update docs

Author: LongxingTan

.gitignore

@@ -18,4 +18,5 @@ MYIDEA.md
 **/.ipynb_checkpoints/
 /examples/data/crawer_data.py
 /reference/*
-/models/*
+/models/variables/*
+/data/*

README.md

@@ -1,9 +1,10 @@
 # Time series prediction
 This repo implements the common methods of time series prediction, especially deep learning methods in TensorFlow2. 
-It's highly welcomed to contribute if you have better idea, just create a PR. If any question, feel free to open an issue.
+It's highly welcomed to contribute if you have any better idea, just create a PR. If any question, feel free to open an issue.
 
+#### Ongoing project, welcome to join
 
-<table style="width:100%">
+<table style="width:100%" align="center">
   <tr>
     <th>
       <p align="center">
@@ -14,6 +15,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
            <a href="./docs/arima.md" name="introduction">intro</a>             
       </p>
+     </th>
+    <th>
        <p align="center">           
            <a href="./deepts/models/arima.py" name="code">code</a>     
       </p>
@@ -28,7 +31,9 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
     <th>
       <p align="center">
         <a href="./docs/tree.md" name="introduction">intro</a> 
-      </p>   
+      </p>
+    </th>
+    <th>   
       <p align="center">
            <a href="./deepts/models/tree.py" name="code">code</a>     
       </p>
@@ -44,6 +49,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
            <a href="./docs/rnn.md" name="introduction">intro</a>      
       </p>
+    </th>
+    <th>
       <p align="center">
            <a href="./deepts/models/seq2seq.py" name="code">code</a>     
       </p>
@@ -59,6 +66,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
            <a href="./docs/wavenet.md" name="introduction">intro</a>      
       </p>
+    </th>
+    <th>
       <p align="center">
            <a href="./deepts/models/wavenet.py" name="code">code</a>     
       </p>
@@ -73,7 +82,9 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
     <th>
       <p align="center">
            <a href="./docs/transformer.md" name="introduction">intro</a>              
-      </p>    
+      </p>   
+    </th>
+    <th> 
       <p align="center">
            <a href="./deepts/models/transformer.py" name="code">code</a>     
       </p>      
@@ -89,6 +100,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
            <a href="./docs/unet.md" name="introduction">intro</a>     
       </p>
+    </th>
+    <th>
       <p align="center">
            <a href="./deepts/models/unet.py" name="code">code</a>     
       </p>      
@@ -104,6 +117,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
             <a href="./docs/nbeats.md" name="introduction">intro</a>     
       </p>
+    </th>
+    <th>
       <p align="center">
            <a href="./deepts/models/nbeats.py" name="code">code</a>     
       </p>      
@@ -119,6 +134,8 @@ It's highly welcomed to contribute if you have better idea, just create a PR. If
       <p align="center">
            <a href="./docs/gan.md" name="introduction">intro</a>      
       </p>
+    </th>
+    <th>
       <p align="center">
            <a href="./deepts/models/gan.py" name="code">code</a>     
       </p>      
@@ -136,7 +153,7 @@ pip install -r requirements.txt
 ```bash
 bash ./data/download_passenger.sh
 ```
-3. Train the model, set `custom_model_params` if you want
+3. Train the model, set `custom_model_params` if you want, and pay attention to your own feature engineering
 ```bash
 cd examples
 python run_train.py --use_model seq2seq
@@ -147,7 +164,9 @@ python run_test.py
 ```
 
 ## Further reading
-https://github.com/awslabs/gluon-ts/
+- https://github.com/awslabs/gluon-ts/
+- https://github.com/Azure/DeepLearningForTimeSeriesForecasting
 
 ## Contributor
 - [LongxingTan](https://longxingtan.github.io/)
+

deepts/layers/__init__.py

@@ -0,0 +1 @@
+#encodeing=utf-8

deepts/layers/attention_layer.py

@@ -215,7 +215,9 @@ def build(self,input_shape):
         super(PositionEncoding,self).build(input_shape)
 
     def get_config(self):
-        pass
+        return {
+            'max_len': self.max_len
+        }
 
     def call(self,x,masking=True):
         E = x.get_shape().as_list()[-1]  # static

deepts/layers/rnn_layer.py

@@ -9,4 +9,4 @@
 
 class RNNLayer(Layer):
     def __init__(self):
-        super(RNNLayer,self).__init__()
+        super(RNNLayer,self).__init__()

deepts/model.py

@@ -11,7 +11,7 @@
 from deepts.models.unet import Unet
 from deepts.models.nbeats import NBeatsNet
 from deepts.models.gan import GAN
-assert tf.__version__>"2.0.0"
+assert tf.__version__>"2.0.0", "Should you consider to use TensorFlow 2?"
 
