Matching Elements Of Pandas Column With Column Of Another Pandas Dataframe

I have a pandas dataframe A with column keywords as :- keywords ['loans','mercedez','bugatti','a4'] ['trump','usa','election','president'] ['galaxy','7s','canon','macbook'] ['

Solution 1:

One way is to use pandas.transform:

import pandas as pd

A = pd.DataFrame({'keywords': [['loans','mercedez','bugatti','a4'],
                           ['trump','usa','election','president']]})
B = pd.DataFrame({'category': ['audi', 'finance'],
                  'words': ['audi a4,audi a6', 'sales,loans,sales price']})

def match_category_to_keywords(kws):
    ret = []
    for kw in kws:
        m = B['words'].transform(lambda words: any([kw in w for w in words.split(',')]))
        ret.extend(B['category'].loc[m].tolist())
    return pd.np.unique(ret)

A['matched_category'] = A['keywords'].transform(lambda kws: match_category_to_keywords(kws))
print(A)

Output:

                            keywords matched_category
0     [loans, mercedez, bugatti, a4]  [audi, finance]
1  [trump, usa, election, president]               []

Solution 2:

I hope you can use:

#create dictionary by split comma and whitespaces
d = df2.set_index('category')['words'].str.split(',\s*|\s+').to_dict()
#flatten lists to dictionary
d1 = {k: oldk for oldk, oldv in d.items() for k in oldv}
print (d1)
{'audi': 'audi', 'a4': 'audi', 'a6': 'audi', 'bugatti': 'bugatti', 
 'veyron': 'bugatti', 'chiron': 'bugatti', 'mercedez': 'mercedez', 
 's-class': 'mercedez', 'e-class': 'mercedez', 'canon': 'dslr', 
 'nikon': 'dslr', 'iphone': 'apple', '7s': 'apple', '6s': 'apple',
 '5': 'apple', 'sales': 'finance', 'loans': 'finance', 'price': 'finance', 
 'donald': 'politics', 'trump': 'politics', 'election': 'politics', 
 'votes': 'politics', 'spiderman': 'entertainment', 'captain': 'entertainment',
 'america': 'entertainment', 'ironmen': 'entertainment', 'justin': 'music', 
 'beiber': 'music', 'rihana': 'music', 'drake': 'music'}

---

#for each value map in nested list comprehension
df1['new'] = [[d1.get(y, None) for y in x if y in d1] for x in df1['keywords']]
print (df1)
                                keywords  \
0         [loans, mercedez, bugatti, a4]   
1      [trump, usa, election, president]   
2           [galaxy, 7s, canon, macbook]   
3  [beiber, spiderman, marvels, ironmen]   

                                     new  
0     [finance, mercedez, bugatti, audi]  
1                   [politics, politics]  
2                          [apple, dslr]  
3  [music, entertainment, entertainment]