Python pandas.compat.product() Examples
The following are 30
code examples of pandas.compat.product().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
pandas.compat
, or try the search function
.
.
Example #1
| Source File: test_rank.py From twitter-stock-recommendation with MIT License | 6 votes |
|
def test_rank_2d_tie_methods(self):
df = self.df
def _check2d(df, expected, method='average', axis=0):
exp_df = DataFrame({'A': expected, 'B': expected})
if axis == 1:
df = df.T
exp_df = exp_df.T
result = df.rank(method=method, axis=axis)
assert_frame_equal(result, exp_df)
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, axis, dtype in product(results, [0, 1], dtypes):
if (dtype, method) in disabled:
continue
frame = df if dtype is None else df.astype(dtype)
_check2d(frame, results[method], method=method, axis=axis)
Example #2
| Source File: test_rank.py From vnpy_crypto with MIT License | 6 votes |
|
def test_rank_tie_methods(self):
s = self.s
def _check(s, expected, method='average'):
result = s.rank(method=method)
tm.assert_series_equal(result, Series(expected))
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, dtype in product(results, dtypes):
if (dtype, method) in disabled:
continue
series = s if dtype is None else s.astype(dtype)
_check(series, results[method], method=method)
Example #3
| Source File: test_pivot.py From recruit with Apache License 2.0 | 6 votes |
|
def test_margins_dtype(self):
# GH 17013
df = self.data.copy()
df[['D', 'E', 'F']] = np.arange(len(df) * 3).reshape(len(df), 3)
mi_val = list(product(['bar', 'foo'], ['one', 'two'])) + [('All', '')]
mi = MultiIndex.from_tuples(mi_val, names=('A', 'B'))
expected = DataFrame({'dull': [12, 21, 3, 9, 45],
'shiny': [33, 0, 36, 51, 120]},
index=mi).rename_axis('C', axis=1)
expected['All'] = expected['dull'] + expected['shiny']
result = df.pivot_table(values='D', index=['A', 'B'],
columns='C', margins=True,
aggfunc=np.sum, fill_value=0)
tm.assert_frame_equal(expected, result)
Example #4
| Source File: test_rank.py From recruit with Apache License 2.0 | 6 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
s = self.s.dropna()
else:
s = self.s.astype(dtype)
res = s.rank(ascending=False)
expected = (s.max() - s).rank()
assert_series_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (s.max() - s).rank(method=method)
res2 = s.rank(method=method, ascending=False)
assert_series_equal(res2, expected)
Example #5
| Source File: test_pivot.py From vnpy_crypto with MIT License | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #6
| Source File: test_resample.py From vnpy_crypto with MIT License | 6 votes |
|
def test_resample_group_info(self): # GH10914
for n, k in product((10000, 100000), (10, 100, 1000)):
dr = date_range(start='2015-08-27', periods=n // 10, freq='T')
ts = Series(np.random.randint(0, n // k, n).astype('int64'),
index=np.random.choice(dr, n))
left = ts.resample('30T').nunique()
ix = date_range(start=ts.index.min(), end=ts.index.max(),
freq='30T')
vals = ts.values
bins = np.searchsorted(ix.values, ts.index, side='right')
sorter = np.lexsort((vals, bins))
vals, bins = vals[sorter], bins[sorter]
mask = np.r_[True, vals[1:] != vals[:-1]]
mask |= np.r_[True, bins[1:] != bins[:-1]]
arr = np.bincount(bins[mask] - 1,
minlength=len(ix)).astype('int64', copy=False)
right = Series(arr, index=ix)
assert_series_equal(left, right)
Example #7
| Source File: test_rank.py From vnpy_crypto with MIT License | 6 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
s = self.s.dropna()
else:
s = self.s.astype(dtype)
res = s.rank(ascending=False)
expected = (s.max() - s).rank()
assert_series_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (s.max() - s).rank(method=method)
res2 = s.rank(method=method, ascending=False)
assert_series_equal(res2, expected)
Example #8
| Source File: test_rank.py From recruit with Apache License 2.0 | 6 votes |
|
def test_rank_tie_methods(self):
s = self.s
def _check(s, expected, method='average'):
result = s.rank(method=method)
tm.assert_series_equal(result, Series(expected))
