def test_selector(self):
index_weight = pd.MultiIndex.from_product([[dt(2014, 1, 30), dt(2014, 2, 28)], ['a', 'b', 'other']],
names=INDEX_INDUSTRY_WEIGHT.full_index)
industry_weight = pd.DataFrame([0.5, 0.4, 0.1, 0.5, 0.3, 0.2], index=index_weight)
index = pd.MultiIndex.from_product([['2014-01-30', '2014-02-28'], ['001', '002', '003', '004', '005']],
names=INDEX_FACTOR.full_index)
X = pd.DataFrame({'score': [2, 3, 3, 8, 4, 5, 9, 11, 2, 0],
'industry_code': ['a', 'a', 'a', 'b', 'b', 'a', 'a', 'other', 'b', 'b']},
index=index)
score = Factor(data=X['score'], name='score', property_dict={'type': FactorType.SCORE})
industry_code = Factor(data=X['industry_code'], name='industry_code',
property_dict={'type': FactorType.INDUSTY_CODE})
fc = FactorContainer(start_date='2014-01-30', end_date='2014-02-28')
fc.add_factor(score)
fc.add_factor(industry_code)
calculated = Selector(industry_weight=industry_weight,
method=SelectionMethod.INDUSTRY_NEUTRAL).fit(fc).predict(fc)
index_exp = pd.MultiIndex.from_arrays(
[[dt(2014, 1, 30), dt(2014, 1, 30), dt(2014, 1, 30), dt(2014, 1, 30), dt(2014, 2, 28), dt(2014, 2, 28),
dt(2014, 2, 28), dt(2014, 2, 28), dt(2014, 2, 28)],
['002', '003', '004', '005', '002', '001', '004', '005', '003']], names=['trade_date', 'ticker'])
expected = pd.DataFrame({'score': [3, 3, 8, 4, 9, 5, 2, 0, 11],
'industry_code': ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'other'],
'weight': [0.25, 0.25, 0.2, 0.2, 0.25, 0.25, 0.15, 0.15, 0.2]},
index=index_exp, dtype=object)
expected = expected[['score', 'industry_code', 'weight']]
assert_frame_equal(calculated, expected)
def test_imputer_2(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data = pd.DataFrame(index=index,
data=[1.0, 3.0, 3.0, np.nan, 5.0, 5.0, 6.0, 8.0])
factor_test = Factor(data=data, name='test1')
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
fi = FactorImputer(numerical_strategy=NAStrategy.MEAN)
calculated = fi.fit_transform(factor_test)
expected = pd.DataFrame(
{'test1': [1.0, 3.0, 3.0, 2.33333333333, 5.0, 5.0, 6.0, 8.0]},
index=index)
assert_frame_equal(calculated, expected)
fi.set_out_container(True)
calculated = fi.fit_transform(factor_test)
expected = FactorContainer(start_date='2014-01-30',
end_date='2014-02-28')
factor = Factor(data=pd.DataFrame(
{'test1': [1.0, 3.0, 3.0, 2.33333333333, 5.0, 5.0, 6.0, 8.0]},
index=index),
name='test1')
expected.add_factor(factor)
assert (isinstance(calculated, FactorContainer))
self.assertEqual(calculated.property, expected.property)
assert_frame_equal(calculated.data, expected.data)
def test_imputer_1(self):
index = pd.MultiIndex.from_product([['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 3.0, 3.0, np.nan, 5.0, 5.0, 6.0, 8.0])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(index=index, data=[3.0, 2.0, 3.0, 7.0, 7.0, np.nan, 6.0, 6.0])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(index=index, data=[3.0, 3.0, np.nan, 5.0, 6.0, 7.0, 6.0, 6.0])
factor_test3 = Factor(data=data3, name='test3')
fc = FactorContainer('2014-01-30', '2014-02-28', [factor_test1, factor_test2, factor_test3])
