Datasets
Models
Downloads: 1
34 lines (34 with data), 4.2 kB
K¸ýYů Ń @ sČ d Z d d l m Z m Z m Z d d l Z d d l Z d d l m Z e d â Z
e d â Z d Z d Z
d g Z d Z d
Z d Z d Z d Z Gd
d ä d â Z d S)zT It reads and parses the variables, then it generate features, in threaded batches.
Ú )┌List┌TypeVar┌DictN)┌itemfreq┌ DataFrame┌ndarrayzMohsen Mesgarpourz-Copyright 2016, https://github.com/mesgarpour┌GPLz1.1zmohsen.mesgarpour@gmail.com┌Releasec @ sU e Z d Z e e e e e e d d d É ä â Z e e e d d d É ä â Z d S)┌FeatureParserThread)┌ postfixes┌
variable_type┌
prevalence┌
variable_cell┌returnc C s¨ t j t | â g â } | d k s0 | d k r4 | S| j d â } d d ä | Dâ } d d ä | Dâ } | d k rŐ t t t | â â } t | â } t j d d ä | Dâ d d d g â} t j | d
d d
g âd d d ů d
} t
t t t | d
â | d â â } xÔt
t | â â D]╬} t | | â d k r┐| | d d ů d k r┐t | | j d â d â d } | t | â k r˝| | }
t |
â | j â k r˝| |
| | <q#t | | â d k r0| | d d ů d k r0t | | d d ů â d } t | â | k r˝| | | | <q#| | d k rSt | â | | <q#| | d k rvt | â | | <q#| | d k rťt j | â | | <q#| | d k r┐t | â | | <q#| | d k rňt j | â | | <q#t | â é q#W| S) aŁ Aggregate the variable value, based on the selected aggregated functions.
:param postfixes: the aggregated variable.
:param variable_type: the type of the input variable.
:param prevalence: the prevalence dictionary of values for all the variables.
:param variable_cell: the variable value (a single row) to aggregate.
:return: the aggregated value (a single row).
N┌ ˙|c S s2 g | ]( } t | j d â â D] } | Ĺ q q S)˙,)┌set┌split)┌.0┌v1┌v2ę r ˙TC:\Users\eagle\Documents\GitHub\Analytics_UoW\TCARER\Features\FeatureParserThread.py˙
<listcomp>> s z6FeatureParserThread.aggregate_cell.<locals>.<listcomp>c S s( g | ] } | d k r | n d Ĺ q S)r r r )r ┌vr r r r ? s ┌INTc S s, g | ]" } | d d k r t | â Ĺ q S)Ú r )┌tuple)r ┌rowr r r r E s ┌dtype┌value┌int┌freq┌orderr Ú r ┌ prevalence_┌_Ú Z max_freq_Z
others_cnt┌max┌avg┌min┌median)r! r" )r# r" Ú )┌np┌zeros┌lenr ┌list┌mapr" r ┌array┌sort┌dict┌zip┌str┌range┌keysr) ┌
statistics┌meanr+ r, ┌
ValueError) r r r
r ┌
features_tempr# Z freq_sortedZfreq_dic┌p┌indexr! r r r ┌aggregate_cell) sF (,&0!
0 z"FeatureParserThread.aggregate_cell)r r c C sn | d k s | d k r g S| j d â } d d ä | Dâ } d d ä | Dâ } t t t | â â } | Sd S)z´Parse the inputted variable value (a single row), to a list of value.
:param variable_cell: the variable value (a single row), to calculate the prevalence.
:return: the list of values of the current variable value.
Nr r c S s2 g | ]( } t | j d â â D] } | Ĺ q q S)r )r r )r r r r r r r p s z7FeatureParserThread.prevalence_cell.<locals>.<listcomp>c S s( g | ] } | d k r | n d Ĺ q S)r r r )r r r r r r q s )r r1 r2 r7 )r r r r ┌prevalence_cellc s z#FeatureParserThread.prevalence_cellN)
┌__name__┌
__module__┌ __qualname__┌ staticmethodr7 r ┌ NumpyNdarrayr@ r rA r r r r r
' s 6r
)┌__doc__┌typingr r r ┌numpyr. r: ┌ scipy.statsr ┌PandasDataFramerF ┌
__author__┌
__copyright__┌ __credits__┌ __license__┌ __version__┌__maintainer__┌ __email__┌
__status__r
r r r r ┌<module> s