,
- early_stopping_rounds=1000)
- regressor.fit(X['train'], y['train'], validation_monitor, logdir=LOG_DIR)
- # > last training steps
- # Step #9500, epoch #117, avg. train loss: 0.00120, avg. val loss: 0.00118
- # Step #9600, epoch #118, avg. train loss: 0.00121, avg. val loss: 0.00118
- # Step #9700, epoch #119, avg. train loss: 0.00118, avg. val loss: 0.00118
- # Step #9800, epoch #120, avg. train loss: 0.00118, avg. val loss: 0.00116
- # Step #9900, epoch #122, avg. train loss: 0.00118, avg. val loss: 0.00115
- # Step #10000, epoch #123, avg. train loss: 0.00117, avg. val loss: 0.00115
- mse = mean_squared_error(regressor.predict(X['test']), y['test'])
- print ("Error: {}".format(mse))
- # 0.001144
还有一个x*sinx的就不玩了,下面贴出英文原文
http://mourafiq.com/2016/05/15/predicting-sequences-using-rnn-in-tensorflow.html