Write a function in the cell below that iterates through the words in file_contents, removes punctuation, and counts the frequency of each word. Oh, and be sure to make it ignore word case, words that do not contain all alphabets and boring words like "and" or "the". Then use it in the generate_from_frequencies function to generate your very own word cloud!
my code:
my code:
def calculate_frequencies(file_contents):
# Here is a list of punctuations and uninteresting words you can use to process your text
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~'''
uninteresting_words = ["the", "a", "to", "if", "is", "it", "of", "and", "or", "an", "as", "i", "me", "my", \
"we", "our", "ours", "you", "your", "yours", "he", "she", "him", "his", "her", "hers", "its", "they", "them", \
"their", "what", "which", "who", "whom", "this", "that", "am", "are", "was", "were", "be", "been", "being", \
"have", "has", "had", "do", "does", "did", "but", "at", "by", "with", "from", "here", "when", "where", "how", \
"all", "any", "both", "each", "few", "more", "some", "such", "no", "nor", "too", "very", "can", "will", "just"]
# LEARNER CODE START HERE
dict1=[]
d ={}
for words in file_contents.split():
if words.isalpha() and words.lower() not in uninteresting_words:
dict1.append(words.lower())
for words in dict1:
if words not in d:
d[words] =0
d[words]+=file_contents.split().count(words)
return d
#wordcloud
cloud = WordCloud(width=900,height=500, max_words=1628,relative_scaling=1,normalize_plurals=False)
cloud.generate_from_frequencies(calculate_frequencies)
return cloud.to_array()
myimage = calculate_frequencies(file_contents)
plt.imshow(np.real(myimage), interpolation = 'nearest')
plt.axis('off')
plt.show()expected a wordcloud