index = pd.MultiIndex.from_product([[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
calculated = FactorImputer(numerical_strategy=NAStrategy.MOST_FREQ).fit_transform(fc)
expected = pd.DataFrame({'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0]},
index=index)
assert_frame_equal(calculated, expected)
calculated = FactorImputer(numerical_strategy=NAStrategy.MEDIAN).fit_transform(fc)
expected = pd.DataFrame({'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0]},
index=index)
assert_frame_equal(calculated, expected)
industry = pd.DataFrame(index=index, data=['a', 'a', 'a', 'a', 'a', 'a', np.nan, 'a'])
factor_industry = Factor(data=industry, name='industry', property_dict={'type': FactorType.INDUSTY_CODE})
fc.add_factor(factor=factor_industry)
calculated = FactorImputer(numerical_strategy=NAStrategy.MEDIAN,
categorical_strategy=NAStrategy.CUSTOM,
custom_value='other').fit_transform(fc)
calculated.sort_index(axis=1, inplace=True)
expected = pd.DataFrame({'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0],
'industry': ['a', 'a', 'a', 'a', 'a', 'a', 'other', 'a']},
index=index,
dtype=object)
assert_frame_equal(calculated, expected)
def test_selector(self):
index_weight = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['a', 'b', 'other']],
names=INDEX_INDUSTRY_WEIGHT.full_index)
industry_weight = pd.DataFrame([0.5, 0.4, 0.1, 0.5, 0.3, 0.2],
index=index_weight)
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004', '005']
],
names=INDEX_FACTOR.full_index)
X = pd.DataFrame(
{
'score': [2, 3, 3, 8, 4, 5, 9, 11, 2, 0],
'industry_code':
['a', 'a', 'a', 'b', 'b', 'a', 'a', 'other', 'b', 'b']
},
index=index)
score = Factor(data=X['score'],
name='score',
property_dict={'type': FactorType.SCORE})
industry_code = Factor(data=X['industry_code'],
name='industry_code',
property_dict={'type': FactorType.INDUSTY_CODE})
fc = FactorContainer(start_date='2014-01-30', end_date='2014-02-28')
fc.add_factor(score)
fc.add_factor(industry_code)
calculated = Selector(
industry_weight=industry_weight,
method=SelectionMethod.INDUSTRY_NEUTRAL).fit(fc).predict(fc)
index_exp = pd.MultiIndex.from_arrays([[
dt(2014, 1, 30),
dt(2014, 1, 30),
dt(2014, 1, 30),
dt(2014, 1, 30),
dt(2014, 2, 28),
dt(2014, 2, 28),
dt(2014, 2, 28),
dt(2014, 2, 28),
dt(2014, 2, 28)
], ['002', '003', '004', '005', '002', '001', '004', '005', '003']],
names=['trade_date', 'ticker'])
expected = pd.DataFrame(
{
'score': [3, 3, 8, 4, 9, 5, 2, 0, 11],
'industry_code':
['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'other'],
'weight': [0.25, 0.25, 0.2, 0.2, 0.25, 0.25, 0.15, 0.15, 0.2]
},
index=index_exp,
dtype=object)
expected = expected[['score', 'industry_code', 'weight']]
assert_frame_equal(calculated, expected)
def test_imputer_2(self):
index = pd.MultiIndex.from_product([['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data = pd.DataFrame(index=index, data=[1.0, 3.0, 3.0, np.nan, 5.0, 5.0, 6.0, 8.0])
factor_test = Factor(data=data, name='test1')
index = pd.MultiIndex.from_product([[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
fi = FactorImputer(numerical_strategy=NAStrategy.MEAN)
calculated = fi.fit_transform(factor_test)
