MLS-C01 Exploratory Data Analysis Practice Test 29 — 15 Questions

Question 1

During EDA, a data scientist finds that a feature has a skewness value of 2.5. What does this indicate about the data distribution?

Accepted Answer

The distribution is right-skewed. A skewness value of 2.5 is positive and well above zero, indicating a right-skewed (positively skewed) distribution where the tail extends toward higher values. In such distributions, the mean is typically greater than the median, which is greater than the mode. This is a standard EDA interpretation of the skewness statistic.

Answer

The distribution is symmetric

Answer

The distribution is left-skewed

Answer

The distribution has no outliers

Question 2

A data scientist uses SageMaker Studio to run EDA on a dataset with 500 features. The goal is to reduce dimensionality before modeling. Which EDA technique should the data scientist use to understand the variance explained by each feature?

Accepted Answer

Scree plot of principal components. A Scree plot from PCA shows the eigenvalues or variance explained by each principal component, helping decide how many components to retain. Option A is wrong because a histogram shows distribution, not variance. Option C is wrong because a heatmap of correlations shows pairwise relationships, not variance. Option D is wrong because a box plot shows summary statistics.

Answer

Histogram of the target variable

Answer

Heatmap of feature correlations

Answer

Box plot of each feature

Question 3

A data scientist is working with a dataset containing text reviews. The goal is to build a sentiment analysis model. Which EDA step is most critical before feature extraction?

Accepted Answer

Checking the distribution of sentiment labels. Checking the distribution of sentiment labels is critical before feature extraction because it reveals class imbalance, which can bias the model towards the majority class and affect evaluation metrics. This EDA step enables informed decisions about resampling or weighting techniques. Option A (vocabulary size) is not a critical first step; option B (word cloud) is a visualization tool, not essential; option C (removing stop words) is a preprocessing step, not part of EDA.

Answer

Calculating the vocabulary size

Answer

Creating a word cloud

Answer

Removing stop words

Question 4

A data scientist is performing EDA on a dataset with both numeric and categorical features. Which TWO techniques are appropriate for visualizing the relationship between a numeric feature and a binary categorical target?

Accepted Answer

Violin plot grouped by target. It shows the full distribution of the numeric feature for each of the two target classes side by side, revealing differences in shape, spread, and central tendency between the binary groups. Option D (Box plot grouped by target) is also correct because it compactly compares the numeric feature's median, quartiles, and outliers across the two categorical target levels, making group differences easy to assess. Both techniques directly visualize a numeric-vs-binary-categorical relationship by conditioning the numeric distribution on the target. Option A (Histogram) shows the distribution of a single numeric variable but does not inherently encode the binary target unless overlaid, so it is not the intended grouped comparison. Option B (Stacked bar chart) is suited to relationships among categorical variables, not a numeric feature versus a binary target. Option E (Scatter plot) requires two numeric axes and is not appropriate when one variable is categorical.

Answer

Histogram

Answer

Stacked bar chart

Answer

Scatter plot

Question 5

A data scientist wants to identify outliers in a dataset. Which TWO techniques are commonly used for outlier detection during EDA?

Accepted Answer

Box plot. A box plot is correct because it visualizes the distribution via quartiles and explicitly flags outliers as points beyond the whiskers, typically those falling below Q1 − 1.5×IQR or above Q3 + 1.5×IQR. Z-score analysis is correct because it standardizes each value as (x − μ)/σ, and observations with |z| greater than a threshold such as 3 are commonly treated as outliers in EDA. A heatmap is not a dedicated outlier-detection technique; it displays a correlation or value matrix and does not flag individual anomalous points. A bar chart is used for comparing categorical frequencies or aggregates and does not reveal statistical outliers. The Pearson correlation coefficient measures the strength and direction of a linear relationship between two variables, not the presence of outliers.

Answer

Heatmap

Answer

Bar chart

Answer

Pearson correlation coefficient

Question 6

A data scientist is working on a project to predict customer churn for a telecom company. The dataset includes 50,000 records with 20 features, including customer demographics, account information, and service usage. The data scientist uses Amazon SageMaker Studio and loads the data into a pandas DataFrame. During EDA, the data scientist notices that the target variable 'churn' has only 10% positive cases. Additionally, several features have missing values: 'income' has 5% missing, 'age' has 2% missing, and 'total_charges' has 1% missing. The data scientist also observes that 'income' is highly skewed with a long right tail, and 'age' is moderately skewed. The data scientist wants to handle missing values and prepare the data for modeling. Which course of action is most appropriate?

Accepted Answer

Impute 'income' with median, 'age' with median, 'total_charges' with median, and use SMOTE to handle class imbalance after splitting the data.. Median imputation is robust to skewness (particularly for income and age), and SMOTE is applied after splitting to avoid data leakage and handle class imbalance. Option B is wrong because removing rows with missing values would discard roughly 8% of the data (5%+2%+1% with potential overlap), which is a significant loss of information; additionally, random oversampling may lead to overfitting. Option C is wrong because mode imputation is appropriate for categorical data, not for continuous features like income, age, and total_charges. Option D is wrong because mean imputation is sensitive to outliers and skewness, especially for income with a long right tail; also, stratified sampling only ensures proportional representation in train/test splits, it does not generate synthetic samples to address imbalance.

