1
0
mirror of https://github.com/SunnyQjm/algorithm-review.git synced 2026-06-03 08:16:43 +08:00
Files
algorithm-review/chapter12/3_top-k-frequent-words.py
T
2020-06-22 18:40:13 +08:00

56 lines
2.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python
# coding=utf-8
#######################################################################################
# Leetcode 692 前K个高频单词
#
# 给一非空的单词列表,返回前 k 个出现次数最多的单词。
# 返回的答案应该按单词出现频率由高到低排序。如果不同的单词有相同出现频率,按字母顺序排序。
#
# 示例 1
# 输入: ["i", "love", "leetcode", "i", "love", "coding"], k = 2
# 输出: ["i", "love"]
# 解析: "i" 和 "love" 为出现次数最多的两个单词,均为2次。
# 注意,按字母顺序 "i" 在 "love" 之前。
#
# 示例 2
# 输入: ["the", "day", "is", "sunny", "the", "the", "the", "sunny", "is", "is"], k = 4
# 输出: ["the", "is", "sunny", "day"]
# 解析: "the", "is", "sunny" 和 "day" 是出现次数最多的四个单词,
# 出现次数依次为 4, 3, 2 和 1 次。
#
# 注意:
# 1. 假定 k 总为有效值, 1 ≤ k ≤ 集合元素数。
# 2. 输入的单词均由小写字母组成。
#
# 扩展练习:
# 尝试以 O(n log k) 时间复杂度和 O(n) 空间复杂度解决。
#######################################################################################
from typing import List
import collections
class Solution:
def topKFrequent(self, words: List[str], k: int) -> List[str]:
"""
:type words: List[str]
:type k: int
:rtype List[str]
(knowledge)
思路:
1. 统计每个单词出现的频率;
2. 然后按照词频和字母序排序(首先按照词频排序,然后如果词频相同就按字母序排序);
3. 最后返回排序后前k个元素
"""
count = collections.Counter(words)
candidates = list(count.keys())
candidates.sort(key=lambda w: (-count[w], w))
return candidates[:k]
if __name__ == '__main__':
solution = Solution()
print(solution.topKFrequent(["i", "love", "leetcode", "i", "love", "coding"], 2), "= [\"i\", \"love\"]")