Data Analysis Skill
Analyze data, create visualizations, and generate actionable insights.
When to Use
Use this skill when the user wants to:
- Analyze data from datasets
- Create data visualizations
- Perform statistical analysis
- Clean and transform data
- Generate data reports
- Find patterns and trends
Data Analysis Workflow
1. Data Understanding
- Examine data structure and content
- Identify data types and formats
- Understand relationships between variables
2. Data Cleaning
- Handle missing values
- Remove duplicates
- Standardize formats
- Fix data quality issues
3. Data Exploration
- Calculate summary statistics
- Find correlations
- Detect outliers
- Identify patterns
4. Data Analysis
- Perform statistical tests
- Group and aggregate data
- Create derived metrics
- Test hypotheses
5. Visualization
- Create charts and graphs
- Build interactive dashboards
- Design meaningful visualizations
- Present findings
Tools & Libraries
Python
- Pandas: Data manipulation
- NumPy: Numerical computing
- Matplotlib: Static plotting
- Seaborn: Statistical visualization
- Plotly: Interactive plots
- Scikit-learn: ML preprocessing
JavaScript
- D3.js: Data visualization
- Chart.js: Simple charts
- Plotly.js: Interactive plots
- Apache ECharts: Powerful charts
R
- ggplot2: Visualization
- dplyr: Data manipulation
- tidyr: Tidying data
Analysis Types
Descriptive Analysis
- Summarize data with statistics
- Create frequency distributions
- Calculate central tendency
Exploratory Analysis
- Identify patterns
- Find correlations
- Visualize distributions
Predictive Analysis
- Forecast trends
- Build predictive models
- Estimate values
Diagnostic Analysis
- Understand cause and effect
- Root cause analysis
- Anomaly detection
Visualization Guidelines
- Clarity over aesthetics: Make data easy to understand
- Tell a story: Each visualization should have a purpose
- Avoid chart junk: Don't overcomplicate
- Color appropriately: Use colors to highlight, not decorate
- Add context: Labels, titles, and annotations
Deliverables
- Analysis report with findings
- Data visualizations
- Data cleaning pipeline
- Statistical analysis results
- Insights and recommendations
Quality Checklist
- Data is properly cleaned and validated
- Analysis is statistically sound
- Visualizations are clear and accurate
- Storyline is logical and compelling
- Code is reproducible and documented
- Findings are actionable