数据与 AI技能

Load, clean, summarize, and join tabular data from CSV, Excel, JSON, or database exports using pandas. Check missing values, data types, and row counts, then independently verify key figures before reporting numbers printed by the code.

中文简介正在准备中。当前显示英语简介。

• Summarizing revenue by region
• Cleaning missing values and duplicate rows
• Joining files by customer ID

Turn data into charts suited to comparisons, trends, distributions, relationships, or shares. Add clear titles, units, and accessible colors, then export a static PNG or interactive HTML with hover details and zoom controls.

中文简介正在准备中。当前显示英语简介。

• Charting monthly revenue trends
• Comparing totals across regions or categories
• Examining order-size distributions

Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.

中文简介正在准备中。当前显示英语简介。

• Summarizing and joining data files
• Exploring trends and distributions
• Cleaning data before analysis

Store large multidimensional arrays in compressed chunks, small sections that can be read separately. Guides local and cloud storage, partial reads and writes, and integration with NumPy, Dask, and Xarray for scientific data workflows.

中文简介正在准备中。当前显示英语简介。

• Processing arrays larger than available memory
• Reading and writing array subsets on S3 or GCS
• Appending new time steps to scientific datasets

Get guidance on fine-tuning language models with Unsloth, including LoRA and QLoRA methods for training with fewer resources. The skill points to documentation for understanding APIs, implementing training code, debugging problems, and exploring speed and memory optimizations.

中文简介正在准备中。当前显示英语简介。

• Exploring faster training with lower memory use
• Learning about LoRA and QLoRA fine-tuning
• Checking Unsloth features and APIs

Retrieve U.S. federal financial data from the Treasury Fiscal Data API, a public data service. Filter debt, revenue, spending, interest rates, and exchange rates by date or field to prepare records for analysis.

中文简介正在准备中。当前显示英语简介。

• Track changes in U.S. federal debt
• Collect monthly revenue and spending data
• Retrieve Treasury interest rates and exchange rates

Build reinforcement learning experiments, where agents learn actions from rewards, using Stable Baselines3. Get guidance on choosing algorithms, creating Gymnasium environments, training and evaluating agents, monitoring progress, and saving models for later use.

中文简介正在准备中。当前显示英语简介。

• Choosing an algorithm for a reinforcement learning experiment
• Creating and checking a custom Gymnasium environment
• Monitoring training and saving checkpoints

Analyze tabular datasets too large to fit in memory using Vaex. Filter rows, calculate statistics, visualize distributions, convert file formats, and prepare machine learning workflows with operations that defer computation until results are needed.

中文简介正在准备中。当前显示英语简介。

• Aggregate CSV files too large to fit in memory
• Explore large datasets with histograms and heatmaps
• Convert CSV data to HDF5 or Arrow

Build and train graph neural networks, models that learn from connected entities, using PyTorch Geometric. The skill covers classifying nodes or whole graphs, predicting missing connections, and modeling molecular properties or networks with multiple entity types.

中文简介正在准备中。当前显示英语简介。

• Classifying papers in citation networks
• Predicting missing connections in graphs
• Modeling molecular properties with graph neural networks

Analyze research data with suitable statistical tests, regression, correlation, or Bayesian methods. Check assumptions, estimate effect sizes and uncertainty, plan sample sizes, and prepare figures, tables, and reports following APA academic reporting conventions.

中文简介正在准备中。当前显示英语简介。

• Choosing statistical tests for research data
• Checking analysis assumptions and alternative methods
• Estimating sample sizes before collecting data

Build PyTorch machine learning workflows for molecules, proteins, and biomedical relationships. Get guidance on datasets, model selection, training, and evaluation for property prediction, protein modeling, molecule generation, and planning synthesis routes from target molecules.

