def test_addColumnsForCycle_udf(self):
from ts.flint import udf
from pyspark.sql.types import DoubleType
from collections import OrderedDict
price2 = self.price2()
result1 = price2.addColumnsForCycle({
'rank':
udf(lambda v: v.rank(), DoubleType())(price2['price'])
}).toPandas()
expected1 = make_pdf([
(0, 1, 1.0, 1.0),
(0, 2, 2.0, 2.0),
(1, 1, 3.0, 1.0),
(1, 2, 4.0, 2.0),
(1, 3, 5.0, 3.0),
], ['time', 'id', 'price', 'rank'])
assert_same(result1, expected1)
result2 = price2.addColumnsForCycle(
OrderedDict([('rank', udf(lambda v: v.rank(),
DoubleType())(price2['price'])),
('pct_rank',
udf(lambda v: v.rank(pct=True),
DoubleType())(price2['price']))])).toPandas()
expected2 = make_pdf([
(0, 1, 1.0, 1.0, 0.5),
(0, 2, 2.0, 2.0, 1.0),
(1, 1, 3.0, 1.0, 0.333333),
(1, 2, 4.0, 2.0, 0.666667),
(1, 3, 5.0, 3.0, 1.0),
], ['time', 'id', 'price', 'rank', 'pct_rank'])
pdt.assert_frame_equal(result2, expected2)
@udf((DoubleType(), DoubleType()))
def rank(v):
return v.rank(), v.rank(pct=True)
result3 = price2.addColumnsForCycle({
('rank', 'pct_rank'):
rank(price2['price']),
}).toPandas()
expected3 = expected2
pdt.assert_frame_equal(result3, expected3)
def test_udf(self):
from ts.flint import udf
import pyspark.sql.functions as F
from pyspark.sql.types import LongType
vol = self.vol()
@udf(LongType())
def foo(v, w):
return v*2
result1 = vol.withColumn("volume", foo(vol['volume'], F.lit(42))).toPandas()
result2 = vol.withColumn("volume", udf(lambda v, w: v*2, LongType())(vol['volume'], F.lit(42))).toPandas()
expected_pdf1 = make_pdf([
(1000, 7, 200,),
(1000, 3, 400,),
(1050, 3, 600,),
(1050, 7, 800,),
(1100, 3, 1000,),
(1100, 7, 1200,),
(1150, 3, 1400,),
(1150, 7, 1600,),
(1200, 3, 1800,),
(1200, 7, 2000,),
(1250, 3, 2200,),
(1250, 7, 2400,)
], ['time', 'id', 'volume'])
assert_same(result1, expected_pdf1)
assert_same(result2, expected_pdf1)
def test_addColumnsForCycle_udf(self):
from ts.flint import udf
from pyspark.sql.types import DoubleType
from collections import OrderedDict
price2 = self.price2()
result1 = price2.addColumnsForCycle({
'rank': udf(lambda v: v.rank(), DoubleType())(price2['price'])
}).toPandas()
expected1 = make_pdf([
(0, 1, 1.0, 1.0),
(0, 2, 2.0, 2.0),
(1, 1, 3.0, 1.0),
(1, 2, 4.0, 2.0),
(1, 3, 5.0, 3.0),
], ['time', 'id', 'price', 'rank'])
assert_same(result1, expected1)
result2 = price2.addColumnsForCycle(OrderedDict([
('rank', udf(lambda v: v.rank(), DoubleType())(price2['price'])),
('pct_rank', udf(lambda v: v.rank(pct=True), DoubleType())(price2['price']))
])).toPandas()
expected2 = make_pdf([
(0, 1, 1.0, 1.0, 0.5),
(0, 2, 2.0, 2.0, 1.0),
(1, 1, 3.0, 1.0, 0.333333),
(1, 2, 4.0, 2.0, 0.666667),
(1, 3, 5.0, 3.0, 1.0),
], ['time', 'id', 'price', 'rank', 'pct_rank'])
pdt.assert_frame_equal(result2, expected2)
@udf((DoubleType(), DoubleType()))
def rank(v):
return v.rank(), v.rank(pct=True)
result3 = price2.addColumnsForCycle({
('rank', 'pct_rank'): rank(price2['price']),
}).toPandas()
expected3 = expected2
pdt.assert_frame_equal(result3, expected3)
