how can ı affect on some attributes?because some of attributes more important than others

User: "Selim"

New Altair Community Member

Updated Nov 5, 2024 by Jocelyn

ı did clustering(k-mean) in my process and now ı want to affect on some attributes .ı used to generate attribute but it is looking lıke doesnt affect to attributes.so what ı need to do ? which way or operator gonna make it work ?
ı shared xml
thanks
-------------------

<?xml version="1.0" encoding="UTF-8"?><process version="9.2.001">

<context>

<input/>

<output/>

<macros/>

</context>

<operator activated="true" class="process" compatibility="9.2.001" expanded="true" name="Process">

<parameter key="logverbosity" value="init"/>

<parameter key="random_seed" value="2001"/>

<parameter key="send_mail" value="never"/>

<parameter key="notification_email" value=""/>

<parameter key="process_duration_for_mail" value="30"/>

<parameter key="encoding" value="SYSTEM"/>

<process expanded="true">

<operator activated="true" class="read_excel" compatibility="9.2.001" expanded="true" height="68" name="Read Excel" width="90" x="45" y="85">

<parameter key="excel_file" value="C:\Users\selimcelebi\Desktop\k-means.xlsx"/>

<parameter key="sheet_selection" value="sheet number"/>

<parameter key="sheet_number" value="1"/>

<parameter key="imported_cell_range" value="F1:J36"/>

<parameter key="encoding" value="SYSTEM"/>

<parameter key="first_row_as_names" value="true"/>

<list key="annotations"/>

<parameter key="date_format" value=""/>

<parameter key="time_zone" value="SYSTEM"/>

<parameter key="locale" value="English (United States)"/>

<parameter key="read_all_values_as_polynominal" value="false"/>

<list key="data_set_meta_data_information">

<parameter key="0" value="ürün ID.true.integer.attribute"/>

<parameter key="1" value="hacim.true.integer.attribute"/>

<parameter key="2" value="satış miktarı.true.integer.attribute"/>

<parameter key="3" value="ağırlık.true.real.attribute"/>

<parameter key="4" value="kırılganlık.true.polynominal.attribute"/>

</list>

<parameter key="read_not_matching_values_as_missings" value="false"/>

<parameter key="datamanagement" value="double_array"/>

<parameter key="data_management" value="auto"/>

</operator>

<operator activated="true" class="set_role" compatibility="9.2.001" expanded="true" height="82" name="Set Role" width="90" x="179" y="85">

<parameter key="attribute_name" value="ürün ID"/>

<parameter key="target_role" value="id"/>

<list key="set_additional_roles"/>

</operator>

<operator activated="true" class="nominal_to_numerical" compatibility="9.2.001" expanded="true" height="103" name="Nominal to Numerical" width="90" x="313" y="85">

<parameter key="return_preprocessing_model" value="false"/>

<parameter key="create_view" value="false"/>

<parameter key="attribute_filter_type" value="single"/>

<parameter key="attribute" value="kırılganlık"/>

<parameter key="attributes" value=""/>

<parameter key="use_except_expression" value="false"/>

<parameter key="value_type" value="nominal"/>

<parameter key="use_value_type_exception" value="false"/>

<parameter key="except_value_type" value="file_path"/>

<parameter key="block_type" value="single_value"/>

<parameter key="use_block_type_exception" value="false"/>

<parameter key="except_block_type" value="single_value"/>

<parameter key="invert_selection" value="false"/>

<parameter key="include_special_attributes" value="false"/>

<parameter key="coding_type" value="dummy coding"/>

<parameter key="use_comparison_groups" value="false"/>

<list key="comparison_groups"/>

<parameter key="unexpected_value_handling" value="all 0 and warning"/>

<parameter key="use_underscore_in_name" value="false"/>

</operator>

<operator activated="true" class="normalize" compatibility="9.2.001" expanded="true" height="103" name="Normalize" width="90" x="447" y="85">