expected = pd.DataFrame({'test1': [1.0, 3.0, 3.0, 2.33333333333, 5.0, 5.0, 6.0, 8.0]}, index=index)
assert_frame_equal(calculated, expected)
fi.set_out_container(True)
calculated = fi.fit_transform(factor_test)
expected = FactorContainer(start_date='2014-01-30',
end_date='2014-02-28')
factor = Factor(data=pd.DataFrame({'test1': [1.0, 3.0, 3.0, 2.33333333333, 5.0, 5.0, 6.0, 8.0]}, index=index),
name='test1')
expected.add_factor(factor)
assert (isinstance(calculated, FactorContainer))
self.assertEqual(calculated.property, expected.property)
assert_frame_equal(calculated.data, expected.data)
def test_factor_simple_rank_1(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
factor_test = Factor(data=data1, name='alpha1')
fc = FactorContainer('2014-01-30', '2014-02-28', [factor_test])
t = FactorSimpleRank()
t.fit(fc)
calculate = t.transform(fc)['score']
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003']],
names=['trade_date', 'ticker'])
expected = pd.Series(index=index,
data=[0.0, 1.0, 2.0, 0.0, 1.0, 2.0],
name='score')
assert_series_equal(calculate, expected)
def setUp(self):
index = pd.MultiIndex.from_product([['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 1.0, 1.2, 2.0, 0.9, 5.0, 5.0, 5.1])
factor_test1 = Factor(data=data1, name='test1',
property_dict={'norm_type': FactorNormType.Industry_Cap_Neutral})
data2 = pd.DataFrame(index=index, data=[2.6, 2.5, 2.8, 2.9, 2.7, 1.9, 5.0, 2.1])
factor_test2 = Factor(data=data2, name='test2', property_dict={'type': FactorType.ALPHA_FACTOR_MV})
data3 = pd.DataFrame(index=index, data=['a', 'b', 'a', 'a', 'a', 'b', 'c', 'b'])
factor_test3 = Factor(data=data3, name='test3', property_dict={'type': FactorType.INDUSTY_CODE})
data4 = pd.DataFrame(index=index, data=[1.0, 1.0, 1.2, 2.0, 0.9, 5.0, 5.0, 5.1])
factor_test4 = Factor(data=data4, name='test4', property_dict={'norm_type': FactorNormType.Industry_Neutral})
fc = FactorContainer('2014-01-30', '2014-02-28', [factor_test1, factor_test2, factor_test3, factor_test4])
self.factor_container = fc
def test_factor_container_1(self):
index = pd.MultiIndex.from_product([['2014-01-30', '2014-02-28', '2014-03-31'], ['001', '002']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(index=index, data=[3.0, 2.0, 3.0, 7.0, 8.0, 9.0])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(index=index, data=[3.0, 4.0, 3.0, 5.0, 6.0, 7.0])
factor_test3 = Factor(data=data3, name='test3')
fc = FactorContainer('2014-01-30', '2014-02-28', [factor_test1, factor_test2])
index_exp = pd.MultiIndex.from_product([[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002']],
names=['trade_date', 'ticker'])
data_exp = pd.DataFrame({'test1': [1.0, 2.0, 3.0, 4.0], 'test2': [3.0, 2.0, 3.0, 7.0]}, index=index_exp)
assert_frame_equal(fc.data, data_exp)
fc.add_factor(factor_test3)
data_exp = pd.DataFrame({'test1': [1.0, 2.0, 3.0, 4.0], 'test2': [3.0, 2.0, 3.0, 7.0],
'test3': [3.0, 4.0, 3.0, 5.0]}, index=index_exp)
assert_frame_equal(fc.data, data_exp)
fc.remove_factor(factor_test2)
data_exp = pd.DataFrame({'test1': [1.0, 2.0, 3.0, 4.0], 'test3': [3.0, 4.0, 3.0, 5.0]}, index=index_exp)
