def exec():
#Querry comes from command line
querry_ = sys.argv[1:]
ii = InvertedIndex()
for file in [f for f in listdir('../data') if isfile(join('../data', f))]:
document_ = Document('../data/'+file)
ii.add_document(document_)
sim_table = sorted(ii.querry(querry_))
for document in sim_table:
print(document)
def main():
# Read in the sample data we used in class
documents = read_data("./dataA")
# Now we have the data we can create a crude inverted index using
# a simple (inefficient!) linked list class.
inv_ind = InvertedIndex()
# Add the documents
for d in documents:
inv_ind.add_document(d)
# Create our semantic space and SVD computation
ss = SemanticSpace(inv_ind)
# Fold in our query vector
q = ss.create_query_vector("Human Computer Interaction")
# This loop prints out the similarity scores between each document
# and our query vector - results should match those of class.
print(
"Showing similarities between our query and documents in semantic space"
)
for i in range(9):
print(inv_ind.docs[i] + ": " +
'{0:0.3f}'.format(ss.cosine_with_doc(q, i)))
print()
# This code snippet iterates through every pair of terms in our semantic
# space printing out the similarities (cosine) score of each pair.
print("Showing similarity between all terms with one another")
for i in range(12):
print("Similarity with " + inv_ind.terms[i][0])
for j in range(12):
print('{0: >10}'.format(inv_ind.terms[j][0]) + ": " +
'{0:0.3f}'.format(ss.cosine_with_term(i, j)))
print()
def add_document(self):
new_doc = Document('test_file')
new_index = InvertedIndex()
new_index.add_document(new_doc)
self.assertIsInstance(new_index, InvertedIndex)