nlp7.py

# create doc2vec vector columns
from gensim.test.utils import common_texts
from gensim.models.doc2vec import Doc2Vec, TaggedDocument

documents = [TaggedDocument(doc, [i]) for i, doc in enumerate(reviews_df["review_clean"].apply(lambda x: x.split(" ")))]

# train a Doc2Vec model with our text data
model = Doc2Vec(documents, vector_size=5, window=2, min_count=1, workers=4)

# transform each document into a vector data
doc2vec_df = reviews_df["review_clean"].apply(lambda x: model.infer_vector(x.split(" "))).apply(pd.Series)
doc2vec_df.columns = ["doc2vec_vector_" + str(x) for x in doc2vec_df.columns]
reviews_df = pd.concat([reviews_df, doc2vec_df], axis=1)