def test_summarizeWindows_udf(self):
from ts.flint import udf
from ts.flint import windows
from collections import OrderedDict
from pyspark.sql.types import DoubleType, LongType
vol = self.vol()
w = windows.past_absolute_time('99s')
df = self.flintContext.read.pandas(
make_pdf([
(1000, 3, 10.0),
(1000, 7, 20.0),
(1050, 3, 30.0),
(1050, 7, 40.0),
(1100, 3, 50.0),
(1150, 3, 60.0),
(1150, 7, 70.0),
(1200, 3, 80.0),
(1200, 7, 90.0),
(1250, 7, 100.0),
], ['time', 'id', 'v']))
result1 = df.summarizeWindows(
w,
OrderedDict([('mean',
udf(lambda time, window: window.mean(),
DoubleType())(df['time'], vol['volume']))]),
key="id",
other=vol).toPandas()
expected1 = make_pdf([
(1000, 3, 10.0, 200.0),
(1000, 7, 20.0, 100.0),
(1050, 3, 30.0, 250.0),
(1050, 7, 40.0, 250.0),
(1100, 3, 50.0, 400.0),
(1150, 3, 60.0, 600.0),
(1150, 7, 70.0, 700.0),
(1200, 3, 80.0, 800.0),
(1200, 7, 90.0, 900.0),
(1250, 7, 100.0, 1100.0),
], ['time', 'id', 'v', 'mean'])
assert_same(result1, expected1)
result2 = df.summarizeWindows(w,
OrderedDict([
('mean',
udf(lambda window: window.mean(),
DoubleType())(vol['volume']))
]),
key='id',
other=vol).toPandas()
expected2 = expected1
assert_same(result2, expected2)
result3 = df.summarizeWindows(
w,
OrderedDict([
('mean', udf(lambda window: window.mean(),
DoubleType())(vol['volume'])),
('count', udf(lambda time, window: len(window),
LongType())(df['time'], vol['volume']))
]),
key='id',
other=vol).toPandas()
expected3 = make_pdf([
(1000, 3, 10.0, 200.0, 1),
(1000, 7, 20.0, 100.0, 1),
(1050, 3, 30.0, 250.0, 2),
(1050, 7, 40.0, 250.0, 2),
(1100, 3, 50.0, 400.0, 2),
(1150, 3, 60.0, 600.0, 2),
(1150, 7, 70.0, 700.0, 2),
(1200, 3, 80.0, 800.0, 2),
(1200, 7, 90.0, 900.0, 2),
(1250, 7, 100.0, 1100.0, 2),
], ['time', 'id', 'v', 'mean', 'count'])
assert_same(result3, expected3)
@udf('double')
def window_udf(time, window):
return (time - window.time).mean().seconds + window.volume.mean()
result4 = df.summarizeWindows(w,
OrderedDict([
('mean',
window_udf(df['time'],
vol[['time',
'volume']])),
]),
key='id',
other=vol).toPandas()
expected4 = make_pdf([
(1000, 3, 10.0, 200.0),
(1000, 7, 20.0, 100.0),
(1050, 3, 30.0, 275.0),
(1050, 7, 40.0, 275.0),
(1100, 3, 50.0, 425.0),
(1150, 3, 60.0, 625.0),
(1150, 7, 70.0, 725.0),
(1200, 3, 80.0, 825.0),
(1200, 7, 90.0, 925.0),
(1250, 7, 100.0, 1125.0),
], ['time', 'id', 'v', 'mean'])
assert_same(result4, expected4)
@udf(DoubleType())
def foo5(row, window):
return (row[0] - window.time).mean().seconds + window.volume.mean()
result5 = df.summarizeWindows(w,
OrderedDict([
('mean',
foo5(df[['time', 'v']],
vol[['time', 'volume']])),
]),
key='id',
other=vol).toPandas()
expected5 = expected4
assert_same(result5, expected5)
@udf((DoubleType(), LongType()))
def mean_and_count(v):
return v.mean(), len(v)
result6 = df.summarizeWindows(w,
OrderedDict([[
('mean', 'count'),
mean_and_count(vol['volume'])
]]),
key='id',
other=vol).toPandas()
expected6 = expected3
assert_same(result6, expected6)
