Learn practical skills, build real-world projects, and advance your career
import spacy
nlp = spacy.load("en_core_web_sm")
tokens = nlp("software developer")
tokens1 = nlp("junior software engineer")
print("similiraty two job roles:  ",tokens.similarity(tokens1))
similiraty two job roles: 0.8323356550138759
/usr/lib/python3.6/runpy.py:193: ModelsWarning: [W007] The model you're using has no word vectors loaded, so the result of the Doc.similarity method will be based on the tagger, parser and NER, which may not give useful similarity judgements. This may happen if you're using one of the small models, e.g. `en_core_web_sm`, which don't ship with word vectors and only use context-sensitive tensors. You can always add your own word vectors, or use one of the larger models instead if available. "__main__", mod_spec)
import pandas as pd
import numpy as np
import random
from tqdm import tqdm
from gensim.models import Word2Vec 
import matplotlib.pyplot as plt
%matplotlib inline

import warnings;
warnings.filterwarnings('ignore')
df = pd.read_excel('/home/python/Downloads/Online Retail.xlsx')

df 
df.shape
(541909, 8)