from gensim.models import FastText

# Simple dataset: each sentence is a list of words.
corpus = [
    ["cat", "sat", "on", "the", "mat"],
    ["dog", "sat", "beside", "the", "cat"],
    ["dogs", "and", "cats", "are", "friends"],
    ["the", "dog", "jumped", "over", "the", "log"]
]

# Train a FastText model. Kept small for clarity.
model = FastText(sentences=corpus, vector_size=10, window=3, min_count=1)

# Common word
print("Vector for 'cat':", model.wv['cat'])

# Rare word (seen once)
print("Vector for 'jumped':", model.wv['jumped'])

# Plausible word never seen in training
print("Vector for 'jumping':", model.wv['jumping'])

# Made-up or misspelled word
print("Vector for 'cattz':", model.wv['cattz'])