Most_Common_Word.py

# Given a string paragraph and a string array of the banned words banned, return the most frequent word that is not banned. 
# It is guaranteed there is at least one word that is not banned, and that the answer is unique.

# The words in paragraph are case-insensitive and the answer should be returned in lowercase.

 

# Example 1:

# Input: paragraph = "Bob hit a ball, the hit BALL flew far after it was hit.", banned = ["hit"]
# Output: "ball"
# Explanation: 
# "hit" occurs 3 times, but it is a banned word.
# "ball" occurs twice (and no other word does), so it is the most frequent non-banned word in the paragraph. 
# Note that words in the paragraph are not case sensitive,
# that punctuation is ignored (even if adjacent to words, such as "ball,"), 
# and that "hit" isn't the answer even though it occurs more because it is banned.
# Example 2:

# Input: paragraph = "a.", banned = []
# Output: "a"
 

# Constraints:

# 1 <= paragraph.length <= 1000
# paragraph consists of English letters, space ' ', or one of the symbols: "!?',;.".
# 0 <= banned.length <= 100
# 1 <= banned[i].length <= 10
# banned[i] consists of only lowercase English letters.

import re

class Solution:
    def mostCommonWord(self, paragraph: str, banned: List[str]) -> str:
        # seperate the words in the paragraph
        words = re.split(",| |\\.|!|\\?|;|'", paragraph)
        
        # we will collect verified words into a map with thier frequencies
        words_verified_map = {}
        for word in words:
            if word == '' or word.lower() in banned:
                continue
            if word.lower() not in words_verified_map:
                words_verified_map[word.lower()] = 1
            else:
                words_verified_map[word.lower()] += 1
        
        # now let's keep track of the max frequency word
        max_freq = -1
        answer = ""
        for word, freq in words_verified_map.items():
            if freq > max_freq:
                max_freq = freq
                answer = word
        
        return answer