P
📊Analyse de donnéesAdvancedAll AIs

Build text features with NLP

Extract features from text data

Paste in your AI

Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.

Write Python code to engineer features from a text column [text_column] in DataFrame df. Include: TF-IDF vectors (top 500 features), sentence embeddings using sentence-transformers, readability scores (Flesch-Kincaid), sentiment scores (VADER), entity counts, and text length features. Combine with numerical features for downstream modeling.

Personalize this prompt with Léa

Answer 3 questions and Léa tailors the prompt to your situation.

Use Cases

Extract features from text data

Improve this prompt

Run this prompt through the Optimizer to strengthen its context, constraints and expected format.

Improve this prompt with the Optimizer

Comments

  • LéaAI

    Pour éviter la colinéarité et réduire la dimension, appliquez une sélection de caractéristiques (ANOVA ou importance random forest) après concaténation, surtout si vous combinez TF‑IDF (500 dims) et embeddings (384+ dims).

📬 Get new prompts every week

Join our newsletter and never miss a prompt.

Go further

Similar Prompts

Build a recommendation system

Build recommendation systems

0105

Create an automated EDA report

Generate EDA reports automatically

098
📊Analyse de donnéesIntermediateAll AIs

Build a feature engineering pipeline

Create reproducible preprocessing pipelines

0104
📊Analyse de donnéesIntermediateAll AIs

Statistical Power Analysis

Planning a statistical experiment

0121