assert_frame_equal(fc.data, data_exp)
property_exp = {'test1': {'type': FactorType.ALPHA_FACTOR,
'data_format': OutputDataFormat.MULTI_INDEX_DF,
'norm_type': FactorNormType.Null,
'freq': FreqType.EOM},
'test3': {'type': FactorType.ALPHA_FACTOR,
'data_format': OutputDataFormat.MULTI_INDEX_DF,
'norm_type': FactorNormType.Null,
'freq': FreqType.EOM}}
self.assertEqual(fc.property, property_exp)
fc.replace_data(np.array([[1.0, 2.0, 3.0, 4.0], [1.0, 2.0, 3.0, 5.0]]).T)
assert_frame_equal(fc.data,
pd.DataFrame({'test1': [1.0, 2.0, 3.0, 4.0], 'test3': [1.0, 2.0, 3.0, 5.0]},
index=index_exp))
self.assertEqual(list(fc.alpha_factor_col), ['test1', 'test3'])
def test_standardizer(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index,
data=[1.0, 1.0, 1.2, 200.0, 0.9, 5.0, 5.0, 5.1])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(index=index,
data=[2.6, 2.5, 2.8, 2.9, 2.7, 1.9, -10.0, 2.1])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(index=index,
data=['a', 'b', 'a', 'd', 'a', 'b', 'c', 'b'])
factor_test3 = Factor(data=data3,
name='test3',
property_dict={'type': FactorType.INDUSTY_CODE})
fc = FactorContainer('2014-01-30', '2014-02-28',
[factor_test1, factor_test2, factor_test3])
calculated = FactorStandardizer().fit_transform(fc)
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
expected = pd.DataFrame(
{
'test1': [
-0.578123937458, -0.578123937458, -0.575802154576,
1.73205002949, -1.73160039778, 0.558580773478,
0.558580773478, 0.614438850826
],
'test2': [
-0.632455532034, -1.26491106407, 0.632455532034,
1.26491106407, 0.664422038189, 0.513631221012,
-1.72938218451, 0.551328925306
],
'test3': ['a', 'b', 'a', 'd', 'a', 'b', 'c', 'b']
},
index=index,
dtype=object)
assert_frame_equal(calculated, expected)
def test_factor_winsorizer(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004', '005']
],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(
index=index,
data=[1.0, 1.0, 1.2, 200.0, 0.9, 5.0, 5.0, 5.1, 5.9, 5.0])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(
index=index,
data=[2.6, 2.5, 2.8, 2.9, 2.7, 1.9, -10.0, 2.1, 2.0, 1.9])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(
index=index,
data=[3.0, 3.0, 30.0, 5.0, 4.0, 6.0, 7.0, 6.0, 6.0, 5.9])
factor_test3 = Factor(data=data3, name='test3')
fc = FactorContainer('2014-01-30', '2014-02-28',
[factor_test1, factor_test2, factor_test3])
quantile_range = (1, 99)
calculated = FactorWinsorizer(quantile_range).fit_transform(fc)
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)],
['001', '002', '003', '004', '005']],
names=['trade_date', 'ticker'])
expected = pd.DataFrame(
{
'test1':
[1.0, 1.0, 1.2, 192.048, 0.904, 5.0, 5.0, 5.1, 5.868, 5.0],
'test2':
[2.6, 2.504, 2.8, 2.896, 2.7, 1.9, -9.524, 2.096, 2.0, 1.9],
'test3':
[3.0, 3.0, 29.0, 5.0, 4.0, 6.0, 6.96, 6.0, 6.0, 5.904]
},
index=index)
assert_frame_equal(calculated, expected)
def test_factor_ic(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28', '2014-03-31'], ['001', '002']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
factor_test1 = Factor(data=data1, name='alpha1')
factor_test3 = Factor(data=data1, name='alpha2')
test2_property = {
