pandas-csv-index_col.py

import pandas as pd
from StringIO import StringIO
import numpy as np
import re
import string

txt = """\
a   b   c   d   e   f   g   h   i
0   0   1   0   0   1   0   0   0
1   0   0   0   0   0   0   0   0
1   0   0   1   0   1   0   1   0
0   0   0   1   0   1   0   1   0
1   0   1   1   0   0   0   0   0
0   0   0   0   0   1   0   0   0
1   0   1   1   0   0   0   0   0
1   0   1   1   0   0   0   0   1
1   0   1   1   0   1   0   0   1"""


df = pd.read_csv(StringIO(txt), dtype=np.int_, sep="\s+")
df.index = [string.letters[i] for i in range(len(df))]
print "original:", df.shape
df.to_csv('t.txt', sep="\t")

df = pd.read_csv('t.txt', dtype=np.int_, sep="\s+", index_col=0)
print "OK \s+", df.shape

# with index_col, and sep of "\t" get an error about dtype.
df = pd.read_csv('t.txt', dtype=np.int_, sep="\t", index_col=0)
print "OK \t"

t.txt

	a	b	c	d	e	f	g	h	i
a	0	0	1	0	0	1	0	0	0
b	1	0	0	0	0	0	0	0	0
c	1	0	0	1	0	1	0	1	0
d	0	0	0	1	0	1	0	1	0
e	1	0	1	1	0	0	0	0	0
f	0	0	0	0	0	1	0	0	0
g	1	0	1	1	0	0	0	0	0
h	1	0	1	1	0	0	0	0	1
i	1	0	1	1	0	1	0	0	1