def test_answerPrototype6(self):
# AnswerType.SIX
dataset = cfdg.ohlcv().reset_index()
exp = datetime.utcfromtimestamp(
dataset[-1:]['index'].values[0].astype(datetime) / 1000000000)
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=datetime.now() +
timedelta(minutes=1),
prize=1.0,
dataset=dataset.iloc[:-1],
metric=CompetitionMetric.ABSDIFF,
targets=dataset.columns[-1],
answer=dataset.iloc[-1:],
dataset_key='index',
when=exp)
df = answerPrototype(competition)[['when', dataset.columns[-1]]]
ans = pd.DataFrame([{
'when': exp,
dataset.columns[-1]: np.nan
} for x in dataset['index'].iloc[:-1]],
index=[x for x in dataset['index'].iloc[:-1]
])[['when', dataset.columns[-1]]]
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype62(self):
# AnswerType.SIX
exp = datetime.now() + timedelta(minutes=2)
competition = CompetitionSpec(
title='',
type=CompetitionType.PREDICT,
when=exp,
prize=1.0,
dataset='https://feeds.citibikenyc.com/stations/stations.json',
dataset_type=DatasetFormat.JSON,
dataset_key='id',
dataset_kwargs={'record_column': 'stationBeanList'},
metric=CompetitionMetric.ABSDIFF,
targets=['availableBikes', 'availableDocks'],
expiration=exp)
dataset = fetchDataset(competition)
df = answerPrototype(competition)[[
'when', 'availableBikes', 'availableDocks'
]]
ans = pd.DataFrame([{
'when': exp,
'availableBikes': np.nan,
'availableDocks': np.nan
} for x in dataset.id],
index=[id for id in dataset.id])[[
'when', 'availableBikes', 'availableDocks'
]]
print(df)
print(ans)
assert df.equals(ans)
def answerPredict1(competitionSpec, *args, **kwargs):
from crowdsource.types.utils import answerPrototype, fetchDataset
from sklearn import linear_model
data = fetchDataset(competitionSpec)
ans = answerPrototype(competitionSpec, data)
when = competitionSpec.when
if not when or competitionSpec.dataset_key:
''' TS prediction'''
return
for col in ans.columns:
if col == competitionSpec.dataset_key:
continue
reg = linear_model.LinearRegression()
x = data[col].index.astype(int).values.reshape(len(data[col].index), 1)
y = data[col].values.reshape(len(data[col]), 1)
reg.fit(x, y)
ans.loc[when, col] = reg.predict([[
when.timestamp() if hasattr(when, 'timestamp') else float(
(time.mktime(when.timetuple()) + when.microsecond / 1000000.0))
]])
return ans
def answerPredictCitibike(competitionSpec, *args, **kwargs):
from random import randint
from crowdsource.types.utils import answerPrototype, fetchDataset
dataset = fetchDataset(competitionSpec)
answer = answerPrototype(competitionSpec, dataset)
when = competitionSpec.when
if not when or not competitionSpec.dataset_key:
"""TS prediction"""
return
for i in answer.index:
for col in answer.columns:
if col == "when":
continue
ran = randint(0, 10)
answer.loc[i, col] = (
dataset[dataset[competitionSpec.dataset_key] == i][col].iloc[0]
+ ran)
return answer
def test_answerPrototype62(self):
# AnswerType.SIX
exp = datetime.now() + timedelta(minutes=2)
competition = CompetitionSpec(
title="",
type=CompetitionType.PREDICT,
when=exp,
prize=1.0,
dataset="https://feeds.citibikenyc.com/stations/stations.json",
dataset_type=DatasetFormat.JSON,
dataset_key="id",
dataset_kwargs={"record_column": "stationBeanList"},
metric=CompetitionMetric.ABSDIFF,
targets=["availableBikes", "availableDocks"],
expiration=exp,
)
dataset = fetchDataset(competition)
df = answerPrototype(competition)[["when", "availableBikes", "availableDocks"]]
ans = pd.DataFrame(
[
{"when": exp, "availableBikes": np.nan, "availableDocks": np.nan}
for x in dataset.id
],
index=[id for id in dataset.id],
)[["when", "availableBikes", "availableDocks"]]
print(df)
print(ans)
assert df.equals(ans)
def foo5(competitionSpec, *args, **kwargs):
if isinstance(competitionSpec.dataset, six.string_types):
dataset = fetchDataset(competitionSpec)
else:
return
answer = answerPrototype(competitionSpec, dataset)
return answer.fillna(0)
def test_answerPrototype5(self):
# AnswerType.FIVE
exp = datetime.now() + timedelta(minutes=2)
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=exp,