'type': FactorType.FWD_RETURN,
'data_format': OutputDataFormat.MULTI_INDEX_DF,
'norm_type': FactorNormType.Null,
'freq': FreqType.EOM
}
data2 = pd.DataFrame(index=index, data=[3.0, 2.0, 3.0, 7.0, 8.0, 9.0])
factor_test2 = Factor(data=data2,
name='fwd_return1',
property_dict=test2_property)
factor_test4 = Factor(data=data2,
name='fwd_return2',
property_dict=test2_property)
fc = FactorContainer(
'2014-01-30', '2014-02-28',
[factor_test1, factor_test2, factor_test3, factor_test4])
t = FactorIC()
calculate = t.predict(fc)
expected = pd.DataFrame(data=[[-1.0, -1.0, -1.0, -1.0],
[1.0, 1.0, 1.0, 1.0]],
index=pd.DatetimeIndex(
['2014-01-30', '2014-02-28'], freq=None),
columns=[
'alpha1_fwd_return1', 'alpha2_fwd_return1',
'alpha1_fwd_return2', 'alpha2_fwd_return2'
])
assert_frame_equal(calculate, expected)
def test_factor_container_1(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28', '2014-03-31'], ['001', '002']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index, data=[1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(index=index, data=[3.0, 2.0, 3.0, 7.0, 8.0, 9.0])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(index=index, data=[3.0, 4.0, 3.0, 5.0, 6.0, 7.0])
factor_test3 = Factor(data=data3, name='test3')
fc = FactorContainer('2014-01-30', '2014-02-28',
[factor_test1, factor_test2])
index_exp = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002']],
names=['trade_date', 'ticker'])
data_exp = pd.DataFrame(
{
'test1': [1.0, 2.0, 3.0, 4.0],
'test2': [3.0, 2.0, 3.0, 7.0]
},
index=index_exp)
assert_frame_equal(fc.data, data_exp)
fc.add_factor(factor_test3)
data_exp = pd.DataFrame(
{
'test1': [1.0, 2.0, 3.0, 4.0],
'test2': [3.0, 2.0, 3.0, 7.0],
'test3': [3.0, 4.0, 3.0, 5.0]
},
index=index_exp)
assert_frame_equal(fc.data, data_exp)
fc.remove_factor(factor_test2)
data_exp = pd.DataFrame(
{
'test1': [1.0, 2.0, 3.0, 4.0],
'test3': [3.0, 4.0, 3.0, 5.0]
},
index=index_exp)
assert_frame_equal(fc.data, data_exp)
property_exp = {
'test1': {
'type': FactorType.ALPHA_FACTOR,
'data_format': OutputDataFormat.MULTI_INDEX_DF,
'norm_type': FactorNormType.Null,
'freq': FreqType.EOM
},
'test3': {
'type': FactorType.ALPHA_FACTOR,
'data_format': OutputDataFormat.MULTI_INDEX_DF,
'norm_type': FactorNormType.Null,
'freq': FreqType.EOM
}
}
self.assertEqual(fc.property, property_exp)
fc.replace_data(
np.array([[1.0, 2.0, 3.0, 4.0], [1.0, 2.0, 3.0, 5.0]]).T)
assert_frame_equal(
fc.data,
pd.DataFrame(
{
'test1': [1.0, 2.0, 3.0, 4.0],
'test3': [1.0, 2.0, 3.0, 5.0]
},
index=index_exp))
self.assertEqual(list(fc.alpha_factor_col), ['test1', 'test3'])
def test_factor_neutralizer(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index,
data=[1.0, 1.0, 1.2, 2.0, 0.9, 5.0, 5.0, 5.1])
factor_test1 = Factor(
data=data1,
name='test1',
property_dict={'norm_type': FactorNormType.Industry_Cap_Neutral})
data2 = pd.DataFrame(index=index,
data=[2.6, 2.5, 2.8, 2.9, 2.7, 1.9, 5.0, 2.1])
factor_test2 = Factor(data=data2,
name='test2',
property_dict={
'type': FactorType.ALPHA_FACTOR_MV,
'norm_type': FactorNormType.Industry_Neutral
})
data3 = pd.DataFrame(index=index,
data=['a', 'b', 'a', 'a', 'a', 'b', 'c', 'b'])