@udf(DoubleType())
def mean(v):
return v.mean()
result7 = vol.summarizeWindows(w, {
'mean': mean(vol['volume'])
},
key='id').toPandas()
expected7 = make_pdf([
(1000, 7, 100, 100.0),
(1000, 3, 200, 200.0),
(1050, 3, 300, 250.0),
(1050, 7, 400, 250.0),
(1100, 3, 500, 400.0),
(1100, 7, 600, 500.0),
(1150, 3, 700, 600.0),
(1150, 7, 800, 700.0),
(1200, 3, 900, 800.0),
(1200, 7, 1000, 900.0),
(1250, 3, 1100, 1000.0),
(1250, 7, 1200, 1100.0),
], ['time', 'id', 'volume', 'mean'])
assert_same(result7, expected7)
result8 = vol.summarizeWindows(w, {
'mean': mean(vol['volume'])
}).toPandas()
expected8 = make_pdf([
(1000, 7, 100, 150.0),
(1000, 3, 200, 150.0),
(1050, 3, 300, 250.0),
(1050, 7, 400, 250.0),
(1100, 3, 500, 450.0),
(1100, 7, 600, 450.0),
(1150, 3, 700, 650.0),
(1150, 7, 800, 650.0),
(1200, 3, 900, 850.0),
(1200, 7, 1000, 850.0),
(1250, 3, 1100, 1050.0),
(1250, 7, 1200, 1050.0),
], ['time', 'id', 'volume', 'mean'])
assert_same(result8, expected8)
def test_summarizeIntervals_udf(self):
from ts.flint.functions import udf
from pyspark.sql.types import LongType, DoubleType
vol = self.vol()
clock = self.flintContext.read.pandas(
make_pdf([
(1000, ),
(1100, ),
(1200, ),
(1300, ),
], ["time"]))
result1 = vol.summarizeIntervals(
clock, {
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)
}).toPandas()
expected1 = make_pdf([
(1100, 1000),
(1200, 2600),
(1300, 4200),
], ["time", "sum"])
assert_same(result1, expected1)
result2 = vol.summarizeIntervals(
clock, {
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)
},
key="id").toPandas()
expected2 = make_pdf([
(1100, 7, 500),
(1100, 3, 500),
(1200, 3, 1200),
(1200, 7, 1400),
(1300, 3, 2000),
(1300, 7, 2200),
], ["time", "id", "sum"])
assert_same(result2, expected2)
result3 = vol.summarizeIntervals(
clock, {
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)
},
rounding="begin").toPandas()
expected3 = make_pdf([
(1000, 1000),
(1100, 2600),
(1200, 4200),
], ["time", "sum"])
assert_same(result3, expected3)
result4 = vol.summarizeIntervals(
clock, {
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)
},
inclusion="end").toPandas()
expected4 = make_pdf([
(1100, 1800),
(1200, 3400),
(1300, 2300),
], ["time", "sum"])
assert_same(result4, expected4)
result5 = vol.summarizeIntervals(
clock, {
'mean': udf(lambda v: v.mean(), DoubleType())(vol.volume),
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)
}).toPandas()
expected5 = make_pdf([
(1100, 250.0, 1000),
(1200, 650.0, 2600),
(1300, 1050.0, 4200),
], ["time", "mean", "sum"])
assert_same(result5, expected5)
@udf((DoubleType(), LongType()))
def mean_and_sum(v):
return v.mean(), v.sum()
result6 = vol.summarizeIntervals(
clock, {
('mean', 'sum'): mean_and_sum(vol.volume)
}).toPandas()
expected6 = make_pdf([
(1100, 250.0, 1000),
(1200, 650.0, 2600),
(1300, 1050.0, 4200),
], ["time", "mean", "sum"])
assert_same(result6, expected6)
from pyspark.sql.functions import lit
vol_with_weights = vol.withColumn('w', lit(1.0))
