Text Mining Action Set

s:upload{'reviews.csv', casout={name='reviews'}}
--s:loadtable(caslib="ReferenceData",path="en_stoplist.sashdat") 
s:loadtable{caslib="casuser",path="en_stoplist.sashdat"} 
-- Load action sets
s:loadactionset{actionset='textmining'}

-- Discover topics and Doc Projections
s:tmMine{
	         docid='did', 
           docpro={name='docpro',replace=True},
           documents='reviews', 
           k=3,
           nounGroups=false, 
           numLabels=3,
           offset={name='offset',replace=true}, 
           parent={name='parent',replace=true}, 
           parseConfig={name='config',replace=true}, 
           reduce=2,
           stopList='en_stoplist',
           tagging=true, 
           terms={name='terms',replace=true}, 
           text='text',  
           topicDecision=true,
           topics={name='topics',replace=True},
           u={name='svdu',replace=True},       
}


-- discovered topics 
r = s:fetch{table={name="topics"}}
print(r.Fetch)
-- relationship of each document to each topic
r = s:fetch{table='docpro'}
print(r.Fetch)
-- relationship of each term to each topic
r = s:fetch{table='svdu'}
print(r.Fetch)

# Create training data
from io import StringIO                
reviews = StringIO('''text,positive,category,did                   
"This is the greatest phone ever! love it! It can replace my tv!",1,electronics,1
"The phone's battery life is too short and screen resolution is low.",0,electronics,2
"The screen resolution is low, but I love this tv.  Good viewing.",1,electronics,3
"The movie itself is great and I liked watching it. Good acting!",1,movies,4
"The movie's story is boring and the acting is poor.",0,movies,5
"I watched this movie but it was boring..",0,movies,6
"The book has a terrific plot!",1,books,7
"The book's plot was suspenseful. Good read.",1,books,8
"I love the author, but this book is a waste of time to read.",0,books,9''')
  

handler = dmh.CSV(reviews, skipinitialspace=True)
s.addtable(table='reviews', **handler.args.addtable)
s.loadtable(caslib="ReferenceData",path="en_stoplist.sashdat") 

# Create testing data
score_reviews = StringIO('''text,did
"Loved the movie! I watched it twice.",1
"I liked the book. Great read! Good Plot!",2''')

handler = dmh.CSV(score_reviews, skipinitialspace=True)
s.addtable(table='score_reviews', **handler.args.addtable)

s.builtins.loadActionSet(actionSet="textMining")                           # 1

s.textMining.tmMine(docId="did",                                           # 2
                    docPro={"name":"docpro", "replace":True},
                    documents={"name":"reviews"},
                    k=3,
                    nounGroups=False,
                    numLabels=3,
                    offset={"name":"offset", "replace":True},
                    parent={"name":"parent", "replace":True},
                    parseConfig={"name":"config", "replace":True},
                    reduce=2,
                    stopList={"name":"en_stopList"},
                    tagging=True,
                    terms={"name":"terms", "replace":True},
                    text="text",
                    topicDecision=True,
                    topics={"name":"topics", "replace":True},
                    u={"name":"svdu", "replace":True}
                   )


#discovered topics 
print(s.fetch(table='topics',orderBy='_TopicID_'))
#relationship of each document to each topic
print(s.fetch (table='docpro',orderBy='did'))
#relationship of each  term to each topic
print(s.fetch(table='svdu', orderBy='_TermNum_'))