 
 class Loss(object):
@@ -29,11 +29,11 @@ class Optimizer(object):
     def __init__(self,use_optimizer):
         self.use_optimizer=use_optimizer
 
-    def __call__(self,):
+    def __call__(self,learning_rate):
         if self.use_optimizer == 'adam':
-            return tf.keras.optimizers.Adam(lr=0.001)
+            return tf.keras.optimizers.Adam(lr=learning_rate)
         elif self.use_optimizer == 'sgd':
-            return tf.keras.optimizers.SGD(lr=0.001)
+            return tf.keras.optimizers.SGD(lr=learning_rate)
 
 
 class Model(object):
@@ -66,7 +66,7 @@ def __init__(self,params, use_model, use_loss='mse',use_optimizer='adam', custom
         self.use_loss = use_loss
         self.use_optimizer = use_optimizer
         self.loss_fn = Loss(use_loss)()
-        self.optimizer_fn = Optimizer(use_optimizer)()
+        self.optimizer_fn = Optimizer(use_optimizer)(learning_rate=params['learning_rate'])
         self.model = tf.keras.Model(inputs, outputs, name=use_model)
 
     def train(self, dataset, n_epochs, mode='eager', export_model=False):
@@ -105,25 +105,41 @@ def train_step(self, x, y):
 
     def eval(self, valid_dataset):
         for step,(x,y) in enumerate(valid_dataset.take(-1)):
-            metrics=self.test_step(x,y)
+            metrics=self.dev_step(x,y)
             print("=> STEP %4d Metrics: %4.2f"%(step, metrics))
 
-    def test_step(self, x, y):
+    def dev_step(self, x, y):
+        '''
+        evaluation step function
+        :param x:
+        :param y:
+        :return:
+        '''
         x=tf.cast(x, tf.float32)
         y=tf.cast(y, tf.float32)
-        y_pred=self.model(x,training=False)
+        try:
+            y_pred=self.model(x,training=False)
+        except:
+            y_pred=self.model((x,tf.ones([tf.shape(x)[0],self.params['output_seq_length'],1],tf.float32)))
         metrics=self.loss_fn(y, y_pred).numpy()
         return metrics
 
     def predict(self, x_test, model_dir, use_model='pb'):
+        '''
+        predict function, don't use self.model here, but saved checkpoint or pb
+        :param x_test:
+        :param model_dir:
+        :param use_model:
+        :return:
+        '''
         if use_model=='pb':
             print('Load saved pb model ...')
             model=tf.saved_model.load(model_dir)
         else:
             print('Load checkpoint model ...')
             model=self.model.load_weights(model_dir)
 
-        y_pred=model(tf.constant(x_test),True,None)  # To be clarified
+        y_pred=model(x_test,True,None)  # To be clarified, not sure why additional args are necessary here
         return y_pred
 
     def export_model(self):

deepts/models/tft.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 # @author: Longxing Tan, [email protected]
-# @date: 2020-05
+# @date: 2020-06
 # paper: https://arxiv.org/pdf/1912.09363v1.pdf
 # other implementations: https://github.com/google-research/google-research/blob/master/tft/libs/tft_model.py
 

deepts/models/transformer.py

@@ -3,6 +3,7 @@
 # @date: 2020-01
 # paper:
 # other implementations: https://github.com/maxjcohen/transformer
+#                        https://github.com/Trigram19/m5-python-starter
 
 
 import tensorflow as tf

deepts/models/wavenet.py

@@ -9,7 +9,6 @@
 import tensorflow as tf
 from tensorflow.keras.layers import Dense
 from deepts.layers.wavenet_layer import Dense3D, ConvTime
-#tf.config.experimental_run_functions_eagerly(True)  # ??
 
 
 params={

docs/arima.md

@@ -2,7 +2,7 @@
 
 
 ## Introduction
-ARIMA is a short for "Autoregressive Integrated Moving Average model", it's a traditional time-series-prediction model. Basically it's a linear model combined the auto regression model and moving average model.
+ARIMA is a short for "Auto-regressive Integrated Moving Average model", it's a traditional time-series-prediction model. Basically it's a linear model combined the auto regression model and moving average model.
 - Auto regression model is a linear regression model using the history data as its feature. The important hyper parameter is how many days from history are used.
 - Moving average model is a linear regression model using the history residual error as its feature. The important hyper parameter is also history data length.
 - arima