unhashable type 'list' error with get_dumies

Question

I have a dataframe with data like the sample data below. I'm trying to create dummy variables for the values in the categories field using get_dummies but I'm getting the error below when I run the code below. What I would like is say for example with the first record, to have one column called "Ramen" with a 1 in it and another column called "Japanese" with a 1 in it.

Sample Data:

                 user_id             business_id  stars_x  \
1  CxDOIDnH8gp9KXzpBHJYXw  XSiqtcVEsP6dLOL7ZA9OxA        4   
2  CxDOIDnH8gp9KXzpBHJYXw  v95ot_TNwTk1iJ5n56dR0g        3   
3  CxDOIDnH8gp9KXzpBHJYXw  uloYxyRAMesZzI99mfNInA        2   
4  CxDOIDnH8gp9KXzpBHJYXw  gtcsOodbmk4E0TulYHnlHA        4   

                address                                         attributes  \
1      522 Yonge Street  {u'BusinessParking': {u'garage': False, u'stre...   
2   1661 Denison Street  {u'BusinessParking': {u'garage': False, u'stre...   
3  4101 Rutherford Road  {u'BusinessParking': {u'garage': False, u'stre...   
4    815 W Bloor Street  {u'Alcohol': u'full_bar', u'HasTV': False, u'N...   

                                          categories        city  \
1                     [Restaurants, Ramen, Japanese]     Toronto   
2                    [Chinese, Seafood, Restaurants]     Markham   
3                             [Italian, Restaurants]  Woodbridge   
4  [Food, Coffee & Tea, Sandwiches, Cafes, Cockta...     Toronto   

                                               hours  is_open   latitude  \
1  {u'Monday': u'11:00-22:00', u'Tuesday': u'11:0...        1  43.663689   
2                                                 {}        0  43.834295   
3  {u'Monday': u'12:00-22:00', u'Tuesday': u'12:0...        1  43.823486   
4  {u'Monday': u'12:00-2:00', u'Tuesday': u'12:00...        1  43.662726   

   longitude                            name   neighborhood postal_code  \
1 -79.384200                     Kenzo Ramen  Downtown Core     M4Y 1X9   
2 -79.305282  Vince Seafood Restaurant & BBQ       Milliken     L3R 6E4   
3 -79.568345                Motorino Enoteca     Pine Grove     L4L 1A5   
4 -79.422167                       Northwood  Bickford Park     M6G 1M1   

   review_count  stars_y state good_reviews  
1            76      3.5    ON         True  
2            23      3.5    ON        False  
3            26      3.5    ON        False  
4            93      4.0    ON         True  

Code:

pd.get_dummies(bus_rev['categories'])

Error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-23-e57eccbfbe12> in <module>()
----> 1 bus_rev_cat2 = pd.get_dummies(bus_rev['categories'])
      2 #bus_revlist = pd.concat([bus_rev,bus_rev_cat2],axis=1)
      3 #bus_revlist.head()

/Users/anaconda/lib/python2.7/site-packages/pandas/core/reshape.pyc in get_dummies(data, prefix, prefix_sep, dummy_na, columns, sparse, drop_first)
   1102     else:
   1103         result = _get_dummies_1d(data, prefix, prefix_sep, dummy_na,
-> 1104                                  sparse=sparse, drop_first=drop_first)
   1105     return result
   1106 

/Users/anaconda/lib/python2.7/site-packages/pandas/core/reshape.pyc in _get_dummies_1d(data, prefix, prefix_sep, dummy_na, sparse, drop_first)
   1109                     sparse=False, drop_first=False):
   1110     # Series avoids inconsistent NaN handling
-> 1111     codes, levels = _factorize_from_iterable(Series(data))
   1112 
   1113     def get_empty_Frame(data, sparse):

/Users/anaconda/lib/python2.7/site-packages/pandas/core/categorical.pyc in _factorize_from_iterable(values)
   2038         codes = values.codes
   2039     else:
-> 2040         cat = Categorical(values, ordered=True)
   2041         categories = cat.categories
   2042         codes = cat.codes

/Users/anaconda/lib/python2.7/site-packages/pandas/core/categorical.pyc in __init__(self, values, categories, ordered, name, fastpath)
    288                 codes, categories = factorize(values, sort=True)
    289             except TypeError:
--> 290                 codes, categories = factorize(values, sort=False)
    291                 if ordered:
    292                     # raise, as we don't have a sortable data structure and so

/Users/anaconda/lib/python2.7/site-packages/pandas/core/algorithms.pyc in factorize(values, sort, order, na_sentinel, size_hint)
    311     table = hash_klass(size_hint or len(vals))
    312     uniques = vec_klass()
--> 313     labels = table.get_labels(vals, uniques, 0, na_sentinel, True)
    314 
    315     labels = _ensure_platform_int(labels)

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_labels (pandas/hashtable.c:15447)()

TypeError: unhashable type: 'list'

Answer 1

You can try this

df=pd.DataFrame( {'categories':[['Restaurants', 'Ramen', 'Japanese'],['Chinese', 'Seafood', 'Restaurants']]})

pd.get_dummies(df.categories.apply(pd.Series).stack()).sum(level=0)
Out[1095]: 
   Chinese  Japanese  Ramen  Restaurants  Seafood
0        0         1      1            1        0
1        1         0      0            1        1