factor_test3 = Factor(data=data3,
name='test3',
property_dict={'type': FactorType.INDUSTY_CODE})
data4 = pd.DataFrame(index=index,
data=[1.0, 1.0, 1.2, 2.0, 0.9, 5.0, 5.0, 5.1])
factor_test4 = Factor(
data=data4,
name='test4',
property_dict={'norm_type': FactorNormType.Industry_Neutral})
fc = FactorContainer(
'2014-01-30', '2014-02-28',
[factor_test1, factor_test2, factor_test3, factor_test4])
calculated = FactorNeutralizer().fit_transform(fc)
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
expected = pd.DataFrame(
{
'test1': [
0.0983574180639, 8.881784197e-16, -0.306074564019,
0.207717145955, -2.10942374679e-15, 8.881784197e-16,
-5.3290705182e-15, 0.0
],
'test2': [
-0.166666666667, 0.0, 0.0333333333333, 0.133333333333, 0.0,
-0.1, 0.0, 0.1
],
'test3': ['a', 'b', 'a', 'a', 'a', 'b', 'c', 'b'],
'test4': [-0.4, 0.0, -0.2, 0.6, 0.0, -0.05, 0.0, 0.05]
},
index=index,
dtype=object)
assert_frame_equal(calculated, expected)
calculated = FactorNeutralizer(out_container=True).fit_transform(fc)
assert_frame_equal(calculated.data, expected)
self.assertEqual(calculated.container_property, fc.container_property)
data_mv = factor_load('2014-01-01', '2014-03-10', 'MV', sec_id='fullA', is_index=True, save_file='mv.csv')
# data_pb = pd.read_csv('pb.csv', encoding='gbk')
# data_mv = pd.read_csv('mv.csv', encoding='gbk')
# data_pb['date'] = pd.to_datetime(data_pb['date'])
# data_mv['date'] = pd.to_datetime(data_mv['date'])
# data_pb.set_index(['date', ' ticker'], inplace=True)
# data_mv.set_index(['date', ' ticker'], inplace=True)
# 创建Factor实例，储存数据以及相关参数
factor_pb = Factor(data=data_pb, name='PB',
property_dict={'type': FactorType.ALPHA_FACTOR, 'norm_type': FactorNormType.Industry_Neutral})
factor_mv = Factor(data=data_mv, name='MV', property_dict={'type': FactorType.ALPHA_FACTOR_MV})
# 创建FactorContainer实例，加载所有的因子信息
fc = FactorContainer(start_date='2014-01-01', end_date='2014-03-10')
fc.add_factor(factor_pb)
fc.add_factor(factor_mv)
# 也可以一次性加载所有因子
# # fc = FactorContainer(start_date='2014-01-01', end_date='2014-03-10', factors=[factor_pb, factor_mv])
# print fc.tiaocang_date
# # [datetime.datetime(2014, 1, 30, 0, 0), datetime.datetime(2014, 2, 28, 0, 0)]
# print fc.alpha_factor_col
# # ['PB', 'MV']
# 提取行业数据
data_industry_code = factor_load('2014-01-01', '2014-03-10', 'SW_C1', sec_id='fullA', is_index=True, save_file='sw.csv')
# data_industry_code = pd.read_csv('sw.csv', encoding='gbk')
# data_pb.set_index(['date', ' ticker'], inplace=True)
# data_mv.set_index(['date', ' ticker'], inplace=True)
# 创建Factor实例，储存数据以及相关参数
factor_pb = Factor(data=data_pb,
name='PB',
property_dict={
'type': FactorType.ALPHA_FACTOR,
'norm_type': FactorNormType.Industry_Neutral
})
factor_mv = Factor(data=data_mv,
name='MV',
property_dict={'type': FactorType.ALPHA_FACTOR_MV})
# 创建FactorContainer实例，加载所有的因子信息
fc = FactorContainer(start_date='2014-01-01', end_date='2014-03-10')
fc.add_factor(factor_pb)
fc.add_factor(factor_mv)
# 也可以一次性加载所有因子
# # fc = FactorContainer(start_date='2014-01-01', end_date='2014-03-10', factors=[factor_pb, factor_mv])
# print fc.tiaocang_date
# # [datetime.datetime(2014, 1, 30, 0, 0), datetime.datetime(2014, 2, 28, 0, 0)]
# print fc.alpha_factor_col
# # ['PB', 'MV']
# 提取行业数据
data_industry_code = factor_load('2014-01-01',
