Given a dataframe like this:
C
A B
1.1 111 20
222 31
3.3 222 24
333 65
5.5 333 22
6.6 777 74
How do I read it in using pd.read_clipboard
? I've tried this:
df = pd.read_clipboard(index_col=[0, 1])
But it throws an error:
ParserError: Error tokenizing data. C error: Expected 2 fields in line 3, saw 3
How can I fix this?
UPDATE: now it parses the clipboard - i.e. no need to save it beforehand
def read_clipboard_mi(index_names_row=None, **kwargs):
encoding = kwargs.pop('encoding', 'utf-8')
# only utf-8 is valid for passed value because that's what clipboard
# supports
if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
raise NotImplementedError(
'reading from clipboard only supports utf-8 encoding')
from pandas import compat, read_fwf
from pandas.io.clipboard import clipboard_get
from pandas.io.common import StringIO
data = clipboard_get()
# try to decode (if needed on PY3)
# Strange. linux py33 doesn't complain, win py33 does
if compat.PY3:
try:
text = compat.bytes_to_str(
text, encoding=(kwargs.get('encoding') or
get_option('display.encoding'))
)
except:
pass
index_names = None
if index_names_row:
if isinstance(index_names_row, int):
index_names = data.splitlines()[index_names_row].split()
skiprows = [index_names_row]
kwargs.update({'skiprows': skiprows})
else:
raise Exception('[index_names_row] must be of [int] data type')
df = read_fwf(StringIO(data), **kwargs)
unnamed_cols = df.columns[df.columns.str.contains(r'Unnamed:')].tolist()
if index_names:
idx_cols = df.columns[range(len(index_names))].tolist()
elif unnamed_cols:
idx_cols = df.columns[range(len(unnamed_cols))].tolist()
index_names = [None] * len(idx_cols)
df[idx_cols] = df[idx_cols].ffill()
df = df.set_index(idx_cols).rename_axis(index_names)
return df
testing multi-index DF without index names:
In [231]: read_clipboard_mi()
Out[231]:
C
1.1 111 20
222 31
3.3 222 24
333 65
5.5 333 22
6.6 777 74
testing multi-index DF with index names:
In [232]: read_clipboard_mi(index_names_row=1)
Out[232]:
C
A B
1.1 111 20
222 31
3.3 222 24
333 65
5.5 333 22
6.6 777 74
NOTE:
NOTE2: please feel free to use this code or to create a pull request on Pandas github
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With