def test_calc_series_stats(series, norm, expected):
result = calc_series_stats(series, norm=norm)
assert type(result) == dict
assert len(result) == len(expected)
assert result.keys() == expected.keys()
for key in result:
assert np.isclose(result[key], expected[key])
if norm == False:
np.random.seed(0)
np.random.shuffle(series)
result = calc_series_stats(series, norm=norm)
for key in result:
assert np.isclose(result[key], expected[key])
def test_calculate(self, data_loader, tickers, columns,
agg_day_counts, max_back_quarter):
fc = DailyAggQuarterFeatures(columns=columns,
agg_day_counts=agg_day_counts,
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
assert X.shape[0] <= max_back_quarter * len(tickers)
assert X.shape[1] == len(calc_series_stats([])) * \
len(columns) * len(agg_day_counts)
for col in columns:
for count in agg_day_counts:
min_col = 'days{}_{}_min'.format(count, col)
max_col = 'days{}_{}_max'.format(count, col)
mean_col = 'days{}_{}_mean'.format(count, col)
median_col = 'days{}_{}_median'.format(count, col)
assert (X[max_col] >= X[min_col]).min()
assert (X[max_col] >= X[mean_col]).min()
assert (X[max_col] >= X[median_col]).min()
assert (X[mean_col] >= X[min_col]).min()
assert (X[median_col] >= X[min_col]).min()
def test_calculate_dayly_index(self, data, tickers, columns,
agg_day_counts, max_back_quarter):
# Instead of real commodities to avoid extra dataloaders
commodities_codes = ['AAPL', 'MSFT']
fc = DailyAggQuarterFeatures(daily_data_key='daily',
quarterly_data_key='quarterly',
columns=columns,
agg_day_counts=agg_day_counts,
max_back_quarter=max_back_quarter,
daily_index=commodities_codes)
X = fc.calculate(data, tickers)
assert type(X) == pd.DataFrame
assert 'ticker' in X.index.names
assert 'date' in X.index.names
assert X.shape[0] <= max_back_quarter * len(tickers)
assert X.shape[1] == len(calc_series_stats([])) * \
len(columns) * len(agg_day_counts) *\
len(commodities_codes)
for code in commodities_codes:
for col in columns:
for count in agg_day_counts:
min_col = '{}_days{}_{}_min'.format(code, count, col)
max_col = '{}_days{}_{}_max'.format(code, count, col)
mean_col = '{}_days{}_{}_mean'.format(code, count, col)
median_col = '{}_days{}_{}_median'.format(code, count, col)
assert (X[max_col] >= X[min_col]).min()
assert (X[max_col] >= X[mean_col]).min()
assert (X[max_col] >= X[median_col]).min()
assert (X[mean_col] >= X[min_col]).min()
assert (X[median_col] >= X[min_col]).min()
def test_calculate(self, data, tickers, columns, quarter_counts,
max_back_quarter):
fc = QuarterlyFeatures(data_key='quarterly',
columns=columns,
quarter_counts=quarter_counts,
max_back_quarter=max_back_quarter)
X = fc.calculate(data, tickers)
assert type(X) == pd.DataFrame
assert 'ticker' in X.index.names
assert 'date' in X.index.names
if type(data['quarterly']) == GenQuarterlyData:
assert X.shape[0] == max_back_quarter * len(tickers)
else:
assert X.shape[0] <= max_back_quarter * len(tickers)
assert X.shape[1] == 2 * len(calc_series_stats([])) * \
len(columns) * len(quarter_counts)
# Minimum can not be lower with reduction of quarter_count
sorted_quarter_counts = np.sort(quarter_counts)
for col in columns:
for k in range(len(sorted_quarter_counts) - 1):
lower_count = sorted_quarter_counts[k]
higher_count = sorted_quarter_counts[k + 1]
l_col = 'quarter{}_{}_min'.format(lower_count, col)
h_col = 'quarter{}_{}_min'.format(higher_count, col)
assert (X[h_col] <= X[l_col]).min()
# Maximum can not be higher with reduction of quarter_count
sorted_quarter_counts = np.sort(quarter_counts)
for col in columns:
for k in range(len(sorted_quarter_counts) - 1):
lower_count = sorted_quarter_counts[k]
higher_count = sorted_quarter_counts[k + 1]
l_col = 'quarter{}_{}_max'.format(lower_count, col)
h_col = 'quarter{}_{}_max'.format(higher_count, col)
assert (X[h_col] >= X[l_col]).min()
std_cols = [x for x in X.columns if '_std' in x]
for col in std_cols:
assert X[col].min() >= 0
for col in columns:
for count in quarter_counts:
min_col = 'quarter{}_{}_min'.format(count, col)
max_col = 'quarter{}_{}_max'.format(count, col)
mean_col = 'quarter{}_{}_mean'.format(count, col)
median_col = 'quarter{}_{}_median'.format(count, col)
assert (X[max_col] >= X[min_col]).min()
assert (X[max_col] >= X[mean_col]).min()
assert (X[max_col] >= X[median_col]).min()
assert (X[mean_col] >= X[min_col]).min()
assert (X[median_col] >= X[min_col]).min()
def test_calc_series_stats_nans():
assert calc_series_stats([np.nan, 10, 0, 1]) == calc_series_stats([10, 0, 1])
assert calc_series_stats([None, 10, 0, 1]) == calc_series_stats([10, 0, 1])
assert calc_series_stats([10, 0, np.nan, 1]) == calc_series_stats([10, 0, 1])
result = calc_series_stats([])
for key in result:
assert np.isnan(result[key])
result = calc_series_stats([np.nan, None])
for key in result:
assert np.isnan(result[key])