def test_reset_index(self):
df = tm.makeDataFrame()[:5]
ser = df.stack()
ser.index.names = ['hash', 'category']
ser.name = 'value'
df = ser.reset_index()
self.assertIn('value', df)
df = ser.reset_index(name='value2')
self.assertIn('value2', df)
# check inplace
s = ser.reset_index(drop=True)
s2 = ser
s2.reset_index(drop=True, inplace=True)
assert_series_equal(s, s2)
# level
index = MultiIndex(levels=[['bar'], ['one', 'two', 'three'], [0, 1]],
labels=[[0, 0, 0, 0, 0, 0], [0, 1, 2, 0, 1, 2],
[0, 1, 0, 1, 0, 1]])
s = Series(np.random.randn(6), index=index)
rs = s.reset_index(level=1)
self.assertEqual(len(rs.columns), 2)
rs = s.reset_index(level=[0, 2], drop=True)
self.assert_index_equal(rs.index, Index(index.get_level_values(1)))
tm.assertIsInstance(rs, Series)
def test_reset_index(self):
df = tm.makeDataFrame()[:5]
ser = df.stack()
ser.index.names = ["hash", "category"]
ser.name = "value"
df = ser.reset_index()
self.assertIn("value", df)
df = ser.reset_index(name="value2")
self.assertIn("value2", df)
# check inplace
s = ser.reset_index(drop=True)
s2 = ser
s2.reset_index(drop=True, inplace=True)
assert_series_equal(s, s2)
# level
index = MultiIndex(
levels=[["bar"], ["one", "two", "three"], [0, 1]],
labels=[[0, 0, 0, 0, 0, 0], [0, 1, 2, 0, 1, 2], [0, 1, 0, 1, 0, 1]],
)
s = Series(np.random.randn(6), index=index)
rs = s.reset_index(level=1)
self.assertEqual(len(rs.columns), 2)
rs = s.reset_index(level=[0, 2], drop=True)
self.assertTrue(rs.index.equals(Index(index.get_level_values(1))))
tm.assertIsInstance(rs, Series)
def test_aggregate_item_by_item(self):
df = self.df.copy()
df['E'] = ['a'] * len(self.df)
grouped = self.df.groupby('A')
# API change in 0.11
# def aggfun(ser):
# return len(ser + 'a')
# result = grouped.agg(aggfun)
# self.assertEqual(len(result.columns), 1)
aggfun = lambda ser: ser.size
result = grouped.agg(aggfun)
foo = (self.df.A == 'foo').sum()
bar = (self.df.A == 'bar').sum()
K = len(result.columns)
# GH5782
# odd comparisons can result here, so cast to make easy
exp = pd.Series(np.array([foo] * K), index=list('BCD'),
dtype=np.float64, name='foo')
tm.assert_series_equal(result.xs('foo'), exp)
exp = pd.Series(np.array([bar] * K), index=list('BCD'),
dtype=np.float64, name='bar')
tm.assert_almost_equal(result.xs('bar'), exp)
def aggfun(ser):
return ser.size
result = DataFrame().groupby(self.df.A).agg(aggfun)
tm.assertIsInstance(result, DataFrame)
self.assertEqual(len(result), 0)
def _check_rng(rng):
converted = rng.to_pydatetime()
tm.assertIsInstance(converted, np.ndarray)
for x, stamp in zip(converted, rng):
tm.assertIsInstance(x, datetime)
self.assertEqual(x, stamp.to_pydatetime())
self.assertEqual(x.tzinfo, stamp.tzinfo)
def test_join_inner(self):
other = Int64Index([7, 12, 25, 1, 2, 5])
other_mono = Int64Index([1, 2, 5, 7, 12, 25])
# not monotonic
res, lidx, ridx = self.index.join(other, how="inner", return_indexers=True)
# no guarantee of sortedness, so sort for comparison purposes
ind = res.argsort()
res = res.take(ind)
lidx = lidx.take(ind)
ridx = ridx.take(ind)
eres = Int64Index([2, 12])
elidx = np.array([1, 6], dtype=np.intp)
eridx = np.array([4, 1], dtype=np.intp)
tm.assertIsInstance(res, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# monotonic
res, lidx, ridx = self.index.join(other_mono, how="inner", return_indexers=True)
res2 = self.index.intersection(other_mono)
self.assert_index_equal(res, res2)
elidx = np.array([1, 6], dtype=np.intp)
eridx = np.array([1, 4], dtype=np.intp)
tm.assertIsInstance(res, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_groupby_groups_datetimeindex(self):
# #1430
from pandas.tseries.api import DatetimeIndex
periods = 1000
ind = DatetimeIndex(start='2012/1/1', freq='5min', periods=periods)
df = DataFrame({'high': np.arange(periods),
'low': np.arange(periods)}, index=ind)
grouped = df.groupby(lambda x: datetime(x.year, x.month, x.day))
