def test_fit_execute_multi_target(self, data_loader):
f1, target, model = self._create_base_components()
target1 = QuarterlyTarget(col='marketcap', quarter_shift=-1)
pipeline = BasePipeline(feature=f1,
target=[target, target1],
model=model,
metric=median_absolute_relative_error,
out_name=None)
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_y_0'] > 0
assert res['metric_y_1'] > 0
df = pipeline.execute(data_loader, tickers)
assert type(df) == pd.DataFrame
assert df['y_0'].mean() > 0
assert df['y_1'].mean() > 0
assert (df['y_0'] == df['y_1']).min() == False
pipeline = BasePipeline(feature=f1,
target=[target, target],
model=model,
metric=median_absolute_relative_error,
out_name=None)
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_y_0'] > 0
assert res['metric_y_1'] > 0
df = pipeline.execute(data_loader, tickers)
assert (df['y_0'] == df['y_1']).min() == True
def test_execute_simple(self, data_loader):
columns = ['revenue', 'netinc', 'ncf', 'ebitda', 'debt', 'fcf']
f1 = QuarterlyFeatures(columns=columns,
quarter_counts=[2, 10],
max_back_quarter=1)
target1 = QuarterlyTarget(col='marketcap', quarter_shift=0)
target2 = QuarterlyTarget(col='marketcap', quarter_shift=-1)
model = lgbm.sklearn.LGBMRegressor()
pipeline1 = BasePipeline(feature=f1,
target=target1,
model=model,
metric=median_absolute_relative_error,
out_name='p1')
pipeline2 = BasePipeline(feature=f1,
target=target2,
model=model,
metric=median_absolute_relative_error,
out_name='p2')
pipeline3 = QuarterlyLoadPipeline(['ticker', 'date', 'marketcap'])
pipeline1.fit(data_loader, tickers)
pipeline2.fit(data_loader, tickers)
merge1 = ExecuteMergePipeline(
pipeline_list=[pipeline1, pipeline2, pipeline3],
on=['ticker', 'date'])
df1 = pipeline1.execute(data_loader, tickers)
df2 = pipeline2.execute(data_loader, tickers)
df3 = pipeline3.execute(data_loader, tickers)
df = merge1.execute(data_loader, tickers)
assert type(df) == pd.DataFrame
assert len(df) == len(df1)
np.testing.assert_array_equal(
df.columns, ['ticker', 'date', 'p1', 'p2', 'marketcap'])
np.testing.assert_array_equal(df1['p1'], df['p1'])
np.testing.assert_array_equal(df2['p2'], df['p2'])
def test_fit_execute_simple(self, data_loader):
f1, target, model = self._create_base_components()
pipeline = BasePipeline(feature=f1,
target=target,
model=model,
metric=median_absolute_relative_error,
out_name=None)
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_y_0'] > 0
df = pipeline.execute(data_loader, tickers)
assert type(df) == pd.DataFrame
assert df['y_0'].mean() > 0
def test_export_load(self, data_loader, tmpdir):
f1, target, model = self._create_base_components()
pipeline = BasePipeline(feature=f1,
target=target,
model=model,
metric=median_absolute_relative_error,
out_name=None)
res = pipeline.fit(data_loader, tickers)
df = pipeline.execute(data_loader, tickers)
pipeline.export_core('{}/pipeline'.format(str(tmpdir)))
pipeline = BasePipeline.load('{}/pipeline.pickle'.format(str(tmpdir)))
df1 = pipeline.execute(data_loader, tickers[:100])
np.testing.assert_array_equal(df['y_0'].values, df1['y_0'].values)
def test_fit_execute_multi_names(self, data_loader):
f1, target, model = self._create_base_components()
pipeline = BasePipeline(feature=f1,
target=[target, target],
model=model,
metric=median_absolute_relative_error,
out_name=['name1', 'name2'])
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_name1'] > 0
assert res['metric_name2'] > 0
df = pipeline.execute(data_loader, tickers)
assert type(df) == pd.DataFrame
assert df['name1'].mean() > 0
assert df['name2'].mean() > 0
assert (df['name1'] == df['name2']).min() == True
def test_fit_execute_multi_target_metric(self, data_loader):
f1, target, model = self._create_base_components()
target1 = QuarterlyTarget(col='marketcap', quarter_shift=-1)
pipeline = BasePipeline(feature=f1,
target=[target, target1],
model=model,
metric=[
median_absolute_relative_error,
mean_absolute_relative_error
],
out_name=None)
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_y_0'] > 0
assert res['metric_y_1'] > 0
assert res['metric_y_0'] < res['metric_y_1']
def test_fit_execute_multi_target_model(self, data_loader):
f1, target, model = self._create_base_components()
target1 = QuarterlyTarget(col='marketcap', quarter_shift=-1)
model1 = GroupedOOFModel(ctb.CatBoostRegressor(verbose=False),
group_column='ticker',
fold_cnt=4)
pipeline = BasePipeline(feature=f1,
target=[target, target],
model=[model, model1],
metric=median_absolute_relative_error,
out_name=None)
res = pipeline.fit(data_loader, tickers)
assert type(res) == dict
assert res['metric_y_0'] > 0
assert res['metric_y_1'] > 0
df = pipeline.execute(data_loader, tickers)
assert type(df) == pd.DataFrame
assert df['y_0'].mean() > 0
assert df['y_1'].mean() > 0
assert (df['y_0'] == df['y_1']).min() == False
agg_day_counts=pipeline_config['agg_day_counts'],
max_back_quarter=pipeline_config['max_back_quarter'])
feature = FeatureMerger(fc1, fc2, on='ticker')
feature = FeatureMerger(feature, fc3, on=['ticker', 'date'])
feature = FeatureMerger(feature, fc4, on=['ticker', 'date'])
target = DailyAggTarget(col='marketcap',
horizon=pipeline_config['target_horizon'],
foo=down_std_norm)
base_models = [
lgbm.sklearn.LGBMRegressor(),
ctb.CatBoostRegressor(verbose=False)
]
ansamble = AnsambleModel(base_models=base_models,
bagging_fraction=0.7,
model_cnt=20)
model = TimeSeriesOOFModel(ansamble, time_column='date', fold_cnt=20)
pipeline = BasePipeline(feature=feature,
target=target,
model=model,
metric=median_absolute_relative_error)
result = pipeline.fit(data_loader, ticker_list)
print(result)
pipeline.export_core('models_data/marketcap_down_std')
fc2 = BaseCompanyFeatures(cat_columns=pipeline_config['cat_columns'])
fc3 = QuarterlyDiffFeatures(
columns=pipeline_config['quarter_columns'],
compare_quarter_idxs=pipeline_config['compare_quarter_idxs'],
max_back_quarter=pipeline_config['max_back_quarter'])
feature = FeatureMerger(fc1, fc2, on='ticker')
feature = FeatureMerger(feature, fc3, on=['ticker', 'date'])
target = QuarterlyDiffTarget(col='marketcap')
base_models = [
lgbm.sklearn.LGBMRegressor(),
ctb.CatBoostRegressor(verbose=False)
]
ansamble = AnsambleModel(base_models=base_models,
bagging_fraction=0.7,
model_cnt=20)
model = GroupedOOFModel(ansamble, group_column='ticker', fold_cnt=5)
pipeline = BasePipeline(feature=feature,
target=target,
model=model,
metric=median_absolute_relative_error)
pipeline.fit(data_loader, ticker_list)
pipeline.export_core('models_data/marketcap_diff')