def select_pred_words_effectiveness(self, numWords=None):
assert self.resp_words is not None
# Add Predictive Words
if self._pred_data_tickers is None:
self.__add_pred_data_tickers()
self.create_data_sorting_array()
# Select How Many Words
if numWords is None:
numWords = geometric(PRED_COUNT_GEOMETRIC_PARAM) + PRED_COUNT_FLOOR
# Select Words
count = 0
chosen = {}
resp_word_names = [str(w) for w in self.resp_words]
min_date = max([w.min_date for w in self.resp_words])
max_date = min([w.max_date for w in self.resp_words])
while (len(chosen) < numWords) and (count < numWords * 10):
count += 1 # Avoid Infinite Loops
# Select Words / Create Data Handle
id_ = weighted_choice(self._pred_data_eff_array["prob"].iteritems(), self._total_prob)
ticker = retrieve_DataSeriesTicker(self.hndl_DB.cursor, id_)
hndl_Data = EMF_DataSeries_Handle(self.hndl_DB, ticker=ticker)
# Select Words / Create Trans Handle
hndl_Trns = EMF_Transformation_Handle(choice(self._pred_trns_ptrns))
# Select Words / Create Trans Handle / Add Parameters to Trans Handle
hndl_Trns.parameters = self.__create_random_trns_params_pred()
# Select Words / Create Word Handle
hndl_Word = EMF_WordSeries_Handle(self.hndl_DB, hndl_Data, hndl_Trns)
# Select Words / Ensure Word Validity
# Select Words / Ensure Word Validity / Make sure Word Isn't Response Word
wordName = str(hndl_Word)
if wordName in resp_word_names:
continue
# Select Words / Ensure Word Validity / Make sure Word Isn't Already Taken
if wordName in chosen:
continue
# Select Words / Ensure Word Validity / Make sure Dates Don't Conflict
min_challenger = hndl_Word.min_date
if min_challenger >= max_date:
continue
max_challenger = hndl_Word.max_date
if max_challenger <= min_date:
continue
min_date = max(min_date, min_challenger)
max_date = min(max_date, max_challenger)
# Select Words / Add Word to Set
chosen[wordName] = hndl_Word
log.info("WORDSELECT: Predictive Words: Chose {0}".format(wordName)) # TEST: Delete
log.info("WORDSELECT: Predictive Words: Chose {0}".format(chosen.keys()))
self._pred_words = chosen.values()
return self.pred_words
def select_pred_words_random(self, numWords=None):
assert self.resp_words is not None
# Add Predictive Words
if self._pred_data_tickers is None:
self.__add_pred_data_tickers()
# Select How Many Words
if numWords is None:
numWords = geometric(PRED_COUNT_GEOMETRIC_PARAM) + PRED_COUNT_FLOOR
log.info("WORDSELECT: Predictive Words: Choosing {0} words".format(numWords))
# Select Words
count = 0
chosen = {}
resp_word_names = [
str(w) for w in self.resp_words
] # TODO: Can make this a one-time calculation to avoid repitition
min_date = max([w.min_date for w in self.resp_words])
max_date = min([w.max_date for w in self.resp_words])
while (len(chosen) < numWords) and (count < numWords * 10):
count += 1 # Avoid Infinite Loops
# Select Words / Create Data Handle
hndl_Data = EMF_DataSeries_Handle(self.hndl_DB, ticker=choice(self._pred_data_tickers))
# Select Words / Create Trans Handle
hndl_Trns = EMF_Transformation_Handle(choice(self._pred_trns_ptrns))
# Select Words / Create Trans Handle / Add Parameters to Trans Handle
hndl_Trns.parameters = self.__create_random_trns_params_pred()
# Select Words / Create Word Handle
hndl_Word = EMF_WordSeries_Handle(self.hndl_DB, hndl_Data, hndl_Trns)
# Select Words / Ensure Word Validity
# Select Words / Ensure Word Validity / Make sure Word Isn't Response Word
wordName = str(hndl_Word)
