Find top n terms with highest TF-IDF score per class

Question

Let\'s suppose that I have a dataframe with two columns in pandas which resembles the following one:

    text                                label
0         


        

Answer 1

The following code will do the work (thanks to Mariia Havrylovych).

Assume we have an input dataframe, df, aligned with your structure.

from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd

# override scikit's tfidf-vectorizer in order to return dataframe with feature names as columns
class DenseTfIdf(TfidfVectorizer):

    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        for k, v in kwargs.items():
            setattr(self, k, v)

    def transform(self, x, y=None) -> pd.DataFrame:
        res = super().transform(x)
        df = pd.DataFrame(res.toarray(), columns=self.get_feature_names())
        return df

    def fit_transform(self, x, y=None) -> pd.DataFrame:
        # run sklearn's fit_transform
        res = super().fit_transform(x, y=y)
        # convert the returned sparse documents-terms matrix into a dataframe to further manipulations
        df = pd.DataFrame(res.toarray(), columns=self.get_feature_names(), index=x.index)
        return df

Usage:

# assume texts are stored in column 'text' within a dataframe
texts = df['text']
df_docs_terms_corpus = DenseTfIdf(sublinear_tf=True,
                 max_df=0.5,
                 min_df=2,
                 encoding='ascii',
                 ngram_range=(1, 2),
                 lowercase=True,
                 max_features=1000,
                 stop_words='english'
                ).fit_transform(texts)


# Need to keep alignment of indexes between the original dataframe and the resulted documents-terms dataframe
df_class = df[df["label"] == "Class XX"]
df_docs_terms_class = df_docs_terms_corpus.iloc[df_class.index]
# sum by columns and get the top n keywords
df_docs_terms_class.sum(axis=0).nlargest(n=50)