# it works!
groups = grouped.groups
tm.assertIsInstance(list(groups.keys())[0], datetime)
# GH 11442
index = pd.date_range('2015/01/01', periods=5, name='date')
df = pd.DataFrame({'A': [5, 6, 7, 8, 9],
'B': [1, 2, 3, 4, 5]}, index=index)
result = df.groupby(level='date').groups
dates = ['2015-01-05', '2015-01-04', '2015-01-03',
'2015-01-02', '2015-01-01']
expected = {pd.Timestamp(date): pd.DatetimeIndex([date], name='date')
for date in dates}
tm.assert_dict_equal(result, expected)
grouped = df.groupby(level='date')
for date in dates:
result = grouped.get_group(date)
data = [[df.loc[date, 'A'], df.loc[date, 'B']]]
expected_index = pd.DatetimeIndex([date], name='date')
expected = pd.DataFrame(data,
columns=list('AB'),
index=expected_index)
tm.assert_frame_equal(result, expected)
def test_applymap(self):
applied = self.frame.applymap(lambda x: x * 2)
assert_frame_equal(applied, self.frame * 2)
result = self.frame.applymap(type)
# GH #465, function returning tuples
result = self.frame.applymap(lambda x: (x, x))
tm.assertIsInstance(result['A'][0], tuple)
# GH 2909, object conversion to float in constructor?
df = DataFrame(data=[1, 'a'])
result = df.applymap(lambda x: x)
self.assertEqual(result.dtypes[0], object)
df = DataFrame(data=[1., 'a'])
result = df.applymap(lambda x: x)
self.assertEqual(result.dtypes[0], object)
# GH2786
df = DataFrame(np.random.random((3, 4)))
df2 = df.copy()
cols = ['a', 'a', 'a', 'a']
df.columns = cols
expected = df2.applymap(str)
expected.columns = cols
result = df.applymap(str)
assert_frame_equal(result, expected)
# datetime/timedelta
df['datetime'] = Timestamp('20130101')
df['timedelta'] = pd.Timedelta('1 min')
result = df.applymap(str)
for f in ['datetime', 'timedelta']:
self.assertEqual(result.loc[0, f], str(df.loc[0, f]))
def test_reset_index_range(self):
# GH 12071
s = pd.Series(range(2), name="A", dtype="int64")
series_result = s.reset_index()
tm.assertIsInstance(series_result.index, RangeIndex)
series_expected = pd.DataFrame([[0, 0], [1, 1]], columns=["index", "A"], index=RangeIndex(stop=2))
assert_frame_equal(series_result, series_expected)
def test_asfreq_datetimeindex(self):
df = DataFrame({"A": [1, 2, 3]}, index=[datetime(2011, 11, 1), datetime(2011, 11, 2), datetime(2011, 11, 3)])
df = df.asfreq("B")
tm.assertIsInstance(df.index, DatetimeIndex)
ts = df["A"].asfreq("B")
tm.assertIsInstance(ts.index, DatetimeIndex)
def assert_block_equal(left, right):
tm.assert_numpy_array_equal(left.values, right.values)
assert (left.dtype == right.dtype)
tm.assertIsInstance(left.mgr_locs, lib.BlockPlacement)
tm.assertIsInstance(right.mgr_locs, lib.BlockPlacement)
tm.assert_numpy_array_equal(left.mgr_locs.as_array,
right.mgr_locs.as_array)
def test_groupby_function_tuple_1677(self):
df = DataFrame(np.random.rand(100),
index=date_range("1/1/2000", periods=100))
monthly_group = df.groupby(lambda x: (x.year, x.month))
result = monthly_group.mean()
tm.assertIsInstance(result.index[0], tuple)
def _compare_ols_results(model1, model2):
tm.assertIsInstance(model1, type(model2))
if hasattr(model1, '_window_type'):
_compare_moving_ols(model1, model2)
else:
_compare_fullsample_ols(model1, model2)
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_file_url(self):
url = self.banklist_data
dfs = self.read_html(file_path_to_url(url), 'First',
attrs={'id': 'table'})
tm.assertIsInstance(dfs, list)
for df in dfs:
tm.assertIsInstance(df, DataFrame)
def test_join_outer(self):
other = Int64Index([7, 12, 25, 1, 2, 5])
other_mono = Int64Index([1, 2, 5, 7, 12, 25])
# not monotonic
# guarantee of sortedness
res, lidx, ridx = self.index.join(other, how="outer", return_indexers=True)
