CSV audit and production-ready cleaning pipeline

Audits a raw dataset for data smells, ties each issue to its business impact, then proposes an imputation, encoding and scaling strategy with a leakage-safe pandas and scikit-learn pipeline.

PLPromptByte Library@promptbytePublished 1w

TextData & Analysis #data cleaning #data quality #etl #pandas #python

Version 1 of 1 · published Aug 29, 2026Version 1 · only version

Example output

See all results

Anthropic · Claude Opus 5 PLPromptByte Library Version 1

Prompt

Version 1 · 3 variables · 2 required

Fill in the values below — the customized prompt updates as you type. marks a required value.

Dataset description{{dataset_description}}

Rows, columns, dtypes, and any known quality problems. Pasting df.info() output works well.

Business objective{{business_objective}}

The decision or product this cleaned data has to support.

Target variable(optional){{target_variable}}

The column being predicted, if any. Drives the data-leakage checks. Default: none

Fill in Dataset description, Business objective to copy the customized prompt.

Resultsfor version 1

All models Claude Opus 51

Version 1 · only version

Claude Opus 5 result by PromptByte Library
Anthropic · Claude Opus 5 PLPromptByte Library (@promptbyte)Version 1Published 1w
Compare
## 1. Technical Audit & Business Context | Column | Smell | Business impact | |---|---|---| | `churn_date` | Populated only for churned accounts | This is the label in disguise. Any model that sees it will score ~perfectly in training and be useless in production. | | `mrr` | Right-skewed, a long tail of enterprise accounts | Mean imputation would drag small accounts upward and understate churn risk in the SMB segment, which is where outreach capacity actually sits. | | `signup_date` | Mixed `YYYY-MM-DD` and `DD/MM/YYYY` strings | Tenure is derived from this. Silent misparsing flips day and…
Community submittedFull output
Settings: Unknown
Open result

Showing all 1 public result on version 1.

Usage notes

Describe the dataset concretely in dataset_description: row count, column count, the column names and types that matter, and anything you already know is messy. Pasting df.info() and df.describe() output works very well here.

Naming a real business_objective is what makes this prompt better than a generic "clean my data" request — the audit step will rank issues by how much they distort that specific decision.

If you are preparing data for a model, always fill in target_variable; that is what drives the leakage checks and the fit-on-train-only handling inside the Pipeline. Leave it as none for pure reporting or BI work.

Treat the generated script as a reviewed starting point. Run it on a copy, check the assertion block actually fires on bad input, and confirm the imputation choices against your domain knowledge before scheduling it.

Attribution: adapted from https://github.com/f/prompts.chat by f (Fatih Kadir Akın), licensed CC0-1.0. Source file: https://github.com/f/prompts.chat/blob/main/PROMPTS.md

Output2,714 characters

## 1. Technical Audit & Business Context | Column | Smell | Business impact | |---|---|---| | `churn_date` | Populated only for churned accounts | This is the label in disguise. Any model that sees it will score ~perfectly in training and be useless in production. | | `mrr` | Right-skewed, a long tail of enterprise accounts | Mean imputation would drag small accounts upward and understate churn risk in the SMB segment, which is where outreach capacity actually sits. | | `signup_date` | Mixed `YYYY-MM-DD` and `DD/MM/YYYY` strings | Tenure is derived from this. Silent misparsing flips day and month for the first twelve days of each month and corrupts every cohort chart. | | `country` | Free text, with `US`, `USA` and `United States` all present | Splits one segment into three, so no country clears a significance threshold. | | 12 usage counters | Zero-inflated; nulls appear to mean "no events", not "unknown" | Imputing the median here invents activity for dormant accounts, which is exactly the signal you are trying to detect. | ## 2. Statistical Strategy - **Imputation** — median for `mrr` and tenure (robust to the enterprise tail); constant `0` for the usage counters, since missing means no events; a `Missing` category for `country`. - **Encoding** — one-hot for `plan` (3 levels, no order) and for a normalised `country_region` (5 levels after cleanup). No label encoding: it would impose a false ordering that tree splits and linear coefficients would both read as real. - **Scaling** — RobustScaler on `mrr` and the counters. StandardScaler assumes roughly symmetric spread and would compress the informative high-usage tail. ## 3. Implementation Block ```python numeric = ["mrr", "tenure_days"] counters = [c for c in df.columns if c.startswith("usage_")] categorical = ["plan", "country_region"] preprocessor = ColumnTransformer([ ("num", Pipeline([("imp", SimpleImputer(strategy="median")), ("sc", RobustScaler())]), numeric), ("cnt", SimpleImputer(strategy="constant", fill_value=0), counters), ("cat", Pipeline([("imp", SimpleImputer(strategy="constant", fill_value="Missing")), ("ohe", OneHotEncoder(handle_unknown="ignore"))]), categorical), ]) ``` Fit the ColumnTransformer inside a Pipeline on the training split only; that is what keeps the imputation medians and scaler quantiles from leaking test-set information. ## 4. Post-Processing Validation ```python assert "churn_date" not in X.columns, "label leakage: drop churn_date" assert X.isna().sum().sum() == 0, "nulls survived the pipeline" assert X.select_dtypes("float64").empty, "downcast float64 -> float32" ```

