What problem does it solve? Working with real-world CSV data often means dealing with missing values, unclear data quality, and the manual effort of building visualizations. This Skill automates the full exploratory data analysis workflow: it detects missing value patterns, applies appropriate imputation methods per column, and produces an interactive dashboard for trend and distribution analysis. ## Core Features & Use Cases - Missing Value Analysis: Scans CSV files to detect missing data, identify column types (numeric, categorical, temporal, ID), and recommend imputation strategies with reasoning, outputting a JSON report. - Intelligent Imputation: Applies mean, median, mode, KNN, forward fill, interpolation, or constant-value imputation based on each column's characteristics, automatically dropping columns with over 70% missing data and rows missing critical IDs. - Interactive Dashboards: Generates Plotly Dash dashboards with summary statistics, time series plots, distribution histograms, correlation heatmaps, categorical bar charts, and scatter plot matrices, with optional static HTML export. - Use Case: Given a sales dataset with gaps in revenue and customer fields, run the full workflow to analyze data quality, impute missing values with statistically appropriate methods, and explore the cleaned data in an interactive browser dashboard. ## Quick Start Analyze the attached CSV file for missing values, impute them with appropriate methods, and create an interactive dashboard to visualize the trends.