result7 = vol_with_weights.summarizeIntervals(
clock,
{'weighted_mean': udf(lambda df: np.average(df.volume, weights=df.w), DoubleType()) \
(vol_with_weights[['volume', 'w']]) }
).toPandas()
expected7 = make_pdf([
(1100, 250.0),
(1200, 650.0),
(1300, 1050.0),
], ["time", "weighted_mean"])
assert_same(result7, expected7)
def test_udf(self):
from ts.flint import udf
import pyspark.sql.functions as F
from pyspark.sql.types import LongType
vol = self.vol()
@udf(LongType())
def foo(v, w):
return v * 2
result1 = vol.withColumn("volume", foo(vol['volume'],
F.lit(42))).toPandas()
result2 = vol.withColumn(
"volume",
udf(lambda v, w: v * 2, LongType())(vol['volume'],
F.lit(42))).toPandas()
expected_pdf1 = make_pdf([(
1000,
7,
200,
), (
1000,
3,
400,
), (
1050,
3,
600,
), (
1050,
7,
800,
), (
1100,
3,
1000,
), (
1100,
7,
1200,
), (
1150,
3,
1400,
), (
1150,
7,
1600,
), (
1200,
3,
1800,
), (
1200,
7,
2000,
), (
1250,
3,
2200,
), (
1250,
7,
2400,
)], ['time', 'id', 'volume'])
assert_same(result1, expected_pdf1)
assert_same(result2, expected_pdf1)
def test_summarizeCycles_udf(self):
from ts.flint import udf
from pyspark.sql.types import DoubleType, LongType
from collections import OrderedDict
import pyspark.sql.functions as F
vol = self.vol()
weighted_vol = vol.withColumn('weight', F.lit(1))
result1 = vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda v: v.mean(),
DoubleType())(weighted_vol.volume)),
('sum', udf(lambda v: v.sum(),
LongType())(weighted_vol.volume)),
])).toPandas()
result2 = vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda df: df.volume.mean(),
DoubleType())(weighted_vol[['volume']])),
('sum', udf(lambda df: df.volume.sum(),
LongType())(weighted_vol[['volume']])),
])).toPandas()
result3 = weighted_vol.summarizeCycles(
OrderedDict([
('mean',
udf(lambda v, w: np.average(v, weights=w),
DoubleType())(weighted_vol['volume'],
weighted_vol['weight'])),
('sum', udf(lambda v, w: (v * w).sum(),
LongType())(weighted_vol['volume'],
weighted_vol['weight'])),
])).toPandas()
result4 = weighted_vol.summarizeCycles(
OrderedDict([
('mean',
udf(lambda df: np.average(df.volume, weights=df.weight),
DoubleType())(weighted_vol[['volume', 'weight']])),
('sum',
udf(lambda df: (df.volume * df.weight).sum(),
LongType())(weighted_vol[['volume', 'weight']])),
])).toPandas()
@udf(DoubleType())
def foo(v, w):
return np.average(v, weights=w)
@udf(LongType())
def bar(v, w):
return (v * w).sum()
result5 = weighted_vol.summarizeCycles(
OrderedDict([
('mean', foo(weighted_vol['volume'], weighted_vol['weight'])),
('sum', bar(weighted_vol['volume'], weighted_vol['weight']))
])).toPandas()
@udf(DoubleType())
def foo1(df):
return np.average(df.volume, weights=df.weight)
@udf(LongType())
def bar1(df):
return (df.volume * df.weight).sum()
result6 = weighted_vol.summarizeCycles(
OrderedDict([('mean', foo1(weighted_vol[['volume', 'weight']])),
('sum', bar1(weighted_vol[['volume',
'weight']]))])).toPandas()
expected_pdf1 = make_pdf([
(
1000,
150.0,
300,
),
(
1050,
350.0,
700,
),
(
