Applied Text Mining in Python Coursera Quiz Answers – Networking Funda

All Weeks Applied Text Mining in Python Coursera Quiz Answers

Applied Text Mining in Python Week 01 Quiz Answers

Practice Quiz Answers

Q1. Which of these options correspond to matching a pattern at least once?

• *
• ?
• + (Ans)
• {2}
• {2, 2}
• {2,3}
• {1,3}
• {3,}
• {,3}
• {2,}

Q2. Which of these options correspond to matching a pattern zero or more times?

• * (Ans)
• ?
• +
• {2}
• {2, 2}
• {2,3}
• {1,3}
• {3,}
• {,3}
• {2,}

Q3. Which of these options correspond to matching xyz at the start of the string?

• [^xyz]
• ^xyz (Ans)
• $xyz
• \\xyz
• .xyz
• []xyz
• [xyz^]
• xyz^
• xyz$
• xyz\\
• xyz.
• xyz[]
• (xyz)
• [xyz]
• xyz
• “xyz”

Q4. Which of these options correspond to matching xyz at the end of the string?

• [^xyz]
• ^xyz
• $xyz
• \\xyz
• .xyz
• []xyz
• [xyz^]
• xyz^
• xyz$ (Ans)
• xyz\\
• xyz.
• xyz[]
• (xyz)
• [xyz]
• xyz
• “xyz”

Module 1 Quiz Answers

Q1. Which of these options correspond to matching a pattern at most once?

• *
• ?
• +
• {2}
• {2, 2}
• {2,3}
• {1,3}
• {3,}
• {,3}
• {2,}

Q2. Which of these options correspond to matching a pattern at least twice?

• *
• ?
• +
• {2}
• {2, 2}
• {2,3}
• {1,3}
• {3,}
• {,3}
• {2,}

Q3. Which of these options correspond to matching a pattern at most thrice?

• *
• ?
• +
• {2}
• {2, 2}
• {2,3}
• {1,3}
• {3,}
• {,3}
• {2,}

Q4. Which of these options correspond to match none of the characters x,y,z?

• [^xyz]
• ^xyz
• $xyz
• \xyz
• .xyz
• []xyz
• xyz^
• xyz$
• xyz\
• xyz.
• xyz[]
• (xyz)
• xyz
• “xyz”

Q5. Which of these options correspond to match one of the characters x,y,z?

• [^xyz]
• ^xyz
• $xyz
• \xyz
• .xyz
• []xyz
• xyz^
• xyz$
• xyz\
• xyz.
• xyz[]
• (xyz)
• xyz
• “xyz”

Q6. Which of these options correspond to match the sequence xyz?

• [^xyz]
• ^xyz
• $xyz
• \xyz
• .xyz
• []xyz
• xyz^
• xyz$
• xyz\\
• xyz.
• xyz[]
• (xyz)
• xyz

Applied Text Mining in Python Week 02 Quiz Answers

Practice Quiz

Q1. The function to check if a string variable “string1” is lowercased is:

• string.lower(string1)
• string1.islower()
• string1.tolower()
• string.islower(string1)

Q2. The POS tag code for adjectives, as given by NLTK is:

• AA
• ADJ
• AJ
• JJ

Module 2 Quiz Answers

Q1. The function to use to make a string variable, string1, uppercase is:

• string1.toupper()
• string.toupper(string1)
• string1.upper()
• string.upper(string1)

Q2. A string variable, string2, has some lagging whitespace characters. You would remove these using:

• string2.lstrip()
• string2.lstrip(‘ ’)
• string2.rstrip()
• string2.rstrip(‘ ’)

Q3. What does NLTK’s function word_tokenize() do?

• It splits a sentence into words.
• It splits a word into characters.
• It retains valid words and tokens in a sentence and removes invalid words.
• It finds valid word forms for tokens in a sentence (i.e. maps all words to closest valid words).

Q4. What is a sentence parser typically used for?

• It is used to parse sentences to check if they are utf8 compliant.
• It is used to parse sentences to derive their most likely syntax tree structures.
• It is used to parse sentences to assign parts of speech tags to all tokens.
• It is used to check if sentences can be parsed into meaningful tokens.

