def main():
# Initial input checking
if len(sys.argv) < 2:
print("Insufficient arguments. Usage: parse.py <fileName>")
sys.exit(22)
if os.path.isfile(sys.argv[1]) == False:
print("File does not exist.")
sys.exit(22)
if sys.argv[1][-3:] == "txt":
doc = Document()
with open(sys.argv[1]) as file:
parser = document.Parser(file, doc)
parser.parseDocument()
# for w in doc:
# print("%s: %s" % (w, doc.getWordCount(w)))
if len(sys.argv) >= 3:
if "-stats" in sys.argv:
print("Document Statistics:")
print("Total Words : %d" % (doc.getNumTotalWords()))
print("Different Words : %d" % (doc.getNumDifferentWords()))
print("Number of Sentences : %d" % (doc.getNumSentences()))
print("Number of Paragraphs: %d" % (doc.getNumParagraphs()))
print("------------")
if "-lw" in sys.argv:
print("Words in Document:")
for w in doc:
print("%s" % (w))
print("------------")
if "-lwf" in sys.argv:
print("Word Frequency in Document:")
for w in doc:
print("%s: %s" % (w, doc.getWordCount(w)))
print("------------")
if "-mfw" in sys.argv:
print("Most Frequent Word(s) in Document:")
maxFreq = 0
mostFreqWords = []
for w in doc:
if doc.getWordCount(w) > maxFreq:
maxFreq = doc.getWordCount(w)
mostFreqWords = []
mostFreqWords.append(w)
elif doc.getWordCount(w) == maxFreq:
mostFreqWords.append(w)
for w in mostFreqWords:
print("%s: %s" % (w, maxFreq))
print("------------")
for args in sys.argv:
if "-find=" in args:
searchWord = args[6:]
if len(searchWord) > 0:
print("Searching for Word \"%s\" in Document:" % searchWord)
print("%s: %s" % (searchWord, doc.getWordCount(searchWord)))
print("------------")
elif sys.argv[1][-3:] == "csv":
csv = Custom_CSV()
with open(sys.argv[1]) as file:
parser = custom_csv.CSV_Parser(file, csv)
parser.parseCSV()
else:
print("Bad file extenstion.")
sys.exit(22)
def main():
argParser = buildArguments()
args = argParser.parse_args()
filename = args.file
print("------------")
if filename[-3:] == 'csv':
print('okay csv')
csv = Custom_CSV()
print('Opening csv...')
try :
with open(args.file) as file:
print('Parsing csv...')
parser = custom_csv.CSV_Parser(file, csv)
parser.parseCSV()
print('Done!')
print("------------")
except FileNotFoundError as e:
print('Could not find file %s' % (args.file))
return e.errno
if args.display_all:
print('Displaying all vectors and their rows...')
print('%-16s %-13s' % ('Row', 'Vector'))
for i in range(0,csv.getNumVectors()):
print("%d: " % i, end="")
for e in csv.getVector(i):
print("%f\t" % e, end="")
print()
print("------------")
if args.top:
top = int(args.top)
if top < 0:
print('Please do not give the program negative numbers')
return 22
if top > csv.getNumVectors():
print('Row %d is out of range' % top)
return 22
print('Displaying top %d rows...' % top)
print('%-16s %-13s' % ('Row', 'Vector'))
for i in range(0,top):
print("%d: " % i, end="")
for e in csv.getVector(i):
print("%f\t" % e, end="")
print()
print("------------")
if args.length:
row = int(args.length)
if row < 0:
print('Please do not give the program negative numbers')
return 22
if row > csv.getNumVectors():
print('Row %d is out of range' % row)
return 22
print('Computing length of row %d...' % row)
v = csv.getVector(row)
if not args.quiet:
print("row %2d: " % row, end="")
for e in v:
print("%f\t" % e, end="")
print()
print("length: %f" % vector_math.length(v))
print("------------")
if args.dot:
row1 = int(args.dot[0])
row2 = int(args.dot[1])
if row1 < 0 or row2 < 0:
print('Please do not give the program negative numbers')
return 22
if row1 > csv.getNumVectors() or row2 > csv.getNumVectors():
print('Row %s is out of range' % args.dot)
return 22
x = csv.getVector(row1)
y = csv.getVector(row2)
print('Computing dot product of row %d and %d...' % (row1, row2))
if len(x) == len(y):
if not args.quiet:
print("row1 %2d: " % row1, end="")
for e in x:
print("%f\t" % e, end="")
print()
print("row2 %2d: " % row2, end="")
for e in y:
print("%f\t" % e, end="")
print()
print("Dot Product: %f" % vector_math.dot(x, y))
else:
print('Row %d does not have the same length as %d' % (row1, row2))
print("------------")
if args.euclidean:
row1 = int(args.euclidean[0])
row2 = int(args.euclidean[1])
if row1 < 0 or row2 < 0:
print('Please do not give the program negative numbers')
return 22
if row1 > csv.getNumVectors() or row2 > csv.getNumVectors():
print('Row %s is out of range' % args.dot)
