I have 3 columns Smiles, Column, and mobile phase.
I want to convert my dataset to the corpus as a training dataset and apply the Gensim model.
Here is my dataset link
https://drive.google.com/file/d/1S80I_5zkjJfeTzby7OjIqrs1vMJI6jVo/view?usp=sharing
I have referred this StackOverflow question but can't work
How to create corpus from pandas data frame to operate with NLTK
Any list of list of words can be converted to list of TaggedDocument & used to train a doc2vec model. OR you can split a dataframe's text column into list of words first and then iterate over output pandas series to create a list of TaggedDocument. Here is example usage for your dataset.Lets assume you load you pandas dataframe as df, then
output_ser = df.loc[:, 'Mobile Phase'].str.split(r'[/\s\\]+')
documents = [TaggedDocument(doc, [i]) for i, doc in enumerate(output_ser)]
model = Doc2Vec(documents, vector_size=5, window=2, min_count=1, workers=1)
Follow this link https://radimrehurek.com/gensim/models/doc2vec.html for usage example