noidx_res = self.index.join(other, how="outer")
self.assert_index_equal(res, noidx_res)
eres = Int64Index([0, 1, 2, 4, 5, 6, 7, 8, 10, 12, 14, 16, 18, 25])
elidx = np.array([0, -1, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, 9, -1], dtype=np.intp)
eridx = np.array([-1, 3, 4, -1, 5, -1, 0, -1, -1, 1, -1, -1, -1, 2], dtype=np.intp)
tm.assertIsInstance(res, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# monotonic
res, lidx, ridx = self.index.join(other_mono, how="outer", return_indexers=True)
noidx_res = self.index.join(other_mono, how="outer")
self.assert_index_equal(res, noidx_res)
elidx = np.array([0, -1, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, 9, -1], dtype=np.intp)
eridx = np.array([-1, 0, 1, -1, 2, -1, 3, -1, -1, 4, -1, -1, -1, 5], dtype=np.intp)
tm.assertIsInstance(res, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_array_interface(self):
result = np.sqrt(self.frame)
tm.assertIsInstance(result, type(self.frame))
self.assertIs(result.index, self.frame.index)
self.assertIs(result.columns, self.frame.columns)
assert_frame_equal(result, self.frame.apply(np.sqrt))
def test_join_right(self):
other = Int64Index([7, 12, 25, 1, 2, 5])
other_mono = Int64Index([1, 2, 5, 7, 12, 25])
# not monotonic
res, lidx, ridx = self.index.join(other, how='right',
return_indexers=True)
eres = other
elidx = np.array([-1, 6, -1, -1, 1, -1], dtype=np.intp)
tm.assertIsInstance(other, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
self.assertIsNone(ridx)
# monotonic
res, lidx, ridx = self.index.join(other_mono, how='right',
return_indexers=True)
eres = other_mono
elidx = np.array([-1, 1, -1, -1, 6, -1], dtype=np.intp)
tm.assertIsInstance(other, Int64Index)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
self.assertIsNone(ridx)
# non-unique
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])
res, lidx, ridx = idx.join(idx2, how='right', return_indexers=True)
eres = Index([1, 1, 2, 5, 7, 9]) # 1 is in idx2, so it should be x2
elidx = np.array([0, 1, 2, 3, -1, -1], dtype=np.intp)
eridx = np.array([0, 0, 1, 2, 3, 4], dtype=np.intp)
self.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_parse_dates_column_list(self):
from pandas.core.datetools import to_datetime
data = '''date;destination;ventilationcode;unitcode;units;aux_date
01/01/2010;P;P;50;1;12/1/2011
01/01/2010;P;R;50;1;13/1/2011
15/01/2010;P;P;50;1;14/1/2011
01/05/2010;P;P;50;1;15/1/2011'''
expected = self.read_csv(StringIO(data), sep=";", index_col=lrange(4))
lev = expected.index.levels[0]
levels = list(expected.index.levels)
levels[0] = lev.to_datetime(dayfirst=True)
# hack to get this to work - remove for final test
levels[0].name = lev.name
expected.index.set_levels(levels, inplace=True)
expected['aux_date'] = to_datetime(expected['aux_date'],
dayfirst=True)
expected['aux_date'] = lmap(Timestamp, expected['aux_date'])
tm.assertIsInstance(expected['aux_date'][0], datetime)
df = self.read_csv(StringIO(data), sep=";", index_col=lrange(4),
parse_dates=[0, 5], dayfirst=True)
tm.assert_frame_equal(df, expected)
df = self.read_csv(StringIO(data), sep=";", index_col=lrange(4),
parse_dates=['date', 'aux_date'], dayfirst=True)
tm.assert_frame_equal(df, expected)
def test_apply_empty_infer_type(self):
no_cols = DataFrame(index=['a', 'b', 'c'])
no_index = DataFrame(columns=['a', 'b', 'c'])
def _check(df, f):
with warnings.catch_warnings(record=True):
test_res = f(np.array([], dtype='f8'))
is_reduction = not isinstance(test_res, np.ndarray)
def _checkit(axis=0, raw=False):
res = df.apply(f, axis=axis, raw=raw)
if is_reduction:
agg_axis = df._get_agg_axis(axis)
tm.assertIsInstance(res, Series)
self.assertIs(res.index, agg_axis)
else:
tm.assertIsInstance(res, DataFrame)
_checkit()
_checkit(axis=1)
_checkit(raw=True)
_checkit(axis=0, raw=True)
with np.errstate(all='ignore'):
_check(no_cols, lambda x: x)
_check(no_cols, lambda x: x.mean())
_check(no_index, lambda x: x)
_check(no_index, lambda x: x.mean())
result = no_cols.apply(lambda x: x.mean(), broadcast=True)
tm.assertIsInstance(result, DataFrame)
def test_daterange_bug_456(self):
# GH #456
rng1 = cdate_range('12/5/2011', '12/5/2011')
rng2 = cdate_range('12/2/2011', '12/5/2011')
rng2.offset = datetools.CDay()
result = rng1.union(rng2)
tm.assertIsInstance(result, DatetimeIndex)
def test_joins(self):
index = period_range('1/1/2000', '1/20/2000', freq='D')
for kind in ['inner', 'outer', 'left', 'right']:
joined = index.join(index[:-5], how=kind)
tm.assertIsInstance(joined, PeriodIndex)
self.assertEqual(joined.freq, index.freq)
def _checkit(axis=0, raw=False):
res = df.apply(f, axis=axis, raw=raw)
if is_reduction:
agg_axis = df._get_agg_axis(axis)
tm.assertIsInstance(res, Series)
self.assertIs(res.index, agg_axis)
else:
tm.assertIsInstance(res, DataFrame)
def test_copy(self):
cp = self.frame.copy()
tm.assertIsInstance(cp, SparseDataFrame)
tm.assert_sp_frame_equal(cp, self.frame)
# as of v0.15.0
# this is now identical (but not is_a )
self.assertTrue(cp.index.identical(self.frame.index))
def test_unpickle_daterange(self):
pth, _ = os.path.split(os.path.abspath(__file__))
filepath = os.path.join(pth, 'data', 'daterange_073.pickle')
rng = read_pickle(filepath)
tm.assertIsInstance(rng[0], datetime)
tm.assertIsInstance(rng.offset, offsets.BDay)
self.assertEqual(rng.values.dtype, object)
def test_regex_idempotency(self):
url = self.banklist_data
dfs = self.read_html(file_path_to_url(url),
match=re.compile(re.compile('Florida')),
attrs={'id': 'table'})
tm.assertIsInstance(dfs, list)
for df in dfs:
tm.assertIsInstance(df, DataFrame)
def test_constructor_empty(self):
idx = pd.PeriodIndex([], freq='M')
tm.assertIsInstance(idx, PeriodIndex)
self.assertEqual(len(idx), 0)
self.assertEqual(idx.freq, 'M')
with tm.assertRaisesRegexp(ValueError, 'freq not specified'):
pd.PeriodIndex([])
def test_coerce_list(self):
# coerce things
arr = Index([1, 2, 3, 4])
tm.assertIsInstance(arr, Int64Index)
# but not if explicit dtype passed
arr = Index([1, 2, 3, 4], dtype=object)
tm.assertIsInstance(arr, Index)
def test_iterator(self):
# See gh-6607
reader = self.read_csv(StringIO(self.data1), index_col=0,
iterator=True)
df = self.read_csv(StringIO(self.data1), index_col=0)
chunk = reader.read(3)
tm.assert_frame_equal(chunk, df[:3])
last_chunk = reader.read(5)
tm.assert_frame_equal(last_chunk, df[3:])
# pass list
lines = list(csv.reader(StringIO(self.data1)))
parser = TextParser(lines, index_col=0, chunksize=2)
df = self.read_csv(StringIO(self.data1), index_col=0)
chunks = list(parser)
tm.assert_frame_equal(chunks[0], df[:2])
tm.assert_frame_equal(chunks[1], df[2:4])
tm.assert_frame_equal(chunks[2], df[4:])
# pass skiprows
parser = TextParser(lines, index_col=0, chunksize=2, skiprows=[1])
chunks = list(parser)
tm.assert_frame_equal(chunks[0], df[1:3])
treader = self.read_table(StringIO(self.data1), sep=',', index_col=0,
iterator=True)
tm.assertIsInstance(treader, TextFileReader)
# gh-3967: stopping iteration when chunksize is specified
data = """A,B,C
foo,1,2,3
bar,4,5,6
baz,7,8,9
"""
reader = self.read_csv(StringIO(data), iterator=True)
result = list(reader)
expected = DataFrame(dict(A=[1, 4, 7], B=[2, 5, 8], C=[
3, 6, 9]), index=['foo', 'bar', 'baz'])
tm.assert_frame_equal(result[0], expected)
# chunksize = 1
reader = self.read_csv(StringIO(data), chunksize=1)
result = list(reader)
expected = DataFrame(dict(A=[1, 4, 7], B=[2, 5, 8], C=[
3, 6, 9]), index=['foo', 'bar', 'baz'])
self.assertEqual(len(result), 3)
tm.assert_frame_equal(pd.concat(result), expected)
# skip_footer is not supported with the C parser yet
if self.engine == 'python':
# test bad parameter (skip_footer)
reader = self.read_csv(StringIO(self.data1), index_col=0,
iterator=True, skip_footer=True)
self.assertRaises(ValueError, reader.read, 3)
def test_longpanel_series_combo(self):
wp = tm.makePanel()
lp = wp.to_frame()
y = lp.pop('ItemA')
model = ols(y=y, x=lp, entity_effects=True, window=20)
self.assertTrue(notnull(model.beta.values).all())
tm.assertIsInstance(model, PanelOLS)
model.summary
def test_append_join_nondatetimeindex(self):
rng = timedelta_range('1 days', periods=10)
idx = Index(['a', 'b', 'c', 'd'])
result = rng.append(idx)
tm.assertIsInstance(result[0], Timedelta)
# it works
rng.join(idx, how='outer')
def test_constructor(self):
for col, series in compat.iteritems(self.frame):
tm.assertIsInstance(series, SparseSeries)
tm.assertIsInstance(self.iframe['A'].sp_index, IntIndex)
# constructed zframe from matrix above
self.assertEqual(self.zframe['A'].fill_value, 0)
tm.assert_almost_equal([0, 0, 0, 0, 1, 2, 3, 4, 5, 6],
self.zframe['A'].values)
# construct no data
sdf = SparseDataFrame(columns=np.arange(10), index=np.arange(10))
for col, series in compat.iteritems(sdf):
tm.assertIsInstance(series, SparseSeries)
# construct from nested dict
data = {}
for c, s in compat.iteritems(self.frame):
data[c] = s.to_dict()
sdf = SparseDataFrame(data)
tm.assert_sp_frame_equal(sdf, self.frame)
# TODO: test data is copied from inputs
# init dict with different index
idx = self.frame.index[:5]
cons = SparseDataFrame(
self.frame, index=idx, columns=self.frame.columns,
default_fill_value=self.frame.default_fill_value,
default_kind=self.frame.default_kind, copy=True)
reindexed = self.frame.reindex(idx)
tm.assert_sp_frame_equal(cons, reindexed, exact_indices=False)
# assert level parameter breaks reindex
self.assertRaises(TypeError, self.frame.reindex, idx, level=0)
repr(self.frame)
def test_dense_to_sparse(self):
df = DataFrame({
'A': [nan, nan, nan, 1, 2],
'B': [1, 2, nan, nan, nan]
})
sdf = df.to_sparse()
tm.assertIsInstance(sdf, SparseDataFrame)
self.assertTrue(np.isnan(sdf.default_fill_value))
tm.assertIsInstance(sdf['A'].sp_index, BlockIndex)
tm.assert_frame_equal(sdf.to_dense(), df)
sdf = df.to_sparse(kind='integer')
tm.assertIsInstance(sdf['A'].sp_index, IntIndex)
df = DataFrame({
'A': [0, 0, 0, 1, 2],
'B': [1, 2, 0, 0, 0]
},
dtype=float)
sdf = df.to_sparse(fill_value=0)
self.assertEqual(sdf.default_fill_value, 0)
tm.assert_frame_equal(sdf.to_dense(), df)
def test_multiindex_header_skiprows_tuples(self):
df = self._bank_data(header=[0, 1], skiprows=1, tupleize_cols=True)[0]
tm.assertIsInstance(df.columns, Index)
def test_multiindex_index(self):
df = self._bank_data(index_col=[0, 1])[0]
tm.assertIsInstance(df.index, MultiIndex)
def test_multiindex_header(self):
df = self._bank_data(header=[0, 1])[0]
tm.assertIsInstance(df.columns, MultiIndex)
def test_tolist(self):
rng = date_range('1/1/2000', periods=10)
result = rng.tolist()
tm.assertIsInstance(result[0], Timestamp)
def test_objects(self):
arr = np.random.randint(0, 100, size=50).astype('O')
result = algos.unique(arr)
tm.assertIsInstance(result, np.ndarray)
def test_subclass_iterrows(self):
# GH 13977
df = tm.SubclassedDataFrame({'a': [1]})
for i, row in df.iterrows():
tm.assertIsInstance(row, tm.SubclassedSeries)
tm.assert_series_equal(row, df.loc[i])
def test_isinstance(self):
expected = "Expected type "
with assertRaisesRegexp(AssertionError, expected):
tm.assertIsInstance(1, pd.Series)
def test_to_frame(self):
s = tm.SubclassedSeries([1, 2, 3, 4], index=list('abcd'), name='xxx')
res = s.to_frame()
exp = tm.SubclassedDataFrame({'xxx': [1, 2, 3, 4]}, index=list('abcd'))
tm.assert_frame_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedDataFrame)
def test_indexing_sliced(self):
# GH 11559
df = tm.SubclassedDataFrame(
{
'X': [1, 2, 3],
'Y': [4, 5, 6],
'Z': [7, 8, 9]
},
index=['a', 'b', 'c'])
res = df.loc[:, 'X']
exp = tm.SubclassedSeries([1, 2, 3], index=list('abc'), name='X')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
res = df.iloc[:, 1]
exp = tm.SubclassedSeries([4, 5, 6], index=list('abc'), name='Y')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
res = df.ix[:, 'Z']
exp = tm.SubclassedSeries([7, 8, 9], index=list('abc'), name='Z')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
res = df.loc['a', :]
exp = tm.SubclassedSeries([1, 4, 7], index=list('XYZ'), name='a')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
res = df.iloc[1, :]
exp = tm.SubclassedSeries([2, 5, 8], index=list('XYZ'), name='b')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
res = df.ix['c', :]
exp = tm.SubclassedSeries([3, 6, 9], index=list('XYZ'), name='c')
tm.assert_series_equal(res, exp)
tm.assertIsInstance(res, tm.SubclassedSeries)
def test_convert_array_of_periods(self):
rng = period_range('1/1/2000', periods=20, freq='D')
periods = list(rng)
result = pd.Index(periods)
tm.assertIsInstance(result, PeriodIndex)
def test_iteration(self):
index = PeriodIndex(start='1/1/10', periods=4, freq='B')
result = list(index)
tm.assertIsInstance(result[0], Period)
self.assertEqual(result[0].freq, index.freq)
def test_make_time_series(self):
index = PeriodIndex(freq='A', start='1/1/2001', end='12/1/2009')
series = Series(1, index=index)
tm.assertIsInstance(series, Series)
def test_applymap(self):
# just test that it works
result = self.frame.applymap(lambda x: x * 2)
tm.assertIsInstance(result, SparseDataFrame)
def test_multiindex_header_index_skiprows(self):
df = self._bank_data(header=[0, 1], index_col=[0, 1], skiprows=1)[0]
tm.assertIsInstance(df.index, MultiIndex)
tm.assertIsInstance(df.columns, MultiIndex)
def test_works_on_valid_markup(self):
filename = os.path.join(DATA_PATH, 'valid_markup.html')
dfs = self.read_html(filename, index_col=0)
tm.assertIsInstance(dfs, list)
tm.assertIsInstance(dfs[0], DataFrame)
def test_mgr_locs(self):
tm.assertIsInstance(self.fblock.mgr_locs, lib.BlockPlacement)
tm.assert_numpy_array_equal(self.fblock.mgr_locs.as_array,
np.array([0, 2, 4], dtype=np.int64))
def test_series_box_timedelta(self):
rng = timedelta_range('1 day 1 s', periods=5, freq='h')
s = Series(rng)
tm.assertIsInstance(s[1], Timedelta)
tm.assertIsInstance(s.iat[2], Timedelta)
def test_spam_no_match(self):
dfs = self.read_html(self.spam_data)
for df in dfs:
tm.assertIsInstance(df, DataFrame)
def test_margins(self):
def _check_output(result,
values_col,
index=['A', 'B'],
columns=['C'],
margins_col='All'):
col_margins = result.ix[:-1, margins_col]
expected_col_margins = self.data.groupby(index)[values_col].mean()
tm.assert_series_equal(col_margins,
expected_col_margins,
check_names=False)
self.assertEqual(col_margins.name, margins_col)
result = result.sortlevel()
index_margins = result.ix[(margins_col, '')].iloc[:-1]
expected_ix_margins = self.data.groupby(columns)[values_col].mean()
tm.assert_series_equal(index_margins,
expected_ix_margins,
check_names=False)
self.assertEqual(index_margins.name, (margins_col, ''))
