infile = open('data/austen-emma-excerpt.txt')

print(infile)

print(infile.read())

infile = open('data/austen-emma-excerpt.txt')
text = infile.read()

infile.close()

number_of_es = 0
# insert your code here

# The following test should print True if your code is correct 
print(number_of_es == 78)

number_of_es = text.count("e")
print(number_of_es)

print(text.count("an"))

print(text.count(" an "))

print(text.split())

words = text.split()
number_of_hits = 0
item_to_count = "in"
# insert your code here

# The following test should print True if your code is correct 
print(number_of_hits == 3)

words = text.split()

number_of_hits = 0

item_to_count = "in"
for word in words:
    if word == item_to_count:
        number_of_hits += 1
print(number_of_hits)

def count_in_list(item_to_count, list_to_search): 
    number_of_hits = 0                            
    for item in list_to_search:                   
        if item == item_to_count:                 
            number_of_hits += 1                   
    return number_of_hits                         

print(count_in_list("an", words))

# insert your code here

counts = {}

for word in words:
    if word in counts:
        counts[word] = counts[word] + 1
    else:
        counts[word] = 1
print(counts)

def counter(list_to_search):                 
    counts = {}                              
    for word in list_to_search:              
        if word in counts:                   
            counts[word] = counts[word] + 1  
        else:                                
            counts[word] = 1                 
    return counts                            

print(counter(words))

emma_count = 0
# insert you code here

# The following test should print True if your code is correct 
print(emma_count == 481)

infile = open('data/austen-emma-excerpt.txt')
text = infile.read()
infile.close()
words = text.split()

for word in words:
    print(word, count_in_list(word, words))

x = ['a', 'a', 'b', 'b', 'c', 'c', 'c']
unique_x = set(x)
print(unique_x)

unique_words = set(words)
for word in unique_words:
    print(word, count_in_list(word, words))

def counter2(list_to_search):
    unique_words = set(list_to_search)
    for word in unique_words:
        print(word, count_in_list(word, list_to_search))

counter2(words)

x = 'Emma'
x_lower = x.lower()
print(x_lower)

text_lower = text.lower()
print(text_lower)

x = 'Please. remove. all. dots. from. this. sentence.'
x = x.replace(".", "")
print(x)

short_text = "Commas, as it turns out, are so much overestimated."
# insert your code here

# The following test should print True if your code is correct 
print(short_text == "commas as it turns out are so much overestimated.")

def remove_punc(text):
    punctuation = '!@#$%^&*()_-+={}[]:;"\'|<>,.?/~`'
    for marker in punctuation:
        text = text.replace(marker, "")
    return text

short_text = "Commas, as it turns out, are overestimated. Dots, however, even more so!"
print(remove_punc(short_text))

def remove_punc2(text):
    punctuation = '!@#$%^&*()_-+={}[]:;"\'|<>,.?/~`'
    clean_text = ""
    for character in text:
        if character not in punctuation:
            clean_text += character
    return clean_text

short_text = "Commas, as it turns out, are overestimated. Dots, however, even more so!"
print(remove_punc2(short_text))

def clean_text(text):
    # insert your code here
    
# The following test should print True if your code is correct 
short_text = "Commas, as it turns out, are overestimated. Dots, however, even more so!"
print(clean_text(short_text) == 
      "commas as it turns out are overestimated dots however even more so")

woodhouse_counts = 0
# insert your code here

# The following test should print True if your code is correct 
print(woodhouse_counts == 263)

outfile = open("first-output.txt", mode="w")
outfile.write("My first output.")
outfile.close()

# first open and read data/austen-emma.txt. Don't forget to close the infile
infile = open("data/austen-emma.txt")
text = # read the contents of the infile
# close the file handler
# clean the text

# next compute the frequency distribution using the function counter
frequency_distribution = 

# now open the file data/austen-frequency-distribution.txt for writing
outfile = 

for word, frequency in frequency_distribution.items():
    outfile.write(word + ";" + str(frequency) + '\n')
    
# close the outfile

from IPython.core.display import HTML
def css_styling():
    styles = open("styles/custom.css", "r").read()
    return HTML(styles)
css_styling()