dtypes = [None, object]
disabled = {(object, 'first')}
results = self.results
for method, dtype in product(results, dtypes):
if (dtype, method) in disabled:
continue
series = s if dtype is None else s.astype(dtype)
_check(series, results[method], method=method)
Example #9
| Source File: test_rank.py From vnpy_crypto with MIT License | 6 votes |
|
def test_rank_2d_tie_methods(self):
df = self.df
def _check2d(df, expected, method='average', axis=0):
exp_df = DataFrame({'A': expected, 'B': expected})
if axis == 1:
df = df.T
exp_df = exp_df.T
result = df.rank(method=method, axis=axis)
assert_frame_equal(result, exp_df)
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, axis, dtype in product(results, [0, 1], dtypes):
if (dtype, method) in disabled:
continue
frame = df if dtype is None else df.astype(dtype)
_check2d(frame, results[method], method=method, axis=axis)
Example #10
| Source File: test_pivot.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #11
| Source File: test_pivot.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 6 votes |
|
def test_margins_dtype(self):
# GH 17013
df = self.data.copy()
df[['D', 'E', 'F']] = np.arange(len(df) * 3).reshape(len(df), 3)
mi_val = list(product(['bar', 'foo'], ['one', 'two'])) + [('All', '')]
mi = MultiIndex.from_tuples(mi_val, names=('A', 'B'))
expected = DataFrame({'dull': [12, 21, 3, 9, 45],
'shiny': [33, 0, 36, 51, 120]},
index=mi).rename_axis('C', axis=1)
expected['All'] = expected['dull'] + expected['shiny']
result = df.pivot_table(values='D', index=['A', 'B'],
columns='C', margins=True,
aggfunc=np.sum, fill_value=0)
tm.assert_frame_equal(expected, result)
Example #12
| Source File: test_rank.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 6 votes |
|
def test_rank_tie_methods(self):
s = self.s
def _check(s, expected, method='average'):
result = s.rank(method=method)
tm.assert_series_equal(result, Series(expected))
dtypes = [None, object]
disabled = {(object, 'first')}
results = self.results
for method, dtype in product(results, dtypes):
if (dtype, method) in disabled:
continue
series = s if dtype is None else s.astype(dtype)
_check(series, results[method], method=method)
Example #13
| Source File: test_pivot.py From recruit with Apache License 2.0 | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #14
| Source File: test_pivot.py From elasticintel with GNU General Public License v3.0 | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #15
| Source File: test_rank.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 6 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
s = self.s.dropna()
else:
s = self.s.astype(dtype)
res = s.rank(ascending=False)
expected = (s.max() - s).rank()
assert_series_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (s.max() - s).rank(method=method)
res2 = s.rank(method=method, ascending=False)
assert_series_equal(res2, expected)
Example #16
| Source File: test_rank.py From twitter-stock-recommendation with MIT License | 6 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
s = self.s.dropna()
else:
s = self.s.astype(dtype)
res = s.rank(ascending=False)
expected = (s.max() - s).rank()
assert_series_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (s.max() - s).rank(method=method)
res2 = s.rank(method=method, ascending=False)
assert_series_equal(res2, expected)
Example #17
| Source File: test_rank.py From twitter-stock-recommendation with MIT License | 6 votes |
|
def test_rank_tie_methods(self):
s = self.s
def _check(s, expected, method='average'):
result = s.rank(method=method)
tm.assert_series_equal(result, Series(expected))
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, dtype in product(results, dtypes):
if (dtype, method) in disabled:
continue
series = s if dtype is None else s.astype(dtype)
_check(series, results[method], method=method)
Example #18
| Source File: test_pivot.py From twitter-stock-recommendation with MIT License | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #19
