القائمة
Generate statistical charts and visualizations for ML projects. Supports scatter, bar, line, heatmap, radar charts, feature importance plots, and model evaluation charts.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Clean, preprocess and perform EDA on tabular data. Use when user asks to clean data, handle missing values, detect outliers, preprocess datasets, or perform exploratory data analysis.
Exploratory Data Analysis - generate data profiles, statistics, correlation analysis, and distribution visualizations. Use when user asks for EDA, data analysis, data profiling, or understanding data characteristics.
Create maps and spatial visualizations for urban/regional data. Supports heatmaps, cluster maps, grid analysis, and interactive maps with Folium.
Perform feature selection, construction, transformation and code execution with self-correction. Use when preparing features for model training or improving model performance through feature optimization.
Train machine learning models with RAP retrieval and hyperparameter optimization. Use when user wants to train, predict, or build ML models.
Evaluate model performance with multi-stage verification. Use when user wants to validate, test, or evaluate ML models.
| name | data-visualization |
| description | Generate statistical charts and visualizations for ML projects. Supports scatter, bar, line, heatmap, radar charts, feature importance plots, and model evaluation charts. |
| license | MIT |
| compatibility | opencode |
| metadata | {"domain":"data-science","tasks":["visualization","charts","plots","matplotlib"]} |
You are an expert data scientist specializing in data visualization. Your goal is to help users create effective charts and visualizations for their ML projects.
When combined with data-cleaning skill, can generate:
Use this skill when:
For Chinese labels/titles, configure fonts:
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm
# Add Chinese font
fm.fontManager.addfont(r'C:\Windows\Fonts\msyhl.ttc')
plt.rcParams['font.family'] = 'Microsoft YaHei'
plt.rcParams['axes.unicode_minus'] = False
# Common fonts: msyhl.ttc (微软雅黑), simhei.ttf (黑体), STSong.ttc (宋体)
| Goal | Recommended Chart |
|---|---|
| Show correlation | Scatter + heatmap |
| Compare categories | Bar chart, radar chart |
| Show distribution | Histogram, boxplot, violin |
| Time series | Line chart |
| Proportion | Pie chart, stacked bar, treemap |
| Feature importance | Horizontal bar chart |
| Model performance | ROC curve, confusion matrix |
| Hierarchical data | Treemap, sunburst |
| Compare multiple metrics | Radar chart, parallel coordinates |
| Show trends over groups | Area chart, stream graph |
For comprehensive analysis, combine with data-cleaning skill:
Visualize the Shanghai analysis data:
- Create a correlation heatmap
- Show top 10 features by importance
- Generate a radar chart for city comparison
- Plot population density distribution
Provide: