PIXELBANKv8.2.1
Menu

One-Hot Sequence Encoder

Given a vocabulary and a sequence of words, encode each word as a one-hot vector.

Input format:

  • Line 1: Comma-separated vocabulary (sorted)
  • Line 2: Space-separated words to encode

Each word becomes a vector of length |vocab| with 1 at the word's index and 0 elsewhere. If a word is not in the vocabulary, use all zeros.

Output: One vector per line as a list.

Example:

Input:
cat,dog,fish
dog cat fish
Output:
[0, 1, 0]
[1, 0, 0]
[0, 0, 1]
Reasoning:

Step 1: Build vocabulary index cat=0, dog=1, fish=2

Step 2: Encode each word "dog" → index 1 → [0, 1, 0] "cat" → index 0 → [1, 0, 0] "fish" → index 2 → [0, 0, 1]

Constraints:

  • Vocabulary is comma-separated and sorted
  • Each output vector has length = vocabulary size
  • Unknown words get all-zero vectors
  • Output each vector as a Python list
Editor

Test Results

0/0
Run code to see test results.