text
```csv quarter,line,units_produced,defects,defect_rate_pct,shift_pattern Q1,Line A,14200,318,2.24,"Two shifts, weekdays" Q1,Line B,11850,402,3.39,"Two shifts, weekdays" Q1,Line C,9600,151,1.57,"One shift, weekdays" Q1,Line D,UNCLEAR,88,UNCLEAR,"One shift, weekends" Q2,Line A,15040,295,1.96,"Three shifts, weekdays" Q2,Line B,12310,377,3.06,"Two shifts, weekdays" Q2,Line C,9880,143,1.45,"One shift, weekdays" Q2,Line D,4120,96,2.33,"One shift, weekends" ``` **Notes** - **UNCLEAR cells:** row 5 (Q
Table image to clean CSV extraction
Extracts a table from a screenshot or scanned page into a flat, copy-paste-ready CSV, unmerging cells, stripping units into their own columns and flagging anything unreadable instead of guessing.
TextData & Analysis Google · Gemini 3.1 Pro
PL@promptbyte5d
Score 0
0 comments1 results
text
# Checkout redesign A/B test — analysis plan and interpretation ## What the design supports Two independent groups, roughly 6,200 per arm, with a binary primary outcome (completed purchase) and a continuous secondary outcome (order value, right-skewed as order values almost always are). Randomisation at the session level with a 21-day run covering three full weekly cycles is sound. One caveat that limits every conclusion below: sessions, not users, were randomised, so a returning visitor could
Statistical analysis report with hypothesis tests and effect sizes
Applies a senior statistician's workflow to your data: descriptive summary, justified test selection, models, effect sizes with confidence intervals, and a plain-language reading of what is practically significant.
TextData & Analysis Anthropic · Claude Sonnet 5
PL@promptbyte1w
Score 0
0 comments1 results
code · sql
```
**Assumptions**

- `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed.
- "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today.
- Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied.
- Cancelled orders are excluded. If `status` uses different values than `'
```
Code preview: **Assumptions** - `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed. - "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today. - Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied. - Cancelled orders are excluded. If `status` uses different values than `'
SQL query generator from a plain-English request
Converts a natural-language data requirement plus a table schema into a syntactically correct SQL query for a named database, with its assumptions stated up front.
CodeData & Analysis OpenAI · GPT-5.5
PL@promptbyte1w
Score 0
0 comments1 results
text
**Recommended formula** — enter in Summary!B2 and fill down: =IFERROR(SUMIFS(Orders!$D$2:$D$5000, Orders!$B$2:$B$5000, $A2, Orders!$C$2:$C$5000, "Shipped", Orders!$A$2:$A$5000, ">="&DATE(2025,10,1), Orders!$A$2:$A$5000, "<="&DATE(2025,12,31)), 0) **How it works, step by step** 1. SUMIFS(sum_range, criteria_range1, criteria1, ...) adds values from Orders!D2:D5000 only for rows where every criteria pair matches. Unlike SUMIF it takes multiple conditions, so no helper column is needed. 2. Orders
Excel formula builder with step-by-step explanation
Turns a described spreadsheet calculation into a working Excel formula plus a plain-language walkthrough of every function, operator and reference it uses.
TextData & Analysis Anthropic · Claude Sonnet 5
PL@promptbyte1w
Score 0
0 comments1 results

Browse Data & Analysis

CSV audit and production-ready cleaning pipeline

Example output

Prompt

Resultsfor version 1

Models represented

Something wrong with this prompt?

Table image to clean CSV extraction

Statistical analysis report with hypothesis tests and effect sizes

SQL query generator from a plain-English request

Excel formula builder with step-by-step explanation

Discussion 0

Example output

Prompt

Resultsfor version 1

Models represented

Something wrong with this prompt?

Related prompts

Table image to clean CSV extraction

Statistical analysis report with hypothesis tests and effect sizes

SQL query generator from a plain-English request

Excel formula builder with step-by-step explanation

Discussion 0