diff --git a/pandas/tests/formats/test_eng_formatting.py b/pandas/tests/formats/test_eng_formatting.py new file mode 100644 index 0000000000000..d2badd4fc160a --- /dev/null +++ b/pandas/tests/formats/test_eng_formatting.py @@ -0,0 +1,195 @@ +import numpy as np +import pandas as pd +from pandas import DataFrame +from pandas.compat import u +import pandas.formats.format as fmt +from pandas.util import testing as tm + + +class TestEngFormatter(tm.TestCase): + + def test_eng_float_formatter(self): + df = DataFrame({'A': [1.41, 141., 14100, 1410000.]}) + + fmt.set_eng_float_format() + result = df.to_string() + expected = (' A\n' + '0 1.410E+00\n' + '1 141.000E+00\n' + '2 14.100E+03\n' + '3 1.410E+06') + self.assertEqual(result, expected) + + fmt.set_eng_float_format(use_eng_prefix=True) + result = df.to_string() + expected = (' A\n' + '0 1.410\n' + '1 141.000\n' + '2 14.100k\n' + '3 1.410M') + self.assertEqual(result, expected) + + fmt.set_eng_float_format(accuracy=0) + result = df.to_string() + expected = (' A\n' + '0 1E+00\n' + '1 141E+00\n' + '2 14E+03\n' + '3 1E+06') + self.assertEqual(result, expected) + + self.reset_display_options() + + def compare(self, formatter, input, output): + formatted_input = formatter(input) + msg = ("formatting of %s results in '%s', expected '%s'" % + (str(input), formatted_input, output)) + self.assertEqual(formatted_input, output, msg) + + def compare_all(self, formatter, in_out): + """ + Parameters: + ----------- + formatter: EngFormatter under test + in_out: list of tuples. Each tuple = (number, expected_formatting) + + It is tested if 'formatter(number) == expected_formatting'. + *number* should be >= 0 because formatter(-number) == fmt is also + tested. *fmt* is derived from *expected_formatting* + """ + for input, output in in_out: + self.compare(formatter, input, output) + self.compare(formatter, -input, "-" + output[1:]) + + def test_exponents_with_eng_prefix(self): + formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) + f = np.sqrt(2) + in_out = [ + (f * 10 ** -24, " 1.414y"), (f * 10 ** -23, " 14.142y"), + (f * 10 ** -22, " 141.421y"), (f * 10 ** -21, " 1.414z"), + (f * 10 ** -20, " 14.142z"), (f * 10 ** -19, " 141.421z"), + (f * 10 ** -18, " 1.414a"), (f * 10 ** -17, " 14.142a"), + (f * 10 ** -16, " 141.421a"), (f * 10 ** -15, " 1.414f"), + (f * 10 ** -14, " 14.142f"), (f * 10 ** -13, " 141.421f"), + (f * 10 ** -12, " 1.414p"), (f * 10 ** -11, " 14.142p"), + (f * 10 ** -10, " 141.421p"), (f * 10 ** -9, " 1.414n"), + (f * 10 ** -8, " 14.142n"), (f * 10 ** -7, " 141.421n"), + (f * 10 ** -6, " 1.414u"), (f * 10 ** -5, " 14.142u"), + (f * 10 ** -4, " 141.421u"), (f * 10 ** -3, " 1.414m"), + (f * 10 ** -2, " 14.142m"), (f * 10 ** -1, " 141.421m"), + (f * 10 ** 0, " 1.414"), (f * 10 ** 1, " 14.142"), + (f * 10 ** 2, " 141.421"), (f * 10 ** 3, " 1.414k"), + (f * 10 ** 4, " 14.142k"), (f * 10 ** 5, " 141.421k"), + (f * 10 ** 6, " 1.414M"), (f * 10 ** 7, " 14.142M"), + (f * 10 ** 8, " 141.421M"), (f * 10 ** 9, " 1.414G"), + (f * 10 ** 10, " 14.142G"), (f * 10 ** 11, " 141.421G"), + (f * 10 ** 12, " 1.414T"), (f * 10 ** 13, " 14.142T"), + (f * 10 ** 14, " 141.421T"), (f * 10 ** 15, " 1.414P"), + (f * 10 ** 16, " 14.142P"), (f * 10 ** 17, " 141.421P"), + (f * 10 ** 18, " 1.414E"), (f * 10 ** 19, " 14.142E"), + (f * 10 ** 20, " 141.421E"), (f * 10 ** 21, " 1.414Z"), + (f * 10 ** 22, " 14.142Z"), (f * 10 ** 23, " 141.421Z"), + (f * 10 ** 24, " 1.414Y"), (f * 10 ** 25, " 14.142Y"), + (f * 10 ** 26, " 141.421Y")] + self.compare_all(formatter, in_out) + + def test_exponents_without_eng_prefix(self): + formatter = fmt.EngFormatter(accuracy=4, use_eng_prefix=False) + f = np.pi + in_out = [ + (f * 10 ** -24, " 3.1416E-24"), + (f * 10 ** -23, " 31.4159E-24"), + (f * 10 ** -22, " 314.1593E-24"), + (f * 10 ** -21, " 3.1416E-21"), + (f * 10 ** -20, " 31.4159E-21"), + (f * 10 ** -19, " 314.1593E-21"), + (f * 10 ** -18, " 3.1416E-18"), + (f * 10 ** -17, " 31.4159E-18"), + (f * 10 ** -16, " 314.1593E-18"), + (f * 10 ** -15, " 3.1416E-15"), + (f * 10 ** -14, " 31.4159E-15"), + (f * 10 ** -13, " 314.1593E-15"), + (f * 10 ** -12, " 3.1416E-12"), + (f * 10 ** -11, " 31.4159E-12"), + (f * 10 ** -10, " 314.1593E-12"), + (f * 10 ** -9, " 3.1416E-09"), + (f * 10 ** -8, " 31.4159E-09"), + (f * 10 ** -7, " 314.1593E-09"), + (f * 10 ** -6, " 3.1416E-06"), + (f * 10 ** -5, " 31.4159E-06"), + (f * 10 ** -4, " 314.1593E-06"), + (f * 10 ** -3, " 3.1416E-03"), + (f * 10 ** -2, " 31.4159E-03"), + (f * 10 ** -1, " 314.1593E-03"), + (f * 10 ** 0, " 3.1416E+00"), + (f * 10 ** 1, " 31.4159E+00"), + (f * 10 ** 2, " 314.1593E+00"), + (f * 10 ** 3, " 3.1416E+03"), + (f * 10 ** 4, " 31.4159E+03"), + (f * 10 ** 5, " 314.1593E+03"), + (f * 10 ** 6, " 3.1416E+06"), + (f * 10 ** 7, " 31.4159E+06"), + (f * 10 ** 8, " 314.1593E+06"), + (f * 10 ** 9, " 3.1416E+09"), + (f * 10 ** 10, " 31.4159E+09"), + (f * 10 ** 11, " 314.1593E+09"), + (f * 10 ** 12, " 3.1416E+12"), + (f * 10 ** 13, " 31.4159E+12"), + (f * 10 ** 14, " 314.1593E+12"), + (f * 10 ** 15, " 3.1416E+15"), + (f * 10 ** 16, " 31.4159E+15"), + (f * 10 ** 17, " 314.1593E+15"), + (f * 10 ** 18, " 3.1416E+18"), + (f * 10 ** 19, " 31.4159E+18"), + (f * 10 ** 20, " 314.1593E+18"), + (f * 10 ** 21, " 3.1416E+21"), + (f * 10 ** 22, " 31.4159E+21"), + (f * 10 ** 23, " 314.1593E+21"), + (f * 10 ** 24, " 3.1416E+24"), + (f * 10 ** 25, " 31.4159E+24"), + (f * 10 ** 26, " 314.1593E+24")] + self.compare_all(formatter, in_out) + + def test_rounding(self): + formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) + in_out = [(5.55555, ' 5.556'), (55.5555, ' 55.556'), + (555.555, ' 555.555'), (5555.55, ' 5.556k'), + (55555.5, ' 55.556k'), (555555, ' 555.555k')] + self.compare_all(formatter, in_out) + + formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) + in_out = [(5.55555, ' 5.6'), (55.5555, ' 55.6'), (555.555, ' 555.6'), + (5555.55, ' 5.6k'), (55555.5, ' 55.6k'), (555555, ' 555.6k')] + self.compare_all(formatter, in_out) + + formatter = fmt.EngFormatter(accuracy=0, use_eng_prefix=True) + in_out = [(5.55555, ' 6'), (55.5555, ' 56'), (555.555, ' 556'), + (5555.55, ' 6k'), (55555.5, ' 56k'), (555555, ' 556k')] + self.compare_all(formatter, in_out) + + formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) + result = formatter(0) + self.assertEqual(result, u(' 0.000')) + + def test_nan(self): + # Issue #11981 + + formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) + result = formatter(np.nan) + self.assertEqual(result, u('NaN')) + + df = pd.DataFrame({'a': [1.5, 10.3, 20.5], + 'b': [50.3, 60.67, 70.12], + 'c': [100.2, 101.33, 120.33]}) + pt = df.pivot_table(values='a', index='b', columns='c') + fmt.set_eng_float_format(accuracy=1) + result = pt.to_string() + self.assertTrue('NaN' in result) + self.reset_display_options() + + def test_inf(self): + # Issue #11981 + + formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) + result = formatter(np.inf) + self.assertEqual(result, u('inf')) diff --git a/pandas/tests/formats/test_format.py b/pandas/tests/formats/test_format.py index 476c6a636ae5a..ddf9d35841ce7 100644 --- a/pandas/tests/formats/test_format.py +++ b/pandas/tests/formats/test_format.py @@ -1,50 +1,41 @@ # -*- coding: utf-8 -*- +""" +test output formatting for Series/DataFrame +including to_string & reprs +""" + # TODO(wesm): lots of issues making flake8 hard # flake8: noqa from __future__ import print_function -from distutils.version import LooseVersion import re -from pandas.compat import (range, zip, lrange, StringIO, PY3, - u, lzip, is_platform_windows, - is_platform_32bit) -import pandas.compat as compat import itertools from operator import methodcaller import os import sys -from textwrap import dedent import warnings +from datetime import datetime -from numpy import nan -from numpy.random import randn -import numpy as np - -import codecs - -div_style = '' -try: - import IPython - if IPython.