Dev

.gitignore

@@ -12,3 +12,4 @@ RLA.egg-info**
 **/.ipynb_checkpoints/*
 **/.DS_Store
 test/target_data_root/*
+**/private_config.py

README.md

@@ -46,7 +46,7 @@ Currently, we store the data items in standard file systems and manage the relat
 - The directory "code" is a backup of code for experiment reproducibility.
 - The directory "checkpoint" save weights of neural networks.
 - We have a table named "demo_task", which is the root directory of log/archive_tester/checkpoint/code/results. 
-- The "index" of experiments in named in the formulation of `${%Y}/${%m}/${%d}/${%H-%M-%S-%f} ${ip address} ${tracked hyper-parameters}`.
+- The "index" of experiments in named in the formulation of `${%Y}/${%m}/${%d}/${%H-%M-%S-%f}_${ip address}_${tracked hyper-parameters}`.
 
 
 ### Tools to Manage the Database
@@ -226,21 +226,24 @@ In practice, we might conduct our experiments in multiple physical machines for
 ```
 SEND_LOG_FILE: True
 REMOTE_SETTING:
-  ftp_server: ''
-  username: ''
-  password: ''
-  remote_data_root: ''
+  ftp_server: '114.114.114.114'
+  username: 'agent'
+  password: '123'
+  remote_data_root: 'remote_project/data_root/'
+  file_transfer_protocol: 'sftp'
 ```
-where we set `SEND_LOG_FILE` to True and `ftp_server`, `username` and `password` are the ip address, username and passward of the master node.  `remote_data_root` define the data_root of the database in the main node. For the main node, just keep `SEND_LOG_FILE` to False. In our experiment code, we should call the function `RLA.easy_log.tester.exp_manager.sync_log_file` periodically, then the data items we be sent to the `remote_data_root`  of the main node. For example, 
+where `SEND_LOG_FILE` is set to True,  `ftp_server`, `username` and `password` are the ip address, username and passward of the master node respectively, and `file_transfer_protocol` is the protocol to send data.  `remote_data_root` defines the data_root of the database in the main node. 
+For the main node, configure the exp_manger by `exp_manager.configure(..., is_master_node=True)`. 
+In our experiment code, we should call the function `RLA.easy_log.tester.exp_manager.sync_log_file` periodically, for example, 
 ```
 for i in range(1000):
     # your trianing code.
     exp_manager.sync_log_file()
 ```
-Since `SEND_LOG_FILE` is set to False in the main node, the `exp_manager.sync_log_file()` will be skipped in the main node.
+then the data items we be sent to the `remote_data_root`  of the main node. Since `SEND_LOG_FILE` is set to False in the main node, the `exp_manager.sync_log_file()` will be skipped in the main node.
 
 PS: 
-1. You might meet "socket.error: [Errno 111] Connection refused" problem in this process. The solution can be found [here](https://stackoverflow.com/questions/16428401/unable-to-use-ip-address-with-ftplib-python).
+1. You might meet "socket.error: [Errno 111] Connection refused" problem in this process. The solution can be found [here](https://stackoverflow.com/a/70784201/6055868).
 
 2. An alternative way is building your own NFS for your physical machines and locate data_root to the NFS.
 
@@ -251,3 +254,4 @@ PS:
 - [ ] add comments and documents to the functions.
 - [ ] add an auto integration script.
 - [ ] download / upload experiment logs through timestamp.
+- [ ] add a document to the plot function.

RLA/auto_ftp.py

@@ -3,10 +3,20 @@
 import shutil
 import os
 import traceback
+from RLA.const import *
 from RLA.easy_log import logger
 
 import pysftp
 
+
+def ftp_factory(name, server, username, password, ignore=None):
+    if name == FTP_PROTOCOL_NAME.FTP:
+        return FTPHandler(ftp_server=server, username=username,password=password, ignore=ignore)
+    elif name == FTP_PROTOCOL_NAME.SFTP:
+        return SFTPHandler(sftp_server=server, username=username, password=password, ignore=ignore)
+    else:
+        raise NotImplementedError
+
 class FTPHandler(object):
 
     def __init__(self, ftp_server, username, password, ignore=None):
@@ -193,17 +203,18 @@ def upload_file(self, remote_dir, local_dir, local_file):
                 raise expection
             logger.warn('create dir succeed {}'.format(remote_dir))
             self.sftp.cwd(remote_dir)
-        self.sftp.put(local_dir + local_file)
+        self.sftp.put(os.path.join(local_dir, local_file))
         self.close()
 
     def download_file(self, remote_file, local_file):
+        self.sftp = self.sftpconnect()
         logger.info("try download {}".format(local_file))
         if not os.path.isfile(local_file):
             logger.info("new file {}".format(local_file))
-            self.sftp.get(remote_file)
+            self.sftp.get(remote_file, local_file)
         elif self.sftp.stat(remote_file).st_size != os.path.getsize(local_file):
             logger.info("update file {}".format(local_file))
-            self.sftp.get(remote_file)
+            self.sftp.get(remote_file, local_file)
         else:
             logger.info("skip download file {}".format(remote_file))
 

RLA/const.py

@@ -2,4 +2,8 @@
 
 class FRAMEWORK:
     tensorflow = 'tensorflow'
-    torch = 'torch'
+    torch = 'torch'
+
+class FTP_PROTOCOL_NAME:
+    FTP = 'ftp'
+    SFTP = 'sftp'

RLA/easy_log/complex_data_recorder.py

@@ -7,6 +7,7 @@
 import matplotlib.pyplot as plt
 from RLA.easy_log.tester import exp_manager
 from RLA.easy_log.time_step import time_step_holder
+from typing import Callable
 # video recorder
 
 
@@ -27,8 +28,35 @@ def save(cls, name=None, fig=None, cover=False, add_timestamp=True, **kwargs):
                 plt.savefig(save_path, **kwargs)
 
     @classmethod
-    def pretty_plot_wrapper(cls, name, plot_func, cover=False, legend_outside=False, xlabel='', ylabel='', title='',
+    def pretty_plot_wrapper(cls, name:str, plot_func:Callable,
+                            cover=False, legend_outside=False, xlabel='', ylabel='', title='',
                             add_timestamp=True, *args, **kwargs):
+        """
+        Save the customized plot figure to the RLA database.
+
+        :param name:  file name to save.
+        :type name: str
+        :param plot_func: the function to plot figures
+        :type plot_func: function
+        :param cover: if you would like to cover the original figure with the same name, you can set cover to True
+        :type cover: bool
+        :param legend_outside: let legend be outside of the figure.
+        :type legend_outside: bool
+        :param xlabel: name of xlabel
+        :type xlabel: str
+        :param ylabel: name of xlabel
+        :type ylabel: str
+        :param title: title of the plotted figure
+        :type title: str
+        :param add_timestamp: add the timestamp (recorded by the timestep holder) to the name.
+        :type add_timestamp:  str
+        :param args: other parameters to plt.savefig
+        :type args:
+        :param kwargs:  other parameters to plt.savefig
+        :type kwargs:
+        :return:
+        :rtype:
+        """
         plt.cla()
         plot_func()
         lgd = plt.legend(prop={'size': 15}, loc=2 if legend_outside else None,