Prepare and Clean Data SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 1)

Questions 1–5

1. 1expert · hard

   A data scientist is building a sentiment analysis model on product reviews. The reviews contain emojis, slang, and negations like 'not good'. The scientist wants to preserve sentiment and negations while reducing noise. Which preprocessing approach is most appropriate?

   • AConvert emojis to text representations, keep negations by replacing 'not' with 'not_' before the following word, and remove stop words except for negation words.
   • BApply lemmatization and remove punctuation, but keep all stop words.
   • CKeep all words as-is and only convert to lowercase.
   • DRemove all emojis, remove all stop words, and apply stemming.
   Reveal Solution Discussion Select an answer first
2. 2application · medium

   A data scientist is working with a dataset where 30% of the values in a key feature are missing. The scientist plans to use a tree-based model that can handle missing values natively. What is the most appropriate action?

   • ALeave the missing values as-is and let the tree-based model handle them.
   • BImpute the missing values with the mean of the feature.
   • CRemove all rows with missing values.
   • DImpute the missing values with a constant like -999.
   Reveal Solution Discussion Select an answer first
4. 3application · medium

   A data scientist is building a logistic regression model. The dataset includes a categorical feature 'Education' with levels: 'High School', 'Bachelor', 'Master', 'PhD'. The scientist wants to preserve the ordinal nature of the feature. Which encoding method is most appropriate?

   • AApply one-hot encoding to all levels.
   • BUse binary encoding to reduce dimensionality.
   • CApply label encoding with a custom mapping that reflects the educational order.
   • DApply frequency encoding based on the count of each level.
   Reveal Solution Discussion Select an answer first
5. 4application · medium

   A data scientist is preprocessing customer review text for a sentiment analysis model. The text contains HTML tags, emojis, and inconsistent capitalization. The scientist wants to reduce noise while preserving sentiment-bearing words. Which preprocessing sequence is most appropriate?

   • ARemove emojis, apply stemming, and then remove stop words.
   • BRemove HTML tags, convert to lowercase, remove stop words, and apply stemming.
   • CTokenize, remove HTML tags, and apply stemming without lowercasing.
   • DConvert to lowercase, remove punctuation, and apply lemmatization without removing stop words.
   Reveal Solution Discussion Select an answer first
6. 5foundation · easy

   What is the purpose of stop-word removal in text preprocessing?

   • ATo remove common words that carry little meaning, such as 'the' and 'and'
   • BTo convert all words to lowercase
   • CTo split text into individual words
   • DTo reduce words to their root form
   Reveal Solution Discussion Select an answer first