<parameter key="return_preprocessing_model" value="false"/>

<parameter key="create_view" value="false"/>

<parameter key="attribute_filter_type" value="all"/>

<parameter key="attribute" value=""/>

<parameter key="attributes" value=""/>

<parameter key="use_except_expression" value="false"/>

<parameter key="value_type" value="numeric"/>

<parameter key="use_value_type_exception" value="false"/>

<parameter key="except_value_type" value="real"/>

<parameter key="block_type" value="value_series"/>

<parameter key="use_block_type_exception" value="false"/>

<parameter key="except_block_type" value="value_series_end"/>

<parameter key="invert_selection" value="false"/>

<parameter key="include_special_attributes" value="false"/>

<parameter key="method" value="Z-transformation"/>

<parameter key="min" value="0.0"/>

<parameter key="max" value="1.0"/>

<parameter key="allow_negative_values" value="false"/>

</operator>

<operator activated="true" class="generate_attributes" compatibility="9.2.001" expanded="true" height="82" name="Generate Attributes" width="90" x="581" y="85">

<list key="function_descriptions">

<parameter key="ağırlık" value="[ağırlık]*0.2"/>

<parameter key="hacim" value="[hacim]*0.5"/>

<parameter key="satış miktarı" value="[satış miktarı]*0.3"/>

</list>

<parameter key="keep_all" value="true"/>

</operator>

<operator activated="true" class="select_attributes" compatibility="9.2.001" expanded="true" height="82" name="Select Attributes" width="90" x="782" y="34">

<parameter key="attribute_filter_type" value="subset"/>

<parameter key="attribute" value="F"/>

<parameter key="attributes" value="|F|ürün ID"/>

<parameter key="use_except_expression" value="false"/>

<parameter key="value_type" value="attribute_value"/>

<parameter key="use_value_type_exception" value="false"/>

<parameter key="except_value_type" value="time"/>

<parameter key="block_type" value="attribute_block"/>

<parameter key="use_block_type_exception" value="false"/>

<parameter key="except_block_type" value="value_matrix_row_start"/>

<parameter key="invert_selection" value="true"/>

<parameter key="include_special_attributes" value="true"/>

</operator>

<operator activated="true" class="select_attributes" compatibility="9.2.001" expanded="true" height="82" name="Select Attributes (2)" width="90" x="782" y="238">

<parameter key="attribute_filter_type" value="subset"/>

<parameter key="attribute" value="F"/>

<parameter key="attributes" value="|ürün ID"/>

<parameter key="use_except_expression" value="false"/>

<parameter key="value_type" value="attribute_value"/>

<parameter key="use_value_type_exception" value="false"/>

<parameter key="except_value_type" value="time"/>

<parameter key="block_type" value="attribute_block"/>

<parameter key="use_block_type_exception" value="false"/>

<parameter key="except_block_type" value="value_matrix_row_start"/>

<parameter key="invert_selection" value="true"/>

<parameter key="include_special_attributes" value="true"/>

</operator>

<operator activated="true" class="generate_id" compatibility="9.2.001" expanded="true" height="82" name="Generate ID (2)" width="90" x="983" y="238">

<parameter key="create_nominal_ids" value="false"/>

<parameter key="offset" value="0"/>

</operator>

<operator activated="true" class="set_macros" compatibility="9.2.001" expanded="true" height="82" name="Set Macros" width="90" x="916" y="34">

<list key="macros">

<parameter key="cluster_number" value="5"/>

</list>

</operator>

<operator activated="true" class="python_scripting:execute_python" compatibility="9.2.000" expanded="true" height="103" name="Execute Python" width="90" x="1050" y="34">

<parameter key="script" value="import pandas as pd
from operator import itemgetter
import numpy as np
import random
import sys
from scipy.spatial import distance
from sklearn.cluster import KMeans


