Data cleansing and preprocessing with cuDF and pandas: Practice Questions — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)

Practice Questions: Data Cleansing and Preprocessing with cuDF and pandas

These multiple-choice questions are designed to help you prepare for the Data Preparation section of the NVIDIA-Certified Professional: Accelerated Data Science exam, focusing specifically on data cleansing and preprocessing using cuDF and pandas.

1. Which cuDF function is typically used to remove rows containing missing values from a DataFrame?

   • A) dropna()
   • B) fillna()
   • C) replace()
   • D) drop_duplicates()

   Correct answer: A) dropna()

   Explanation: The dropna() function removes rows with missing (NaN) values, which is a common data cleansing step. fillna() replaces missing values but does not remove rows.

2. When converting a pandas DataFrame to a cuDF DataFrame for GPU processing, which method is recommended?

   • A) cudf.DataFrame(pandas_df)
   • B) pandas_df.to_cudf()
   • C) cudf.from_pandas(pandas_df)
   • D) pandas_df.convert_to_cudf()

   Correct answer: C) cudf.from_pandas(pandas_df)

   Explanation: The cudf.from_pandas() function efficiently converts a pandas DataFrame to a cuDF DataFrame for accelerated GPU operations.

3. Which pandas function is used to standardize column names by removing leading/trailing whitespace and converting to lowercase?

   • A) df.columns.strip().lower()
   • B) df.columns = df.columns.str.strip().str.lower()
   • C) df.rename(columns=lambda x: x.strip().lower())
   • D) df.clean_columns()

   Correct answer: B) df.columns = df.columns.str.strip().str.lower()

   Explanation: The str.strip() and str.lower() string methods applied to the columns attribute standardize column names. Option C is close but does not assign the result back.

4. In cuDF, which method would you use to replace all occurrences of a specific value in a column?

   • A) replace()
   • B) fillna()
   • C) map()
   • D) dropna()

   Correct answer: A) replace()

   Explanation: The replace() method substitutes specified values with new ones, useful for correcting or standardizing data entries.

5. Which pandas function helps identify duplicate rows in a DataFrame before deciding to remove them?

   • A) duplicated()
   • B) drop_duplicates()
   • C) unique()
   • D) isnull()

   Correct answer: A) duplicated()

   Explanation: duplicated() returns a boolean Series indicating duplicate rows, allowing inspection before removal. drop_duplicates() removes duplicates directly.

6. Which of the following is a key advantage of using cuDF over pandas for data preprocessing?

   • A) Supports more file formats
   • B) Runs on CPU with multi-threading
   • C) Accelerated GPU processing for large datasets
   • D) Automatically fixes missing data

   Correct answer: C) Accelerated GPU processing for large datasets

   Explanation: cuDF leverages NVIDIA GPUs to speed up data cleansing and preprocessing tasks, especially beneficial for large-scale data.

7. Which pandas method is used to fill missing values with a specified constant?

   • A) fillna()
   • B) dropna()
   • C) replace()
   • D) interpolate()

   Correct answer: A) fillna()

   Explanation: fillna() replaces missing values with a specified value, which is a common preprocessing step to handle incomplete data.

8. In a data preprocessing pipeline, why is it important to monitor bottlenecks when using cuDF and pandas?

   • A) To ensure data is encrypted
   • B) To optimize performance and resource usage
   • C) To increase data redundancy
   • D) To reduce the number of columns

   Correct answer: B) To optimize performance and resource usage

   Explanation: Monitoring bottlenecks helps identify slow stages in the pipeline, enabling targeted optimization for faster data processing and efficient GPU utilization.

More in this topic

Data cleansing and preprocessing with cuDF and pandas: Common Mistakes — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Monitoring pipeline bottlenecks — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Data Preparation — NVIDIA-Certified Professional: Accelerated Data ScienceData cleansing and preprocessing with cuDF and pandas — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Data cleansing and preprocessing with cuDF and pandas: Quick Reference — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Generating synthetic data with cuDF and RAPIDS — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Data cleansing and preprocessing with cuDF and pandas: Worked Example — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)Transforming and standardizing features — Data Preparation (NVIDIA-Certified Professional: Accelerated Data Science)