Created
November 19, 2015 20:22
-
-
Save rpmuller/2cb56d87a7306835e4cf to your computer and use it in GitHub Desktop.
Parse an orgmode table into a Pandas dataframe
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def parse_orgtable(s): | |
"""Parse an org-table (input as a multiline string) into a Pandas data frame.""" | |
# This didn't quite work, because spaces messed things up | |
#import cStringIO | |
#table = pd.read_table(cStringIO.StringIO(s),sep='|',skiprows=[1],skipinitialspace=True) | |
#table = table.drop(table.columns[[0,-1]],1) | |
# I suppose I could have simply run strip() on all of the resulting column names, since that was the problem | |
def parseline(l): | |
w = l.split('|')[1:-1] | |
return [wi.strip() for wi in w] | |
lines = s.splitlines() | |
columns = parseline(lines[0]) | |
data = [] | |
for line in lines[2:]: | |
data.append(map(float,parseline(line))) | |
return pd.DataFrame(data=data,columns=columns) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment