def _create_feature():
fc1 = QuarterlyFeatures(data_key='quarterly',
columns=QUARTER_COLUMNS,
quarter_counts=QUARTER_COUNTS,
max_back_quarter=MAX_BACK_QUARTER)
fc2 = BaseCompanyFeatures(data_key='base', cat_columns=CAT_COLUMNS)
fc3 = QuarterlyDiffFeatures(data_key='quarterly',
columns=QUARTER_COLUMNS,
compare_quarter_idxs=COMPARE_QUARTER_IDXS,
max_back_quarter=MAX_BACK_QUARTER)
fc4 = DailyAggQuarterFeatures(daily_data_key='commodities',
quarterly_data_key='quarterly',
columns=['price'],
agg_day_counts=AGG_DAY_COUNTS,
max_back_quarter=MAX_BACK_QUARTER,
daily_index=COMMODITIES_CODES)
feature = FeatureMerger(fc1, fc2, on='ticker')
feature = FeatureMerger(feature, fc3, on=['ticker', 'date'])
feature = FeatureMerger(feature, fc4, on=['ticker', 'date'])
return feature
def test_calculate(self, data_loader, tickers, columns,
compare_quarter_idxs, max_back_quarter):
fc = QuarterlyDiffFeatures(columns=columns,
compare_quarter_idxs=compare_quarter_idxs,
max_back_quarter=max_back_quarter)
X = fc.calculate(data_loader, tickers)
assert type(X) == pd.DataFrame
assert 'ticker' in X.index.names
assert 'date' in X.index.names
if type(data_loader) == GeneratedData:
assert X.shape[0] == max_back_quarter * len(tickers)
else:
assert X.shape[0] <= max_back_quarter * len(tickers)
assert X.shape[1] == len(compare_quarter_idxs) * len(columns)
def test_calculate(self, data, tickers):
fc1 = QuarterlyFeatures(data_key='quarterly',
columns=['ebit'],
quarter_counts=[2],
max_back_quarter=10)
fc2 = QuarterlyDiffFeatures(data_key='quarterly',
columns=['ebit', 'debt'],
compare_quarter_idxs=[1, 4],
max_back_quarter=10)
fc3 = BaseCompanyFeatures(data_key='base',
cat_columns=['sector', 'sicindustry'])
X1 = fc1.calculate(data, tickers)
X2 = fc2.calculate(data, tickers)
X3 = fc3.calculate(data, tickers)
fm1 = FeatureMerger(fc1, fc2, on=['ticker', 'date'])
Xm1 = fm1.calculate(data, tickers)
fm2 = FeatureMerger(fc1, fc3, on='ticker')
Xm2 = fm2.calculate(data, tickers)
assert Xm1.shape[0] == X1.shape[0]
assert Xm2.shape[0] == X1.shape[0]
assert Xm1.shape[1] == X1.shape[1] + X2.shape[1]
assert Xm2.shape[1] == X1.shape[1] + X3.shape[1]
assert (Xm1.index == X1.index).min()
assert (Xm2.index == X1.index).min()
new_cols = Xm1.columns[:X1.shape[1]]
old_cols = X1.columns
for nc, oc in zip(new_cols, old_cols):
assert (Xm1[nc] == X1[oc]).min()
new_cols = Xm2.columns[:X1.shape[1]]
old_cols = X1.columns
for nc, oc in zip(new_cols, old_cols):
assert (Xm2[nc] == X1[oc]).min()
def _create_feature():
fc1 = QuarterlyFeatures(data_key='quarterly',
columns=QUARTER_COLUMNS,
quarter_counts=QUARTER_COUNTS,
max_back_quarter=MAX_BACK_QUARTER)
fc2 = BaseCompanyFeatures(data_key='base', cat_columns=CAT_COLUMNS)
fc3 = QuarterlyDiffFeatures(data_key='quarterly',
columns=QUARTER_COLUMNS,
compare_quarter_idxs=COMPARE_QUARTER_IDXS,
max_back_quarter=MAX_BACK_QUARTER)
feature = FeatureMerger(fc1, fc2, on='ticker')
feature = FeatureMerger(feature, fc3, on=['ticker', 'date'])
return feature
data_loader = SF1Data(config['sf1_data_path'])
tickers_df = data_loader.load_base_data(
currency=CURRENCY,
scalemarketcap=SCALE_MARKETCAP)
ticker_list = tickers_df['ticker'].unique().tolist()
fc1 = QuarterlyFeatures(
columns=QUARTER_COLUMNS,
quarter_counts=QUARTER_COUNTS,
max_back_quarter=MAX_BACK_QUARTER)
fc2 = BaseCompanyFeatures(cat_columns=CAT_COLUMNS)
fc3 = QuarterlyDiffFeatures(
columns=QUARTER_COLUMNS,
compare_quarter_idxs=COMPARE_QUARTER_IDXS,
max_back_quarter=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)]
ensemble = EnsembleModel(base_models=base_models,
bagging_fraction=BAGGING_FRACTION,
model_cnt=MODEL_CNT)
model = GroupedOOFModel(ensemble,