__version__ < LooseVersion('3.0.0'): - div_style = ' style="max-width:1500px;overflow:auto;"' -except (ImportError, AttributeError): - pass +import pytest -from pandas import DataFrame, Series, Index, Timestamp, MultiIndex, date_range, NaT +import numpy as np +import pandas as pd +from pandas import (DataFrame, Series, Index, Timestamp, MultiIndex, + date_range, NaT, read_table) +from pandas.compat import (range, zip, lrange, StringIO, PY3, + u, lzip, is_platform_windows, + is_platform_32bit) +import pandas.compat as compat import pandas.formats.format as fmt -import pandas.util.testing as tm -import pandas.core.common as com import pandas.formats.printing as printing + +import pandas.util.testing as tm from pandas.util.terminal import get_terminal_size -import pandas as pd from pandas.core.config import (set_option, get_option, option_context, reset_option) -from datetime import datetime - -import pytest use_32bit_repr = is_platform_windows() or is_platform_32bit() @@ -288,7 +279,7 @@ def test_repr_max_columns_max_rows(self): term_width, term_height = get_terminal_size() if term_width < 10 or term_height < 10: pytest.skip("terminal size too small, " - "{0} x {1}".format(term_width, term_height)) + "{0} x {1}".format(term_width, term_height)) def mkframe(n): index = ['%05d' % i for i in range(n)] @@ -829,1393 +820,6 @@ def test_datetimelike_frame(self): '[10 rows x 2 columns]') self.assertEqual(repr(df), expected) - def test_to_html_with_col_space(self): - def check_with_width(df, col_space): - import re - # check that col_space affects HTML generation - # and be very brittle about it. - html = df.to_html(col_space=col_space) - hdrs = [x for x in html.split(r"\n") if re.search(r"\s]", x)] - self.assertTrue(len(hdrs) > 0) - for h in hdrs: - self.assertTrue("min-width" in h) - self.assertTrue(str(col_space) in h) - - df = DataFrame(np.random.random(size=(1, 3))) - - check_with_width(df, 30) - check_with_width(df, 50) - - def test_to_html_with_empty_string_label(self): - # GH3547, to_html regards empty string labels as repeated labels - data = {'c1': ['a', 'b'], 'c2': ['a', ''], 'data': [1, 2]} - df = DataFrame(data).set_index(['c1', 'c2']) - res = df.to_html() - self.assertTrue("rowspan" not in res) - - def test_to_html_unicode(self): - df = DataFrame({u('\u03c3'): np.arange(10.)}) - expected = u'\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
\u03c3
00.0
11.0
22.0
33.0
44.0
55.0
66.0
77.0
88.0
99.0
' - self.assertEqual(df.to_html(), expected) - df = DataFrame({'A': [u('\u03c3')]}) - expected = u'\n \n \n \n \n \n \n \n \n \n \n \n \n
A
0\u03c3
' - self.assertEqual(df.to_html(), expected) - - def test_to_html_decimal(self): - # GH 12031 - df = DataFrame({'A': [6.0, 3.1, 2.2]}) - result = df.to_html(decimal=',') - expected = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
A
06,0
13,1
22,2
') - self.assertEqual(result, expected) - - def test_to_html_escaped(self): - a = 'str", - b: ""}, - 'co>l2': {a: "", - b: ""}} - rs = DataFrame(test_dict).to_html() - xp = """ - - - - - - - - - - - - - - - - - - - -
co<l1co>l2
str<ing1 &amp;<type 'str'><type 'str'>
stri>ng2 &amp;<type 'str'><type 'str'>
""" - - self.assertEqual(xp, rs) - - def test_to_html_escape_disabled(self): - a = 'strbold", - b: "bold"}, - 'co>l2': {a: "bold", - b: "bold"}} - rs = DataFrame(test_dict).to_html(escape=False) - xp = """ - - - - - - - - - - - - - - - - - -
co - co>l2
str - boldbold
stri>ng2 &boldbold
""" - - self.assertEqual(xp, rs) - - def test_to_html_multiindex_index_false(self): - # issue 8452 - df = DataFrame({ - 'a': range(2), - 'b': range(3, 5), - 'c': range(5, 7), - 'd': range(3, 5) - }) - df.columns = MultiIndex.from_product([['a', 'b'], ['c', 'd']]) - result = df.to_html(index=False) - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - -
ab
cdcd
0353
1464
""" - - self.assertEqual(result, expected) - - df.index = Index(df.index.values, name='idx') - result = df.to_html(index=False) - self.assertEqual(result, expected) - - def test_to_html_multiindex_sparsify_false_multi_sparse(self): - with option_context('display.multi_sparse', False): - index = MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]], - names=['foo', None]) - - df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], index=index) - - result = df.to_html() - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
01
foo
0001
0123
1045
1167
""" - - self.assertEqual(result, expected) - - df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], - columns=index[::2], index=index) - - result = df.to_html() - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
foo01
00
foo
0001
0123
1045
1167
""" - - self.assertEqual(result, expected) - - def test_to_html_multiindex_sparsify(self): - index = MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]], - names=['foo', None]) - - df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], index=index) - - result = df.to_html() - expected = """ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
01
foo
0001
123
1045
167
""" - - self.assertEqual(result, expected) - - df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], columns=index[::2], - index=index) - - result = df.to_html() - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
foo01
00
foo
0001
123
1045
167
""" - - self.assertEqual(result, expected) - - def test_to_html_multiindex_odd_even_truncate(self): - # GH 14882 - Issue on truncation with odd length DataFrame - mi = MultiIndex.from_product([[100, 200, 300], - [10, 20, 30], - [1, 2, 3, 4, 5, 6, 7]], - names=['a', 'b', 'c']) - df = DataFrame({'n': range(len(mi))}, index=mi) - result = df.to_html(max_rows=60) - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
n
abc
1001010
21
32
43
54
65
76
2017
28
39
410
511
612
713
30114
215
316
417
518
619
720
20010121
222
323
424
525
626
727
20128
229
......
633
734
30135
236
337
438
539
640
741
30010142
243
344
445
546
647
748
20149
250
351
452
553
654
755
30156
257
358
459
560
661
762
""" - self.assertEqual(result, expected) - - # Test that ... appears in a middle level - result = df.to_html(max_rows=56) - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
n
abc
1001010
21
32
43
54
65
76
2017
28
39
410
511
612
713
30114
215
316
417
518
619
720
20010121
222
323
424
525
626
727
.........
30135
236
337
438
539
640
741
30010142
243
344
445
546
647
748
20149
250
351
452
553
654
755
30156
257
358
459
560
661
762
""" - self.assertEqual(result, expected) - - def test_to_html_index_formatter(self): - df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], columns=['foo', None], - index=lrange(4)) - - f = lambda x: 'abcd' [x] - result = df.to_html(formatters={'__index__': f}) - expected = """\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
fooNone
a01
b23
c45
d67
""" - - self.assertEqual(result, expected) - - def test_to_html_datetime64_monthformatter(self): - months = [datetime(2016, 1, 1), datetime(2016, 2, 2)] - x = DataFrame({'months': months}) - - def format_func(x): - return x.strftime('%Y-%m') - result = x.to_html(formatters={'months': format_func}) - expected = """\ - - - - - - - - - - - - - - - - - -
months
02016-01
12016-02
""" - self.assertEqual(result, expected) - - def test_to_html_datetime64_hourformatter(self): - - x = DataFrame({'hod': pd.to_datetime(['10:10:10.100', '12:12:12.120'], - format='%H:%M:%S.%f')}) - - def format_func(x): - return x.strftime('%H:%M') - result = x.to_html(formatters={'hod': format_func}) - expected = """\ - - - - - - - - - - - - - - - - - -
hod
010:10
112:12
""" - self.assertEqual(result, expected) - - def test_to_html_regression_GH6098(self): - df = DataFrame({u('clé1'): [u('a'), u('a'), u('b'), u('b'), u('a')], - u('clé2'): [u('1er'), u('2ème'), u('1er'), u('2ème'), - u('1er')], - 'données1': np.random.randn(5), - 'données2': np.random.randn(5)}) - # it works - df.pivot_table(index=[u('clé1')], columns=[u('clé2')])._repr_html_() - - def test_to_html_truncate(self): - pytest.skip("unreliable on travis") - index = pd.DatetimeIndex(start='20010101', freq='D', periods=20) - df = DataFrame(index=index, columns=range(20)) - fmt.set_option('display.max_rows', 8) - fmt.set_option('display.max_columns', 4) - result = df._repr_html_() - expected = '''\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
01...1819
2001-01-01NaNNaN...NaNNaN
2001-01-02NaNNaN...NaNNaN
2001-01-03NaNNaN...NaNNaN
2001-01-04NaNNaN...NaNNaN
..................
2001-01-17NaNNaN...NaNNaN
2001-01-18NaNNaN...NaNNaN
2001-01-19NaNNaN...NaNNaN
2001-01-20NaNNaN...NaNNaN
-

20 rows × 20 columns

-'''.format(div_style) - if compat.PY2: - expected = expected.decode('utf-8') - self.assertEqual(result, expected) - - def test_to_html_truncate_multi_index(self): - pytest.skip("unreliable on travis") - arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'], - ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']] - df = DataFrame(index=arrays, columns=arrays) - fmt.set_option('display.max_rows', 7) - fmt.set_option('display.max_columns', 7) - result = df._repr_html_() - expected = '''\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
barbaz...fooqux
onetwoone...twoonetwo
baroneNaNNaNNaN...NaNNaNNaN
twoNaNNaNNaN...NaNNaNNaN
bazoneNaNNaNNaN...NaNNaNNaN
...........................
