def test_add_revenue_value_spot_check(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
z = rev.aligned_data.iloc[42, :]
assert isclose(z[0], 9.14, rel_tol=1e-04)
assert isclose(z[1], 2517.049924, rel_tol=1e-04)
assert isclose(z[2], 25.164100, rel_tol=1e-04)
assert isclose(z[3], 6.333930, rel_tol=1e-04)
def test_subset_data_badpeak(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="perk")
oncount = subdf.isna().sum()
offcount = subdf.notnull().sum()
for elem in oncount:
assert elem == 4380
for elem in offcount:
assert elem == 4380
def test_write_grouped_data_to_file(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="peak")
grouped = rev.group_data(subdf)
outfile = "peak-data.csv"
rev.save_grouped_data(grouped, outfile)
assert os.path.isfile(outfile)
def test_groupby_runs_default_methods(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="peak")
grouped = rev.group_data(subdf)
assert grouped.shape == (12, 4)
print(grouped)
assert grouped.index.min() == 1
assert grouped.index.max() == 12
def test_groupby_other_methods_spotcheck(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="peak")
grouped = rev.group_data(subdf, [max, min, max, min])
z = grouped.iloc[6, :]
print(z)
assert isclose(z[0], 9.530556, rel_tol=1e-04)
assert isclose(z[1], 131.111105, rel_tol=1e-04)
assert isclose(z[2], 43.969100, rel_tol=1e-04)
assert isclose(z[3], 0.309022, rel_tol=1e-04)
def test_groupby_defaults_spotcheck(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="peak")
grouped = rev.group_data(subdf)
z = grouped.iloc[6, :]
print(z)
assert isclose(z[0], 6.793248, rel_tol=1e-04)
assert isclose(z[1], 1422.076282, rel_tol=1e-04)
assert isclose(z[2], 10184.529100, rel_tol=1e-04)
assert isclose(z[3], 1469.932431, rel_tol=1e-04)
def test_add_revenue_column_na_size(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
assert rev.aligned_data.isna().sum().all() == 0
assert rev.aligned_data.shape == (8760, 4)
def test_revenue_init_aligned_data_na_size(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
assert rev.aligned_data.isna().sum().all() == 0
assert rev.aligned_data.shape == (8760, 3)
def test_revenue_init_defined_peak_hours(self, sample_data):
pkhrs = PeakHours(peak=[4, 5, 1, 10], offpeak=[2, 3, 1, 8, 9])
rev = GrossRevenue(aligned_data=sample_data, peak_hours=pkhrs)
val = rev.peak_hours.get_peak_hours()
assert (val[0] == [4, 5, 1, 10]).all()
assert (val[1] == [2, 3, 1, 8, 9]).all()
def test_revenue_init_default_peak_hours(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
val = rev.peak_hours.get_peak_hours()
assert (val[0] == peak_default).all()
assert (val[1] == off_peak_default).all()
def test_calculate_gross_revenue(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.calculate_gross_revenue()
assert os.path.isfile('GrossRevenue-PeakHrs.csv')
assert os.path.isfile('GrossRevenue-OffPeakHrs.csv')
def test_groupby_runs_other_methods(self, sample_data):
rev = GrossRevenue(aligned_data=sample_data)
rev.add_revenue_column()
subdf = rev.subset_data(subset_on="peak")
grouped = rev.group_data(subdf, [max, min, max, min])
assert grouped.shape == (12, 4)