def test_rolling1(self):
# size 3 without unroll
def test_impl(n):
df = pd.DataFrame({'A': np.arange(n), 'B': np.random.ranf(n)})
Ac = df.A.rolling(3).sum()
return Ac.sum()
hpat_func = sdc.jit(test_impl)
n = 121
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
# size 7 with unroll
def test_impl_2(n):
df = pd.DataFrame({
'A': np.arange(n) + 1.0,
'B': np.random.ranf(n)
})
Ac = df.A.rolling(7).sum()
return Ac.sum()
hpat_func = sdc.jit(test_impl)
n = 121
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_reduce_filter1(self):
import sys
dtypes = ['float32', 'float64', 'int32', 'int64']
funcs = ['sum', 'prod', 'min', 'max', 'argmin', 'argmax']
for (dtype, func) in itertools.product(dtypes, funcs):
# loc allreduce doesn't support int64 on windows
if (sys.platform.startswith('win') and dtype == 'int64'
and func in ['argmin', 'argmax']):
continue
func_text = """def f(A):
A = A[A>5]
return A.{}()
""".format(func)
loc_vars = {}
exec(func_text, {'np': np}, loc_vars)
test_impl = loc_vars['f']
hpat_func = self.jit(locals={'A:input': 'distributed'})(test_impl)
n = 21
start, end = get_start_end(n)
np.random.seed(0)
A = np.random.randint(0, 10, n).astype(dtype)
np.testing.assert_almost_equal(hpat_func(A[start:end]),
test_impl(A),
decimal=3,
err_msg="{} on {}".format(
func, dtype))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_shape(self):
def test_impl(N):
return np.ones(N).shape[0]
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pq_float_no_nan(self):
def test_impl():
df = pq.read_table('example.parquet').to_pandas()
return df.four.sum()
hpat_func = self.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_astype(self):
def test_impl(N):
return np.ones(N).astype(np.int32).sum()
hpat_func = sdc.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pq_read_global_str1(self):
def test_impl():
df = pd.read_parquet(kde_file)
X = df['points']
return X.sum()
hpat_func = self.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_np_io2(self):
# parallel version
def test_impl():
A = np.fromfile("np_file1.dat", np.float64)
return A.sum()
hpat_func = self.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pq_str_with_nan_par_multigroup(self):
def test_impl():
df = pq.read_table('example2.parquet').to_pandas()
A = df.five.values == 'foo'
return A.sum()
hpat_func = self.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pq_str(self):
def test_impl():
df = pq.read_table('example.parquet').to_pandas()
A = df.two.values == 'foo'
return A.sum()
hpat_func = sdc.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pd_read_parquet(self):
def test_impl():
df = pd.read_parquet('kde.parquet')
X = df['points']
return X.sum()
hpat_func = sdc.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_agg_parallel_str(self):
def test_impl():
df = pq.read_table("groupby3.pq").to_pandas()
A = df.groupby('A')['B'].agg(lambda x: x.max() - x.min())
return A.sum()
hpat_func = self.jit(test_impl)
self.assertEqual(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_df_values_parallel1(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n), 'B': np.arange(n)})
return df.values.sum()
hpat_func = sdc.jit(test_impl)
n = 11
np.testing.assert_array_equal(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_quantile_parallel_int(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(0, n, 1, np.int32)})
return df.A.quantile(.25)
hpat_func = sdc.jit(test_impl)
n = 1001
np.testing.assert_almost_equal(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_whole_slice(self):
def test_impl(N):
X = np.ones((N, 4))
X[:, 3] = (X[:, 3]) / (np.max(X[:, 3]) - np.min(X[:, 3]))
return X.sum()
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_setitem1(self):
def test_impl(N):
A = np.arange(10) + 1.0
A[0] = 30
return A.sum()
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_pq_read(self):
def test_impl():
t = pq.read_table('kde.parquet')
df = t.to_pandas()
X = df['points']
return X.sum()
hpat_func = self.jit(test_impl)
np.testing.assert_almost_equal(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_strided_getitem(self):
def test_impl(N):
A = np.ones(N)
B = A[::7]
return B.sum()
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_shift2(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(n) + 1.0, 'B': np.random.ranf(n)})
Ac = df.A.pct_change(1)
return Ac.sum()
hpat_func = self.jit(test_impl)
n = 11
np.testing.assert_almost_equal(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_agg_parallel_std(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n, np.int64), 'B': np.arange(n)})
A = df.groupby('A')['B'].std()
return A.sum()
hpat_func = self.jit(test_impl)
n = 11
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_filter3(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(n) + n, 'B': np.arange(n)**2})
df1 = df.iloc[(df.A > .5).values]
return np.sum(df1.B)
hpat_func = sdc.jit(test_impl)
n = 11
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_agg_parallel_as_index(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n, np.int64), 'B': np.arange(n)})
df2 = df.groupby('A', as_index=False).max()
return df2.A.sum()
hpat_func = self.jit(test_impl)
n = 11
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_concat_series_str(self):
def test_impl():
df1 = pq.read_table('example.parquet').to_pandas()
df2 = pq.read_table('example.parquet').to_pandas()
A3 = pd.concat([df1.two, df2.two])
return (A3 == 'foo').sum()
hpat_func = sdc.jit(test_impl)
self.assertEqual(hpat_func(), test_impl())
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_rolling3(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n), 'B': np.random.ranf(n)})
Ac = df.A.rolling(3, center=True).apply(lambda a: a[0] + 2 * a[1] + a[2])
return Ac.sum()
hpat_func = self.jit(test_impl)
n = 121
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_1D_Var_len(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(n), 'B': np.arange(n) + 1.0})
df1 = df[df.A > 5]
return len(df1.B)
hpat_func = sdc.jit(test_impl)
n = 11
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_rolling2(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n), 'B': np.random.ranf(n)})
df['moving average'] = df.A.rolling(window=5, center=True).mean()
return df['moving average'].sum()
hpat_func = sdc.jit(test_impl)
n = 121
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_describe(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(0, n, 1, np.float64)})
return df.A.describe()
hpat_func = sdc.jit(test_impl)
n = 1001
hpat_func(n)
# XXX: test actual output
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_getitem_multidim(self):
def test_impl(N):
A = np.ones((N, 3))
B = np.ones(N) > .5
C = A[B, 2]
return C.sum()
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_transpose(self):
def test_impl(n):
A = np.ones((30, 40, 50))
B = A.transpose((0, 2, 1))
C = A.transpose(0, 2, 1)
return B.sum() + C.sum()
hpat_func = self.jit(test_impl)
n = 128
np.testing.assert_allclose(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_quantile_parallel_float_nan(self):
def test_impl(n):
df = pd.DataFrame({'A': np.arange(0, n, 1, np.float32)})
df.A[0:100] = np.nan
df.A[200:331] = np.nan
return df.A.quantile(.25)
hpat_func = sdc.jit(test_impl)
n = 1001
np.testing.assert_almost_equal(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
def test_column_getitem1(self):
def test_impl(n):
df = pd.DataFrame({'A': np.ones(n), 'B': np.random.ranf(n)})
Ac = df['A'].values
return Ac.sum()
hpat_func = sdc.jit(test_impl)
n = 11
self.assertEqual(hpat_func(n), test_impl(n))
self.assertEqual(count_array_REPs(), 0)
self.assertEqual(count_parfor_REPs(), 0)
self.assertEqual(count_parfor_OneDs(), 1)