footwoNaNNaNNaN...NaNNaNNaN
quxoneNaNNaNNaN...NaNNaNNaN
twoNaNNaNNaN...NaNNaNNaN
-

8 rows × 8 columns

-'''.format(div_style) - if compat.PY2: - expected = expected.decode('utf-8') - self.assertEqual(result, expected) - - def test_to_html_truncate_multi_index_sparse_off(self): - pytest.skip("unreliable on travis") - arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'], - ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']] - df = DataFrame(index=arrays, columns=arrays) - fmt.set_option('display.max_rows', 7) - fmt.set_option('display.max_columns', 7) - fmt.set_option('display.multi_sparse', False) - result = df._repr_html_() - expected = '''\ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
barbarbaz...fooquxqux
onetwoone...twoonetwo
baroneNaNNaNNaN...NaNNaNNaN
bartwoNaNNaNNaN...NaNNaNNaN
bazoneNaNNaNNaN...NaNNaNNaN
footwoNaNNaNNaN...NaNNaNNaN
quxoneNaNNaNNaN...NaNNaNNaN
quxtwoNaNNaNNaN...NaNNaNNaN
-

8 rows × 8 columns

-'''.format(div_style) - if compat.PY2: - expected = expected.decode('utf-8') - self.assertEqual(result, expected) - - def test_to_html_border(self): - df = DataFrame({'A': [1, 2]}) - result = df.to_html() - assert 'border="1"' in result - - def test_to_html_border_option(self): - df = DataFrame({'A': [1, 2]}) - with pd.option_context('html.border', 0): - result = df.to_html() - self.assertTrue('border="0"' in result) - self.assertTrue('border="0"' in df._repr_html_()) - - def test_to_html_border_zero(self): - df = DataFrame({'A': [1, 2]}) - result = df.to_html(border=0) - self.assertTrue('border="0"' in result) - def test_nonunicode_nonascii_alignment(self): df = DataFrame([["aa\xc3\xa4\xc3\xa4", 1], ["bbbb", 2]]) rep_str = df.to_string() @@ -2223,7 +827,7 @@ def test_nonunicode_nonascii_alignment(self): self.assertEqual(len(lines[1]), len(lines[2])) def test_unicode_problem_decoding_as_ascii(self): - dm = DataFrame({u('c/\u03c3'): Series({'test': np.NaN})}) + dm = DataFrame({u('c/\u03c3'): Series({'test': np.nan})}) compat.text_type(dm.to_string()) def test_string_repr_encoding(self): @@ -2271,7 +875,7 @@ def test_pprint_thing(self): # escape embedded tabs in string # GH #2038 - self.assertTrue(not "\t" in pp_t("a\tb", escape_chars=("\t", ))) + assert "\t" not in pp_t("a\tb", escape_chars=("\t", )) def test_wide_repr(self): with option_context('mode.sim_interactive', True, @@ -2294,7 +898,8 @@ def test_wide_repr(self): def test_wide_repr_wide_columns(self): with option_context('mode.sim_interactive', True): - df = DataFrame(randn(5, 3), columns=['a' * 90, 'b' * 90, 'c' * 90]) + df = DataFrame(np.random.randn(5, 3), + columns=['a' * 90, 'b' * 90, 'c' * 90]) rep_str = repr(df) self.assertEqual(len(rep_str.splitlines()), 20) @@ -2346,8 +951,8 @@ def test_wide_repr_multiindex_cols(self): with option_context('mode.sim_interactive', True): max_cols = get_option('display.max_columns') midx = MultiIndex.from_arrays(tm.rands_array(5, size=(2, 10))) - mcols = MultiIndex.from_arrays(tm.rands_array(3, size=(2, max_cols - - 1))) + mcols = MultiIndex.from_arrays( + tm.rands_array(3, size=(2, max_cols - 1))) df = DataFrame(tm.rands_array(25, (10, max_cols - 1)), index=midx, columns=mcols) df.index.names = ['Level 0', 'Level 1'] @@ -2465,16 +1070,14 @@ def test_index_with_nan(self): self.assertEqual(result, expected) def test_to_string(self): - from pandas import read_table - import re # big mixed - biggie = DataFrame({'A': randn(200), + biggie = DataFrame({'A': np.random.randn(200), 'B': tm.makeStringIndex(200)}, index=lrange(200)) - biggie.loc[:20, 'A'] = nan - biggie.loc[:20, 'B'] = nan + biggie.loc[:20, 'A'] = np.nan + biggie.loc[:20, 'B'] = np.nan s = biggie.to_string() buf = StringIO() @@ -2713,414 +1316,6 @@ def test_show_dimensions(self): self.assertFalse('5 rows' in str(df)) self.assertFalse('5 rows' in df._repr_html_()) - def test_to_html(self): - # big mixed - biggie = DataFrame({'A': randn(200), - 'B': tm.makeStringIndex(200)}, - index=lrange(200)) - - biggie.loc[:20, 'A'] = nan - biggie.loc[:20, 'B'] = nan - s = biggie.to_html() - - buf = StringIO() - retval = biggie.to_html(buf=buf) - self.assertIsNone(retval) - self.assertEqual(buf.getvalue(), s) - - tm.assertIsInstance(s, compat.string_types) - - biggie.to_html(columns=['B', 'A'], col_space=17) - biggie.to_html(columns=['B', 'A'], - formatters={'A': lambda x: '%.1f' % x}) - - biggie.to_html(columns=['B', 'A'], float_format=str) - biggie.to_html(columns=['B', 'A'], col_space=12, float_format=str) - - frame = DataFrame(index=np.arange(200)) - frame.to_html() - - def test_to_html_filename(self): - biggie = DataFrame({'A': randn(200), - 'B': tm.makeStringIndex(200)}, - index=lrange(200)) - - biggie.loc[:20, 'A'] = nan - biggie.loc[:20, 'B'] = nan - with tm.ensure_clean('test.html') as path: - biggie.to_html(path) - with open(path, 'r') as f: - s = biggie.to_html() - s2 = f.read() - self.assertEqual(s, s2) - - frame = DataFrame(index=np.arange(200)) - with tm.ensure_clean('test.html') as path: - frame.to_html(path) - with open(path, 'r') as f: - self.assertEqual(frame.to_html(), f.read()) - - def test_to_html_with_no_bold(self): - x = DataFrame({'x': randn(5)}) - ashtml = x.to_html(bold_rows=False) - self.assertFalse('")]) - - def test_to_html_columns_arg(self): - result = self.frame.to_html(columns=['A']) - self.assertNotIn('B', result) - - def test_to_html_multiindex(self): - columns = MultiIndex.from_tuples(list(zip(np.arange(2).repeat(2), - np.mod(lrange(4), 2))), - names=['CL0', 'CL1']) - df = DataFrame([list('abcd'), list('efgh')], columns=columns) - result = df.to_html(justify='left') - expected = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
CL001
CL10101
0abcd
1efgh
') - - self.assertEqual(result, expected) - - columns = MultiIndex.from_tuples(list(zip( - range(4), np.mod( - lrange(4), 2)))) - df = DataFrame([list('abcd'), list('efgh')], columns=columns) - - result = df.to_html(justify='right') - expected = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
0123
0101
0abcd
1efgh
') - - self.assertEqual(result, expected) - - def test_to_html_justify(self): - df = DataFrame({'A': [6, 30000, 2], - 'B': [1, 2, 70000], - 'C': [223442, 0, 1]}, - columns=['A', 'B', 'C']) - result = df.to_html(justify='left') - expected = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
061223442
13000020
22700001
') - self.assertEqual(result, expected) - - result = df.to_html(justify='right') - expected = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
061223442
13000020
22700001
') - self.assertEqual(result, expected) - - def test_to_html_index(self): - index = ['foo', 'bar', 'baz'] - df = DataFrame({'A': [1, 2, 3], - 'B': [1.2, 3.4, 5.6], - 'C': ['one', 'two', np.NaN]}, - columns=['A', 'B', 'C'], - index=index) - expected_with_index = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
foo11.2one
bar23.4two
baz35.6NaN
') - self.assertEqual(df.to_html(), expected_with_index) - - expected_without_index = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
11.2one
23.4two
35.6NaN
') - result = df.to_html(index=False) - for i in index: - self.assertNotIn(i, result) - self.assertEqual(result, expected_without_index) - df.index = Index(['foo', 'bar', 'baz'], name='idx') - expected_with_index = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
idx
foo11.2one
bar23.4two
baz35.6NaN
') - self.assertEqual(df.to_html(), expected_with_index) - self.assertEqual(df.to_html(index=False), expected_without_index) - - tuples = [('foo', 'car'), ('foo', 'bike'), ('bar', 'car')] - df.index = MultiIndex.from_tuples(tuples) - - expected_with_index = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
foocar11.2one
bike23.4two
barcar35.6NaN
') - self.assertEqual(df.to_html(), expected_with_index) - - result = df.to_html(index=False) - for i in ['foo', 'bar', 'car', 'bike']: - self.assertNotIn(i, result) - # must be the same result as normal index - self.assertEqual(result, expected_without_index) - - df.index = MultiIndex.from_tuples(tuples, names=['idx1', 'idx2']) - expected_with_index = ('\n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - ' \n' - '
ABC
idx1idx2
foocar11.2one
bike23.4two
barcar35.6NaN
') - self.assertEqual(df.to_html(), expected_with_index) - self.assertEqual(df.to_html(index=False), expected_without_index) - def test_repr_html(self): self.frame._repr_html_() @@ -3254,7 +1449,7 @@ def test_info_repr(self): def test_info_repr_max_cols(self): # GH #6939 - df = DataFrame(randn(10, 5)) + df = DataFrame(np.random.randn(10, 5)) with option_context('display.large_repr', 'info', 'display.max_columns', 1, 'display.max_info_columns', 4): @@ -3299,46 +1494,6 @@ def get_ipython(): self.reset_display_options() - def test_to_html_with_classes(self): - df = DataFrame() - result = df.to_html(classes="sortable draggable") - expected = dedent(""" - - - - - - - - - -
- - """).strip() - self.assertEqual(result, expected) - - result = df.to_html(classes=["sortable", "draggable"]) - self.assertEqual(result, expected) - - def test_to_html_no_index_max_rows(self): - # GH https://github.com/pandas-dev/pandas/issues/14998 - df = DataFrame({"A": [1, 2, 3, 4]}) - result = df.to_html(index=False, max_rows=1) - expected = dedent("""\ - - - - - - - - - - - -
A
1