grand_total_margins = result.loc[(margins_col, ''), margins_col]
expected_total_margins = self.data[values_col].mean()
self.assertEqual(grand_total_margins, expected_total_margins)
# column specified
result = self.data.pivot_table(values='D',
index=['A', 'B'],
columns='C',
margins=True,
aggfunc=np.mean)
_check_output(result, 'D')
# Set a different margins_name (not 'All')
result = self.data.pivot_table(values='D',
index=['A', 'B'],
columns='C',
margins=True,
aggfunc=np.mean,
margins_name='Totals')
_check_output(result, 'D', margins_col='Totals')
# no column specified
table = self.data.pivot_table(index=['A', 'B'],
columns='C',
margins=True,
aggfunc=np.mean)
for value_col in table.columns.levels[0]:
_check_output(table[value_col], value_col)
# no col
# to help with a buglet
self.data.columns = [k * 2 for k in self.data.columns]
table = self.data.pivot_table(index=['AA', 'BB'],
margins=True,
aggfunc=np.mean)
for value_col in table.columns:
totals = table.loc[('All', ''), value_col]
self.assertEqual(totals, self.data[value_col].mean())
# no rows
rtable = self.data.pivot_table(columns=['AA', 'BB'],
margins=True,
aggfunc=np.mean)
tm.assertIsInstance(rtable, Series)
table = self.data.pivot_table(index=['AA', 'BB'],
margins=True,
aggfunc='mean')
for item in ['DD', 'EE', 'FF']:
totals = table.loc[('All', ''), item]
self.assertEqual(totals, self.data[item].mean())
# issue number #8349: pivot_table with margins and dictionary aggfunc
data = [
{
'JOB': 'Worker',
'NAME': 'Bob',
'YEAR': 2013,
'MONTH': 12,
'DAYS': 3,
'SALARY': 17
},
{
'JOB': 'Employ',
'NAME': 'Mary',
'YEAR': 2013,
'MONTH': 12,
'DAYS': 5,
'SALARY': 23
},
{
'JOB': 'Worker',
'NAME': 'Bob',
'YEAR': 2014,
'MONTH': 1,
'DAYS': 10,
'SALARY': 100
},
{
'JOB': 'Worker',
'NAME': 'Bob',
'YEAR': 2014,
'MONTH': 1,
'DAYS': 11,
'SALARY': 110
},
{
'JOB': 'Employ',
'NAME': 'Mary',
'YEAR': 2014,
'MONTH': 1,
'DAYS': 15,
'SALARY': 200
},
{
'JOB': 'Worker',
'NAME': 'Bob',
'YEAR': 2014,
'MONTH': 2,
'DAYS': 8,
'SALARY': 80
},
{
'JOB': 'Employ',
'NAME': 'Mary',
'YEAR': 2014,
'MONTH': 2,
'DAYS': 5,
'SALARY': 190
},
]
df = DataFrame(data)
df = df.set_index(['JOB', 'NAME', 'YEAR', 'MONTH'],
drop=False,
append=False)
result = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'],
values=['DAYS', 'SALARY'],
aggfunc={
'DAYS': 'mean',
'SALARY': 'sum'
},
margins=True)
expected = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'],
values=['DAYS'],
aggfunc='mean',
margins=True)
tm.assert_frame_equal(result['DAYS'], expected['DAYS'])
expected = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'],
values=['SALARY'],
aggfunc='sum',
margins=True)
tm.assert_frame_equal(result['SALARY'], expected['SALARY'])
def test_banklist_no_match(self):
dfs = self.read_html(self.banklist_data, attrs={'id': 'table'})
for df in dfs:
tm.assertIsInstance(df, DataFrame)
def _validate_periodindex(self, pickled, current):
tm.assert_index_equal(pickled, current)
tm.assertIsInstance(pickled.freq, MonthEnd)
tm.assert_equal(pickled.freq, MonthEnd())
tm.assert_equal(pickled.freqstr, 'M')
tm.assert_index_equal(pickled.shift(2), current.shift(2))
def _check(res):
tm.assertIsInstance(res, SparseArray)
self.assertEqual(res.dtype, np.bool)
self.assertIsInstance(res.fill_value, bool)
def test_constructor_corner(self):
df = tm.makeTimeDataFrame()
objs = [df, df]
s = Series(objs, index=[0, 1])
tm.assertIsInstance(s, Series)
def test_ufunc_coercions(self):
idx = self._holder([1, 2, 3, 4, 5], name='x')
result = np.sqrt(idx)
tm.assertIsInstance(result, Float64Index)
exp = Float64Index(np.sqrt(np.array([1, 2, 3, 4, 5])), name='x')
tm.assert_index_equal(result, exp)
result = np.divide(idx, 2.)