return 22
x = csv.getVector(row1)
y = csv.getVector(row2)
print('Computing Euclidean Distance of row %d and %d...' % (row1, row2))
if len(x) == len(y):
if not args.quiet:
print("row1 %2d: " % row1, end="")
for e in x:
print("%f\t" % e, end="")
print()
print("row2 %2d: " % row2, end="")
for e in y:
print("%f\t" % e, end="")
print()
print("Euclidean Distance: %f" % vector_math.euclideanDistance(x, y))
else:
print('Row %d does not have the same length as %d' % (row1, row2))
print("------------")
if args.manhattan:
row1 = int(args.manhattan[0])
row2 = int(args.manhattan[1])
if row1 < 0 or row2 < 0:
print('Please do not give the program negative numbers')
return 22
if row1 > csv.getNumVectors() or row2 > csv.getNumVectors():
print('Row %s is out of range' % args.dot)
return 22
x = csv.getVector(row1)
y = csv.getVector(row2)
print('Computing Manhattan Distance of row %d and %d...' % (row1, row2))
if len(x) == len(y):
if not args.quiet:
print("row1 %2d: " % row1, end="")
for e in x:
print("%f\t" % e, end="")
print()
print("row2 %2d: " % row2, end="")
for e in y:
print("%f\t" % e, end="")
print()
print("Manhattan Distance : %f" % vector_math.manhattanDistance(x, y))
else:
print('Row %d does not have the same length as %d' % (row1, row2))
print("------------")
if args.pearson:
row1 = int(args.pearson[0])
row2 = int(args.pearson[1])
if row1 < 0 or row2 < 0:
print('Please do not give the program negative numbers')
return 22
if row1 > csv.getNumVectors() or row2 > csv.getNumVectors():
print('Row %s is out of range' % args.dot)
return 22
x = csv.getVector(row1)
y = csv.getVector(row2)
print('Computing Pearson Correlation of row %d and %d...' % (row1, row2))
if len(x) == len(y):
if not args.quiet:
print("row1 %2d: " % row1, end="")
for e in x:
print("%f\t" % e, end="")
print()
print("row2 %2d: " % row2, end="")
for e in y:
print("%f\t" % e, end="")
print()
print("Pearson Correlation: %f" % vector_math.pearsonCorrelation(x, y))
else:
print('Row %d does not have the same length as %d' % (row1, row2))
print("------------")
if args.min_row:
row = int(args.min_row)
print('Computing min for row %d' % row)
if row < 0:
print('Please do not give the program negative numbers')
return 22
if row > csv.getNumVectors():
print('Row %d is out of range' % row)
return 22
print('Computing min of row %d...' % row)
v = csv.getVector(row)
if not args.quiet:
print("row %2d: " % row, end="")
for e in v:
print("%f\t" % e, end="")
print()
print("min: %f" % vector_math.minRow(v))
print("------------")
if args.max_row:
row = int(args.max_row)
print('Computing max for row %d' % row)
if row < 0:
print('Please do not give the program negative numbers')
return 22
if row > csv.getNumVectors():
print('Row %d is out of range' % row)
return 22
print('Computing max of row %d...' % row)
v = csv.getVector(row)
if not args.quiet:
print("row %2d: " % row, end="")
for e in v:
print("%f\t" % e, end="")
print()
print("max: %f" % vector_math.maxRow(v))
print("------------")
if args.median_row:
row = int(args.median_row)
print('Computing median for row %d' % row)
if row < 0:
print('Please do not give the program negative numbers')
return 22
if row > csv.getNumVectors():
print('Row %d is out of range' % row)
return 22
print('Computing median of row %d...' % row)
v = csv.getVector(row)
if not args.quiet:
print("row %2d: " % row, end="")
for e in v:
print("%f\t" % e, end="")
print()
print("median: %f" % vector_math.medianRow(v))
print("------------")
if args.mean_row:
row = int(args.mean_row)
print('Computing mean for row %d' % row)
if row < 0:
print('Please do not give the program negative numbers')
return 22
if row > csv.getNumVectors():
print('Row %d is out of range' % row)
return 22
print('Computing mean of row %d...' % row)
v = csv.getVector(row)
if not args.quiet:
print("row %2d: " % row, end="")
for e in v:
print("%f\t" % e, end="")
print()
print("mean: %f" % vector_math.meanRow(v))
print("------------")
if args.min_col:
col = int(args.min_col)
print('Computing min for col %d' % col)
if col < 0:
print('Please do not give the program negative numbers')
return 22
print('Computing min of column %d...' % col)
c = csv.getColumn(col)
if len(c) > 0:
if not args.quiet:
print("%d" % col);
print("---");
for e in c:
print("%f" % e)
print("min: %f" % vector_math.minRow(c))
else:
