Exploratory data analysis and descriptive statistics: Worked Example — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)

Exploratory Data Analysis and Descriptive Statistics: Worked Example

Exploratory Data Analysis (EDA) and descriptive statistics are foundational skills for any data scientist, especially when preparing data for GPU-accelerated modeling as covered in the NVIDIA-Certified Associate: Accelerated Data Science certification. This worked example demonstrates the step-by-step process of performing EDA and calculating descriptive statistics on a realistic dataset.

Scenario

Suppose you are given a dataset containing customer information for an e-commerce platform. The dataset includes variables such as Age, Annual Income (in thousands), and Spending Score (a score assigned by the platform based on customer behavior).

Step 1: Initial Data Inspection

Start by loading the dataset and inspecting the first few rows to understand its structure and identify any missing values or anomalies.

• Check data types for each variable.
• Look for null or missing values.

Reasoning: Understanding data types helps determine appropriate statistical methods and visualizations. Missing values need to be addressed before analysis.

Step 2: Summary Descriptive Statistics

Calculate key descriptive statistics for each numeric variable:

• Mean: Average value, indicating central tendency.
• Median: Middle value, robust to outliers.
• Standard Deviation (SD): Measures spread or variability.
• Minimum and Maximum: Range of data.
• Quartiles (Q1, Q3): Help understand distribution shape.

Example Calculation for Age:

• Mean Age = sum of all ages / number of customers.
• Median Age = middle value when ages are sorted.
• SD Age = square root of variance (average squared deviation from mean).

Step 3: Visualizing Distributions

Choose appropriate plots to visualize the distribution of each variable:

• Histograms: Show frequency distribution of continuous variables like Age and Annual Income.
• Boxplots: Highlight median, quartiles, and potential outliers.

Reasoning: Visualizations reveal patterns such as skewness, modality, and outliers that descriptive statistics alone may not fully capture.

Step 4: Identifying Relationships

Explore relationships between variables using scatter plots and correlation coefficients:

• Scatter Plot: Plot Annual Income vs. Spending Score to visually assess any trend.
• Pearson Correlation Coefficient: Quantify linear relationship strength and direction.

Interpretation: A positive correlation indicates that higher income customers tend to have higher spending scores.

Step 5: Interpretation and Next Steps

Summarize findings from descriptive statistics and visualizations:

• Age distribution may be approximately normal with some skewness.
• Annual Income shows wide variability with some high-income outliers.
• Spending Score distribution may be bimodal, suggesting distinct customer segments.
• Moderate positive correlation between Annual Income and Spending Score.

These insights guide feature engineering and model selection for accelerated data science workflows on GPUs.

Worked Example Summary

Dataset: Customer Age, Annual Income (k$), Spending Score

Step 1: Loaded data, confirmed no missing values.

Step 2: Calculated descriptive statistics:

• Age: Mean = 38.5, Median = 37, SD = 12.4
• Annual Income: Mean = 60.2k, Median = 58k, SD = 26.1k
• Spending Score: Mean = 50.3, Median = 49, SD = 25.7

Step 3: Histograms showed slight right skew for Age; boxplots identified a few income outliers.

Step 4: Scatter plot and Pearson correlation (r = 0.45) indicated a moderate positive relationship between income and spending score.

Step 5: Concluded data is suitable for further modeling after normalization and outlier treatment.

More in this topic

Interpreting patterns, trends, and relationships — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Descriptive Analysis and Visualization — NVIDIA-Certified Associate: Accelerated Data ScienceHypothesis testing and statistical significance: Quick Reference — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Exploratory data analysis and descriptive statistics: Common Mistakes — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Exploratory data analysis and descriptive statistics: Practice Questions — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Exploratory data analysis and descriptive statistics — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Hypothesis testing and statistical significance: Common Mistakes — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Hypothesis testing and statistical significance — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Hypothesis testing and statistical significance: Practice Questions — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Hypothesis testing and statistical significance: Worked Example — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Visualization and appropriate plot selection — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)Exploratory data analysis and descriptive statistics: Quick Reference — Descriptive Analysis and Visualization (NVIDIA-Certified Associate: Accelerated Data Science)