DataReader with google source returns DataFrame with incorrect index name #8967
Description
Hello,
import pandas.io.data as web import datetime symbol = "AAPL" end = datetime.datetime.now() start = end - datetime.timedelta(days=10) df = web.DataReader("AAPL", 'google', start, end) df.index.name is '\xef\xbb\xbfDate' it should be only 'Date'
\xef\xbb\xbf characters are invisible !
A quick and dirty solution is to change
def _retry_read_url(url, retry_count, pause, name): for _ in range(retry_count): time.sleep(pause) # kludge to close the socket ASAP try: with urlopen(url) as resp: lines = resp.read() except _network_error_classes: pass else: rs = read_csv(StringIO(bytes_to_str(lines)), index_col=0, parse_dates=True)[::-1] # Yahoo! Finance sometimes does this awesome thing where they # return 2 rows for the most recent business day if len(rs) > 2 and rs.index[-1] == rs.index[-2]: # pragma: no cover rs = rs[:-1] return rs raise IOError("after %d tries, %s did not " "return a 200 for url %r" % (retry_count, name, url)) to
def _retry_read_url(url, retry_count, pause, name): for _ in range(retry_count): time.sleep(pause) # kludge to close the socket ASAP try: with urlopen(url) as resp: lines = resp.read() except _network_error_classes: pass else: rs = read_csv(StringIO(bytes_to_str(lines)), index_col=0, parse_dates=True)[::-1] rs.index.name = 'Date' # Yahoo! Finance sometimes does this awesome thing where they # return 2 rows for the most recent business day if len(rs) > 2 and rs.index[-1] == rs.index[-2]: # pragma: no cover rs = rs[:-1] return rs raise IOError("after %d tries, %s did not " "return a 200 for url %r" % (retry_count, name, url)) so adding rs.index.name = 'Date'
fix the problem but it could have side effect for other datasource
Kind regards