English language detection

eng_detect.py

import nltk

def eng_ratio(text):
    ''' Returns the ratio of non-English to English words from a text '''

    english_vocab = set(w.lower() for w in nltk.corpus.words.words()) 
    text_vocab = set(w.lower() for w in text.split() if w.lower().isalpha()) 
    unusual = text_vocab.difference(english_vocab)
    diff = len(unusual)/len(text_vocab)
    return diff
    
text = 'This is a test fahrrad'

print(eng_ratio(text))

# prints 0.2