NLP Basics Assessment - Solutions

For this assessment we'll be using the short story An Occurrence at Owl Creek Bridge by Ambrose Bierce (1890).
The story is in the public domain; the text file was obtained from Project Gutenberg.



In [1]:

    
# RUN THIS CELL to perform standard imports:
import spacy
nlp = spacy.load('en_core_web_sm')

1. Create a Doc object from the file owlcreek.txt

HINT: Use with open('../TextFiles/owlcreek.txt') as f:



In [2]:

    
# Enter your code here:

with open('../TextFiles/owlcreek.txt') as f:
    doc = nlp(f.read())



In [3]:

    
# Run this cell to verify it worked:

doc[:36]









    Out[3]:





AN OCCURRENCE AT OWL CREEK BRIDGE

by Ambrose Bierce

I

A man stood upon a railroad bridge in northern Alabama, looking down
into the swift water twenty feet below.

2. How many tokens are contained in the file?



In [4]:

    
len(doc)









    Out[4]:





4833

3. How many sentences are contained in the file?
HINT: You'll want to build a list first!



In [5]:

    
sents = [sent for sent in doc.sents]
len(sents)









    Out[5]:





211

4. Print the second sentence in the document
HINT: Indexing starts at zero, and the title counts as the first sentence.



In [6]:

    
print(sents[1].text)









    



A man stood upon a railroad bridge in northern Alabama, looking down
into the swift water twenty feet below.

5. For each token in the sentence above, print its text, POS tag, dep tag and lemma
CHALLENGE: Have values line up in columns in the print output.



In [7]:

    
# NORMAL SOLUTION:
for token in sents[1]:
    print(token.text, token.pos_, token.dep_, token.lemma_)









    



A DET det a
man NOUN nsubj man
stood VERB ROOT stand
upon ADP prep upon
a DET det a
railroad NOUN compound railroad
bridge NOUN pobj bridge
in ADP prep in
northern ADJ amod northern
Alabama PROPN pobj alabama
, PUNCT punct ,
looking VERB advcl look
down PART prt down

 SPACE  

into ADP prep into
the DET det the
swift ADJ amod swift
water NOUN pobj water
twenty NUM nummod twenty
feet NOUN npadvmod foot
below ADV advmod below
. PUNCT punct .
  SPACE



In [8]:

    
# CHALLENGE SOLUTION:
    for token in sents[1]:
        print(f'{token.text:{15}} {token.pos_:{5}} {token.dep_:{10}} {token.lemma_:{15}}')









    



A               DET   det        a              
man             NOUN  nsubj      man            
stood           VERB  ROOT       stand          
upon            ADP   prep       upon           
a               DET   det        a              
railroad        NOUN  compound   railroad       
bridge          NOUN  pobj       bridge         
in              ADP   prep       in             
northern        ADJ   amod       northern       
Alabama         PROPN pobj       alabama        
,               PUNCT punct      ,              
looking         VERB  advcl      look           
down            PART  prt        down           

               SPACE            
              
into            ADP   prep       into           
the             DET   det        the            
swift           ADJ   amod       swift          
water           NOUN  pobj       water          
twenty          NUM   nummod     twenty         
feet            NOUN  npadvmod   foot           
below           ADV   advmod     below          
.               PUNCT punct      .              
                SPACE

6. Write a matcher called 'Swimming' that finds both occurrences of the phrase "swimming vigorously" in the text
HINT: You should include an 'IS_SPACE': True pattern between the two words!



In [9]:

    
# Import the Matcher library:

from spacy.matcher import Matcher
matcher = Matcher(nlp.vocab)



In [10]:

    
# Create a pattern and add it to matcher:

pattern = [{'LOWER': 'swimming'}, {'IS_SPACE': True, 'OP':'*'}, {'LOWER': 'vigorously'}]

matcher.add('Swimming', None, pattern)



In [11]:

    
# Create a list of matches called "found_matches" and print the list:

found_matches = matcher(doc)
print(found_matches)









    



[(12881893835109366681, 1274, 1277), (12881893835109366681, 3607, 3610)]

7. Print the text surrounding each found match



In [12]:

    
print(doc[1265:1290])









    



By diving I could evade the bullets and, swimming
vigorously, reach the bank, take to the woods and get away home



In [13]:

    
print(doc[3600:3615])









    



over his shoulder; he was now swimming
vigorously with the current.

EXTRA CREDIT:
Print the sentence that contains each found match



In [18]:

    
for sent in sents:
    if found_matches[0][1] < sent.end:
        print(sent)
        break









    



By diving I could evade the bullets and, swimming
vigorously, reach the bank, take to the woods and get away home.



In [19]:

    
for sent in sents:
    if found_matches[1][1] < sent.end:
        print(sent)
        break









    



The hunted man saw all this over his shoulder; he was now swimming
vigorously with the current.

NLP Basics Assessment - Solutions

Great Job!