Splitting dictionary/list inside a Pandas Column into Separate Columns

Question

I have data saved in a postgreSQL database. I am querying this data using Python2.7 and turning it into a Pandas DataFrame. However, the last column of this dat

Answer 1

>>> df

   Station ID                        Pollutants
0        8809  {"a": "46", "b": "3", "c": "12"}
1        8810   {"a": "36", "b": "5", "c": "8"}
2        8811              {"b": "2", "c": "7"}
3        8812                       {"c": "11"}
4        8813            {"a": "82", "c": "15"}

speed comparison for a large dataset of 10 million rows

>>> df = pd.concat([df]*100000).reset_index(drop=True)
>>> df = pd.concat([df]*20).reset_index(drop=True)
>>> print(df.shape)
(10000000, 2)

def apply_drop(df):
    return df.join(df['Pollutants'].apply(pd.Series)).drop('Pollutants', axis=1)  

def json_normalise_drop(df):
    return df.join(pd.json_normalize(df.Pollutants)).drop('Pollutants', axis=1)  

def tolist_drop(df):
    return df.join(pd.DataFrame(df['Pollutants'].tolist())).drop('Pollutants', axis=1)  

def vlues_tolist_drop(df):
    return df.join(pd.DataFrame(df['Pollutants'].values.tolist())).drop('Pollutants', axis=1)  

def pop_tolist(df):
    return df.join(pd.DataFrame(df.pop('Pollutants').tolist()))  

def pop_values_tolist(df):
    return df.join(pd.DataFrame(df.pop('Pollutants').values.tolist()))

>>> %timeit apply_drop(df.copy())
1 loop, best of 3: 53min 20s per loop
>>> %timeit json_normalise_drop(df.copy())
1 loop, best of 3: 54.9 s per loop
>>> %timeit tolist_drop(df.copy())
1 loop, best of 3: 6.62 s per loop
>>> %timeit vlues_tolist_drop(df.copy())
1 loop, best of 3: 6.63 s per loop
>>> %timeit pop_tolist(df.copy())
1 loop, best of 3: 5.99 s per loop
>>> %timeit pop_values_tolist(df.copy())
1 loop, best of 3: 5.94 s per loop

+---------------------+-----------+
| apply_drop          | 53min 20s |
| json_normalise_drop |    54.9 s |
| tolist_drop         |    6.62 s |
| vlues_tolist_drop   |    6.63 s |
| pop_tolist          |    5.99 s |
| pop_values_tolist   |    5.94 s |
+---------------------+-----------+

df.join(pd.DataFrame(df.pop('Pollutants').values.tolist())) is the fastest