def test_distinct(): (chunk, chunk_expr), (agg, agg_expr) = split(t, count(t.amount.distinct())) assert chunk.schema == t.schema assert chunk_expr.isidentical(chunk.amount.distinct()) assert isscalar(agg.dshape.measure) assert agg_expr.isidentical(count(agg.distinct()))
def test_reductions(): assert compute(sum(t['amount']), data) == 100 + 200 + 50 assert compute(min(t['amount']), data) == 50 assert compute(max(t['amount']), data) == 200 assert compute(nunique(t['amount']), data) == 3 assert compute(nunique(t['name']), data) == 2 assert compute(count(t['amount']), data) == 3 assert compute(any(t['amount'] > 150), data) is True assert compute(any(t['amount'] > 250), data) is False
def test_reductions(): assert str(compute(sum(t['amount']), s, post_compute=False)) == \ str(sa.sql.functions.sum(s.c.amount)) assert str(compute(mean(t['amount']), s, post_compute=False)) == \ str(sa.sql.func.avg(s.c.amount)) assert str(compute(count(t['amount']), s, post_compute=False)) == \ str(sa.sql.func.count(s.c.amount)) assert 'amount_sum' == compute(sum(t['amount']), s, post_compute=False).name
def test_reductions(): assert compute(mean(t['amount']), ddf) == 350 / 3 assert compute(count(t['amount']), ddf) == 3 assert compute(sum(t['amount']), ddf) == 100 + 200 + 50 assert compute(min(t['amount']), ddf) == 50 assert compute(max(t['amount']), ddf) == 200 assert compute(var(t['amount']), ddf) == df.amount.var(ddof=0) assert compute(var(t['amount'], unbiased=True), ddf) == df.amount.var() assert compute(std(t['amount']), ddf) == df.amount.std(ddof=0) assert compute(std(t['amount'], unbiased=True), ddf) == df.amount.std()
def test_reductions(): assert compute(mean(t['amount']), ddf) == 350 / 3.0 assert compute(count(t['amount']), ddf) == 3 assert compute(sum(t['amount']), ddf) == 100 + 200 + 50 assert compute(min(t['amount']), ddf) == 50 assert compute(max(t['amount']), ddf) == 200 tm.assert_almost_equal(compute(var(t['amount']), ddf), df.amount.var(ddof=0)) tm.assert_almost_equal(compute(var(t['amount'], unbiased=True), ddf), df.amount.var()) assert compute(std(t['amount']), ddf) == df.amount.std(ddof=0) assert compute(std(t['amount'], unbiased=True), ddf) == df.amount.std()
def test_reductions(): assert compute(mean(t['amount']), df) == 350./3 assert compute(count(t['amount']), df) == 3 assert compute(sum(t['amount']), df) == 100 + 200 + 50 assert compute(min(t['amount']), df) == 50 assert compute(max(t['amount']), df) == 200 assert compute(nunique(t['amount']), df) == 3 assert compute(nunique(t['name']), df) == 2 assert compute(any(t['amount'] > 150), df) == True assert compute(any(t['amount'] > 250), df) == False assert compute(var(t['amount']), df) == df.amount.var(ddof=0) assert compute(var(t['amount'], unbiased=True), df) == df.amount.var() assert compute(std(t['amount']), df) == df.amount.std(ddof=0) assert compute(std(t['amount'], unbiased=True), df) == df.amount.std()
def test_path_split(): expr = t.amount.sum() + 1 assert path_split(t, expr).isidentical(t.amount.sum()) expr = t.amount.distinct().sort() assert path_split(t, expr).isidentical(t.amount.distinct()) t2 = transform(t, id=t.id * 2) expr = by(t2.id, amount=t2.amount.sum()).amount + 1 assert path_split(t, expr).isidentical(by(t2.id, amount=t2.amount.sum())) expr = count(t.amount.distinct()) assert path_split(t, expr).isidentical(t.amount.distinct()) expr = summary(total=t.amount.sum()) assert path_split(t, expr).isidentical(expr)
def test_reductions_on_dataframes(): assert compute(count(t), df) == 3 assert shape(compute(count(t, keepdims=True), df)) == (1,)
def test_reductions_on_dataframes(): assert compute(count(t), df) == 3 assert shape(compute(count(t, keepdims=True), df)) == (1, )
def test_nelements_count(): assert compute(t.nelements(), ddf) == len(df) assert compute(t.nrows, ddf) == len(df) assert compute(count(t), ddf) == len(df)