def _main():
a = stdio.readAllStrings()
reverse(a)
for v in a[:-1]:
stdio.writef('%s ', v)
stdio.writeln(a[-1])
def _main():
words = stdio.readAllStrings()
write_word_frequencies(count_word_frequencies(words))
def main():
a = stdio.readAllStrings()
sort(a)
for s in a:
stdio.write(s + ' ')
stdio.writeln()
def main():
a = stdio.readAllStrings()
sort(a)
for s in a:
stdio.write(s + ' ')
stdio.writeln()
#-----------------------------------------------------------------------
# frequencycount.py
#-----------------------------------------------------------------------
import sys
import stdio
from counter import Counter
# Read words from standard input, and write the frequency counts
# of the words to standard output.
words = stdio.readAllStrings()
# Previous doesn't eliminate punctuation chars, but this does:
# import re
# s = stdio.readAll()
# regExp = re.compile(r'\w+') # One or more alphanumeric chars
# words = regExp.findall(s)
words.sort() # or merge.sort(words)
zipf = []
for i in range(len(words)):
if (i == 0) or (words[i] != words[i - 1]):
entry = Counter(words[i], len(words))
zipf += [entry]
zipf[len(zipf) - 1].increment()
zipf.sort() # or merge.sort(zipf)
zipf.reverse()
for entry in zipf:
import stdio
from instream import InStream
from sketch import Sketch
#-----------------------------------------------------------------------
# Accept integers k and d as command-line arguments. Read a document
# list from standard input, compute profiles based on k-gram
# frequencies for all the documents, and write a matrix of similarity
# measures between all pairs of documents. d is the dimension of the
# profiles.
k = int(sys.argv[1])
d = int(sys.argv[2])
filenames = stdio.readAllStrings()
sketches = stdarray.create1D(len(filenames))
for i in range(len(filenames)):
text = InStream(filenames[i]).readAll()
sketches[i] = Sketch(text, k, d)
stdio.write(' ')
for i in range(len(filenames)):
stdio.writef('%8.4s', filenames[i])
stdio.writeln()
for i in range(len(filenames)):
stdio.writef('%.4s', filenames[i])
for j in range(len(filenames)):
stdio.writef('%8.2f', sketches[i].similarTo(sketches[j]))
import sys
import stdio
from bst import OrderedSymbolTable
# Accept integers minLength and minCount as command-line arguments. Read
# words from standard input until end-of-file. Create an index
# indicating where each word appears within standard input. Consider
# only words that have at least minLength characters. Then write
# the index to standard output. Write only words that occur at
# least minCount times.
minLength = int(sys.argv[1])
minCount = int(sys.argv[2])
words = stdio.readAllStrings()
bst = OrderedSymbolTable()
for i in range(len(words)):
word = words[i]
if len(word) >= minLength:
if not word in bst:
bst[word] = []
bst[word] += [i]
for word in bst:
occurrences = bst[word]
if len(occurrences) >= minCount:
stdio.write(word + ': ')
for occurrence in occurrences:
import stdio
from instream import InStream
from sketch import Sketch
#-----------------------------------------------------------------------
# Accept integers k and d as command-line arguments. Read a document
# list from standard input, compute profiles based on k-gram
# frequencies for all the documents, and write a matrix of similarity
# measures between all pairs of documents. d is the dimension of the
# profiles.
k = int(sys.argv[1])
d = int(sys.argv[2])
filenames = stdio.readAllStrings()
sketches = stdarray.create1D(len(filenames))
for i in range(len(filenames)):
text = InStream(filenames[i]).readAll()
sketches[i] = Sketch(text, k, d)
stdio.write(' ')
for i in range(len(filenames)):
stdio.writef('%8.4s', filenames[i])
stdio.writeln()
for i in range(len(filenames)):
stdio.writef('%.4s', filenames[i])
for j in range(len(filenames)):
stdio.writef('%8.2f', sketches[i].similarTo(sketches[j]))