Answer

Remove all rows with any missing values, and use random oversampling to handle class imbalance.

Answer

Impute 'income' with mode, 'age' with mode, 'total_charges' with mode, and use SMOTE after splitting.

Answer

Impute all missing values with the mean of each column, and use stratified sampling to handle class imbalance.

Question 7

A data scientist is building a model to predict housing prices using a dataset with 100,000 records and 50 features. The features include 'sqft_living', 'sqft_lot', 'bedrooms', 'bathrooms', 'floors', 'waterfront', 'view', 'condition', 'grade', etc. The data scientist uses Amazon SageMaker Data Wrangler for EDA. Upon reviewing the data, the data scientist finds that 'sqft_living' has a correlation of 0.7 with 'sqft_above' (square footage above ground) and 0.6 with 'sqft_basement'. Also, 'grade' (overall grade of the house) is highly correlated with 'condition' (0.8). The target variable 'price' is right-skewed. The data scientist plans to use a linear regression model. Which set of actions should the data scientist take to improve model performance?

Accepted Answer

Apply log transformation to the target variable 'price' to reduce skewness, and remove either 'sqft_above' or 'sqft_living' and either 'grade' or 'condition' to handle multicollinearity.. The target 'price' is right-skewed, so a log transform stabilizes variance and makes the relationship more linear for linear regression. The dataset also has strong multicollinearity (sqft_living vs sqft_above/basement; grade vs condition), which inflates coefficient variance and destabilizes OLS estimates, so dropping one feature from each highly correlated pair is the correct fix. Option D addresses both issues directly.

Answer

Apply standard scaling to all numeric features and use the data as is, since linear regression is robust to multicollinearity.

Answer

Remove all features that have correlation >0.5 with any other feature to eliminate multicollinearity, and apply standard scaling to all numeric features.

Answer

Apply principal component analysis (PCA) to all features to reduce dimensionality, and then fit linear regression on the principal components.

Question 8

A data scientist is performing exploratory data analysis on a dataset stored in Amazon S3 using Amazon SageMaker Studio. The dataset has missing values in several columns. Which approach is the MOST efficient way to handle missing values within SageMaker Studio?

Accepted Answer

Use SageMaker Data Wrangler to impute missing values with mean, median, or mode.. SageMaker Data Wrangler is a purpose-built visual data preparation tool inside SageMaker Studio that provides built-in transforms for imputing missing values using mean, median, or mode, along with other common cleaning operations. It integrates directly with S3 data sources and can export the transformed data or the generated processing code, making it the most efficient approach within Studio.

Answer

Run a Jupyter notebook on a local machine to clean the data and upload back to S3.

Answer

Use AWS Glue to run a find-and-replace operation.

Answer

Write a custom Python script using pandas to drop rows with missing values.

Question 9

During exploratory data analysis, a data scientist notices that the distribution of a continuous feature is heavily right-skewed. Which transformation should be applied to make the distribution more symmetric for linear regression?

Accepted Answer

Log transformation. A log transformation compresses the right tail of a right-skewed distribution, pulling in extreme high values and making the distribution more symmetric — which satisfies the normality assumption of linear regression. It is the standard remedy for positive skew in continuous features.

Answer

Standardization (z-score)

Answer

One-hot encoding

Answer

Min-max scaling

Question 10

A data scientist is performing EDA on a dataset with 1,000 features. The goal is to select the most important features for a regression model. Which technique can be used to rank feature importance quickly?

Accepted Answer

Calculate the correlation coefficient of each feature with the target. Correlation analysis with the target variable is a quick way to rank features. Option B (t-SNE) is used for visualization, not feature ranking. Option C (k-means clustering) is an unsupervised clustering method and does not provide feature importance. Option D (PCA) component loadings show variance contribution but are not a direct ranking of feature importance to the target.

Answer

Use t-SNE to visualize feature relationships

Answer

Run k-means clustering and use cluster centroids

Answer

Apply Principal Component Analysis (PCA) and examine component loadings

Question 11

A data scientist needs to profile a large dataset in Amazon S3 to understand its schema, data types, and quality. Which AWS service can automatically generate a data profile with statistics and visualizations?

Accepted Answer

AWS Glue DataBrew. AWS Glue DataBrew is purpose-built for visual data preparation and profiling, automatically generating column-level statistics (null counts, distinct values, min/max, correlations) and visualizations like histograms and box plots without writing code. It connects directly to S3 and produces a 'data profile' artifact that summarizes schema, data types, and quality metrics. This matches the requirement exactly.

