I have a table with both numeric and string data but in separate columns. The table is answers to a web form and contains empty cells. I want to use text processing on the string columns. I cannot drop the rows with empty cells so for the empty string columns, I replaced the NaN with aplhabet 'a'.
Sample data
colmun_name1 column_name2 column_name3 column_name4 classify
This is a cat This is a dog 1 2 0
This is a rat This is a mouse 45 32 1
a Good mouse 0 0 0
I used the following code to make sure all data in the string columns is actually string data.
df2=df[[column_name1, column_name2]]
for i in range(0,len(df2)):
cell=df2.iloc[i]
cell=str(str)
df2.iloc[i]=cell
Then when I tokenize, I get an error
<ipython-input-64-24a99733ba19> in <module>
1 from nltk.tokenize import word_tokenize
----> 2 tokenized_word=word_tokenize(df2)
3 print(tokenized_word)
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/__init__.py in word_tokenize(text, language, preserve_line)
126 :type preserver_line: bool
127 """
--> 128 sentences = [text] if preserve_line else sent_tokenize(text, language)
129 return [token for sent in sentences
130 for token in _treebank_word_tokenizer.tokenize(sent)]
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/__init__.py in sent_tokenize(text, language)
93 """
94 tokenizer = load('tokenizers/punkt/{0}.pickle'.format(language))
---> 95 return tokenizer.tokenize(text)
96
97 # Standard word tokenizer.
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in tokenize(self, text, realign_boundaries)
1239 Given a text, returns a list of the sentences in that text.
1240 """
-> 1241 return list(self.sentences_from_text(text, realign_boundaries))
1242
1243 def debug_decisions(self, text):
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in sentences_from_text(self, text, realign_boundaries)
1289 follows the period.
1290 """
-> 1291 return [text[s:e] for s, e in self.span_tokenize(text, realign_boundaries)]
1292
1293 def _slices_from_text(self, text):
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in <listcomp>(.0)
1289 follows the period.
1290 """
-> 1291 return [text[s:e] for s, e in self.span_tokenize(text, realign_boundaries)]
1292
1293 def _slices_from_text(self, text):
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in span_tokenize(self, text, realign_boundaries)
1279 if realign_boundaries:
1280 slices = self._realign_boundaries(text, slices)
-> 1281 for sl in slices:
1282 yield (sl.start, sl.stop)
1283
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in _realign_boundaries(self, text, slices)
1320 """
1321 realign = 0
-> 1322 for sl1, sl2 in _pair_iter(slices):
1323 sl1 = slice(sl1.start + realign, sl1.stop)
1324 if not sl2:
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in _pair_iter(it)
311 """
312 it = iter(it)
--> 313 prev = next(it)
314 for el in it:
315 yield (prev, el)
/anaconda3/lib/python3.6/site-packages/nltk/tokenize/punkt.py in _slices_from_text(self, text)
1293 def _slices_from_text(self, text):
1294 last_break = 0
-> 1295 for match in self._lang_vars.period_context_re().finditer(text):
1296 context = match.group() + match.group('after_tok')
1297 if self.text_contains_sentbreak(context):
TypeError: expected string or bytes-like object
I tried changing
df2=df[column_name1][column_name2]
But I get the same error.
What should I do?
Please see How to apply NLTK word_tokenize library on a Pandas dataframe for Twitter data?
# Creates a `colmun_name1_tokenized` column by
# taking the `colmun_name1` column and
# applying the word_tokenize function on every cell in the column.
>>> df['colmun_name1_tokenized'] = df['colmun_name1'].apply(word_tokenize)
>>> df.head()
colmun_name1 column_name2 column_name3 column_name4 classify \
0 This is a cat This is a dog 1 2 0
1 This is a rat This is a mouse 45 32 1
2 a Good mouse 0 0 0
colmun_name1_tokenized
0 [This, is, a, cat]
1 [This, is, a, rat]
2 [a]
If you need more than one column to be tokenized and you want to overwrite the column with the tokenized output:
>>> with StringIO(file_str) as fin:
... df = pd.read_csv(fin, sep='\t')
...
>>> for col_name in ['colmun_name1', 'column_name2']:
... df[col_name] = df[col_name].apply(word_tokenize)
...
>>> df.head()
colmun_name1 column_name2 column_name3 column_name4 \
0 [This, is, a, cat] [This, is, a, dog] 1 2
1 [This, is, a, rat] [This, is, a, mouse] 45 32
2 [a] [Good, mouse] 0 0
classify
0 0
1 1
2 0
Just the code:
from io import StringIO
import pandas as pd
from nltk import word_tokenize
file_str = """colmun_name1\tcolumn_name2\tcolumn_name3\tcolumn_name4\tclassify
This is a cat\tThis is a dog\t1\t2\t0
This is a rat\tThis is a mouse\t45\t32\t1
a\tGood mouse\t0\t0\t0 """
with StringIO(file_str) as fin:
df = pd.read_csv(fin, sep='\t')
for col_name in ['colmun_name1', 'column_name2']:
df[col_name] = df[col_name].apply(word_tokenize)