Q5. If you want to map all derivationally related words to their root verb using NLTK, you will use:

• Lemmatizer
• Porter Stemmer
• Splitter
• Word sense disambiguator

Applied Text Mining in Python Week 03 Quiz Answers

Week 3: Classification of Text

Q1. You are given a dataset on movie reviews with a 1,000 labeled reviews. The labels are one of five movie genres: Action, Comedy, Drama, Horror, and Sci-Fi. The dataset has roughly 200 movie reviews for each movie genre.

Your first task is to learn a supervised classifier to identify just the reviews for Comedy movies from the dataset. Such a task is:

• Single-class classification
• Two-class (Binary) classification
• Multi-class classification
• Multi-label classification

Q2. The dataset available for the first task is:

• Balanced
• Insufficient
• Skewed
• Unlabeled

Q3. Suppose you decide to train a support vector machine classifier for this first task. The methodology you will employ will be a:

• A. One vs One classifier
• B. One vs Rest classifier
• C. Single binary classifier
• Either A or B
• Classifier cannot be trained

Q4. You are given a dataset on movie reviews with a 1,000 labeled reviews. The labels are one of five movie genres: Action, Comedy, Drama, Horror, and Sci-Fi. The dataset has roughly 200 movie reviews for each movie genre.

Your second task is to learn to identify all five movie genres. Such a task is:

• Single-class classification
• Two-class (Binary) classification
• Multi-class classification
• Multi-label classification

Q5. The dataset available for the second task is:

• Balanced
• Insufficient
• Skewed
• Unbalanced

Q6. Suppose you decide to train a support vector machine classifier for the second task. The methodology you will employ will be a:

• A. One vs One classifier
• B. One vs Rest classifier
• C. Single five-class classifier
• Either A or B
• Classifier cannot be trained

Q7. How many binary classifiers will you need to train for the second task using the one-vs-one classification approach?

• 1
• 5
• 10
• 25

Applied Text Mining in Python Week 04 Quiz Answers

Practice Quiz Answers

Q1. In the WordNet hierarchy, the word ‘puppy’ is a direct hyponym of ‘dog’ (i.e. ‘puppy’ is a kind of ‘dog’. The least common subsumer for ‘puppy’ and ‘dog’ is:

• Puppy
• Dog
• Something other than ‘puppy’ or ‘dog’
• No least common subsumers exist for hyponym relationships

Q2. If ‘puppy’ is a direct hyponym of ‘dog’, ‘dog’ is a direct ______ of ‘puppy’

• Hyponym
• Hypernym
• Meronym
• Synonym

Module 4 Quiz Answers

Q1. Which of the following is not included in WordNet:

• Sense of a word
• Derivationally related forms
• Pronunciation
• Synonyms

Q2. If the shortest distance between words A and B in the WordNet hierarchy is 6, the path-based similarity measure PathSim(A,B) would be:

• 6
• 1/6 = 0.167
• 1 – 1/5 = 5/6 = 0.833
• 1/(6+1) = 1/7 = 0.143

Q3. When computing the similarity between words C and D, the distributional similarity based metric gives a higher score than a path-based similarity measure. What can be inferred from this observation?

• Distributional Similarity-based measure is a better metric to compute similarity between C and D (because higher numbers are better)
• Path-based similarity measure is a better metric to compute similarity between C and D (because lower numbers are better)
• This cannot happen — distributional similarity is always lower than path-based similarity.
• Nothing can be inferred. The similarity values from different measures cannot be directly compared.

Q4. Which of the following approaches can be used to recognize monetary values (like USD 100, JPY 1000, etc.)

• Building regular expressions
• Looking up entries in a list
• Checking if something is capitalized or title cased
• All of the above

Q5. Which of the following is not given as input for a topic modeling setup?

• Number of topics
• The document corpus
• The topics
• The topic modeling approach (LDA, PLSA, …)

Get All Course Quiz Answers of Applied Data Science with Python Specialization

Introduction to Data Science in Python Coursera Quiz Answers

Applied Plotting, Charting & Data Representation in Python Quiz Answers

Applied Machine Learning in Python Coursera Quiz Answers

Applied Text Mining in Python Coursera Quiz Answers

Applied Social Network Analysis in Python Coursera Quiz Answers