C = %{cluster_number}

def k_means(X) : 

 kmeans = KMeans(n_clusters=C, random_state=0).fit(X)
 return kmeans.cluster_centers_




def samesizecluster( D ):
 """ in: point-to-cluster-centre distances D, Npt x C
 
 out: xtoc, X -> C, equal-size clusters
 
 """
 
 Npt, C = D.shape
 clustersize = (Npt + C - 1) // C
 xcd = list( np.ndenumerate(D) ) # ((0,0), d00), ((0,1), d01) ...
 xcd.sort( key=itemgetter(1) )
 xtoc = np.ones( Npt, int ) * -1
 nincluster = np.zeros( C, int )
 nall = 0
 for (x,c), d in xcd:
 if xtoc[x] < 0 and nincluster[c] < clustersize:
 xtoc[x] = c
 nincluster[c] += 1
 nall += 1
 if nall >= Npt: break
 return xtoc

def rm_main(data):
 
 data_2 = data.values
 
 centres = k_means(data_2)
 D = distance.cdist( data_2, centres )
 xtoc = samesizecluster( D )
 data['cluster'] = xtoc

 
 return data"/>

<parameter key="use_default_python" value="true"/>

<parameter key="package_manager" value="conda (anaconda)"/>

</operator>

<operator activated="true" class="set_role" compatibility="9.2.001" expanded="true" height="82" name="Set Role (2)" width="90" x="1184" y="34">

<parameter key="attribute_name" value="cluster"/>

<parameter key="target_role" value="cluster"/>

<list key="set_additional_roles"/>

</operator>

<operator activated="true" class="generate_id" compatibility="9.2.001" expanded="true" height="82" name="Generate ID" width="90" x="1318" y="34">

<parameter key="create_nominal_ids" value="false"/>

<parameter key="offset" value="0"/>

</operator>

<operator activated="true" class="concurrency:join" compatibility="9.2.001" expanded="true" height="82" name="Join" width="90" x="1251" y="238">

<parameter key="remove_double_attributes" value="true"/>

<parameter key="join_type" value="inner"/>

<parameter key="use_id_attribute_as_key" value="true"/>

<list key="key_attributes"/>

<parameter key="keep_both_join_attributes" value="false"/>

</operator>

<connect from_port="input 1" to_op="Read Excel" to_port="file"/>

<connect from_op="Read Excel" from_port="output" to_op="Set Role" to_port="example set input"/>

<connect from_op="Set Role" from_port="example set output" to_op="Nominal to Numerical" to_port="example set input"/>

<connect from_op="Nominal to Numerical" from_port="example set output" to_op="Normalize" to_port="example set input"/>

<connect from_op="Normalize" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>

<connect from_op="Generate Attributes" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>

<connect from_op="Select Attributes" from_port="example set output" to_op="Set Macros" to_port="through 1"/>

<connect from_op="Select Attributes" from_port="original" to_op="Select Attributes (2)" to_port="example set input"/>

<connect from_op="Select Attributes (2)" from_port="example set output" to_op="Generate ID (2)" to_port="example set input"/>

<connect from_op="Generate ID (2)" from_port="example set output" to_op="Join" to_port="left"/>

<connect from_op="Set Macros" from_port="through 1" to_op="Execute Python" to_port="input 1"/>

<connect from_op="Execute Python" from_port="output 1" to_op="Set Role (2)" to_port="example set input"/>

<connect from_op="Set Role (2)" from_port="example set output" to_op="Generate ID" to_port="example set input"/>

<connect from_op="Generate ID" from_port="example set output" to_op="Join" to_port="right"/>

<connect from_op="Join" from_port="join" to_port="result 1"/>

<portSpacing port="source_input 1" spacing="0"/>

<portSpacing port="source_input 2" spacing="0"/>

<portSpacing port="sink_result 1" spacing="0"/>

<portSpacing port="sink_result 2" spacing="0"/>

</process>

</operator>

</process>

Find more posts tagged with

Quick Links