""") - self.assertEqual(result, expected) - def test_pprint_pathological_object(self): """ if the test fails, the stack will overflow and nose crash, @@ -3373,541 +1528,6 @@ def test_dict_entries(self): self.assertTrue("'a': 1" in val) self.assertTrue("'b': 2" in val) - def test_to_latex_filename(self): - with tm.ensure_clean('test.tex') as path: - self.frame.to_latex(path) - - with open(path, 'r') as f: - self.assertEqual(self.frame.to_latex(), f.read()) - - # test with utf-8 and encoding option (GH 7061) - df = DataFrame([[u'au\xdfgangen']]) - with tm.ensure_clean('test.tex') as path: - df.to_latex(path, encoding='utf-8') - with codecs.open(path, 'r', encoding='utf-8') as f: - self.assertEqual(df.to_latex(), f.read()) - - # test with utf-8 without encoding option - if compat.PY3: # python3: pandas default encoding is utf-8 - with tm.ensure_clean('test.tex') as path: - df.to_latex(path) - with codecs.open(path, 'r', encoding='utf-8') as f: - self.assertEqual(df.to_latex(), f.read()) - else: - # python2 default encoding is ascii, so an error should be raised - with tm.ensure_clean('test.tex') as path: - self.assertRaises(UnicodeEncodeError, df.to_latex, path) - - def test_to_latex(self): - # it works! - self.frame.to_latex() - - df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) - withindex_result = df.to_latex() - withindex_expected = r"""\begin{tabular}{lrl} -\toprule -{} & a & b \\ -\midrule -0 & 1 & b1 \\ -1 & 2 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withindex_result, withindex_expected) - - withoutindex_result = df.to_latex(index=False) - withoutindex_expected = r"""\begin{tabular}{rl} -\toprule - a & b \\ -\midrule - 1 & b1 \\ - 2 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withoutindex_result, withoutindex_expected) - - def test_to_latex_format(self): - # GH Bug #9402 - self.frame.to_latex(column_format='ccc') - - df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) - withindex_result = df.to_latex(column_format='ccc') - withindex_expected = r"""\begin{tabular}{ccc} -\toprule -{} & a & b \\ -\midrule -0 & 1 & b1 \\ -1 & 2 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withindex_result, withindex_expected) - - def test_to_latex_with_formatters(self): - df = DataFrame({'int': [1, 2, 3], - 'float': [1.0, 2.0, 3.0], - 'object': [(1, 2), True, False], - 'datetime64': [datetime(2016, 1, 1), - datetime(2016, 2, 5), - datetime(2016, 3, 3)]}) - - formatters = {'int': lambda x: '0x%x' % x, - 'float': lambda x: '[% 4.1f]' % x, - 'object': lambda x: '-%s-' % str(x), - 'datetime64': lambda x: x.strftime('%Y-%m'), - '__index__': lambda x: 'index: %s' % x} - result = df.to_latex(formatters=dict(formatters)) - - expected = r"""\begin{tabular}{llrrl} -\toprule -{} & datetime64 & float & int & object \\ -\midrule -index: 0 & 2016-01 & [ 1.0] & 0x1 & -(1, 2)- \\ -index: 1 & 2016-02 & [ 2.0] & 0x2 & -True- \\ -index: 2 & 2016-03 & [ 3.0] & 0x3 & -False- \\ -\bottomrule -\end{tabular} -""" - self.assertEqual(result, expected) - - def test_to_latex_multiindex(self): - df = DataFrame({('x', 'y'): ['a']}) - result = df.to_latex() - expected = r"""\begin{tabular}{ll} -\toprule -{} & x \\ -{} & y \\ -\midrule -0 & a \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(result, expected) - - result = df.T.to_latex() - expected = r"""\begin{tabular}{lll} -\toprule - & & 0 \\ -\midrule -x & y & a \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(result, expected) - - df = DataFrame.from_dict({ - ('c1', 0): pd.Series(dict((x, x) for x in range(4))), - ('c1', 1): pd.Series(dict((x, x + 4) for x in range(4))), - ('c2', 0): pd.Series(dict((x, x) for x in range(4))), - ('c2', 1): pd.Series(dict((x, x + 4) for x in range(4))), - ('c3', 0): pd.Series(dict((x, x) for x in range(4))), - }).T - result = df.to_latex() - expected = r"""\begin{tabular}{llrrrr} -\toprule - & & 0 & 1 & 2 & 3 \\ -\midrule -c1 & 0 & 0 & 1 & 2 & 3 \\ - & 1 & 4 & 5 & 6 & 7 \\ -c2 & 0 & 0 & 1 & 2 & 3 \\ - & 1 & 4 & 5 & 6 & 7 \\ -c3 & 0 & 0 & 1 & 2 & 3 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(result, expected) - - # GH 10660 - df = pd.DataFrame({'a': [0, 0, 1, 1], - 'b': list('abab'), - 'c': [1, 2, 3, 4]}) - result = df.set_index(['a', 'b']).to_latex() - expected = r"""\begin{tabular}{llr} -\toprule - & & c \\ -a & b & \\ -\midrule -0 & a & 1 \\ - & b & 2 \\ -1 & a & 3 \\ - & b & 4 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(result, expected) - - result = df.groupby('a').describe().to_latex() - expected = ('\\begin{tabular}{lrrrrrrrr}\n\\toprule\n{} & c & ' - ' & & & & & & ' - '\\\\\n{} & count & mean & std & min & 25\\% & ' - '50\\% & 75\\% & max \\\\\na & & & ' - ' & & & & & \\\\\n\\midrule\n0 ' - '& 2.0 & 1.5 & 0.707107 & 1.0 & 1.25 & 1.5 & 1.75 ' - '& 2.0 \\\\\n1 & 2.0 & 3.5 & 0.707107 & 3.0 & 3.25 ' - '& 3.5 & 3.75 & 4.0 ' - '\\\\\n\\bottomrule\n\\end{tabular}\n') - - self.assertEqual(result, expected) - - def test_to_latex_escape(self): - a = 'a' - b = 'b' - - test_dict = {u('co^l1'): {a: "a", - b: "b"}, - u('co$e^x$'): {a: "a", - b: "b"}} - - unescaped_result = DataFrame(test_dict).to_latex(escape=False) - escaped_result = DataFrame(test_dict).to_latex( - ) # default: escape=True - - unescaped_expected = r'''\begin{tabular}{lll} -\toprule -{} & co$e^x$ & co^l1 \\ -\midrule -a & a & a \\ -b & b & b \\ -\bottomrule -\end{tabular} -''' - - escaped_expected = r'''\begin{tabular}{lll} -\toprule -{} & co\$e\textasciicircumx\$ & co\textasciicircuml1 \\ -\midrule -a & a & a \\ -b & b & b \\ -\bottomrule -\end{tabular} -''' - - self.assertEqual(unescaped_result, unescaped_expected) - self.assertEqual(escaped_result, escaped_expected) - - def test_to_latex_longtable(self): - self.frame.to_latex(longtable=True) - - df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) - withindex_result = df.to_latex(longtable=True) - withindex_expected = r"""\begin{longtable}{lrl} -\toprule -{} & a & b \\ -\midrule -\endhead -\midrule -\multicolumn{3}{r}{{Continued on next page}} \\ -\midrule -\endfoot - -\bottomrule -\endlastfoot -0 & 1 & b1 \\ -1 & 2 & b2 \\ -\end{longtable} -""" - - self.assertEqual(withindex_result, withindex_expected) - - withoutindex_result = df.to_latex(index=False, longtable=True) - withoutindex_expected = r"""\begin{longtable}{rl} -\toprule - a & b \\ -\midrule -\endhead -\midrule -\multicolumn{3}{r}{{Continued on next page}} \\ -\midrule -\endfoot - -\bottomrule -\endlastfoot - 1 & b1 \\ - 2 & b2 \\ -\end{longtable} -""" - - self.assertEqual(withoutindex_result, withoutindex_expected) - - def test_to_latex_escape_special_chars(self): - special_characters = ['&', '%', '$', '#', '_', '{', '}', '~', '^', - '\\'] - df = DataFrame(data=special_characters) - observed = df.to_latex() - expected = r"""\begin{tabular}{ll} -\toprule -{} & 0 \\ -\midrule -0 & \& \\ -1 & \% \\ -2 & \$ \\ -3 & \# \\ -4 & \_ \\ -5 & \{ \\ -6 & \} \\ -7 & \textasciitilde \\ -8 & \textasciicircum \\ -9 & \textbackslash \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(observed, expected) - - def test_to_latex_no_header(self): - # GH 7124 - df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) - withindex_result = df.to_latex(header=False) - withindex_expected = r"""\begin{tabular}{lrl} -\toprule -0 & 1 & b1 \\ -1 & 2 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withindex_result, withindex_expected) - - withoutindex_result = df.to_latex(index=False, header=False) - withoutindex_expected = r"""\begin{tabular}{rl} -\toprule - 1 & b1 \\ - 2 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withoutindex_result, withoutindex_expected) - - def test_to_latex_decimal(self): - # GH 12031 - self.frame.to_latex() - df = DataFrame({'a': [1.0, 2.1], 'b': ['b1', 'b2']}) - withindex_result = df.to_latex(decimal=',') - print("WHAT THE") - withindex_expected = r"""\begin{tabular}{lrl} -\toprule -{} & a & b \\ -\midrule -0 & 1,0 & b1 \\ -1 & 2,1 & b2 \\ -\bottomrule -\end{tabular} -""" - - self.assertEqual(withindex_result, withindex_expected) - - def test_to_csv_quotechar(self): - df = DataFrame({'col': [1, 2]}) - expected = """\ -"","col" -"0","1" -"1","2" -""" - - with tm.ensure_clean('test.csv') as path: - df.to_csv(path, quoting=1) # 1=QUOTE_ALL - with open(path, 'r') as f: - self.assertEqual(f.read(), expected) - - expected = """\ -$$,$col$ -$0$,$1$ -$1$,$2$ -""" - - with tm.ensure_clean('test.csv') as path: - df.to_csv(path, quoting=1, quotechar="$") - with open(path, 'r') as f: - self.assertEqual(f.read(), expected) - - with tm.ensure_clean('test.csv') as path: - with tm.assertRaisesRegexp(TypeError, 'quotechar'): - df.to_csv(path, quoting=1, quotechar=None) - - def test_to_csv_doublequote(self): - df = DataFrame({'col': ['a"a', '"bb"']}) - expected = '''\ -"","col" -"0","a""a" -"1","""bb""" -''' - - with tm.ensure_clean('test.csv') as path: - df.to_csv(path, quoting=1, doublequote=True) # QUOTE_ALL - with open(path, 'r') as f: - self.assertEqual(f.read(), expected) - - from _csv import Error - with tm.ensure_clean('test.csv') as path: - with tm.assertRaisesRegexp(Error, 'escapechar'): - df.to_csv(path, doublequote=False) # no escapechar set - - def test_to_csv_escapechar(self): - df = DataFrame({'col': ['a"a', '"bb"']}) - expected = '''\ -"","col" -"0","a\\"a" -"1","\\"bb\\"" -''' - - with tm.ensure_clean('test.csv') as path: # QUOTE_ALL - df.to_csv(path, quoting=1, doublequote=False, escapechar='\\') - with open(path, 'r') as f: - self.assertEqual(f.read(), expected) - - df = DataFrame({'col': ['a,a', ',bb,']}) - expected = """\ -,col -0,a\\,a -1,\\,bb\\, -""" - - with tm.ensure_clean('test.csv') as path: - df.to_csv(path, quoting=3, escapechar='\\') # QUOTE_NONE - with open(path, 'r') as f: - self.assertEqual(f.read(), expected) - - def test_csv_to_string(self): - df = DataFrame({'col': [1, 2]}) - expected = ',col\n0,1\n1,2\n' - self.assertEqual(df.to_csv(), expected) - - def test_to_csv_decimal(self): - # GH 781 - df = DataFrame({'col1': [1], 'col2': ['a'], 'col3': [10.1]}) - - expected_default = ',col1,col2,col3\n0,1,a,10.1\n' - self.assertEqual(df.to_csv(), expected_default) - - expected_european_excel = ';col1;col2;col3\n0;1;a;10,1\n' - self.assertEqual( - df.to_csv(decimal=',', sep=';'), expected_european_excel) - - expected_float_format_default = ',col1,col2,col3\n0,1,a,10.10\n' - self.assertEqual( - df.to_csv(float_format='%.2f'), expected_float_format_default) - - expected_float_format = ';col1;col2;col3\n0;1;a;10,10\n' - self.assertEqual( - df.to_csv(decimal=',', sep=';', - float_format='%.2f'), expected_float_format) - - # GH 11553: testing if decimal is taken into account for '0.0' - df = pd.DataFrame({'a': [0, 1.1], 'b': [2.2, 3.3], 'c': 1}) - expected = 'a,b,c\n0^0,2^2,1\n1^1,3^3,1\n' - self.assertEqual(df.to_csv(index=False, decimal='^'), expected) - - # same but for an index - self.assertEqual(df.set_index('a').to_csv(decimal='^'), expected) - - # same for a multi-index - self.assertEqual( - df.set_index(['a', 'b']).to_csv(decimal="^"), expected) - - def test_to_csv_float_format(self): - # testing if float_format is taken into account for the index - # GH 11553 - df = pd.DataFrame({'a': [0, 1], 'b': [2.2, 3.3], 'c': 1}) - expected = 'a,b,c\n0,2.20,1\n1,3.30,1\n' - self.assertEqual( - df.set_index('a').to_csv(float_format='%.2f'), expected) - - # same for a multi-index - self.assertEqual( - df.set_index(['a', 'b']).to_csv(float_format='%.2f'), expected) - - def test_to_csv_na_rep(self): - # testing if NaN values are correctly represented in the index - # GH 11553 - df = DataFrame({'a': [0, np.NaN], 'b': [0, 1], 'c': [2, 3]}) - expected = "a,b,c\n0.0,0,2\n_,1,3\n" - self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) - self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) - - # now with an index containing only NaNs - df = DataFrame({'a': np.NaN, 'b': [0, 1], 'c': [2, 3]}) - expected = "a,b,c\n_,0,2\n_,1,3\n" - self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) - self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) - - # check if na_rep parameter does not break anything when no NaN - df = DataFrame({'a': 0, 'b': [0, 1], 'c': [2, 3]}) - expected = "a,b,c\n0,0,2\n0,1,3\n" - self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) - self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) - - def test_to_csv_date_format(self): - # GH 10209 - df_sec = DataFrame({'A': pd.date_range('20130101', periods=5, freq='s') - }) - df_day = DataFrame({'A': pd.date_range('20130101', periods=5, freq='d') - }) - - expected_default_sec = ',A\n0,2013-01-01 00:00:00\n1,2013-01-01 00:00:01\n2,2013-01-01 00:00:02' + \ - '\n3,2013-01-01 00:00:03\n4,2013-01-01 00:00:04\n' - self.assertEqual(df_sec.to_csv(), expected_default_sec) - - expected_ymdhms_day = ',A\n0,2013-01-01 00:00:00\n1,2013-01-02 00:00:00\n2,2013-01-03 00:00:00' + \ - '\n3,2013-01-04 00:00:00\n4,2013-01-05 00:00:00\n' - self.assertEqual( - df_day.to_csv( - date_format='%Y-%m-%d %H:%M:%S'), expected_ymdhms_day) - - expected_ymd_sec = ',A\n0,2013-01-01\n1,2013-01-01\n2,2013-01-01\n3,2013-01-01\n4,2013-01-01\n' - self.assertEqual( - df_sec.to_csv(date_format='%Y-%m-%d'), expected_ymd_sec) - - expected_default_day = ',A\n0,2013-01-01\n1,2013-01-02\n2,2013-01-03\n3,2013-01-04\n4,2013-01-05\n' - self.assertEqual(df_day.to_csv(), expected_default_day) - self.assertEqual( - df_day.to_csv(date_format='%Y-%m-%d'), expected_default_day) - - # testing if date_format parameter is taken into account for - # multi-indexed dataframes (GH 7791) - df_sec['B'] = 0 - df_sec['C'] = 1 - expected_ymd_sec = 'A,B,C\n2013-01-01,0,1\n' - df_sec_grouped = df_sec.groupby([pd.Grouper(key='A', freq='1h'), 'B']) - self.assertEqual(df_sec_grouped.mean().to_csv(date_format='%Y-%m-%d'), - expected_ymd_sec) - - def test_to_csv_multi_index(self): - # see gh-6618 - df = DataFrame([1], columns=pd.MultiIndex.from_arrays([[1], [2]])) - - exp = ",1\n,2\n0,1\n" - self.assertEqual(df.to_csv(), exp) - - exp = "1\n2\n1\n" - self.assertEqual(df.to_csv(index=False), exp) - - df = DataFrame([1], columns=pd.MultiIndex.from_arrays([[1], [2]]), - index=pd.MultiIndex.from_arrays([[1], [2]])) - - exp = ",,1\n,,2\n1,2,1\n" - self.assertEqual(df.to_csv(), exp) - - exp = "1\n2\n1\n" - self.assertEqual(df.to_csv(index=False), exp) - - df = DataFrame( - [1], columns=pd.MultiIndex.from_arrays([['foo'], ['bar']])) - - exp = ",foo\n,bar\n0,1\n" - self.assertEqual(df.to_csv(), exp) - - exp = "foo\nbar\n1\n" - self.assertEqual(df.to_csv(index=False), exp) - def test_period(self): # GH 12615 df = pd.DataFrame({'A': pd.period_range('2013-01', @@ -4291,7 +1911,7 @@ def test_max_multi_index_display(self): ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']] tuples = list(zip(*arrays)) index = MultiIndex.from_tuples(tuples, names=['first', 'second']) - s = Series(randn(8), index=index) + s = Series(np.random.randn(8), index=index) with option_context("display.max_rows", 10): self.assertEqual(len(str(s).split('\n')), 10) @@ -4305,7 +1925,7 @@ def test_max_multi_index_display(self): self.assertEqual(len(str(s).split('\n')), 10) # index - s = Series(randn(8), None) + s = Series(np.random.randn(8), None) with option_context("display.max_rows", 10): self.assertEqual(len(str(s).split('\n')), 9) @@ -4436,176 +2056,6 @@ def test_to_string_header(self): self.assertEqual(res, exp) -class TestEngFormatter(tm.TestCase): - - def test_eng_float_formatter(self): - df = DataFrame({'A': [1.41, 141., 14100, 1410000.]}) - - fmt.set_eng_float_format() - result = df.to_string() - expected = (' A\n' - '0 1.410E+00\n' - '1 141.000E+00\n' - '2 14.100E+03\n' - '3 1.410E+06') - self.assertEqual(result, expected) - - fmt.set_eng_float_format(use_eng_prefix=True) - result = df.to_string() - expected = (' A\n' - '0 1.410\n' - '1 141.000\n' - '2 14.100k\n' - '3 1.410M') - self.assertEqual(result, expected) - - fmt.set_eng_float_format(accuracy=0) - result = df.to_string() - expected = (' A\n' - '0 1E+00\n' - '1 141E+00\n' - '2 14E+03\n' - '3 1E+06') - self.assertEqual(result, expected) - - self.reset_display_options() - - def compare(self, formatter, input, output): - formatted_input = formatter(input) - msg = ("formatting of %s results in '%s', expected '%s'" % - (str(input), formatted_input, output)) - self.assertEqual(formatted_input, output, msg) - - def compare_all(self, formatter, in_out): - """ - Parameters: - ----------- - formatter: EngFormatter under test - in_out: list of tuples. Each tuple = (number, expected_formatting) - - It is tested if 'formatter(number) == expected_formatting'. - *number* should be >= 0 because formatter(-number) == fmt is also - tested. *fmt* is derived from *expected_formatting* - """ - for input, output in in_out: - self.compare(formatter, input, output) - self.compare(formatter, -input, "-" + output[1:]) - - def test_exponents_with_eng_prefix(self): - formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) - f = np.sqrt(2) - in_out = [(f * 10 ** -24, " 1.414y"), (f * 10 ** -23, " 14.142y"), - (f * 10 ** -22, " 141.421y"), (f * 10 ** -21, " 1.414z"), - (f * 10 ** -20, " 14.142z"), (f * 10 ** -19, " 141.421z"), - (f * 10 ** -18, " 1.414a"), (f * 10 ** -17, " 14.142a"), - (f * 10 ** -16, " 141.421a"), (f * 10 ** -15, " 1.414f"), - (f * 10 ** -14, " 14.142f"), (f * 10 ** -13, " 141.421f"), - (f * 10 ** -12, " 1.414p"), (f * 10 ** -11, " 14.142p"), - (f * 10 ** -10, " 141.421p"), (f * 10 ** -9, " 1.414n"), - (f * 10 ** -8, " 14.142n"), (f * 10 ** -7, " 141.421n"), - (f * 10 ** -6, " 1.414u"), (f * 10 ** -5, " 14.142u"), - (f * 10 ** -4, " 141.421u"), (f * 10 ** -3, " 1.414m"), - (f * 10 ** -2, " 14.142m"), (f * 10 ** -1, " 141.421m"), - (f * 10 ** 0, " 1.414"), (f * 10 ** 1, " 14.142"), - (f * 10 ** 2, " 141.421"), (f * 10 ** 3, " 1.414k"), - (f * 10 ** 4, " 14.142k"), (f * 10 ** 5, " 141.421k"), - (f * 10 ** 6, " 1.414M"), (f * 10 ** 7, " 14.142M"), - (f * 10 ** 8, " 141.421M"), (f * 10 ** 9, " 1.414G"), ( - f * 10 ** 10, " 14.142G"), (f * 10 ** 11, " 141.421G"), - (f * 10 ** 12, " 1.414T"), (f * 10 ** 13, " 14.142T"), ( - f * 10 ** 14, " 141.421T"), (f * 10 ** 15, " 1.414P"), ( - f * 10 ** 16, " 14.142P"), (f * 10 ** 17, " 141.421P"), ( - f * 10 ** 18, " 1.414E"), (f * 10 ** 19, " 14.142E"), - (f * 10 ** 20, " 141.421E"), (f * 10 ** 21, " 1.414Z"), ( - f * 10 ** 22, " 14.142Z"), (f * 10 ** 23, " 141.421Z"), ( - f * 10 ** 24, " 1.414Y"), (f * 10 ** 25, " 14.142Y"), ( - f * 10 ** 26, " 141.421Y")] - self.compare_all(formatter, in_out) - - def test_exponents_without_eng_prefix(self): - formatter = fmt.EngFormatter(accuracy=4, use_eng_prefix=False) - f = np.pi - in_out = [(f * 10 ** -24, " 3.1416E-24"), - (f * 10 ** -23, " 31.4159E-24"), - (f * 10 ** -22, " 314.1593E-24"), - (f * 10 ** -21, " 3.1416E-21"), - (f * 10 ** -20, " 31.4159E-21"), - (f * 10 ** -19, " 314.1593E-21"), - (f * 10 ** -18, " 3.1416E-18"), - (f * 10 ** -17, " 31.4159E-18"), - (f * 10 ** -16, " 314.1593E-18"), - (f * 10 ** -15, " 3.1416E-15"), - (f * 10 ** -14, " 31.4159E-15"), - (f * 10 ** -13, " 314.1593E-15"), - (f * 10 ** -12, " 3.1416E-12"), - (f * 10 ** -11, " 31.4159E-12"), - (f * 10 ** -10, " 314.1593E-12"), - (f * 10 ** -9, " 3.1416E-09"), (f * 10 ** -8, " 31.4159E-09"), - (f * 10 ** -7, " 314.1593E-09"), (f * 10 ** -6, " 3.1416E-06"), - (f * 10 ** -5, " 31.4159E-06"), (f * 10 ** -4, - " 314.1593E-06"), - (f * 10 ** -3, " 3.1416E-03"), (f * 10 ** -2, " 31.4159E-03"), - (f * 10 ** -1, " 314.1593E-03"), (f * 10 ** 0, " 3.1416E+00"), ( - f * 10 ** 1, " 31.4159E+00"), (f * 10 ** 2, " 314.1593E+00"), - (f * 10 ** 3, " 3.1416E+03"), (f * 10 ** 4, " 31.4159E+03"), ( - f * 10 ** 5, " 314.1593E+03"), (f * 10 ** 6, " 3.1416E+06"), - (f * 10 ** 7, " 31.4159E+06"), (f * 10 ** 8, " 314.1593E+06"), ( - f * 10 ** 9, " 3.1416E+09"), (f * 10 ** 10, " 31.4159E+09"), - (f * 10 ** 11, " 314.1593E+09"), (f * 10 ** 12, " 3.1416E+12"), - (f * 10 ** 13, " 31.4159E+12"), (f * 10 ** 14, " 314.1593E+12"), - (f * 10 ** 15, " 3.1416E+15"), (f * 10 ** 16, " 31.4159E+15"), - (f * 10 ** 17, " 314.1593E+15"), (f * 10 ** 18, " 3.1416E+18"), - (f * 10 ** 19, " 31.4159E+18"), (f * 10 ** 20, " 314.1593E+18"), - (f * 10 ** 21, " 3.1416E+21"), (f * 10 ** 22, " 31.4159E+21"), - (f * 10 ** 23, " 314.1593E+21"), (f * 10 ** 24, " 3.1416E+24"), - (f * 10 ** 25, " 31.4159E+24"), (f * 10 ** 26, " 314.1593E+24")] - self.compare_all(formatter, in_out) - - def test_rounding(self): - formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) - in_out = [(5.55555, ' 5.556'), (55.5555, ' 55.556'), - (555.555, ' 555.555'), (5555.55, ' 5.556k'), - (55555.5, ' 55.556k'), (555555, ' 555.555k')] - self.compare_all(formatter, in_out) - - formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) - in_out = [(5.55555, ' 5.6'), (55.5555, ' 55.6'), (555.555, ' 555.6'), - (5555.55, ' 5.6k'), (55555.5, ' 55.6k'), (555555, ' 555.6k')] - self.compare_all(formatter, in_out) - - formatter = fmt.EngFormatter(accuracy=0, use_eng_prefix=True) - in_out = [(5.55555, ' 6'), (55.5555, ' 56'), (555.555, ' 556'), - (5555.55, ' 6k'), (55555.5, ' 56k'), (555555, ' 556k')] - self.compare_all(formatter, in_out) - - formatter = fmt.EngFormatter(accuracy=3, use_eng_prefix=True) - result = formatter(0) - self.assertEqual(result, u(' 0.000')) - - def test_nan(self): - # Issue #11981 - - formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) - result = formatter(np.nan) - self.assertEqual(result, u('NaN')) - - df = pd.DataFrame({'a': [1.5, 10.3, 20.5], - 'b': [50.3, 60.67, 70.12], - 'c': [100.2, 101.33, 120.33]}) - pt = df.pivot_table(values='a', index='b', columns='c') - fmt.set_eng_float_format(accuracy=1) - result = pt.to_string() - self.assertTrue('NaN' in result) - self.reset_display_options() - - def test_inf(self): - # Issue #11981 - - formatter = fmt.EngFormatter(accuracy=1, use_eng_prefix=True) - result = formatter(np.inf) - self.assertEqual(result, u('inf')) - - def _three_digit_exp(): return '%.4g' % 1.7e8 == '1.7e+008' diff --git a/pandas/tests/formats/test_to_csv.py b/pandas/tests/formats/test_to_csv.py new file mode 100644 index 0000000000000..51295fd750602 --- /dev/null +++ b/pandas/tests/formats/test_to_csv.py @@ -0,0 +1,216 @@ +from pandas import DataFrame +import numpy as np +import pandas as pd +from pandas.util import testing as tm + + +class TestToCSV(tm.TestCase): + + def test_to_csv_quotechar(self): + df = DataFrame({'col': [1, 2]}) + expected = """\ +"","col" +"0","1" +"1","2" +""" + + with tm.ensure_clean('test.csv') as path: + df.to_csv(path, quoting=1) # 1=QUOTE_ALL + with open(path, 'r') as f: + self.assertEqual(f.read(), expected) + + expected = """\ +$$,$col$ +$0$,$1$ +$1$,$2$ +""" + + with tm.ensure_clean('test.csv') as path: + df.to_csv(path, quoting=1, quotechar="$") + with open(path, 'r') as f: + self.assertEqual(f.read(), expected) + + with tm.ensure_clean('test.csv') as path: + with tm.assertRaisesRegexp(TypeError, 'quotechar'): + df.to_csv(path, quoting=1, quotechar=None) + + def test_to_csv_doublequote(self): + df = DataFrame({'col': ['a"a', '"bb"']}) + expected = '''\ +"","col" +"0","a""a" +"1","""bb""" +''' + + with tm.ensure_clean('test.csv') as path: + df.to_csv(path, quoting=1, doublequote=True) # QUOTE_ALL + with open(path, 'r') as f: + self.assertEqual(f.read(), expected) + + from _csv import Error + with tm.ensure_clean('test.csv') as path: + with tm.assertRaisesRegexp(Error, 'escapechar'): + df.to_csv(path, doublequote=False) # no escapechar set + + def test_to_csv_escapechar(self): + df = DataFrame({'col': ['a"a', '"bb"']}) + expected = '''\ +"","col" +"0","a\\"a" +"1","\\"bb\\"" +''' + + with tm.ensure_clean('test.csv') as path: # QUOTE_ALL + df.to_csv(path, quoting=1, doublequote=False, escapechar='\\') + with open(path, 'r') as f: + self.assertEqual(f.read(), expected) + + df = DataFrame({'col': ['a,a', ',bb,']}) + expected = """\ +,col +0,a\\,a +1,\\,bb\\, +""" + + with tm.ensure_clean('test.csv') as path: + df.to_csv(path, quoting=3, escapechar='\\') # QUOTE_NONE + with open(path, 'r') as f: + self.assertEqual(f.read(), expected) + + def test_csv_to_string(self): + df = DataFrame({'col': [1, 2]}) + expected = ',col\n0,1\n1,2\n' + self.assertEqual(df.to_csv(), expected) + + def test_to_csv_decimal(self): + # GH 781 + df = DataFrame({'col1': [1], 'col2': ['a'], 'col3': [10.1]}) + + expected_default = ',col1,col2,col3\n0,1,a,10.1\n' + self.assertEqual(df.to_csv(), expected_default) + + expected_european_excel = ';col1;col2;col3\n0;1;a;10,1\n' + self.assertEqual( + df.to_csv(decimal=',', sep=';'), expected_european_excel) + + expected_float_format_default = ',col1,col2,col3\n0,1,a,10.10\n' + self.assertEqual( + df.to_csv(float_format='%.2f'), expected_float_format_default) + + expected_float_format = ';col1;col2;col3\n0;1;a;10,10\n' + self.assertEqual( + df.to_csv(decimal=',', sep=';', + float_format='%.2f'), expected_float_format) + + # GH 11553: testing if decimal is taken into account for '0.0' + df = pd.DataFrame({'a': [0, 1.1], 'b': [2.2, 3.3], 'c': 1}) + expected = 'a,b,c\n0^0,2^2,1\n1^1,3^3,1\n' + self.assertEqual(df.to_csv(index=False, decimal='^'), expected) + + # same but for an index + self.assertEqual(df.set_index('a').to_csv(decimal='^'), expected) + + # same for a multi-index + self.assertEqual( + df.set_index(['a', 'b']).to_csv(decimal="^"), expected) + + def test_to_csv_float_format(self): + # testing if float_format is taken into account for the index + # GH 11553 + df = pd.DataFrame({'a': [0, 1], 'b': [2.2, 3.3], 'c': 1}) + expected = 'a,b,c\n0,2.20,1\n1,3.30,1\n' + self.assertEqual( + df.set_index('a').to_csv(float_format='%.2f'), expected) + + # same for a multi-index + self.assertEqual( + df.set_index(['a', 'b']).to_csv(float_format='%.2f'), expected) + + def test_to_csv_na_rep(self): + # testing if NaN values are correctly represented in the index + # GH 11553 + df = DataFrame({'a': [0, np.NaN], 'b': [0, 1], 'c': [2, 3]}) + expected = "a,b,c\n0.0,0,2\n_,1,3\n" + self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) + self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) + + # now with an index containing only NaNs + df = DataFrame({'a': np.NaN, 'b': [0, 1], 'c': [2, 3]}) + expected = "a,b,c\n_,0,2\n_,1,3\n" + self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) + self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) + + # check if na_rep parameter does not break anything when no NaN + df = DataFrame({'a': 0, 'b': [0, 1], 'c': [2, 3]}) + expected = "a,b,c\n0,0,2\n0,1,3\n" + self.assertEqual(df.set_index('a').to_csv(na_rep='_'), expected) + self.assertEqual(df.set_index(['a', 'b']).to_csv(na_rep='_'), expected) + + def test_to_csv_date_format(self): + # GH 10209 + df_sec = DataFrame({'A': pd.date_range('20130101', periods=5, freq='s') + }) + df_day = DataFrame({'A': pd.date_range('20130101', periods=5, freq='d') + }) + + expected_default_sec = (',A\n0,2013-01-01 00:00:00\n1,' + '2013-01-01 00:00:01\n2,2013-01-01 00:00:02' + '\n3,2013-01-01 00:00:03\n4,' + '2013-01-01 00:00:04\n') + self.assertEqual(df_sec.to_csv(), expected_default_sec) + + expected_ymdhms_day = (',A\n0,2013-01-01 00:00:00\n1,' + '2013-01-02 00:00:00\n2,2013-01-03 00:00:00' + '\n3,2013-01-04 00:00:00\n4,' + '2013-01-05 00:00:00\n') + self.assertEqual( + df_day.to_csv( + date_format='%Y-%m-%d %H:%M:%S'), expected_ymdhms_day) + + expected_ymd_sec = (',A\n0,2013-01-01\n1,2013-01-01\n2,' + '2013-01-01\n3,2013-01-01\n4,2013-01-01\n') + self.assertEqual( + df_sec.to_csv(date_format='%Y-%m-%d'), expected_ymd_sec) + + expected_default_day = (',A\n0,2013-01-01\n1,2013-01-02\n2,' + '2013-01-03\n3,2013-01-04\n4,2013-01-05\n') + self.assertEqual(df_day.to_csv(), expected_default_day) + self.assertEqual( + df_day.to_csv(date_format='%Y-%m-%d'), expected_default_day) + + # testing if date_format parameter is taken into account for + # multi-indexed dataframes (GH 7791) + df_sec['B'] = 0 + df_sec['C'] = 1 + expected_ymd_sec = 'A,B,C\n2013-01-01,0,1\n' + df_sec_grouped = df_sec.groupby([pd.Grouper(key='A', freq='1h'), 'B']) + self.assertEqual(df_sec_grouped.mean().to_csv(date_format='%Y-%m-%d'), + expected_ymd_sec) + + def test_to_csv_multi_index(self): + # see gh-6618 + df = DataFrame([1], columns=pd.MultiIndex.from_arrays([[1], [2]])) + + exp = ",1\n,2\n0,1\n" + self.assertEqual(df.to_csv(), exp) + + exp = "1\n2\n1\n" + self.assertEqual(df.to_csv(index=False), exp) + + df = DataFrame([1], columns=pd.MultiIndex.from_arrays([[1], [2]]), + index=pd.MultiIndex.from_arrays([[1], [2]])) + + exp = ",,1\n,,2\n1,2,1\n" + self.assertEqual(df.to_csv(), exp) + + exp = "1\n2\n1\n" + self.assertEqual(df.to_csv(index=False), exp) + + df = DataFrame( + [1], columns=pd.MultiIndex.from_arrays([['foo'], ['bar']])) + + exp = ",foo\n,bar\n0,1\n" + self.assertEqual(df.to_csv(), exp) + + exp = "foo\nbar\n1\n" + self.assertEqual(df.to_csv(index=False), exp) diff --git a/pandas/tests/formats/test_to_html.py b/pandas/tests/formats/test_to_html.py new file mode 100644 index 0000000000000..771c66e84037c --- /dev/null +++ b/pandas/tests/formats/test_to_html.py @@ -0,0 +1,1861 @@ +# -*- coding: utf-8 -*- + +import re +from textwrap import dedent +from datetime import datetime +from distutils.version import LooseVersion + +import pytest +import numpy as np +import pandas as pd +from pandas import compat, DataFrame, MultiIndex, option_context, Index +from pandas.compat import u, lrange, StringIO +from pandas.util import testing as tm +import pandas.formats.format as fmt + +div_style = '' +try: + import IPython + if IPython.__version__ < LooseVersion('3.0.0'): + div_style = ' style="max-width:1500px;overflow:auto;"' +except (ImportError, AttributeError): + pass + + +class TestToHTML(tm.TestCase): + + def test_to_html_with_col_space(self): + def check_with_width(df, col_space): + # check that col_space affects HTML generation + # and be very brittle about it. + html = df.to_html(col_space=col_space) + hdrs = [x for x in html.split(r"\n") if re.search(r"\s]", x)] + self.assertTrue(len(hdrs) > 0) + for h in hdrs: + self.assertTrue("min-width" in h) + self.assertTrue(str(col_space) in h) + + df = DataFrame(np.random.random(size=(1, 3))) + + check_with_width(df, 30) + check_with_width(df, 50) + + def test_to_html_with_empty_string_label(self): + # GH3547, to_html regards empty string labels as repeated labels + data = {'c1': ['a', 'b'], 'c2': ['a', ''], 'data': [1, 2]} + df = DataFrame(data).set_index(['c1', 'c2']) + res = df.to_html() + self.assertTrue("rowspan" not in res) + + def test_to_html_unicode(self): + df = DataFrame({u('\u03c3'): np.arange(10.)}) + expected = u'\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
\u03c3
00.0
11.0
22.0
33.0
44.0
55.0
66.0
77.0
88.0
99.0
' # noqa + self.assertEqual(df.to_html(), expected) + df = DataFrame({'A': [u('\u03c3')]}) + expected = u'\n \n \n \n \n \n \n \n \n \n \n \n \n
A
0\u03c3
' # noqa + self.assertEqual(df.to_html(), expected) + + def test_to_html_decimal(self): + # GH 12031 + df = DataFrame({'A': [6.0, 3.1, 2.2]}) + result = df.to_html(decimal=',') + expected = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
A
06,0
13,1
22,2
') + self.assertEqual(result, expected) + + def test_to_html_escaped(self): + a = 'str", + b: ""}, + 'co>l2': {a: "", + b: ""}} + rs = DataFrame(test_dict).to_html() + xp = """ + + + + + + + + + + + + + + + + + + + +
co<l1co>l2
str<ing1 &amp;<type 'str'><type 'str'>
stri>ng2 &amp;<type 'str'><type 'str'>
""" + + self.assertEqual(xp, rs) + + def test_to_html_escape_disabled(self): + a = 'strbold", + b: "bold"}, + 'co>l2': {a: "bold", + b: "bold"}} + rs = DataFrame(test_dict).to_html(escape=False) + xp = """ + + + + + + + + + + + + + + + + + +
co + co>l2
str + boldbold
stri>ng2 &boldbold
""" + + self.assertEqual(xp, rs) + + def test_to_html_multiindex_index_false(self): + # issue 8452 + df = DataFrame({ + 'a': range(2), + 'b': range(3, 5), + 'c': range(5, 7), + 'd': range(3, 5) + }) + df.columns = MultiIndex.from_product([['a', 'b'], ['c', 'd']]) + result = df.to_html(index=False) + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ab
cdcd
0353
1464
""" + + self.assertEqual(result, expected) + + df.index = Index(df.index.values, name='idx') + result = df.to_html(index=False) + self.assertEqual(result, expected) + + def test_to_html_multiindex_sparsify_false_multi_sparse(self): + with option_context('display.multi_sparse', False): + index = MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]], + names=['foo', None]) + + df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], index=index) + + result = df.to_html() + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
01
foo
0001
0123
1045
1167
""" + + self.assertEqual(result, expected) + + df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], + columns=index[::2], index=index) + + result = df.to_html() + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
foo01
00
foo
0001
0123
1045
1167
""" + + self.assertEqual(result, expected) + + def test_to_html_multiindex_sparsify(self): + index = MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]], + names=['foo', None]) + + df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], index=index) + + result = df.to_html() + expected = """ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
01
foo
0001
123
1045
167
""" + + self.assertEqual(result, expected) + + df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], columns=index[::2], + index=index) + + result = df.to_html() + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
foo01
00
foo
0001
123
1045
167
""" + + self.assertEqual(result, expected) + + def test_to_html_multiindex_odd_even_truncate(self): + # GH 14882 - Issue on truncation with odd length DataFrame + mi = MultiIndex.from_product([[100, 200, 300], + [10, 20, 30], + [1, 2, 3, 4, 5, 6, 7]], + names=['a', 'b', 'c']) + df = DataFrame({'n': range(len(mi))}, index=mi) + result = df.to_html(max_rows=60) + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
n
abc
1001010
21
32
43
54
65
76
2017
28
39
410
511
612
713
30114
215
316
417
518
619
720
20010121
222
323
424
525
626
727
20128
229
......