Answer

Amazon Athena

Answer

Amazon QuickSight

Answer

Amazon Redshift

Question 12

A data scientist is performing EDA on a dataset with 1 million rows and 50 features. The dataset includes a column 'user_id' with unique identifiers, a column 'event_date' with timestamps, and other columns. Which TWO actions should the data scientist take to understand data quality issues?

Accepted Answer

Analyze missing value patterns across columns. Option A is correct because analyzing missing value patterns across columns is a core EDA step for data quality: it reveals null counts, co-occurrence of missingness, and whether missingness is random or systematic, which directly informs imputation or exclusion decisions. Option B is correct because checking for duplicate rows based on 'user_id' and 'event_date' detects redundant or improperly joined records; since 'user_id' is a unique identifier and 'event_date' a timestamp, a composite key check exposes duplicate events that would distort counts and aggregations. Option C is not appropriate because dropping 'user_id' is a dimensionality-reduction or modeling choice, not a data quality diagnostic, and it discards the key needed for duplicate detection. Option D is not appropriate because PCA is a dimensionality-reduction and visualization technique that does not surface data quality issues like missingness or duplicates. Option E is not appropriate because training a random forest for feature importance is a modeling task, not an EDA step for assessing data quality.

Answer

Drop the 'user_id' column to reduce dimensionality

Answer

Use PCA to reduce dimensions and visualize

Answer

Train a random forest model to identify feature importance

Question 13

A data scientist is analyzing a dataset with a binary target variable. The dataset has 50,000 rows and 200 features. The data scientist wants to identify which features are most predictive. Which TWO methods are appropriate for feature selection during EDA?

Accepted Answer

Mutual information. Mutual information (A) is correct because it measures the dependency between each feature and the binary target, capturing both linear and non-linear relationships, which makes it well-suited for ranking the predictive power of 200 features during EDA. The chi-squared test (B) is also correct because it evaluates the statistical independence between categorical (or discretized) features and a binary target, directly indicating which features are most associated with the target. LSTM neural networks (C) are sequence models for time-series or sequential data and are not a feature-selection method for tabular EDA. K-means clustering (D) is an unsupervised algorithm that groups rows by similarity and does not use the target variable, so it cannot rank feature predictiveness. PCA (E) is a dimensionality-reduction technique that creates new uncorrelated components rather than identifying which original features are most predictive of the target.

Answer

LSTM neural network

Answer

K-means clustering

Answer

Principal Component Analysis (PCA)

Question 14

A data scientist is performing EDA on a dataset with 10 million rows. The dataset has a column 'income' with outliers. The data scientist wants to detect and handle outliers. Which THREE approaches are appropriate?

Accepted Answer

Calculate z-scores and flag values beyond 3 standard deviations. Option A is correct because computing z-scores (value minus mean, divided by standard deviation) and flagging observations beyond ±3 standard deviations is a standard statistical method for detecting outliers in a roughly normal numeric distribution such as 'income'. Option D is correct because box plots visualize the median, quartiles, and whiskers, making values beyond 1.5×IQR immediately visible as plotted points, which is an effective EDA technique for spotting outliers in a 10-million-row column. Option E is correct because the IQR method (flagging values below Q1 − 1.5×IQR or above Q3 + 1.5×IQR) is a robust, distribution-agnostic approach to identifying outliers and is widely used for skewed data like income. Option B is not appropriate because min-max scaling merely rescales values to [0,1] and does not detect or handle outliers; in fact, outliers distort the scaling. Option C is not appropriate because one-hot encoding is for categorical variables and would be meaningless for a continuous numeric 'income' column.

Answer

Apply min-max scaling to the column

Answer

Convert the column to one-hot encoding

Question 15

A data scientist is analyzing a dataset stored in Amazon S3 (100 GB, CSV format) using Amazon SageMaker Studio. The dataset contains 500 columns and 10 million rows. The data scientist wants to understand the distribution of each column, detect missing values, and identify outliers. However, the SageMaker Studio notebook instance runs out of memory when loading the entire dataset into a pandas DataFrame. The data scientist needs to complete the EDA efficiently without modifying the source data. What should the data scientist do?

Accepted Answer

Use Amazon SageMaker Data Wrangler to create a data flow that samples and profiles the data.. SageMaker Data Wrangler is purpose-built for EDA on large datasets; it automatically samples data and profiles columns without requiring the entire dataset to be loaded into memory. Option A (sampling 10% of rows) could work but risks missing critical patterns or outliers, and is less integrated than Data Wrangler. Option B (converting to Parquet with AWS Glue) adds complexity and still requires memory to load into pandas. Option C (larger instance) may still be insufficient and is more expensive. Data Wrangler provides a seamless, integrated experience within SageMaker Studio for efficient EDA.

Answer

Write a script that loads only a random 10% sample of rows to reduce memory usage.

Answer

Use AWS Glue ETL to transform the data into Parquet format and then load into pandas.

Answer

Launch a larger notebook instance with more memory (e.g., ml.r5.24xlarge) and reload the data.