data-maker/data/maker/__init__.py

"""
(c) 2019 Data Maker, hiplab.mc.vanderbilt.edu
version 1.0.0

This package serves as a proxy to the overall usage of the framework.
This package is designed to generate synthetic data from a dataset from an original dataset using deep learning techniques

@TODO:
    - Make configurable GPU, EPOCHS
"""
import pandas as pd
import numpy as np
    ROUND_UP = 2
        # _BINARY= ContinuousToDiscrete.binary(X,BIN_SIZE)
        # This 
    if 'gpu' in _args :
        # f = open(os.sep.join([_args['logs'],'output',_args['context'],'map.json']))
        lparams['partition'] = partition
        # self.logpath= _args['logpath'] if 'logpath' in _args else 'logs'
        writer.write(self._encoder._map,overwrite=True)
        writer.close()

        #
        # @TODO: At this point we need to generate another some other objects
        #
        _args = {"network_args":self.network_args,"store":self.store,"info":self.info,"candidates":self.candidates,"data":self._df}
        if self.gpu :
            _args['gpu'] = self.gpu
        g = Generator(**_args)
        # g.run() 
        self.generate = g
        if self.autopilot :
            self.generate.run()
    def generate (self):
        if self.autopilot :
            print( "Autopilot is set ... No need to call this function")
        else:
            raise Exception( "Autopilot has not been, Wait till training is finished. Use is_alive function on process object")

class Generator (Learner):
    def __init__(self,**_args):
        super().__init__(**_args)
        #
        # We need to load the mapping information for the space we are working with ...
        #
        self.network_args['candidates'] = int(_args['candidates']) if 'candidates' in _args else 1
        filename = os.sep.join([self.network_args['logs'],'output',self.network_args['context'],'map.json'])
        file = open(filename)
        self._map = json.loads(file.read())
        file.close()
    def run(self):
        self.initalize()
        #
        # The values will be returned because we have provided _map information from the constructor
        #
        values,_matrix = self._encoder.convert()
        _args = self.network_args
        _args['map'] = self._map
        _args['values'] = np.array(values)
        _args['row_count'] = self._df.shape[0]
        
        gHandler = gan.Predict(**_args)
        gHandler.load_meta(columns=None)
        _iomatrix = gHandler.apply()
        _candidates= [ self._encoder.revert(matrix=_item) for _item in _iomatrix]
        self.post(_candidates)
    def appriximate(self,_df):
        _columns = self.info['approximate']
        _schema = {}
        for _info in self.get_schema() :
            _schema[_info['name']] = _info['type']

        
        for name in _columns :
            batches = np.array_split(_df[name].values,10)
            x = []
            for values in batches :
                _values = np.random.dirichlet(values)
                x += list(values + _values )if np.random.randint(0,2) else list(values - _values)
            _df[name] = np.int64(x) if 'int' in _schema[name] else np.float64(x)
        return _df
    def format(self,_df):
        pass
    def post(self,_candidates):
        
        _store = self.store['target'] if 'target' in self.store else {'provider':'console'}
        _store['lock'] = True
        writer = transport.factory.instance(**_store)
       
        for _iodf in _candidates :
            _df = self._df.copy()
            _df[self.columns] = _iodf[self.columns]
            if 'approximate' in self.info :
                
                _df = self.appriximate(_df)
            writer.write(_df,schema=self.get_schema())
        pass
class factory :
    _infocache = {}
    @staticmethod
    def instance(**_args):
        """
        An instance of an object that trains and generates candidate datasets
        :param gpu (optional)         index of the gpu to be used if using one
        :param store                  {source,target} if no target is provided console will be output
        :param epochs (default 2)     number of epochs to train
        :param candidates(default 1)  number of candidates to generate
        :param info             {columns,sql,from}
        :param autopilot        will generate output automatically
        :param batch (default 2k)           size of the batch
        """
        return Trainer(**_args)