tm.assertIsInstance(result, Float64Index)
exp = Float64Index([0.5, 1., 1.5, 2., 2.5], name='x')
tm.assert_index_equal(result, exp)
# _evaluate_numeric_binop
result = idx + 2.
tm.assertIsInstance(result, Float64Index)
exp = Float64Index([3., 4., 5., 6., 7.], name='x')
tm.assert_index_equal(result, exp)
result = idx - 2.
tm.assertIsInstance(result, Float64Index)
exp = Float64Index([-1., 0., 1., 2., 3.], name='x')
tm.assert_index_equal(result, exp)
result = idx * 1.
tm.assertIsInstance(result, Float64Index)
exp = Float64Index([1., 2., 3., 4., 5.], name='x')
tm.assert_index_equal(result, exp)
result = idx / 2.
tm.assertIsInstance(result, Float64Index)
exp = Float64Index([0.5, 1., 1.5, 2., 2.5], name='x')
tm.assert_index_equal(result, exp)
def test_apply_multi_index(self):
s = DataFrame([[1, 2], [3, 4], [5, 6]])
s.index = MultiIndex.from_arrays([['a', 'a', 'b'], ['c', 'd', 'd']])
s.columns = ['col1', 'col2']
res = s.apply(lambda x: Series({'min': min(x), 'max': max(x)}), 1)
tm.assertIsInstance(res.index, MultiIndex)
def test_operators_timedelta64(self):
# invalid ops
self.assertRaises(Exception, self.objSeries.__add__, 1)
self.assertRaises(Exception, self.objSeries.__add__,
np.array(1, dtype=np.int64))
self.assertRaises(Exception, self.objSeries.__sub__, 1)
self.assertRaises(Exception, self.objSeries.__sub__,
np.array(1, dtype=np.int64))
# seriese ops
v1 = date_range('2012-1-1', periods=3, freq='D')
v2 = date_range('2012-1-2', periods=3, freq='D')
rs = Series(v2) - Series(v1)
xp = Series(1e9 * 3600 * 24,
rs.index).astype('int64').astype('timedelta64[ns]')
assert_series_equal(rs, xp)
self.assertEqual(rs.dtype, 'timedelta64[ns]')
df = DataFrame(dict(A=v1))
td = Series([timedelta(days=i) for i in range(3)])
self.assertEqual(td.dtype, 'timedelta64[ns]')
# series on the rhs
result = df['A'] - df['A'].shift()
self.assertEqual(result.dtype, 'timedelta64[ns]')
result = df['A'] + td
self.assertEqual(result.dtype, 'M8[ns]')
# scalar Timestamp on rhs
maxa = df['A'].max()
tm.assertIsInstance(maxa, Timestamp)
resultb = df['A'] - df['A'].max()
self.assertEqual(resultb.dtype, 'timedelta64[ns]')
# timestamp on lhs
result = resultb + df['A']
values = [
Timestamp('20111230'),
Timestamp('20120101'),
Timestamp('20120103')
]
expected = Series(values, name='A')
assert_series_equal(result, expected)
# datetimes on rhs
result = df['A'] - datetime(2001, 1, 1)
expected = Series([timedelta(days=4017 + i) for i in range(3)],
name='A')
assert_series_equal(result, expected)
self.assertEqual(result.dtype, 'm8[ns]')
d = datetime(2001, 1, 1, 3, 4)
resulta = df['A'] - d
self.assertEqual(resulta.dtype, 'm8[ns]')
# roundtrip
resultb = resulta + d
assert_series_equal(df['A'], resultb)
# timedeltas on rhs
td = timedelta(days=1)
resulta = df['A'] + td
resultb = resulta - td
assert_series_equal(resultb, df['A'])
self.assertEqual(resultb.dtype, 'M8[ns]')
# roundtrip
td = timedelta(minutes=5, seconds=3)
resulta = df['A'] + td
resultb = resulta - td
assert_series_equal(df['A'], resultb)
self.assertEqual(resultb.dtype, 'M8[ns]')
# inplace
value = rs[2] + np.timedelta64(timedelta(minutes=5, seconds=1))
rs[2] += np.timedelta64(timedelta(minutes=5, seconds=1))
self.assertEqual(rs[2], value)
def compare_index_period(result, expected, typ, version):
tm.assert_index_equal(result, expected)
tm.assertIsInstance(result.freq, MonthEnd)
tm.assert_equal(result.freq, MonthEnd())
tm.assert_equal(result.freqstr, 'M')
tm.assert_index_equal(result.shift(2), expected.shift(2))
def check_result(self, result, expected, klass=None):
klass = klass or self.klass
assertIsInstance(result, klass)
self.assertEqual(result, expected)