if wordName in resp_word_names:
continue
# Select Words / Ensure Word Validity / Make sure Word Isn't Already Taken
if wordName in chosen:
continue
# Select Words / Ensure Word Validity / Make sure Dates Don't Conflict
min_challenger = hndl_Word.min_date
if min_challenger >= max_date:
continue
max_challenger = hndl_Word.max_date
if max_challenger <= min_date:
continue
min_date = max(min_date, min_challenger)
max_date = min(max_date, max_challenger)
# Select Words / Add Word to Set
chosen[wordName] = hndl_Word
log.info("WORDSELECT: Predictive Words: Chose {0}".format(chosen.keys()))
self._pred_words = chosen.values()
return self.pred_words
def select_pred_words_random(self, numWords=None):
assert self._resp_word is not None
# Add Predictive Words
if self._pred_data_tickers is None:
self.__add_pred_data_tickers()
# Select How Many Words
if numWords is None:
numWords = geometric(PRED_COUNT_GEOMETRIC_PARAM) + PRED_COUNT_FLOOR
log.info('WORDSELECT: Predictive Words: Choosing {0} words'.format(numWords))
# Select Words
count = 0
chosen = {}
min_date = self.resp_data_min_date
if min_date is None: min_ = maxint
max_date = self.resp_data_max_date
if max_date is None: max_ = -maxint-1
while (len(chosen) < numWords) and (count < numWords*10):
count += 1 # Avoid Infinite Loops
# Select Words / Create Data Handle
ticker = choice(self._resp_data_tickers)
hndl_Data = EMF_DataSeries_Handle(self.hndl_DB, ticker=ticker)
# Select Words / Create Trans Handle
hndl_Trns = EMF_Transformation_Handle(choice(self._pred_trns_ptrns))
# Select Words / Create Trans Handle / Add Parameters to Trans Handle
hndl_Trns.parameters = self.__create_random_trns_params()
# Select Words / Create Word Handle
hndl_Word = EMF_WordSeries_Handle(self.hndl_DB, hndl_Data, hndl_Trns)
# Select Words / Ensure Word Validity
# Select Words / Ensure Word Validity / Make sure Word Isn't Response Word
wordName = str(hndl_Word)
if wordName == str(self._resp_word):
continue
# Select Words / Ensure Word Validity / Make sure Dates Don't Conflict
min_challenger = hndl_Word.min_date
if min_challenger >= max_date:
continue
max_challenger = hndl_Word.max_date
if max_challenger <= min_date:
continue
min_date = max(min_date, min_challenger)
max_date = min(max_date, max_challenger)
# Select Words / Add Word to Set
chosen[wordName] = hndl_Word
log.info('WORDSELECT: Predictive Words: Chose {0}'.format(wordName)) # TEST: Delete
log.info('WORDSELECT:Predictive Words: Chose {0}'.format(chosen.keys()))
self._pred_words = chosen.values()
return self.pred_words
def select_pred_words_all_tickers(self, trns_ptrn=None, trns_kwargs=None, trns_rndm=False):
self._pred_words = []
log.info('WORDSELECT: Predictive Words: Choosing All Data Tickers')
if trns_ptrn is None:
if trns_rndm:
ticker = choice(self._pred_data_tickers)
else:
trns_ptrn = 'None'
if self._pred_data_tickers is None:
self.__add_pred_data_tickers()
hndl_Trns = EMF_Transformation_Handle(trns_ptrn)
if trns_kwargs is None:
trns_kwargs = self.pred_trns_kwargs
hndl_Trns.parameters = self.__create_random_trns_params(kwargs_list=trns_kwargs)
log.info('WORDSELECT: Predictive Words: Chose {0} Transformation'.format(hndl_Trns))
for ticker in self._pred_data_tickers:
hndl_Data = EMF_DataSeries_Handle(self.hndl_DB, ticker=ticker)
hndl_Word = EMF_WordSeries_Handle(self.hndl_DB, hndl_Data, hndl_Trns)
self._pred_words.append(hndl_Word)
