I am trying to create a new DataFrame column that contains words that match between a list of keywords and strings in a df column…

data = {
'Sandwich Opinions':['Roast beef is overrated','Toasted bread is always best','Hot sandwiches are better than cold']
}
df = pd.DataFrame(data)

keywords = ['bread', 'bologna', 'toast', 'sandwich']

df['Matches'] = [df.apply(lambda x: ' '.join([i for i in df['Sandwich iOpinions'].str.split() if i in keywords]), axis=1)

This seems like it should do the job but it’s getting stuck in endless processing.

>Solution :

for kw in keywords:
    df[kw] = np.where(df['Sandwich Opinions'].str.contains(kw), 1, 0)

def add_contain_row(row):
    contains = []
    for kw in keywords:
        if row[kw] == 1:
            contains.append(kw)
    return contains

df['contains'] = df.apply(add_contain_row, axis=1)

# if you want to drop the temp columns
[df.drop(columns=kw, inplace=True) for kw in keywords]