upload

@@ -7,10 +7,14 @@ cd /home/egaytan/automatic-extraction-growth-conditions/extraction-geo/outputs/
 
 echo "Access to output extracted baglines"
 echo "directory: "$(pwd);
-
+#all output-extraction files
 index="/home/egaytan/automatic-extraction-growth-conditions/extraction-geo/reports/all-output-index.txt"
-output="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/input/annotation/bg_sentences_v2.txt"
-report="/home/egaytan/automatic-extraction-growth-conditions/extraction-geo/reports/bg_report_v2.txt"
+#input sentences to run CoreNLP
+output="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/input/annotation/bg_sentences_v3.txt"
+#GSE index by bg_sentence row
+mapping="/home/egaytan/automatic-extraction-growth-conditions/predict-annot/mapping/bg_sentences_midx.txt"
+#Number of fields by bagline
+report="/home/egaytan/automatic-extraction-growth-conditions/extraction-geo/reports/bg_report_v3.txt"
 echo
 echo
 echo
@@ -29,10 +33,15 @@ echo "==============================Baglines extraction=========================
 echo
 echo
 echo "Add sentence-end-tag PGCGROWTHCONDITIONS"
-for gsef in $( cat $index )
-do
-  cat $gsef | sort | uniq;
-done | cut -f1 | cut -f2 -d'"' | sort | uniq | awk '{ print $_ " PGCGROWTHCONDITIONS" }'  > $output
+#for gsef in $( cat $index )
+#do
+#  cat $gsef | sort | uniq;
+#done | cut -f1 | cut -f2 -d'"' | sort | uniq | awk '{ print $_ " PGCGROWTHCONDITIONS" }'  > $output
+cext=$(grep -E ".*" $(cat $index | tr '\n' ' ')| sed 's/"//g'| sed 's/.tsv:/.tsv\t/' | tr '/' '\t'| cut -f7,9 | sort | uniq | awk 'BEGIN {FS="\t"}  length($2) > 3 { print  $_}' | awk '{ print $_ " PGCGROWTHCONDITIONS" }' | sed 's/\\null\\/null/g' )
+echo "$cext" | cut -f2 > $output
+echo "$cext" | cut -f2 |wc
+echo "$cext" | cut -f1 > $mapping
+echo "$cext" | cut -f1 |wc
 echo
 echo
 echo "Number of total baglines: "$(wc -l $output );
@@ -40,7 +49,7 @@ echo
 echo "Baglines report"
 
 
-for gsef in $( cat ../reports/all-output-index.txt)
+for gsef in $( cat $index)
 do
   cat $gsef | sort | uniq ;
 done | cut -f2 | cut -f2 -d'"' | sed 's/_ch/./g' | cut -f1 -d'.' | sort | uniq -c |  awk '{print $1"\t"$2}' > $report
@@ -48,4 +57,4 @@ done | cut -f2 | cut -f2 -d'"' | sed 's/_ch/./g' | cut -f1 -d'.' | sort | uniq -
 cat $report
 echo
 echo
-echo "Saving file: /home/egaytan/automatic-extraction-growth-conditions/extraction/bg_sentences_v2.txt";
+echo "Saving file: "$output;

@@ -4,7 +4,7 @@ echo "==============================Run CoreNLP=================================
 echo
 echo
 
-input="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/input/annotation/bg_sentences_v2.txt"
+input="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/input/annotation/bg_sentences_v3.txt"
 output="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/output/annotation"
 regexfile="/home/egaytan/automatic-extraction-growth-conditions/CoreNLP/input/NER/inputEntities.txt"
 

-index="/home/egaytan/automatic-extraction-growth-conditions/extraction-geo/reports/all-output-index.txt"
-mapfiel="/home/egaytan/automatic-extraction-growth-conditions/extraction-geo/reports/bg_map_index.txt"
-grep -E ".*" $(cat $index | tr '\n' ' ')| sed 's/"//g'| sed 's/.tsv:/.tsv\t/' | tr '/' '\t'| cut -f7,9 | sort | uniq | awk 'BEGIN {FS="\t"}  length($2) > 3 { print  $_}' > $mapfile
-
-

--------------------------------- PARAMETERS --------------------------------
-Path of CoreNLP output: /home/egaytan/automatic-extraction-growth-conditions/CoreNLP/output/annotation
-File with CoreNLP-tagging bg-sentences: bg_sentences_v2.txt.ner
-Path to save data set: /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input
-File to save recontrsucted bg-sentences: annot-input_bg_v2.txt
--------------------------------- PROCESSING --------------------------------
-EXCLUDE: 
-EXCLUDE: 
-EXCLUDE: .|.|.
-EXCLUDE: \|\|SYM
-EXCLUDE: C1|c1|NN
-EXCLUDE: C2|c2|NN
-EXCLUDE: F1|f1|NN
-EXCLUDE: F2|f2|NN
-EXCLUDE: LB|lb|NN
-EXCLUDE: NA|NA|NNP
-EXCLUDE: NC|nc|NN
-EXCLUDE: V1|v1|NN
-EXCLUDE: wt|wt|JJ
-EXCLUDE: WT|WT|NNP
-Number of sentences: 13889
-==================================END===================================

 -------------------------------- PARAMETERS --------------------------------
 Path of CoreNLP output: /home/egaytan/automatic-extraction-growth-conditions/CoreNLP/output/annotation
-File with CoreNLP-tagging bg-sentences: bg_sentences_v2.txt.ner
+File with CoreNLP-tagging bg-sentences: bg_sentences_v3.txt.ner
 Path to save data set: /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input
-File to save recontrsucted bg-sentences: annot-input_bg_v1.txt
+File to save recontrsucted bg-sentences: annot-input_bg_v3.txt
 -------------------------------- PROCESSING --------------------------------
-Number of sentences: 13903
+Number of sentences: 14716
 ==================================END===================================