CSV Data Cleaner

IntermediadataContexto mínimo: 16K

Inspects messy tabular data and produces a repeatable cleaning plan plus code. Detects and fixes common issues: inconsistent types, duplicate rows, missing values, malformed dates, mixed encodings, whitespace and casing problems, and outliers. Outputs pandas or Polars code, a summary of changes, and a validation checklist.

data-cleaningcsvpandasetldata-quality

Casos de uso

  • Standardizing types, dates, and encodings in a raw CSV
  • Deduplicating and imputing missing values with documented rules
  • Generating reusable pandas or Polars cleaning scripts
  • Producing a before/after data quality report

Prompt de ejemplo

Here is a sample of a messy CSV (first 20 rows below).

Produce:
1. A diagnosis of data quality issues (types, nulls, duplicates, date formats, encoding)
2. A cleaning plan with an explicit rule for each issue
3. Reproducible pandas code that applies the plan
4. A validation checklist to confirm the output is clean

Data:
```
[paste CSV sample here]
```

Modelos recomendados

claude-opus-4-6gpt-5deepseek-v4qwen3-coder

Herramientas compatibles

claude-codecursorkiroany

Modalidades

Entrada: text, code, file
→
Salida: text, code

Skills relacionadas

data-quality-validatordata-analysisdata-pipeline-builder

Autor

OpenModels Community

@openmodelsrun