'2014-03-10',
'SW_C1',
sec_id='fullA',
data_industry_code = load_factor_data_from_csv('sw.csv')
factor_industry_code = Factor(data=data_industry_code,
name='industry_code',
property_dict={'type': FactorType.INDUSTY_CODE})
# 加载月度收益数据
data_return = load_factor_data_from_csv('return.csv')
# 将数据改成未来1月收益
data_return = fwd_return(data_return)
factor_return = Factor(data=data_return,
name='1_Fwd_Return',
property_dict={'type': FactorType.FWD_RETURN, 'norm_type': FactorNormType.Industry_Neutral})
# 创建FactorContainer实例，加载所有的因子信息
fc = FactorContainer(start_date='2014-01-01',
end_date='2014-03-01',
factors=[factor_mv, factor_pb, factor_return, factor_industry_code])
# pipeline
# 第一步，处理极个别N/A, 有中位数替换
step_1 = ('imputer', FactorImputer(numerical_strategy=NAStrategy.MEDIAN,
categorical_strategy=NAStrategy.CUSTOM,
custom_value='other'))
# 第二部，去极值化
step_2 = ('winsorize', FactorWinsorizer(quantile_range=(5, 95)))
# 第三步，标准化
step_3 = ('std', FactorStandardizer())
# 第四步，中性化
step_4 = ('neutralize', FactorNeutralizer())
def test_imputer_1(self):
index = pd.MultiIndex.from_product(
[['2014-01-30', '2014-02-28'], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
data1 = pd.DataFrame(index=index,
data=[1.0, 3.0, 3.0, np.nan, 5.0, 5.0, 6.0, 8.0])
factor_test1 = Factor(data=data1, name='test1')
data2 = pd.DataFrame(index=index,
data=[3.0, 2.0, 3.0, 7.0, 7.0, np.nan, 6.0, 6.0])
factor_test2 = Factor(data=data2, name='test2')
data3 = pd.DataFrame(index=index,
data=[3.0, 3.0, np.nan, 5.0, 6.0, 7.0, 6.0, 6.0])
factor_test3 = Factor(data=data3, name='test3')
fc = FactorContainer('2014-01-30', '2014-02-28',
[factor_test1, factor_test2, factor_test3])
index = pd.MultiIndex.from_product(
[[dt(2014, 1, 30), dt(2014, 2, 28)], ['001', '002', '003', '004']],
names=['trade_date', 'ticker'])
calculated = FactorImputer(
numerical_strategy=NAStrategy.MOST_FREQ).fit_transform(fc)
expected = pd.DataFrame(
{
'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0]
},
index=index)
assert_frame_equal(calculated, expected)
calculated = FactorImputer(
numerical_strategy=NAStrategy.MEDIAN).fit_transform(fc)
expected = pd.DataFrame(
{
'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0]
},
index=index)
assert_frame_equal(calculated, expected)
industry = pd.DataFrame(
index=index, data=['a', 'a', 'a', 'a', 'a', 'a', np.nan, 'a'])
factor_industry = Factor(
data=industry,
name='industry',
property_dict={'type': FactorType.INDUSTY_CODE})
fc.add_factor(factor=factor_industry)
calculated = FactorImputer(numerical_strategy=NAStrategy.MEDIAN,
categorical_strategy=NAStrategy.CUSTOM,
custom_value='other').fit_transform(fc)
calculated.sort_index(axis=1, inplace=True)
expected = pd.DataFrame(
{
'test1': [1.0, 3.0, 3.0, 3.0, 5.0, 5.0, 6.0, 8.0],
'test2': [3.0, 2.0, 3.0, 7.0, 7.0, 6.0, 6.0, 6.0],
'test3': [3.0, 3.0, 3.0, 5.0, 6.0, 7.0, 6.0, 6.0],
'industry': ['a', 'a', 'a', 'a', 'a', 'a', 'other', 'a']
},
index=index,
dtype=object)
assert_frame_equal(calculated, expected)