| Source File: test_resample.py From twitter-stock-recommendation with MIT License | 6 votes |
|
def test_resample_group_info(self): # GH10914
for n, k in product((10000, 100000), (10, 100, 1000)):
dr = date_range(start='2015-08-27', periods=n // 10, freq='T')
ts = Series(np.random.randint(0, n // k, n).astype('int64'),
index=np.random.choice(dr, n))
left = ts.resample('30T').nunique()
ix = date_range(start=ts.index.min(), end=ts.index.max(),
freq='30T')
vals = ts.values
bins = np.searchsorted(ix.values, ts.index, side='right')
sorter = np.lexsort((vals, bins))
vals, bins = vals[sorter], bins[sorter]
mask = np.r_[True, vals[1:] != vals[:-1]]
mask |= np.r_[True, bins[1:] != bins[:-1]]
arr = np.bincount(bins[mask] - 1,
minlength=len(ix)).astype('int64', copy=False)
right = Series(arr, index=ix)
assert_series_equal(left, right)
Example #20
| Source File: test_pivot.py From coffeegrindsize with MIT License | 6 votes |
|
def test_margins_dtype(self):
# GH 17013
df = self.data.copy()
df[['D', 'E', 'F']] = np.arange(len(df) * 3).reshape(len(df), 3)
mi_val = list(product(['bar', 'foo'], ['one', 'two'])) + [('All', '')]
mi = MultiIndex.from_tuples(mi_val, names=('A', 'B'))
expected = DataFrame({'dull': [12, 21, 3, 9, 45],
'shiny': [33, 0, 36, 51, 120]},
index=mi).rename_axis('C', axis=1)
expected['All'] = expected['dull'] + expected['shiny']
result = df.pivot_table(values='D', index=['A', 'B'],
columns='C', margins=True,
aggfunc=np.sum, fill_value=0)
tm.assert_frame_equal(expected, result)
Example #21
| Source File: test_pivot.py From coffeegrindsize with MIT License | 6 votes |
|
def test_pivot_table_dropna(self):
df = DataFrame({'amount': {0: 60000, 1: 100000, 2: 50000, 3: 30000},
'customer': {0: 'A', 1: 'A', 2: 'B', 3: 'C'},
'month': {0: 201307, 1: 201309, 2: 201308, 3: 201310},
'product': {0: 'a', 1: 'b', 2: 'c', 3: 'd'},
'quantity': {0: 2000000, 1: 500000,
2: 1000000, 3: 1000000}})
pv_col = df.pivot_table('quantity', 'month', [
'customer', 'product'], dropna=False)
pv_ind = df.pivot_table(
'quantity', ['customer', 'product'], 'month', dropna=False)
m = MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('A', 'c'),
('A', 'd'), ('B', 'a'), ('B', 'b'),
('B', 'c'), ('B', 'd'), ('C', 'a'),
('C', 'b'), ('C', 'c'), ('C', 'd')],
names=['customer', 'product'])
tm.assert_index_equal(pv_col.columns, m)
tm.assert_index_equal(pv_ind.index, m)
Example #22
| Source File: test_rank.py From elasticintel with GNU General Public License v3.0 | 6 votes |
|
def test_rank_2d_tie_methods(self):
df = self.df
def _check2d(df, expected, method='average', axis=0):
exp_df = DataFrame({'A': expected, 'B': expected})
if axis == 1:
df = df.T
exp_df = exp_df.T
result = df.rank(method=method, axis=axis)
assert_frame_equal(result, exp_df)
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, axis, dtype in product(results, [0, 1], dtypes):
if (dtype, method) in disabled:
continue
frame = df if dtype is None else df.astype(dtype)
_check2d(frame, results[method], method=method, axis=axis)
Example #23
| Source File: test_rank.py From elasticintel with GNU General Public License v3.0 | 6 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
s = self.s.dropna()
else:
s = self.s.astype(dtype)
res = s.rank(ascending=False)
expected = (s.max() - s).rank()
assert_series_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (s.max() - s).rank(method=method)
res2 = s.rank(method=method, ascending=False)
assert_series_equal(res2, expected)
Example #24
| Source File: test_rank.py From elasticintel with GNU General Public License v3.0 | 6 votes |
|
def test_rank_tie_methods(self):
s = self.s
def _check(s, expected, method='average'):
result = s.rank(method=method)
tm.assert_series_equal(result, Series(expected))
dtypes = [None, object]
disabled = set([(object, 'first')])
results = self.results
for method, dtype in product(results, dtypes):
if (dtype, method) in disabled:
continue
series = s if dtype is None else s.astype(dtype)
_check(series, results[method], method=method)
Example #25
