About this skill

Problem

Many tabular analysis tasks are simple: open a CSV/Excel file, inspect mean, median, and missing values, filter rows, and export results. Without a small utility, developers still need to write parsing, encoding, and validation code, especially for GBK files. DataLens数析 packages these frequent operations into callable Python functions, reducing glue code between raw data and analysis output.

How It Works

Read data: load_csv(path) reads a CSV file into a list of dictionaries and auto-detects utf-8, gbk, or gb2312.
Analyze columns: analyze_column(data, column) returns mean, median, max/min, and null count.
Filter rows: filter_data(data, column, operator, value) supports eq, neq, gt, gte, lt, lte, contains, and in.
Export results: export_json(data, path) saves processed data as JSON; get_column_summary(data) returns a quick column overview.

Boundaries

The skill is centered on Python function calls and is best for CSV data, column-level statistics, filtering, and JSON export. The provided materials do not show concrete chart rendering or report export implementations, so do not assume it produces PNG/SVG/PDF or one-click reports. For Excel files, confirm whether the host tool converts them to CSV first.

Screenshots

Use Cases

After receiving a sales CSV, inspect columns and nulls, filter by region, then export JSON.
Check whether a GBK customer file is readable and compute mean and median for amount columns.
Give an Agent a consistent Python function to validate fields, filter rows, and save JSON results.
Before release, sample-check order CSV key columns and output min, max, and null summaries.

Best For

Data analysts processing weekly sales CSVs who need quick column overviews and stats.
Python engineers building Agent tools who want standard-library tabular functions.
Business ops teams handling GBK reports who need readable filtering of customer data.
Data-quality engineers validating nulls, extremes, and missing fields at scale.