I want to join all the text columns of my dataframe, so that i can fit this into a CountVectorizer.
def populate_distance_metrics(in_df, col_list, prim_col):
vect_data=in_df[col_list[0]].map(str)
print (type(vect_data))
for col,idx in enumerate(col_list):
if idx==0:
continue;
vect_data = vect_data + " " + in_df[col]
cv = CountVectorizer(stop_words='english', max_features=1000)
# Learn a vocabulary dictionary of all tokens
cv.fit(vect_data)
print ('cv fit')
in_df is the source data frame and col_list is a an array such as ['a','b','c',...] and i want to keep this flexible. the type of
vect_data=in_df[col_list[0]].map(str)
is
<class 'pandas.core.series.Series'>
the above code fails at vect_data = vect_data + " " + in_df[col]
vect_data = vect_data + " " + in_df[col]
File "asd/asd/dsfg/lib/python3.6/site-packages/pandas/core/frame.py", line 2059, in __getitem__
return self._getitem_column(key)
File "asd/asd/dsfg/lib/python3.6/site-packages/pandas/core/frame.py", line 2066, in _getitem_column
return self._get_item_cache(key)
File "asd/asd/dsfg/lib/python3.6/site-packages/pandas/core/generic.py", line 1386, in _get_item_cache
values = self._data.get(item)
File "asd/asd/dsfg/lib/python3.6/site-packages/pandas/core/internals.py", line 3543, in get
loc = self.items.get_loc(item)
File "asd/asd/dsfg/lib/python3.6/site-packages/pandas/indexes/base.py", line 2136, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas/index.pyx", line 132, in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)
File "pandas/index.pyx", line 154, in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)
File "pandas/src/hashtable_class_helper.pxi", line 732, in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)
File "pandas/src/hashtable_class_helper.pxi", line 740, in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)
KeyError: 0
However, it works when i do
cv.fit(in_df['a']+ ' '+ in_df['b']+ in_df['c'])
what am i doing wrong?