print("Column %d had no entries" % col)
print("------------")
if args.max_col:
col = int(args.max_col)
print('Computing max for col %d' % col)
if col < 0:
print('Please do not give the program negative numbers')
return 22
print('Computing max of column %d...' % col)
c = csv.getColumn(col)
if len(c) > 0:
if not args.quiet:
print("%d" % col);
print("---");
for e in c:
print("%f" % e)
print("max: %f" % vector_math.maxRow(c))
else:
print("Column %d had no entries" % col)
print("------------")
if args.median_col:
col = int(args.median_col)
print('Computing median for col %d' % col)
if col < 0:
print('Please do not give the program negative numbers')
return 22
print('Computing median of column %d...' % col)
c = csv.getColumn(col)
if len(c) > 0:
if not args.quiet:
print("%d" % col);
print("---");
for e in c:
print("%f" % e)
print("median: %f" % vector_math.medianRow(c))
else:
print("Column %d had no entries" % col)
print("------------")
if args.mean_col:
col = int(args.mean_col)
print('Computing mean for col %d' % col)
if col < 0:
print('Please do not give the program negative numbers')
return 22
print('Computing mean of column %d...' % col)
c = csv.getColumn(col)
if len(c) > 0:
if not args.quiet:
print("%d" % col);
print("---");
for e in c:
print("%f" % e)
print("mean: %f" % vector_math.meanRow(c))
else:
print("Column %d had no entries" % col)
print("------------")
elif filename[-3:] == 'txt':
doc = Document()
# Read Document
print('Opening document...')
try:
with open(args.file) as file:
print('Parsing document...')
parser = document.Parser(file, doc)
parser.parseDocument()
print('Done!')
print("------------")
except FileNotFoundError as e:
print('Could not find file %s' % (args.file))
return e.errno
# Display Document
if args.display_all:
print('Displaying all words and their occurrences...')
print('%-16s %-13s' % ('Word', 'Occurrences'))
for w in doc:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.most_frequent:
print('Finding most frequent...')
mostFreq = doc.getMostFrequentWord()
print('%-16s %-13s' % ('Most Frequent', 'Occurrences'))
print('%-16s %-13d' % (mostFreq, doc.getWordCount(mostFreq)))
print("------------")
if args.most_frequent_percent:
percent = int(args.most_frequent_percent)
if percent > 100 or percent < 0:
print('%d is an invalid percentage -- must be between 0 and 100' % percent)
return 22
print('Finding words within %d percent of the most frequent...' % percent)
mostFreqWords = doc.getMostFrequentWords(percent)
print('%-16s %-13s' % ('Most Frequent', 'Occurrences'))
for w in mostFreqWords:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.top:
topNum = int(args.top)
if topNum < 0:
print('Please do not give the program negative numbers')
return 22
print('Finding top %d words...' % topNum)
topWords = doc.getTopWords(topNum)
print('%-16s %-13s' % ('Top %d Frequent' % topNum, 'Occurrences'))
for w in topWords:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.equal_to:
freq = int(args.equal_to)
print('Finding words with %d ocurrences...' % freq)
wordsEqual = doc.getWordsEqualToFrequency(freq)
print('%-16s %-13s' % ('Word', 'Occurrences'))
wordsEqual = sorted(wordsEqual)
for w in wordsEqual:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.above:
freq = int(args.above)
print('Finding words above %d occurrences...' % freq)
wordsAbove = doc.getWordsAboveFrequency(freq)
print('%-16s %-13s' % ('Word', 'Occurrences'))
wordsAbove = sorted(wordsAbove)
for w in wordsAbove:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.word:
print('Finding occurrences for %s...' % args.word)
print('%-16s %-13s' % ('Word', 'Occurrences'))
for w in args.word.split(','):
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.is_in:
print('Checking if %s is in the document...' % args.is_in)
if doc.getWordCount(args.is_in) > 0:
print('"%s" IS in the document!' % args.is_in)
else:
print('"%s" IS NOT in the document!' % args.is_in)
print("------------")
if args.stats:
print("Document Statistics:")
print("Number Total Words : %d" % (doc.getNumTotalWords()))
print("Number Different Words: %d" % (doc.getNumDifferentWords()))
print("Number of Sentences : %d" % (doc.getNumSentences()))
print("Number of Paragraphs : %d" % (doc.getNumParagraphs()))
print("------------")
else:
print('Please provide either a .csv or a .txt file to be parsed')
return 22
return 0