633
734
30135
236
337
438
539
640
741
30010142
243
344
445
546
647
748
20149
250
351
452
553
654
755
30156
257
358
459
560
661
762
""" + self.assertEqual(result, expected) + + # Test that ... appears in a middle level + result = df.to_html(max_rows=56) + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
n
abc
1001010
21
32
43
54
65
76
2017
28
39
410
511
612
713
30114
215
316
417
518
619
720
20010121
222
323
424
525
626
727
.........
30135
236
337
438
539
640
741
30010142
243
344
445
546
647
748
20149
250
351
452
553
654
755
30156
257
358
459
560
661
762
""" + self.assertEqual(result, expected) + + def test_to_html_index_formatter(self): + df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], columns=['foo', None], + index=lrange(4)) + + f = lambda x: 'abcd' [x] + result = df.to_html(formatters={'__index__': f}) + expected = """\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
fooNone
a01
b23
c45
d67
""" + + self.assertEqual(result, expected) + + def test_to_html_datetime64_monthformatter(self): + months = [datetime(2016, 1, 1), datetime(2016, 2, 2)] + x = DataFrame({'months': months}) + + def format_func(x): + return x.strftime('%Y-%m') + result = x.to_html(formatters={'months': format_func}) + expected = """\ + + + + + + + + + + + + + + + + + +
months
02016-01
12016-02
""" + self.assertEqual(result, expected) + + def test_to_html_datetime64_hourformatter(self): + + x = DataFrame({'hod': pd.to_datetime(['10:10:10.100', '12:12:12.120'], + format='%H:%M:%S.%f')}) + + def format_func(x): + return x.strftime('%H:%M') + result = x.to_html(formatters={'hod': format_func}) + expected = """\ + + + + + + + + + + + + + + + + + +
hod
010:10
112:12
""" + self.assertEqual(result, expected) + + def test_to_html_regression_GH6098(self): + df = DataFrame({ + u('clé1'): [u('a'), u('a'), u('b'), u('b'), u('a')], + u('clé2'): [u('1er'), u('2ème'), u('1er'), u('2ème'), u('1er')], + 'données1': np.random.randn(5), + 'données2': np.random.randn(5)}) + + # it works + df.pivot_table(index=[u('clé1')], columns=[u('clé2')])._repr_html_() + + def test_to_html_truncate(self): + pytest.skip("unreliable on travis") + index = pd.DatetimeIndex(start='20010101', freq='D', periods=20) + df = DataFrame(index=index, columns=range(20)) + fmt.set_option('display.max_rows', 8) + fmt.set_option('display.max_columns', 4) + result = df._repr_html_() + expected = '''\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
01...1819
2001-01-01NaNNaN...NaNNaN
2001-01-02NaNNaN...NaNNaN
2001-01-03NaNNaN...NaNNaN
2001-01-04NaNNaN...NaNNaN
..................
2001-01-17NaNNaN...NaNNaN
2001-01-18NaNNaN...NaNNaN
2001-01-19NaNNaN...NaNNaN
2001-01-20NaNNaN...NaNNaN
+

20 rows × 20 columns

+'''.format(div_style) + if compat.PY2: + expected = expected.decode('utf-8') + self.assertEqual(result, expected) + + def test_to_html_truncate_multi_index(self): + pytest.skip("unreliable on travis") + arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'], + ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']] + df = DataFrame(index=arrays, columns=arrays) + fmt.set_option('display.max_rows', 7) + fmt.set_option('display.max_columns', 7) + result = df._repr_html_() + expected = '''\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
barbaz...fooqux
onetwoone...twoonetwo
baroneNaNNaNNaN...NaNNaNNaN
twoNaNNaNNaN...NaNNaNNaN
bazoneNaNNaNNaN...NaNNaNNaN
...........................
footwoNaNNaNNaN...NaNNaNNaN
quxoneNaNNaNNaN...NaNNaNNaN
twoNaNNaNNaN...NaNNaNNaN
+

8 rows × 8 columns

+'''.format(div_style) + if compat.PY2: + expected = expected.decode('utf-8') + self.assertEqual(result, expected) + + def test_to_html_truncate_multi_index_sparse_off(self): + pytest.skip("unreliable on travis") + arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'], + ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']] + df = DataFrame(index=arrays, columns=arrays) + fmt.set_option('display.max_rows', 7) + fmt.set_option('display.max_columns', 7) + fmt.set_option('display.multi_sparse', False) + result = df._repr_html_() + expected = '''\ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
barbarbaz...fooquxqux
onetwoone...twoonetwo
baroneNaNNaNNaN...NaNNaNNaN
bartwoNaNNaNNaN...NaNNaNNaN
bazoneNaNNaNNaN...NaNNaNNaN
footwoNaNNaNNaN...NaNNaNNaN
quxoneNaNNaNNaN...NaNNaNNaN
quxtwoNaNNaNNaN...NaNNaNNaN
+

8 rows × 8 columns

+'''.format(div_style) + if compat.PY2: + expected = expected.decode('utf-8') + self.assertEqual(result, expected) + + def test_to_html_border(self): + df = DataFrame({'A': [1, 2]}) + result = df.to_html() + assert 'border="1"' in result + + def test_to_html_border_option(self): + df = DataFrame({'A': [1, 2]}) + with pd.option_context('html.border', 0): + result = df.to_html() + self.assertTrue('border="0"' in result) + self.assertTrue('border="0"' in df._repr_html_()) + + def test_to_html_border_zero(self): + df = DataFrame({'A': [1, 2]}) + result = df.to_html(border=0) + self.assertTrue('border="0"' in result) + + def test_to_html(self): + # big mixed + biggie = DataFrame({'A': np.random.randn(200), + 'B': tm.makeStringIndex(200)}, + index=lrange(200)) + + biggie.loc[:20, 'A'] = np.nan + biggie.loc[:20, 'B'] = np.nan + s = biggie.to_html() + + buf = StringIO() + retval = biggie.to_html(buf=buf) + self.assertIsNone(retval) + self.assertEqual(buf.getvalue(), s) + + tm.assertIsInstance(s, compat.string_types) + + biggie.to_html(columns=['B', 'A'], col_space=17) + biggie.to_html(columns=['B', 'A'], + formatters={'A': lambda x: '%.1f' % x}) + + biggie.to_html(columns=['B', 'A'], float_format=str) + biggie.to_html(columns=['B', 'A'], col_space=12, float_format=str) + + frame = DataFrame(index=np.arange(200)) + frame.to_html() + + def test_to_html_filename(self): + biggie = DataFrame({'A': np.random.randn(200), + 'B': tm.makeStringIndex(200)}, + index=lrange(200)) + + biggie.loc[:20, 'A'] = np.nan + biggie.loc[:20, 'B'] = np.nan + with tm.ensure_clean('test.html') as path: + biggie.to_html(path) + with open(path, 'r') as f: + s = biggie.to_html() + s2 = f.read() + self.assertEqual(s, s2) + + frame = DataFrame(index=np.arange(200)) + with tm.ensure_clean('test.html') as path: + frame.to_html(path) + with open(path, 'r') as f: + self.assertEqual(frame.to_html(), f.read()) + + def test_to_html_with_no_bold(self): + x = DataFrame({'x': np.random.randn(5)}) + ashtml = x.to_html(bold_rows=False) + self.assertFalse('")]) + + def test_to_html_columns_arg(self): + frame = DataFrame(tm.getSeriesData()) + result = frame.to_html(columns=['A']) + self.assertNotIn('B', result) + + def test_to_html_multiindex(self): + columns = MultiIndex.from_tuples(list(zip(np.arange(2).repeat(2), + np.mod(lrange(4), 2))), + names=['CL0', 'CL1']) + df = DataFrame([list('abcd'), list('efgh')], columns=columns) + result = df.to_html(justify='left') + expected = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
CL001
CL10101
0abcd
1efgh
') + + self.assertEqual(result, expected) + + columns = MultiIndex.from_tuples(list(zip( + range(4), np.mod( + lrange(4), 2)))) + df = DataFrame([list('abcd'), list('efgh')], columns=columns) + + result = df.to_html(justify='right') + expected = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
0123
0101
0abcd
1efgh
') + + self.assertEqual(result, expected) + + def test_to_html_justify(self): + df = DataFrame({'A': [6, 30000, 2], + 'B': [1, 2, 70000], + 'C': [223442, 0, 1]}, + columns=['A', 'B', 'C']) + result = df.to_html(justify='left') + expected = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
061223442
13000020
22700001
') + self.assertEqual(result, expected) + + result = df.to_html(justify='right') + expected = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
061223442
13000020
22700001
') + self.assertEqual(result, expected) + + def test_to_html_index(self): + index = ['foo', 'bar', 'baz'] + df = DataFrame({'A': [1, 2, 3], + 'B': [1.2, 3.4, 5.6], + 'C': ['one', 'two', np.nan]}, + columns=['A', 'B', 'C'], + index=index) + expected_with_index = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
foo11.2one
bar23.4two
baz35.6NaN
') + self.assertEqual(df.to_html(), expected_with_index) + + expected_without_index = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
11.2one
23.4two
35.6NaN
') + result = df.to_html(index=False) + for i in index: + self.assertNotIn(i, result) + self.assertEqual(result, expected_without_index) + df.index = Index(['foo', 'bar', 'baz'], name='idx') + expected_with_index = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
idx
foo11.2one
bar23.4two
baz35.6NaN
') + self.assertEqual(df.to_html(), expected_with_index) + self.assertEqual(df.to_html(index=False), expected_without_index) + + tuples = [('foo', 'car'), ('foo', 'bike'), ('bar', 'car')] + df.index = MultiIndex.from_tuples(tuples) + + expected_with_index = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
foocar11.2one
bike23.4two
barcar35.6NaN