1100,
550.0,
1100,
),
(
1150,
750.0,
1500,
),
(
1200,
950.0,
1900,
),
(
1250,
1150.0,
2300,
),
], ["time", "mean", "sum"])
@udf((DoubleType(), LongType()))
def foobar(v, w):
foo = np.average(v, weights=w)
bar = (v * w).sum()
return (foo, bar)
result7 = weighted_vol.summarizeCycles({
('mean', 'sum'):
foobar(weighted_vol['volume'], weighted_vol['weight'])
}).toPandas()
result8 = weighted_vol.summarizeCycles({
"mean":
udf(lambda v: v.mean(), DoubleType())(weighted_vol['volume']),
"sum":
udf(lambda v: v.sum(), LongType())(weighted_vol['volume'])
}).toPandas()
assert_same(result1, expected_pdf1)
assert_same(result2, expected_pdf1)
assert_same(result3, expected_pdf1)
assert_same(result4, expected_pdf1)
assert_same(result5, expected_pdf1)
assert_same(result6, expected_pdf1)
assert_same(result7, expected_pdf1)
assert_same(result8, expected_pdf1)
def test_summarizeIntervals_udf(self):
from ts.flint.functions import udf
from pyspark.sql.types import LongType, DoubleType
vol = self.vol()
clock = self.flintContext.read.pandas(make_pdf([
(1000,),
(1100,),
(1200,),
(1300,),
], ["time"]))
result1 = vol.summarizeIntervals(
clock,
{'sum': udf(lambda v: v.sum(), LongType())(vol.volume)}
).toPandas()
expected1 = make_pdf([
(1100, 1000),
(1200, 2600),
(1300, 4200),
], ["time", "sum"])
assert_same(result1, expected1)
result2 = vol.summarizeIntervals(
clock,
{'sum': udf(lambda v: v.sum(), LongType())(vol.volume)},
key="id"
).toPandas()
expected2 = make_pdf([
(1100, 7, 500),
(1100, 3, 500),
(1200, 3, 1200),
(1200, 7, 1400),
(1300, 3, 2000),
(1300, 7, 2200),
], ["time", "id", "sum"])
assert_same(result2, expected2)
result3 = vol.summarizeIntervals(
clock,
{'sum': udf(lambda v: v.sum(), LongType())(vol.volume)},
rounding="begin"
).toPandas()
expected3 = make_pdf([
(1000, 1000),
(1100, 2600),
(1200, 4200),
], ["time", "sum"])
assert_same(result3, expected3)
result4 = vol.summarizeIntervals(
clock,
{'sum': udf(lambda v: v.sum(), LongType())(vol.volume)},
inclusion="end"
).toPandas()
expected4 = make_pdf([
(1100, 1800),
(1200, 3400),
(1300, 2300),
], ["time", "sum"])
assert_same(result4, expected4)
result5 = vol.summarizeIntervals(
clock,
{'mean': udf(lambda v: v.mean(), DoubleType())(vol.volume),
'sum': udf(lambda v: v.sum(), LongType())(vol.volume)}
).toPandas()
expected5 = make_pdf([
(1100, 250.0, 1000),
(1200, 650.0, 2600),
(1300, 1050.0, 4200),
], ["time", "mean", "sum"])
assert_same(result5, expected5)
@udf((DoubleType(), LongType()))
def mean_and_sum(v):
return v.mean(), v.sum()
result6 = vol.summarizeIntervals(
clock,
{('mean', 'sum'): mean_and_sum(vol.volume) }
).toPandas()
expected6 = make_pdf([
(1100, 250.0, 1000),
(1200, 650.0, 2600),
(1300, 1050.0, 4200),
], ["time", "mean", "sum"])
assert_same(result6, expected6)
from pyspark.sql.functions import lit
vol_with_weights = vol.withColumn('w', lit(1.0))
result7 = vol_with_weights.summarizeIntervals(
clock,
{'weighted_mean': udf(lambda df: np.average(df.volume, weights=df.w), DoubleType()) \
