PwC_Bash_code.txt

### "Paying with Change" Article Bash Code ###

# Marshall A. Taylor #
# Dustin S. Stoltz #
	
##############################
## PwC_Bash_Code.txt: "Paying with Change" Article State Code
## Note: Used Stanford NER tagger, version 3.6.0. You will need to download the tagger and
	##nest it within your file path. You will then need to download the "Data.zip" folder,
	##unzip it, and then nest it within the NER tagger folder. You can also bypass tagging
	##any of this yourself and simply unzip the "tagged_docs" folder, which contains the tags
	##for each of the 280 documents.
## Author: Marshall A. Taylor
##############################

############################
##  COMMANDS BEGIN HERE   ##
############################

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data1/“

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data2/”

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data3/“

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data4/”

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data5/“

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/Data/Data6/”

$ echo "  unique_identifier" | tee -a *.txt

$ cd "/file/path/to/stanford-ner-2015-12-09/“

$ cat Data/Data1/*.txt >> text1.txt

$ cat Data/Data2/*.txt >> text2.txt

$ cat Data/Data3/*.txt >> text3.txt

$ cat Data/Data4/*.txt >> text4.txt

$ cat Data/Data5/*.txt >> text5.txt

$ cat Data/Data6/*.txt >> text6.txt 

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \ 
> classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text1.txt > tagged_text1.txt

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \
> classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text2.txt > tagged_text2.txt

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \
$ classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text3.txt > tagged_text3.txt

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \
> classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text4.txt > tagged_text4.txt

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \
> classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text5.txt > tagged_text5.txt

$ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier \
> classifiers/english.all.3class.distsim.crf.ser.gz outputFormat slashTags -textFile text6.txt > tagged_text6.txt

$ csplit -f tagsa tagged_text1.txt /"unique_identifier/O”/ {49}

$ csplit -f tagsb tagged_text2.txt /“unique_identifier/O”/ {49}

$ csplit -f tagsc tagged_text3.txt /“unique_identifier/O”/ {49}

$ csplit -f tagsd tagged_text4.txt /“unique_identifier/O”/ {49}

$ csplit -f tagse tagged_text5.txt /“unique_identifier/O”/ {49}

$ csplit -f tagsf tagged_text6.txt /“unique_identifier/O”/ {29}

$ rm tagsa50 tagsb50 tagsc50 tagsd50 tagse50 tagsf30

$ mkdir tagged_docs

$ mv tags* tagged_docs/