') + self.assertEqual(df.to_html(), expected_with_index) + + result = df.to_html(index=False) + for i in ['foo', 'bar', 'car', 'bike']: + self.assertNotIn(i, result) + # must be the same result as normal index + self.assertEqual(result, expected_without_index) + + df.index = MultiIndex.from_tuples(tuples, names=['idx1', 'idx2']) + expected_with_index = ('\n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + ' \n' + '
ABC
idx1idx2
foocar11.2one
bike23.4two
barcar35.6NaN
') + self.assertEqual(df.to_html(), expected_with_index) + self.assertEqual(df.to_html(index=False), expected_without_index) + + def test_to_html_with_classes(self): + df = DataFrame() + result = df.to_html(classes="sortable draggable") + expected = dedent(""" + + + + + + + + + +
+ + """).strip() + self.assertEqual(result, expected) + + result = df.to_html(classes=["sortable", "draggable"]) + self.assertEqual(result, expected) + + def test_to_html_no_index_max_rows(self): + # GH https://github.com/pandas-dev/pandas/issues/14998 + df = DataFrame({"A": [1, 2, 3, 4]}) + result = df.to_html(index=False, max_rows=1) + expected = dedent("""\ + + + + + + + + + + + +
A
1
""") + self.assertEqual(result, expected) diff --git a/pandas/tests/formats/test_to_latex.py b/pandas/tests/formats/test_to_latex.py new file mode 100644 index 0000000000000..89e18e1cec06e --- /dev/null +++ b/pandas/tests/formats/test_to_latex.py @@ -0,0 +1,351 @@ +from datetime import datetime + +import pytest + +import pandas as pd +from pandas import DataFrame, compat +from pandas.util import testing as tm +from pandas.compat import u +import codecs + + +@pytest.fixture +def frame(): + return DataFrame(tm.getSeriesData()) + + +class TestToLatex(object): + + def test_to_latex_filename(self, frame): + with tm.ensure_clean('test.tex') as path: + frame.to_latex(path) + + with open(path, 'r') as f: + assert frame.to_latex() == f.read() + + # test with utf-8 and encoding option (GH 7061) + df = DataFrame([[u'au\xdfgangen']]) + with tm.ensure_clean('test.tex') as path: + df.to_latex(path, encoding='utf-8') + with codecs.open(path, 'r', encoding='utf-8') as f: + assert df.to_latex() == f.read() + + # test with utf-8 without encoding option + if compat.PY3: # python3: pandas default encoding is utf-8 + with tm.ensure_clean('test.tex') as path: + df.to_latex(path) + with codecs.open(path, 'r', encoding='utf-8') as f: + assert df.to_latex() == f.read() + else: + # python2 default encoding is ascii, so an error should be raised + with tm.ensure_clean('test.tex') as path: + with pytest.raises(UnicodeEncodeError): + df.to_latex(path) + + def test_to_latex(self, frame): + # it works! + frame.to_latex() + + df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) + withindex_result = df.to_latex() + withindex_expected = r"""\begin{tabular}{lrl} +\toprule +{} & a & b \\ +\midrule +0 & 1 & b1 \\ +1 & 2 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withindex_result == withindex_expected + + withoutindex_result = df.to_latex(index=False) + withoutindex_expected = r"""\begin{tabular}{rl} +\toprule + a & b \\ +\midrule + 1 & b1 \\ + 2 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withoutindex_result == withoutindex_expected + + def test_to_latex_format(self, frame): + # GH Bug #9402 + frame.to_latex(column_format='ccc') + + df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) + withindex_result = df.to_latex(column_format='ccc') + withindex_expected = r"""\begin{tabular}{ccc} +\toprule +{} & a & b \\ +\midrule +0 & 1 & b1 \\ +1 & 2 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withindex_result == withindex_expected + + def test_to_latex_with_formatters(self): + df = DataFrame({'int': [1, 2, 3], + 'float': [1.0, 2.0, 3.0], + 'object': [(1, 2), True, False], + 'datetime64': [datetime(2016, 1, 1), + datetime(2016, 2, 5), + datetime(2016, 3, 3)]}) + + formatters = {'int': lambda x: '0x%x' % x, + 'float': lambda x: '[% 4.1f]' % x, + 'object': lambda x: '-%s-' % str(x), + 'datetime64': lambda x: x.strftime('%Y-%m'), + '__index__': lambda x: 'index: %s' % x} + result = df.to_latex(formatters=dict(formatters)) + + expected = r"""\begin{tabular}{llrrl} +\toprule +{} & datetime64 & float & int & object \\ +\midrule +index: 0 & 2016-01 & [ 1.0] & 0x1 & -(1, 2)- \\ +index: 1 & 2016-02 & [ 2.0] & 0x2 & -True- \\ +index: 2 & 2016-03 & [ 3.0] & 0x3 & -False- \\ +\bottomrule +\end{tabular} +""" + assert result == expected + + def test_to_latex_multiindex(self): + df = DataFrame({('x', 'y'): ['a']}) + result = df.to_latex() + expected = r"""\begin{tabular}{ll} +\toprule +{} & x \\ +{} & y \\ +\midrule +0 & a \\ +\bottomrule +\end{tabular} +""" + + assert result == expected + + result = df.T.to_latex() + expected = r"""\begin{tabular}{lll} +\toprule + & & 0 \\ +\midrule +x & y & a \\ +\bottomrule +\end{tabular} +""" + + assert result == expected + + df = DataFrame.from_dict({ + ('c1', 0): pd.Series(dict((x, x) for x in range(4))), + ('c1', 1): pd.Series(dict((x, x + 4) for x in range(4))), + ('c2', 0): pd.Series(dict((x, x) for x in range(4))), + ('c2', 1): pd.Series(dict((x, x + 4) for x in range(4))), + ('c3', 0): pd.Series(dict((x, x) for x in range(4))), + }).T + result = df.to_latex() + expected = r"""\begin{tabular}{llrrrr} +\toprule + & & 0 & 1 & 2 & 3 \\ +\midrule +c1 & 0 & 0 & 1 & 2 & 3 \\ + & 1 & 4 & 5 & 6 & 7 \\ +c2 & 0 & 0 & 1 & 2 & 3 \\ + & 1 & 4 & 5 & 6 & 7 \\ +c3 & 0 & 0 & 1 & 2 & 3 \\ +\bottomrule +\end{tabular} +""" + + assert result == expected + + # GH 10660 + df = pd.DataFrame({'a': [0, 0, 1, 1], + 'b': list('abab'), + 'c': [1, 2, 3, 4]}) + result = df.set_index(['a', 'b']).to_latex() + expected = r"""\begin{tabular}{llr} +\toprule + & & c \\ +a & b & \\ +\midrule +0 & a & 1 \\ + & b & 2 \\ +1 & a & 3 \\ + & b & 4 \\ +\bottomrule +\end{tabular} +""" + + assert result == expected + + result = df.groupby('a').describe().to_latex() + expected = ('\\begin{tabular}{lrrrrrrrr}\n\\toprule\n{} & c & ' + ' & & & & & & ' + '\\\\\n{} & count & mean & std & min & 25\\% & ' + '50\\% & 75\\% & max \\\\\na & & & ' + ' & & & & & \\\\\n\\midrule\n0 ' + '& 2.0 & 1.5 & 0.707107 & 1.0 & 1.25 & 1.5 & 1.75 ' + '& 2.0 \\\\\n1 & 2.0 & 3.5 & 0.707107 & 3.0 & 3.25 ' + '& 3.5 & 3.75 & 4.0 ' + '\\\\\n\\bottomrule\n\\end{tabular}\n') + + assert result == expected + + def test_to_latex_escape(self): + a = 'a' + b = 'b' + + test_dict = {u('co^l1'): {a: "a", + b: "b"}, + u('co$e^x$'): {a: "a", + b: "b"}} + + unescaped_result = DataFrame(test_dict).to_latex(escape=False) + escaped_result = DataFrame(test_dict).to_latex( + ) # default: escape=True + + unescaped_expected = r'''\begin{tabular}{lll} +\toprule +{} & co$e^x$ & co^l1 \\ +\midrule +a & a & a \\ +b & b & b \\ +\bottomrule +\end{tabular} +''' + + escaped_expected = r'''\begin{tabular}{lll} +\toprule +{} & co\$e\textasciicircumx\$ & co\textasciicircuml1 \\ +\midrule +a & a & a \\ +b & b & b \\ +\bottomrule +\end{tabular} +''' + + assert unescaped_result == unescaped_expected + assert escaped_result == escaped_expected + + def test_to_latex_longtable(self, frame): + frame.to_latex(longtable=True) + + df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) + withindex_result = df.to_latex(longtable=True) + withindex_expected = r"""\begin{longtable}{lrl} +\toprule +{} & a & b \\ +\midrule +\endhead +\midrule +\multicolumn{3}{r}{{Continued on next page}} \\ +\midrule +\endfoot + +\bottomrule +\endlastfoot +0 & 1 & b1 \\ +1 & 2 & b2 \\ +\end{longtable} +""" + + assert withindex_result == withindex_expected + + withoutindex_result = df.to_latex(index=False, longtable=True) + withoutindex_expected = r"""\begin{longtable}{rl} +\toprule + a & b \\ +\midrule +\endhead +\midrule +\multicolumn{3}{r}{{Continued on next page}} \\ +\midrule +\endfoot + +\bottomrule +\endlastfoot + 1 & b1 \\ + 2 & b2 \\ +\end{longtable} +""" + + assert withoutindex_result == withoutindex_expected + + def test_to_latex_escape_special_chars(self): + special_characters = ['&', '%', '$', '#', '_', '{', '}', '~', '^', + '\\'] + df = DataFrame(data=special_characters) + observed = df.to_latex() + expected = r"""\begin{tabular}{ll} +\toprule +{} & 0 \\ +\midrule +0 & \& \\ +1 & \% \\ +2 & \$ \\ +3 & \# \\ +4 & \_ \\ +5 & \{ \\ +6 & \} \\ +7 & \textasciitilde \\ +8 & \textasciicircum \\ +9 & \textbackslash \\ +\bottomrule +\end{tabular} +""" + + assert observed == expected + + def test_to_latex_no_header(self): + # GH 7124 + df = DataFrame({'a': [1, 2], 'b': ['b1', 'b2']}) + withindex_result = df.to_latex(header=False) + withindex_expected = r"""\begin{tabular}{lrl} +\toprule +0 & 1 & b1 \\ +1 & 2 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withindex_result == withindex_expected + + withoutindex_result = df.to_latex(index=False, header=False) + withoutindex_expected = r"""\begin{tabular}{rl} +\toprule + 1 & b1 \\ + 2 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withoutindex_result == withoutindex_expected + + def test_to_latex_decimal(self, frame): + # GH 12031 + frame.to_latex() + + df = DataFrame({'a': [1.0, 2.1], 'b': ['b1', 'b2']}) + withindex_result = df.to_latex(decimal=',') + + withindex_expected = r"""\begin{tabular}{lrl} +\toprule +{} & a & b \\ +\midrule +0 & 1,0 & b1 \\ +1 & 2,1 & b2 \\ +\bottomrule +\end{tabular} +""" + + assert withindex_result == withindex_expected