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)
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')
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'])
target = QuarterlyTarget(col='marketcap', quarter_shift=0)
base_models = [LogExpModel(lgbm.sklearn.LGBMRegressor()),
LogExpModel(ctb.CatBoostRegressor(verbose=False))]
ansamble = AnsambleModel(
base_models=base_models,
bagging_fraction=pipeline_config['bagging_fraction'],
model_cnt=pipeline_config['model_cnt'])
model = GroupedOOFModel(ansamble, group_column='ticker', fold_cnt=5)
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')
# normalized and there are no leakage.
fc3 = DailyAggQuarterFeatures(columns=DAILY_AGG_COLUMNS,
agg_day_counts=AGG_DAY_COUNTS,
max_back_quarter=MAX_BACK_QUARTER)
feature = FeatureMerger(fc1, fc2, on='ticker')
feature = FeatureMerger(feature, fc3, on=['ticker', 'date'])
target = QuarterlyTarget(col='marketcap', quarter_shift=0)
base_models = [
LogExpModel(lgbm.sklearn.LGBMRegressor()),
LogExpModel(ctb.CatBoostRegressor(verbose=False))
]
ensemble = EnsembleModel(base_models=base_models,
bagging_fraction=BAGGING_FRACTION,
model_cnt=MODEL_CNT)
model = GroupedOOFModel(ensemble, group_column='ticker', fold_cnt=FOLD_CNT)
pipeline = BasePipeline(feature=feature,
target=target,
model=model,
metric=median_absolute_relative_error,
out_name=OUT_NAME)
result = pipeline.fit(data_loader, ticker_list)
print(result)
pipeline.export_core(SAVE_PATH)