1
def process_word(word):
2
        remove = '.!?,"\'()*_:;0123456789'
3
        word = word.strip()
4
        for character in remove:
5
                word = word.replace(character," ")
6

7
        word = word.lower()
8
        return word
9

10
def process_line(line):
11
        line = line.strip()
12
        line = line.replace("-"," ")
13
        words = line.split()
14
        processed_words =  []
15
        for word in words:
16
                processed_words.append(process_word(word))
17
        return processed_words
18

19
def process_file(path):
20
        with open(path) as file:
21
                words = []
22
                data = file.readlines()
23

24
                for line in data:
25
                        words = words + process_line(line)
26
        return words 
27

28
def find_unique(words):
29
        unique_words = []
30
        for word in words:
31
                if word not in unique_words:
32
                        unique_words.append(word)
33
        return unique_words
34

35
def find_frequency(words):
36
        freq_dict = {}
37
        for word in words:
38
                if word in freq_dict:
39
                        freq_dict[word]+=1
40
                else:
41
                        freq_dict[word]=1
42
        return freq_dict
43

44
def remove_stop(words,stop):
45
        non_stop_words = []
46
        for word in words:
47
                if word not in stop:
48
                        non_stop_words.append(word)
49

50
        return non_stop_words
51

52
def most_common(freq_dict,n):
53
        freq_list = []
54
        for item in list(freq_dict.items()):
55
                val = (item[1],item[0])
56
                freq_list.append(val)
57
        freq_list.sort(reverse=True)
58
        print(f"{'Word':<12}{'Count':>4}")
59
        print(("-"*16))
60
        for index in range(0,n):
61
                count = freq_list[index][0]
62
                word = freq_list[index][1]
63
                print(f"{word: <12}{count: >4}")
64

65
def count_by_length(words):
66
        count_dict = {}
67
        for word in words:
68
                length = len(word)
69
                if length in count_dict:
70
                        count_dict[length]+=1
71
                else:
72
                        count_dict[length]=1
73
        count_list = []
74
        for item in list(count_dict.items()):
75
                count_list.append(item)
76

77
        count_list.sort(reverse=True)
78
        print(f"{'Length':<12}{'Count':>4}")
79
        print(("-"*16))
80
        for item in count_list:
81
                print(f"{item[0]: <12}{item[1]: >4}")
82

83
def count_by_first(words):
84
        count_dict = {}
85
        for word in words:
86
                char= word[0]
87
                if char in count_dict:
88
                        count_dict[char]+=1
89
                else:
90
                        count_dict[char]=1
91
        count_list = []
92
        for item in list(count_dict.items()):
93
                count_list.append(item)
94

95
        count_list.sort(reverse=True)
96
        print(f"{'Letter':<12}{'Count':>4}")
97
        print(("-"*16))
98
        for item in count_list:
99
                print(f"{item[0]: <12}{item[1]: >4}") 
100