prize=1.0,
dataset='http://bonds.paine.nyc',
dataset_type=DatasetFormat.JSON,
metric=CompetitionMetric.ABSDIFF,
targets={0: ['Price']})
df = answerPrototype(competition)
ans = pd.DataFrame([{'Price': np.nan}])
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype1(self):
# AnswerType.ONE
dataset = make_classification()
competition = CompetitionSpec(title='',
type=CompetitionType.CLASSIFY,
expiration=datetime.now() +
timedelta(minutes=1),
prize=1.0,
num_classes=2,
dataset=pd.DataFrame(dataset[0]),
metric=CompetitionMetric.LOGLOSS,
answer=pd.DataFrame(dataset[1]))
dataset = fetchDataset(competition)
df = answerPrototype(competition)
ans = pd.DataFrame([{'class': np.nan} for x in dataset.index])
print(df)
print(ans)
assert df.equals(ans)
def answerPredictCorporateBonds(competitionSpec, *args, **kwargs):
from random import normalvariate
from crowdsource.types.utils import answerPrototype, fetchDataset
dataset = fetchDataset(competitionSpec)
answer = answerPrototype(competitionSpec, dataset)
if competitionSpec.when or not competitionSpec.dataset_key:
'''next val prediction'''
return
for i in answer.index:
for col in answer.columns:
if col == competitionSpec.dataset_key:
continue
ran = normalvariate(0, 5.0)
answer.loc[i, col] = dataset.loc[i, col] + ran
return answer
def test_answerPrototype9(self):
# AnswerType.NINE
dataset = cfdg.ohlcv()
competition = CompetitionSpec(
title="",
type=CompetitionType.PREDICT,
expiration=datetime.now() + timedelta(minutes=1),
prize=1.0,
dataset=dataset.iloc[:-1],
metric=CompetitionMetric.ABSDIFF,
targets=dataset.columns[-1],
answer=dataset.iloc[-1:],
)
df = answerPrototype(competition)
ans = pd.DataFrame([{dataset.columns[-1]: np.nan} for x in dataset.index])
ans = pd.DataFrame([{dataset.columns[-1]: np.nan}])
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype8(self):
# AnswerType.EIGHT
dataset = cfdg.ohlcv()
exp = datetime.utcfromtimestamp(
dataset[-1:].index.values[0].astype(datetime) / 1000000000)
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=datetime.now() +
timedelta(minutes=1),
prize=1.0,
dataset=dataset.iloc[:-1],
metric=CompetitionMetric.ABSDIFF,
targets=dataset.columns[-1],
answer=dataset.iloc[-1:],
when=exp)
df = answerPrototype(competition)
ans = pd.DataFrame([{dataset.columns[-1]: np.nan}], index=[exp])
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype7(self):
# AnswerType.SEVEN
dataset = cfdg.ohlcv().reset_index()
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=datetime.now() +
timedelta(minutes=1),
prize=1.0,
dataset=dataset.iloc[:-1],
metric=CompetitionMetric.ABSDIFF,
targets=dataset.columns[-1],
dataset_key='index',
answer=dataset.iloc[-1:])
df = answerPrototype(competition)
ans = pd.DataFrame([{
dataset.columns[-1]: np.nan
} for x in dataset['index'].iloc[:-1]],
index=dataset['index'].iloc[:-1])
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype2(self):
# AnswerType.TWO
exp = datetime.now() + timedelta(minutes=2)
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=exp,
when=exp,
prize=1.0,
dataset='http://bonds.paine.nyc',
dataset_type=DatasetFormat.JSON,
metric=CompetitionMetric.ABSDIFF,
dataset_key='Name',
targets={'ABC Corp': ['Price']})
df = answerPrototype(competition)[['Price', 'when']]
ans = pd.DataFrame([{
'when': exp,
'Price': np.nan
}],
index=['ABC Corp'])[['Price', 'when']]
print(df)
print(ans)
assert df.equals(ans)
def test_answerPrototype3(self):
# AnswerType.THREE
competition = CompetitionSpec(title='',
type=CompetitionType.PREDICT,
expiration=datetime.now() +
timedelta(minutes=1),
prize=1.0,
dataset='http://bonds.paine.nyc',
dataset_type=DatasetFormat.JSON,
metric=CompetitionMetric.ABSDIFF,
dataset_key='Name',
targets={'ABC Corp': ['Price']})
dataset = fetchDataset(competition)
df = answerPrototype(competition, dataset)
index = dataset[dataset['Name'] == 'ABC Corp'].index
ans = pd.DataFrame([{
'Name': 'ABC Corp',
'Price': np.nan
} for _ in index],
index=index)
print(df)
print(ans)
assert df.equals(ans)
