from collections import Counter
from matplotlib import pyplot as plt
import math
# -*- coding: utf-8 -*-
print("""Problem 1: Replace the word EXAMPLE three times in the next line
with three examples of problems that can be solved by data science.""")
print("Answer 1: EXAMPLE, EXAMPLE, EXAMPLE ")
print()
#The test continues after the Gettysburg Address.
gettysburg= """Four score and seven years ago our fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created equal.
Now we are engaged in a great civil war, testing whether that nation, or any nation so conceived and so dedicated, can long endure. We are met on a great battle-field of that war. We have come to dedicate a portion of that field, as a final resting place for those who here gave their lives that that nation might live. It is altogether fitting and proper that we should do this.
But, in a larger sense, we can not dedicate -- we can not consecrate -- we can not hallow -- this ground. The brave men, living and dead, who struggled here, have consecrated it, far above our poor power to add or detract. The world will little note, nor long remember what we say here, but it can never forget what they did here. It is for us the living, rather, to be dedicated here to the unfinished work which they who fought here have thus far so nobly advanced. It is rather for us to be here dedicated to the great task remaining before us -- that from these honored dead we take increased devotion to that cause for which they gave the last full measure of devotion -- that we here highly resolve that these dead shall not have died in vain -- that this nation, under God, shall have a new birth of freedom -- and that government of the people, by the people, for the people, shall not perish from the earth.
Abraham Lincoln
November 19, 1863
"""
#The next statement removes punctuation
text=gettysburg.replace(',','').replace('.','').replace(':','').replace("-","")
print("""Problem 2: Complete the next line so that uppercase letters in text
will be replaced by lower case letters in lowtext.""")
lowtext=text
print("Answer 2:",lowtext[:30], " etc.")
print()
#the next line splits the text into a list of words.
words=lowtext.split()
print("words=", words[:6], "etc.")
print()
print("""Problem 3: Replace the {} in the next line so that word_counts
will be a counter with the number of times each word appears.""")
word_counts = {}
print("Answer 3:", list(zip(list(word_counts.keys())[:3], list(word_counts.values())[:3])), "etc.")
print()
print("""Problem 4: Make two replacements in the list important_words in the
next line. Use a word that you think is imporant in the Gettysburg. Address""")
important_words=['nation', 'REPLACE','REPLACE']
print("Answer 4:", important_words)
print()
print("""Problem 5: Replace 0 in the third line below with an expression to
print the number of times each 'important' word appears in the Address.""")
print("Answer 5:")
for word in important_words:
print(word, 0)
print()
print("""Problem 6: Replace the [] in the next line so that top10 will be a
list of the 10 most frequent words in the Address and their frequencies.""")
top10=[]
print("Answer 6:", top10)
print()
#The next line creates a list of the top 10 words.
top_words=[word for word,_ in top10]
print("top words=", top_words)
print()
print("""Problem 7: Insert code inside the [] in the next line so that
top_freqs will be a list of the frequencies (or counts) for the top 10 words.""")
top_freqs=[]
print("Answer 7:", top_freqs)
print()
#the next line creates a list of indices for the top 10 words (0 to 9)
indices=[i for i,_ in enumerate(top_words)]
print("indices=",indices)
print()
#Bar Graph
print("""Problem 8: Repace the [] in the next line so the bar heights will be
the frequencies.""")
graph1=plt.bar(indices, [],.9)
plt.xticks(indices, top_words)
plt.ylabel("Frequency")
plt.title("Top ten words in the Gettysburg Address")
print("Answer 8:")
plt.show(graph1)
print()
#Historgram
print("""Problem 9: Replace the 0 and [] in the next line with appropriate code
so that world_lengths will be a list of the lengths of the words in the Address.""")
word_lengths=[0 for word in []]
print("Answer 9:", word_lengths[:10], "etc.")
print()
#the next two functions can be used to create a historgram
def bucketize(point, bucket_size):
"""floor the point to the next lower multiple of bucket_size"""
return bucket_size * math.floor(point / bucket_size)
def make_histogram(points, bucket_size):
"""buckets the points and counts how many in each bucket"""
return Counter(bucketize(point, bucket_size) for point in points)
length_count= make_histogram(word_lengths, 3)
print("""Problem 10: Replace the [] in the next line with appropriate code to
create a histogram of the word lengths.""")
graph2=plt.bar(length_count.keys(), [], 2.9, align='edge')
print("Answer 10:")
plt.xticks(list(length_count.keys()))
plt.xlabel('Word length (with bucketsize 3)')
plt.ylabel('Frequency')
plt.title("Histogram of word lengths")
#plt.show(graph2)
What I have tried:
Just need helping solving all ten questions that are given above.
Submit an article or tip