Styjun

I am trying to explore this dataset with pandas 0.20.3 in Python 3.6.2.

%pylab inline
import pandas as pd
df = pd.read_csv('OnlineNewsPopularity.csv')
df['n_tokens_content'][:9]

last line produces error

KeyError Traceback (most recent call
last)
~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/indexes/base.py
in get_loc(self, key, method, tolerance) 2441 try:
-> 2442 return self._engine.get_loc(key) 2443 except KeyError:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc
(pandas/_libs/index.c:5280)()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc
(pandas/_libs/index.c:5126)()

pandas/_libs/hashtable_class_helper.pxi in
pandas._libs.hashtable.PyObjectHashTable.get_item
(pandas/_libs/hashtable.c:20523)()

pandas/_libs/hashtable_class_helper.pxi in
pandas._libs.hashtable.PyObjectHashTable.get_item
(pandas/_libs/hashtable.c:20477)()

KeyError: 'n_tokens_content'

During handling of the above exception, another exception occurred:

KeyError Traceback (most recent call
last) in ()
----> 1 df['n_tokens_content'][:9]

~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/frame.py
in getitem(self, key) 1962 return
self._getitem_multilevel(key) 1963 else:
-> 1964 return self._getitem_column(key) 1965 1966 def _getitem_column(self, key):

~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/frame.py
in _getitem_column(self, key) 1969 # get column 1970

if self.columns.is_unique:
-> 1971 return self._get_item_cache(key) 1972 1973 # duplicate columns & possible reduce dimensionality

~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/generic.py
in _get_item_cache(self, item) 1643 res = cache.get(item)

1644 if res is None:
-> 1645 values = self._data.get(item) 1646 res = self._box_item_values(item, values) 1647

cache[item] = res

~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/internals.py
in get(self, item, fastpath) 3588 3589 if not
isnull(item):
-> 3590 loc = self.items.get_loc(item) 3591 else: 3592 indexer =
np.arange(len(self.items))[isnull(self.items)]

~/anaconda3/envs/tf11/lib/python3.6/site-packages/pandas/core/indexes/base.py
in get_loc(self, key, method, tolerance) 2442

return self._engine.get_loc(key) 2443 except KeyError:
-> 2444 return self._engine.get_loc(self._maybe_cast_indexer(key)) 2445 2446

indexer = self.get_indexer([key], method=method, tolerance=tolerance)

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc
(pandas/_libs/index.c:5280)()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc
(pandas/_libs/index.c:5126)()

pandas/_libs/hashtable_class_helper.pxi in
pandas._libs.hashtable.PyObjectHashTable.get_item
(pandas/_libs/hashtable.c:20523)()

pandas/_libs/hashtable_class_helper.pxi in
pandas._libs.hashtable.PyObjectHashTable.get_item
(pandas/_libs/hashtable.c:20477)()

KeyError: 'n_tokens_content'

I think this is caused by some rows in the csv file, as this piece of code work well for other csv.

if yes, how to locate the bad rows efficiently?

When you print the columns using df.columns then 'n_tokens_content' has a leading space at the start.

Input: df.columns

Output:

Index(['url', ' timedelta', ' n_tokens_title', ' n_tokens_content',
 ' n_unique_tokens', ' n_non_stop_words', ' n_non_stop_unique_tokens',
 ' num_hrefs', ' num_self_hrefs', ' num_imgs', ' num_videos',
 ' average_token_length', ' num_keywords', ' data_channel_is_lifestyle',
 ' data_channel_is_entertainment', ' data_channel_is_bus',
 ' data_channel_is_socmed', ' data_channel_is_tech',
 ' data_channel_is_world', ' kw_min_min', ' kw_max_min', ' kw_avg_min',
 ' kw_min_max', ' kw_max_max', ' kw_avg_max', ' kw_min_avg',
 ' kw_max_avg', ' kw_avg_avg', ' self_reference_min_shares',
 ' self_reference_max_shares', ' self_reference_avg_sharess',
 ' weekday_is_monday', ' weekday_is_tuesday', ' weekday_is_wednesday',
 ' weekday_is_thursday', ' weekday_is_friday', ' weekday_is_saturday',
 ' weekday_is_sunday', ' is_weekend', ' LDA_00', ' LDA_01', ' LDA_02',
 ' LDA_03', ' LDA_04', ' global_subjectivity',
 ' global_sentiment_polarity', ' global_rate_positive_words',
 ' global_rate_negative_words', ' rate_positive_words',
 ' rate_negative_words', ' avg_positive_polarity',
 ' min_positive_polarity', ' max_positive_polarity',
 ' avg_negative_polarity', ' min_negative_polarity',
 ' max_negative_polarity', ' title_subjectivity',
 ' title_sentiment_polarity', ' abs_title_subjectivity',
 ' abs_title_sentiment_polarity', ' shares'],
 dtype='object')

Give input as: df[' n_tokens_content'][:9]

output:

0 219
1 255
2 211
3 531
4 1072
5 370
6 960
7 989
8 97