bug fix: random shuffle improvements

data/maker/__init__.py

@@ -22,7 +22,7 @@ import nujson as json
 from multiprocessing import Process, RLock
 from datetime import datetime, timedelta
 from multiprocessing import Queue
-
+from version import __version__
 import time
 
 
@@ -179,6 +179,7 @@ class Learner(Process):
         for name in columns :
             #
             # randomly sampling 5 elements to make sense of data-types
+            
             if self._df[name].size < 5 :
                 continue
             _index = np.random.choice(np.arange(self._df[name].size),5,False)
@@ -552,27 +553,53 @@ class Shuffle(Generator):
     """
     def __init__(self,**_args):
         super().__init__(**_args)
+        if 'data' not in _args :
+            reader = transport.factory.instance(**self.store['source'])            
+            self._df = reader.read(sql=self.info['sql'])
+        
     def run(self):
         
         np.random.seed(1)
+        
         self.initalize()
-        _index = np.arange(self._df.shape[0])
-        np.random.shuffle(_index)
-        np.random.shuffle(_index)
-        _iocolumns = self.info['columns']
-        _ocolumns = list(set(self._df.columns) - set(_iocolumns) )
-        # _iodf = pd.DataFrame(self._df[_ocolumns],self._df.loc[_index][_iocolumns],index=np.arange(_index.size))
-        _iodf = pd.DataFrame(self._df[_iocolumns].copy(),index = np.arange(_index.size))
-        # self._df = self._df.loc[_index][_ocolumns].join(_iodf)
-        self._df = self._df.loc[_index][_ocolumns]
-        self._df.index = np.arange(self._df.shape[0])
-        self._df = self._df.join(_iodf)
         #
-        # The following is a full shuffle 
-        self._df = self._df.loc[_index]
-        self._df.index = np.arange(self._df.shape[0])
-        
+        # If we are given lists of columns instead of a list-of-list
+        #   unpack the list
+        _invColumns = []
+        _colNames = []
+        _ucolNames= []
+        for _item in self.info['columns'] :
+            if type(_item) == list :
+                _invColumns.append(_item)
+            elif _item in self._df.columns.tolist():
+                _colNames.append(_item)
+        #
+        # At this point we build the matrix of elements we are interested in considering the any unspecified column
+        #
+        if _colNames :
+            _invColumns.append(_colNames)
+        _ucolNames = list(set(self._df.columns) - set(_colNames))
+        if _ucolNames :
+            _invColumns += [ [_name] for _name in _ucolNames]
+
+        _xdf = pd.DataFrame()
+        _xdf = pd.DataFrame()
+        _index = np.arange(self._df.shape[0])
         
+        for _columns in _invColumns :
+            
+            _tmpdf = self._df[_columns].copy()[_columns]
+            np.random.shuffle(_index)
+            
+            _tmpdf = _tmpdf.iloc[_index]
+            
+            if _xdf.shape[0] == 0 :
+                _xdf = _tmpdf
+            else:
+                _xdf = _xdf.join(_tmpdf)
+
+        _xdf = _xdf[self._df.columns]            
+        self._df = _xdf
         _log = {'action':'io-data','input':{'candidates':1,'rows':int(self._df.shape[0])}}
         self.log(**_log)
         try:

data/maker/version.py

@@ -0,0 +1 @@
+__version__='1.7.0'

setup.py

@@ -1,10 +1,10 @@
 from setuptools import setup, find_packages
 import os
 import sys
-
+import version
 def read(fname):
     return open(os.path.join(os.path.dirname(__file__), fname)).read() 
-args = {"name":"data-maker","version":"1.6.8",
+args = {"name":"data-maker","version":version.__version__,
         "author":"Vanderbilt University Medical Center","author_email":"steve.l.nyemba@vumc.org","license":"MIT",
         "packages":find_packages(),"keywords":["healthcare","data","transport","protocol"]}
 args["install_requires"] = ['data-transport@git+https://github.com/lnyemba/data-transport.git','tensorflow']

version.py

@@ -0,0 +1 @@
+data/maker/version.py