def part1(documentPath, maximumDocuments=0):
startTime = time.time()
print("Executing code for Part 1...\n")
print("Extracting data from XML Document...")
values = XMLParse(documentPath, maximumDocuments)
print("Number of Documents: "+str(len(values)))
extractionTime = round(time.time() - startTime, 3)
print("Time: " + str(extractionTime) + " seconds")
print("Removing stopwords and stemming...")
for i in range(len(values)-1, -1, -1):
if values[i].hasField('BODY'):
values[i].setField('BODY',removeStopwords(values[i].getField("BODY")))
else:
del values[i]
removingTime = round(time.time() - startTime - extractionTime, 3)
print("Time: " + str(removingTime) + " seconds")
print("Creating list of all unique words in corpus...")
uniqueWords = getUniqueWords(values)
uniqueWordsTime = round(time.time() - startTime - extractionTime - removingTime, 3)
print("Time: " + str(uniqueWordsTime) + " seconds")
print("Computing TF, IDF, and TFIDF...")
computedTFIDF = TFIDF(values, uniqueWords)
idfTime = round(time.time() - startTime - extractionTime - removingTime - uniqueWordsTime, 3)
print("Time: " + str(idfTime) + " seconds")
print("Computing Cosine Similarity...")
computedTFIDF.calculateCosineSimilarity()
#computedTFIDF.printVal('sim', 19)
cosineSimTime = round(time.time() - startTime - extractionTime - removingTime - uniqueWordsTime - idfTime, 3)
print("Time: " + str(cosineSimTime) + " seconds")
print('\nPart 1 Complete')
print("Execution Time: " + str(round(time.time() - startTime, 3)) + " seconds\n")
return computedTFIDF
