Skip to content

BUG: Corrects stopping logic when nrows argument is supplied (#7626) #14747

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

BUG: Corrects stopping logic when nrows argument is supplied (#7626) #14747

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6f1965a
BUG: Corrects stopping logic when nrows argument is supplied (Fixes #…
jeffcarey Nov 25, 2016
cac1bac
Removed duplicative test
jeffcarey Dec 5, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions doc/source/whatsnew/v0.19.2.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,7 @@ Bug Fixes


- Bug in ``pd.read_csv()`` in which the ``dtype`` parameter was not being respected for empty data (:issue:`14712`)
- Bug in ``pd.read_csv()`` in which the ``nrows`` parameter was not being respected for large input when using the C engine for parsing (:issue:`7626`)



Expand Down
17 changes: 17 additions & 0 deletions pandas/io/tests/parser/c_parser_only.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -371,3 +371,20 @@ def test_internal_null_byte(self):

result = self.read_csv(StringIO(data), names=names)
tm.assert_frame_equal(result, expected)

def test_read_nrows_large(self):
# gh-7626 - Read only nrows of data in for large inputs (>262144b)
header_narrow = '\t'.join(['COL_HEADER_' + str(i)
for i in range(10)]) + '\n'
data_narrow = '\t'.join(['somedatasomedatasomedata1'
for i in range(10)]) + '\n'
header_wide = '\t'.join(['COL_HEADER_' + str(i)
for i in range(15)]) + '\n'
data_wide = '\t'.join(['somedatasomedatasomedata2'
for i in range(15)]) + '\n'
test_input = (header_narrow + data_narrow * 1050 +
header_wide + data_wide * 2)

df = self.read_csv(StringIO(test_input), sep='\t', nrows=1010)

self.assertTrue(df.size == 1010 * 10)
17 changes: 17 additions & 0 deletions pandas/io/tests/parser/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,6 +427,23 @@ def test_read_nrows(self):
with tm.assertRaisesRegexp(ValueError, msg):
self.read_csv(StringIO(self.data1), nrows='foo')

def test_read_nrows_large(self):
# GH-7626 - Read only nrows of data in for large inputs (>262144b)
header_narrow = '\t'.join(['COL_HEADER_' + str(i)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is duplicating the above test in c_parser_only

for i in range(10)]) + '\n'
data_narrow = '\t'.join(['somedatasomedatasomedata1'
for i in range(10)]) + '\n'
header_wide = '\t'.join(['COL_HEADER_' + str(i)
for i in range(15)]) + '\n'
data_wide = '\t'.join(['somedatasomedatasomedata2'
for i in range(15)]) + '\n'
test_input = (header_narrow + data_narrow * 1050 +
header_wide + data_wide * 2)

df = self.read_csv(StringIO(test_input), sep="\t", nrows=1010)

self.assertTrue(df.size == 1010 * 10)

def test_read_chunksize(self):
reader = self.read_csv(StringIO(self.data1), index_col=0, chunksize=2)
df = self.read_csv(StringIO(self.data1), index_col=0)
Expand Down
8 changes: 3 additions & 5 deletions pandas/src/parser/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -726,16 +726,14 @@ int skip_this_line(parser_t *self, int64_t rownum) {
}
}

int tokenize_bytes(parser_t *self, size_t line_limit)
int tokenize_bytes(parser_t *self, size_t line_limit, int start_lines)
{
int i, slen, start_lines;
int i, slen;
long maxstreamsize;
char c;
char *stream;
char *buf = self->data + self->datapos;

start_lines = self->lines;

if (make_stream_space(self, self->datalen - self->datapos) < 0) {
self->error_msg = "out of memory";
return -1;
Expand Down Expand Up @@ -1384,7 +1382,7 @@ int _tokenize_helper(parser_t *self, size_t nrows, int all) {
TRACE(("_tokenize_helper: Trying to process %d bytes, datalen=%d, datapos= %d\n",
self->datalen - self->datapos, self->datalen, self->datapos));

status = tokenize_bytes(self, nrows);
status = tokenize_bytes(self, nrows, start_lines);

if (status < 0) {
// XXX
Expand Down