Initial data commit

Task/Word-frequency/Python/word-frequency-1.py

@@ -0,0 +1,11 @@
+import collections
+import re
+import string
+import sys
+
+def main():
+  counter = collections.Counter(re.findall(r"\w+",open(sys.argv[1]).read().lower()))
+  print counter.most_common(int(sys.argv[2]))
+
+if __name__ == "__main__":
+  main()

Task/Word-frequency/Python/word-frequency-2.py

@@ -0,0 +1,20 @@
+from collections import Counter
+from re import findall
+
+les_mis_file = 'les_mis_135-0.txt'
+
+def _count_words(fname):
+    with open(fname) as f:
+        text = f.read()
+    words = findall(r'\w+', text.lower())
+    return Counter(words)
+
+def most_common_words_in_file(fname, n):
+    counts = _count_words(fname)
+    for word, count in [['WORD', 'COUNT']] + counts.most_common(n):
+        print(f'{word:>10} {count:>6}')
+
+
+if __name__ == "__main__":
+    n = int(input('How many?: '))
+    most_common_words_in_file(les_mis_file, n)

Task/Word-frequency/Python/word-frequency-3.py

@@ -0,0 +1,47 @@
+"""
+Word count task from Rosetta Code
+http://www.rosettacode.org/wiki/Word_count#Python
+"""
+from itertools import (groupby,
+                       starmap)
+from operator import itemgetter
+from pathlib import Path
+from typing import (Iterable,
+                    List,
+                    Tuple)
+
+
+FILEPATH = Path('lesMiserables.txt')
+COUNT = 10
+
+
+def main():
+    words_and_counts = most_frequent_words(FILEPATH)
+    print(*words_and_counts[:COUNT], sep='\n')
+
+
+def most_frequent_words(filepath: Path,
+                        *,
+                        encoding: str = 'utf-8') -> List[Tuple[str, int]]:
+    """
+    A list of word-frequency pairs sorted by their occurrences.
+    The words are read from the given file.
+    """
+    def word_and_frequency(word: str,
+                           words_group: Iterable[str]) -> Tuple[str, int]:
+        return word, capacity(words_group)
+
+    file_contents = filepath.read_text(encoding=encoding)
+    words = file_contents.lower().split()
+    grouped_words = groupby(sorted(words))
+    words_and_frequencies = starmap(word_and_frequency, grouped_words)
+    return sorted(words_and_frequencies, key=itemgetter(1), reverse=True)
+
+
+def capacity(iterable: Iterable) -> int:
+    """Returns a number of elements in an iterable"""
+    return sum(1 for _ in iterable)
+
+
+if __name__ == '__main__':
+    main()

Task/Word-frequency/Python/word-frequency-4.py

@@ -0,0 +1,19 @@
+#!/usr/bin/python3
+import collections
+import re
+
+count = 10
+
+with open("135-0.txt") as f:
+    text = f.read()
+
+word_freq = sorted(
+    collections.Counter(sorted(re.split(r"\W+", text.lower()))).items(),
+    key=lambda c: c[1],
+    reverse=True,
+)
+
+for i in range(len(word_freq)):
+    print("[{:2d}] {:>10} : {}".format(i + 1, word_freq[i][0], word_freq[i][1]))
+    if i == count - 1:
+        break