| Source File: test_resample.py From elasticintel with GNU General Public License v3.0 | 6 votes |
|
def test_resample_group_info(self): # GH10914
for n, k in product((10000, 100000), (10, 100, 1000)):
dr = date_range(start='2015-08-27', periods=n // 10, freq='T')
ts = Series(np.random.randint(0, n // k, n).astype('int64'),
index=np.random.choice(dr, n))
left = ts.resample('30T').nunique()
ix = date_range(start=ts.index.min(), end=ts.index.max(),
freq='30T')
vals = ts.values
bins = np.searchsorted(ix.values, ts.index, side='right')
sorter = np.lexsort((vals, bins))
vals, bins = vals[sorter], bins[sorter]
mask = np.r_[True, vals[1:] != vals[:-1]]
mask |= np.r_[True, bins[1:] != bins[:-1]]
arr = np.bincount(bins[mask] - 1,
minlength=len(ix)).astype('int64', copy=False)
right = Series(arr, index=ix)
assert_series_equal(left, right)
Example #26
| Source File: test_pivot.py From recruit with Apache License 2.0 | 5 votes |
|
def test_margins_dtype_len(self):
mi_val = list(product(['bar', 'foo'], ['one', 'two'])) + [('All', '')]
mi = MultiIndex.from_tuples(mi_val, names=('A', 'B'))
expected = DataFrame({'dull': [1, 1, 2, 1, 5],
'shiny': [2, 0, 2, 2, 6]},
index=mi).rename_axis('C', axis=1)
expected['All'] = expected['dull'] + expected['shiny']
result = self.data.pivot_table(values='D', index=['A', 'B'],
columns='C', margins=True,
aggfunc=len, fill_value=0)
tm.assert_frame_equal(expected, result)
Example #27
| Source File: test_pivot.py From coffeegrindsize with MIT License | 5 votes |
|
def test_margins_dtype_len(self):
mi_val = list(product(['bar', 'foo'], ['one', 'two'])) + [('All', '')]
mi = MultiIndex.from_tuples(mi_val, names=('A', 'B'))
expected = DataFrame({'dull': [1, 1, 2, 1, 5],
'shiny': [2, 0, 2, 2, 6]},
index=mi).rename_axis('C', axis=1)
expected['All'] = expected['dull'] + expected['shiny']
result = self.data.pivot_table(values='D', index=['A', 'B'],
columns='C', margins=True,
aggfunc=len, fill_value=0)
tm.assert_frame_equal(expected, result)
Example #28
| Source File: test_function.py From recruit with Apache License 2.0 | 5 votes |
|
def test_size(df):
grouped = df.groupby(['A', 'B'])
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = df.groupby('A')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
grouped = df.groupby('B')
result = grouped.size()
for key, group in grouped:
assert result[key] == len(group)
df = DataFrame(np.random.choice(20, (1000, 3)), columns=list('abc'))
for sort, key in cart_product((False, True), ('a', 'b', ['a', 'b'])):
left = df.groupby(key, sort=sort).size()
right = df.groupby(key, sort=sort)['c'].apply(lambda a: a.shape[0])
tm.assert_series_equal(left, right, check_names=False)
# GH11699
df = DataFrame([], columns=['A', 'B'])
out = Series([], dtype='int64', index=Index([], name='A'))
tm.assert_series_equal(df.groupby('A').size(), out)
# pipe
# --------------------------------
Example #29
| Source File: test_counting.py From recruit with Apache License 2.0 | 5 votes |
|
def test_ngroup_cumcount_pair(self):
# brute force comparison for all small series
for p in cart_product(range(3), repeat=4):
df = DataFrame({'a': p})
g = df.groupby(['a'])
order = sorted(set(p))
ngroupd = [order.index(val) for val in p]
cumcounted = [p[:i].count(val) for i, val in enumerate(p)]
assert_series_equal(g.ngroup(), Series(ngroupd))
assert_series_equal(g.cumcount(), Series(cumcounted))
Example #30
| Source File: test_rank.py From twitter-stock-recommendation with MIT License | 5 votes |
|
def test_rank_descending(self):
dtypes = ['O', 'f8', 'i8']
for dtype, method in product(dtypes, self.results):
if 'i' in dtype:
df = self.df.dropna()
else:
df = self.df.astype(dtype)
res = df.rank(ascending=False)
expected = (df.max() - df).rank()
assert_frame_equal(res, expected)
if method == 'first' and dtype == 'O':
continue
expected = (df.max() - df).rank(method=method)
if dtype != 'O':
res2 = df.rank(method=method, ascending=False,
numeric_only=True)
assert_frame_equal(res2, expected)
res3 = df.rank(method=method, ascending=False,
numeric_only=False)
assert_frame_equal(res3, expected)