(vol_with_weights[['volume', 'w']]) }
).toPandas()
expected7 = make_pdf([
(1100, 250.0),
(1200, 650.0),
(1300, 1050.0),
], ["time", "weighted_mean"])
assert_same(result7, expected7)
def test_summarizeCycles_udf(self):
from ts.flint import udf
from pyspark.sql.types import DoubleType, LongType
from collections import OrderedDict
import pyspark.sql.functions as F
vol = self.vol()
weighted_vol = vol.withColumn('weight', F.lit(1))
result1 = vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda v: v.mean(), DoubleType())(weighted_vol.volume)),
('sum', udf(lambda v: v.sum(), LongType())(weighted_vol.volume)),
])
).toPandas()
result2 = vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda df: df.volume.mean(), DoubleType())(weighted_vol[['volume']])),
('sum', udf(lambda df: df.volume.sum(), LongType())(weighted_vol[['volume']])),
])
).toPandas()
result3 = weighted_vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda v, w: np.average(v, weights=w), DoubleType())(weighted_vol['volume'],
weighted_vol['weight'])),
('sum', udf(lambda v, w: (v * w).sum(), LongType())(weighted_vol['volume'], weighted_vol['weight'])),
])
).toPandas()
result4 = weighted_vol.summarizeCycles(
OrderedDict([
('mean', udf(lambda df: np.average(df.volume, weights=df.weight), DoubleType())(
weighted_vol[['volume', 'weight']])),
('sum', udf(lambda df: (df.volume * df.weight).sum(), LongType())(weighted_vol[['volume', 'weight']])),
])
).toPandas()
@udf(DoubleType())
def foo(v, w):
return np.average(v, weights=w)
@udf(LongType())
def bar(v, w):
return (v * w).sum()
result5 = weighted_vol.summarizeCycles(
OrderedDict([
('mean', foo(weighted_vol['volume'], weighted_vol['weight'])),
('sum', bar(weighted_vol['volume'], weighted_vol['weight']))
])
).toPandas()
@udf(DoubleType())
def foo1(df):
return np.average(df.volume, weights=df.weight)
@udf(LongType())
def bar1(df):
return (df.volume * df.weight).sum()
result6 = weighted_vol.summarizeCycles(
OrderedDict([
('mean', foo1(weighted_vol[['volume', 'weight']])),
('sum', bar1(weighted_vol[['volume', 'weight']]))
])
).toPandas()
expected_pdf1 = make_pdf([
(1000, 150.0, 300,),
(1050, 350.0, 700,),
(1100, 550.0, 1100,),
(1150, 750.0, 1500,),
(1200, 950.0, 1900,),
(1250, 1150.0, 2300,),
], ["time", "mean", "sum"])
@udf((DoubleType(), LongType()))
def foobar(v, w):
foo = np.average(v, weights=w)
bar = (v * w).sum()
return (foo, bar)
result7 = weighted_vol.summarizeCycles(
{('mean', 'sum'): foobar(weighted_vol['volume'], weighted_vol['weight'])}
).toPandas()
result8 = weighted_vol.summarizeCycles({
"mean": udf(lambda v: v.mean(), DoubleType())(weighted_vol['volume']),
"sum": udf(lambda v: v.sum(), LongType())(weighted_vol['volume'])
}).toPandas()
assert_same(result1, expected_pdf1)
assert_same(result2, expected_pdf1)
assert_same(result3, expected_pdf1)
assert_same(result4, expected_pdf1)
assert_same(result5, expected_pdf1)
assert_same(result6, expected_pdf1)
assert_same(result7, expected_pdf1)
assert_same(result8, expected_pdf1)
