skills.rest
slantview
slantviewCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

data-scientist

Perform end-to-end data science tasks with pandas, scikit-learn, and plotly.

1|1|Updated Aug 5, 2025
Search Tags:#analytics#python#mlops#data science#machine learning#visualization#modeling
One-click install
npx skills add https://github.com/slantview/claude --skill data-scientist-slantview
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-scientist
Source: https://github.com/slantview/claude/tree/main/skills/data-scientist
Command: npx skills add https://github.com/slantview/claude --skill data-scientist-slantview

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, matplotlib, seaborn, sklearn, xgboost, lightgbm, catboost, tensorflow, pytorch, keras, huggingface, spark, dask, ray, vaex, plotly, bokeh, altair, streamlit, mlflow, weights-biases, neptune, dvc, joblib, mlflow.sklearn, scipy.stats, sklearn.ensemble, sklearn.metrics, sklearn.pipeline, sklearn.model_selection, sklearn.preprocessing, plotly.express, plotly.graph_objects, plotly.subplots, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of extracting meaningful insights from complex datasets, building predictive models, and implementing machine learning solutions for data-driven decision-making.

Core Features & Use Cases

  • Exploratory Data Analysis (EDA): Perform in-depth analysis, identify patterns, and understand data distributions.
  • Machine Learning Pipeline Development: Build, train, and evaluate various ML models for classification and regression tasks.
  • Data Visualization: Create interactive plots and dashboards for clear communication of findings.
  • Production ML Systems: Deploy, monitor, and manage ML models in production environments.
  • Use Case: Analyze customer transaction data to build a model that predicts customer churn, enabling proactive retention strategies.

Quick Start

Use the data-scientist skill to perform a comprehensive EDA on the provided dataset.

Frequently Asked Questions about data-scientist

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a machine learning pipeline for exploratory data analysis and model training?▼

To build a machine learning pipeline, perform exploratory data analysis with pandas, engineer features, and train models using scikit-learn pipelines. This workflow supports classification and regression tasks while ensuring production readiness through MLflow integration.

What's the best way to track machine learning model experiments and monitor data drift?▼

The best way to track machine learning experiments is using MLflow integration to log parameters and metrics. You can monitor data drift and manage production readiness by tracking model performance across versions using MLflow and Weights & Biases.

Can I use TensorFlow and PyTorch for predictive modeling within the same data science workflow?▼

Yes, you can use TensorFlow and PyTorch for predictive modeling in your data science workflow. The environment supports both frameworks alongside XGBoost and LightGBM, allowing you to select the optimal library for your specific machine learning tasks.

How do I create interactive data visualizations from complex datasets?▼

You create interactive data visualizations from complex datasets using Plotly, Bokeh, and Altair. These libraries transform exploratory data analysis outputs into interactive plots and dashboards, enabling clear communication of patterns and data distributions.

Does Spark or Dask work for large-scale feature engineering and statistical analysis?▼

Spark and Dask work for large-scale feature engineering and statistical analysis by distributing computing workloads. They integrate with scipy.stats for statistical analysis, enabling efficient processing of complex datasets that exceed single-machine memory limits.

Why use MLflow for deploying machine learning models instead of just saving models with joblib?▼

You use MLflow for deploying machine learning models because it handles production readiness, data drift monitoring, and version tracking. Saving models with joblib only persists the object, whereas MLflow manages the entire model lifecycle and deployment pipeline.

Related Skills

Explore More Data & Analytics Skills→
AllanYiinAllanYiin
2

data-analysis

Analyze CSV, Parquet, and JSON datasets to produce summaries, trends, and visualizations.

Community
Intermediate
JNZader-VaultJNZader-Vault

mlflow

Manage ML experiments, model registries, and deployments using MLflow.

Official
Advanced
cas-bigdatalabcas-bigdatalab
541

ray_document_deduplicator

Remove duplicate documents from large-scale datasets using MD5 hashing and Ray distributed computing.

Official
Advanced
Ced3-hanCed3-han

ray-train

Orchestrates PyTorch, TensorFlow and HuggingFace distributed training across clusters with hyperparameter tuning and fault tolerance.

Community
Advanced