中文简介正在准备中。当前显示英语简介。

• Predicting molecular solubility and toxicity
• Predicting protein function from sequences or structures
• Exploring new drug uses through biomedical relationships

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

中文简介正在准备中。当前显示英语简介。

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Process large CSV and TSV files from the terminal with filtering, sorting, deduplication, grouping, and joins. The skill uses xan CLI, a command-line tool, for streaming workflows that keep memory use low.

中文简介正在准备中。当前显示英语简介。

• Filtering rows in large CSV files
• Summarizing sales by category
• Removing duplicates and joining tables

Guides statistical analysis in Python, including regression, time series forecasting, and hypothesis tests. Helps interpret estimates and uncertainty, check model assumptions, investigate influential observations, compare models, and produce statistical tables for reporting.

中文简介正在准备中。当前显示英语简介。

• Interpreting regression coefficients and confidence intervals
• Forecasting time series with prediction intervals
• Checking model assumptions and influential observations

Work with mathematical formulas in Python to solve equations, calculate derivatives and integrals, and manipulate matrices. Keep exact results using symbols, then turn expressions into executable code or formatted LaTeX equations.

中文简介正在准备中。当前显示英语简介。

• Solve equations while keeping variables and exact values
• Calculate derivatives, integrals, and limits
• Find matrix eigenvalues and inverses

Use pre-trained models with Hugging Face Transformers for text generation, translation, image recognition, and speech tasks. Load models, prepare inputs, run predictions, and fine-tune them, meaning further training with your own data.

中文简介正在准备中。当前显示英语简介。

• Prototyping text classification, summarization, or translation
• Building image recognition or speech recognition workflows
• Adjusting text generation settings

Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.

中文简介正在准备中。当前显示英语简介。

• Monitoring training loss and accuracy
• Comparing experiments with different training settings
• Inspecting weight and gradient distributions

Build queryable collections of genomic variants from VCF and BCF files, formats for recording genetic differences. Covers compressed storage, incremental sample additions, searches by genomic region or sample, and exporting subsets for further analysis.

中文简介正在准备中。当前显示英语简介。

• Building a variant database for a research cohort
• Adding samples to an existing dataset
• Extracting variants for selected regions and samples

Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.

中文简介正在准备中。当前显示英语简介。

• Recording and visualizing training metrics
• Comparing experiments with different training settings
• Automatically searching for better training settings

Review existing charts for clear communication, appropriate chart types, readable labels, scales, and color choices. Get concrete suggestions for simplifying layouts, improving accessibility, and making the visualization suit its intended audience.

中文简介正在准备中。当前显示英语简介。

• Reviewing whether an existing chart communicates clearly
• Fixing chart labels, legends, and scales
• Checking colors and accessibility

Study and apply statistics, probability, and linear algebra through Python examples. Calculate summary statistics, compare groups, analyze A/B tests, and build regression models while checking assumptions and considering the size of observed differences.

中文简介正在准备中。当前显示英语简介。

• Summarizing data with averages and measures of spread
• Comparing conversion rates in an A/B test
• Comparing regression models

Forecast sales, sensor readings, and other single-variable time series with Google's TimesFM, without training a custom model. Accept CSV files, DataFrames, or arrays and obtain forecast values with prediction intervals that express uncertainty.

中文简介正在准备中。当前显示英语简介。

• Forecast monthly sales from a CSV file
• Forecast demand across multiple stores
• Plot sensor forecasts with prediction intervals

Use UMAP to reduce data with many features into fewer dimensions for plotting or further analysis. The skill guides parameter choices, preprocessing for clustering, label-guided projections, and transforming new data with an already trained model.

中文简介正在准备中。当前显示英语简介。

• Visualize data with many features in two or three dimensions
• Prepare data for HDBSCAN clustering
• Guide projections using fully or partially labeled data

Helps plan dataset splits for machine learning training, validation, and testing. Specifies ratios, random seeds, class balance rules, and time or group constraints, with guidance for handing the split to leakage review and model training.

中文简介正在准备中。当前显示英语简介。

• Planning training, validation, and test partitions
• Preserving class proportions across dataset splits
• Defining time-based or grouped split constraints