Feature extraction and vectorizer three sentences

@@ -7,6 +7,7 @@ import argparse
 import sys
 import sys
 from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
 from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
 from scipy.sparse import csr_matrix
 from scipy.sparse import csr_matrix
+from sklearn.metrics.pairwise import cosine_similarity
 
 
 __author__ = 'CMendezC'
 __author__ = 'CMendezC'
 
 
@@ -81,10 +82,15 @@ if __name__ == "__main__":
     matrix = csr_matrix(vectorizer.fit_transform(documents), dtype='double')
     matrix = csr_matrix(vectorizer.fit_transform(documents), dtype='double')
     print('   matrix.shape: ', matrix.shape)
     print('   matrix.shape: ', matrix.shape)
 
 
+    similarityMatrix = cosine_similarity(matrix)
+    print("   Cosine similarity matrix shape: {}".format(similarityMatrix.shape))
+
     with open(os.path.join(args.outputPath, "report-vectorizer.{}.txt".format(args.vectorizer)), encoding="utf-8", mode="w") as oFile:
     with open(os.path.join(args.outputPath, "report-vectorizer.{}.txt".format(args.vectorizer)), encoding="utf-8", mode="w") as oFile:
         oFile.write("Vectorizer: {}\n".format(args.vectorizer))
         oFile.write("Vectorizer: {}\n".format(args.vectorizer))
         oFile.write(str(vectorizer.get_feature_names()))
         oFile.write(str(vectorizer.get_feature_names()))
         oFile.write("\n")
         oFile.write("\n")
         oFile.write(str(matrix.toarray()))
         oFile.write(str(matrix.toarray()))
+        oFile.write("\n")
+        oFile.write(str(similarityMatrix.toarray()))
 
 
     print("Feature extraction and vectorizer in: %fs" % (time() - t0))
     print("Feature extraction and vectorizer in: %fs" % (time() - t0))