def test_datamation_groupby_multiple():
df = small_salary().df
df = DatamationFrame(df)
# Group by Degree, Work
mean = df.groupby(['Degree', 'Work']).mean()
assert "groupby" in mean.operations
assert "mean" in mean.operations
assert len(mean.states) == 2
assert df.equals(mean.states[0])
assert mean.Salary.Masters.Academia == 84.0298831968801
assert mean.Salary.Masters.Industry == 91.22576155606282
assert mean.Salary.PhD.Academia == 85.55796571969728
assert mean.Salary.PhD.Industry == 93.08335885824636
# sum
sum = df.groupby(['Degree', 'Work']).sum()
assert "groupby" in sum.operations
assert "sum" in sum.operations
assert len(sum.states) == 2
assert df.equals(sum.states[0])
assert sum.Salary.Masters.Academia == 840.2988319688011
assert sum.Salary.Masters.Industry == 5655.997216475895
assert sum.Salary.PhD.Academia == 1540.043382954551
assert sum.Salary.PhD.Industry == 930.8335885824636
# product
product = df.groupby(['Degree', 'Work']).prod()
assert "groupby" in product.operations
assert "product" in product.operations
assert len(product.states) == 2
assert df.equals(product.states[0])
assert product.Salary.Masters.Academia == 1.753532557780977e+19
assert product.Salary.Masters.Industry == 3.3602152421057308e+121
assert product.Salary.PhD.Academia == 6.027761935702164e+34
assert product.Salary.PhD.Industry == 4.8818435443657834e+19
# Group by species, island, sex
df = DatamationFrame(load_penguins())
mean = df.groupby(['species', 'island', 'sex']).mean()
assert "groupby" in mean.operations
assert "mean" in mean.operations
assert len(mean.states) == 2
assert df.equals(mean.states[0])
assert mean.bill_length_mm.Adelie.Biscoe.male == approx(40.5909090909091)
assert mean.bill_length_mm.Adelie.Biscoe.female == approx(
37.35909090909092)
def test_datamation_frame_groupby():
df = small_salary().df
df = DatamationFrame(df)
grouped = df.groupby('Work')
assert 'groupby' in grouped.operations
assert df.equals(grouped.states[0])
def test_small_salary(capsys):
df = small_salary().df
print(df.groupby('Work').mean())
captured = capsys.readouterr()
assert "Work" in captured.out
assert "Salary" in captured.out
assert "Academia" in captured.out
assert "Industry" in captured.out
assert "85.012222" in captured.out
assert "91.483761" in captured.out
def test_datamation_frame_datamation_sanddance():
df = small_salary().df
df = DatamationFrame(df)
datamation = df.groupby('Work').mean().datamation_sanddance()
assert len(datamation.states) == 2
assert len(datamation.operations) == 2
assert df.equals(datamation.states[0])
assert isinstance(datamation.states[1], DatamationGroupBy)
assert datamation.operations[0] == 'groupby'
assert datamation.operations[1] == 'mean'
assert isinstance(datamation.output, DatamationFrame)
assert datamation.output.Salary.Academia == 85.01222196154829
assert datamation.output.Salary.Industry == 91.48376118136609
assert 'Salary' in str(datamation)
def test_datamation_frame_specs():
df = small_salary().df
df = DatamationFrame(df)
# Mean
# Group by Degree
specs = df.groupby('Degree').mean().specs()
script_dir = os.path.dirname(__file__)
with open(os.path.join(script_dir, '../../inst/specs/raw_spec.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Group by Work
specs = df.groupby('Work').mean().specs()
script_dir = os.path.dirname(__file__)
with open(os.path.join(script_dir, '../../inst/specs/groupby_work.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Group by Degree, Work
specs = df.groupby(['Degree', 'Work']).mean().specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/groupby_degree_work.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Group by Work, Degree
specs = df.groupby(['Work', 'Degree']).mean().specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/groupby_work_degree.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
#Min
# Group by Degree Min
specs = df.groupby('Degree').min('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(
script_dir,
'../../sandbox/custom_animations/custom-animations-min-R.json'
), 'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Group by Degree, Work Min
specs = df.groupby(['Degree', 'Work']).min('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/min_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
#Max
# Group by Degree Max
specs = df.groupby('Degree').max('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(
script_dir,
'../../sandbox/custom_animations/custom-animations-max-R.json'
), 'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Group by Degree, Work Max
specs = df.groupby(['Degree', 'Work']).max('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/max_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Sum
# Sum of Group by Degree
specs = df.groupby('Degree').sum().specs()
script_dir = os.path.dirname(__file__)
with open(os.path.join(script_dir, '../../inst/specs/sum_specs.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Sum of Group by Degree, Work
specs = df.groupby(['Degree', 'Work']).sum().specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/sum_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Product
# Product of Group by Degree
specs = df.groupby('Degree').prod().specs()
script_dir = os.path.dirname(__file__)
with open(os.path.join(script_dir, '../../inst/specs/prod_specs.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
# Product of Group by Degree, Work
specs = df.groupby(['Degree', 'Work']).prod().specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/prod_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(specs, specs_file)
#Count group by Degree
count_spec = df.groupby('Degree').count('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/count_specs_one_column.json'),
'r') as specs_file:
compare_specs_with_file(count_spec, specs_file)
#Count group by Degree, Work
count_spec = df.groupby(['Degree', 'Work']).count('Salary').specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/count_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(count_spec, specs_file)
#Quantile group by Degree
quant_spec = df.groupby('Degree').quantile('Salary', 0.01).specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(
script_dir,
'../../sandbox/custom_animations/custom-animations-quantile-R.json'
), 'r') as specs_file:
compare_specs_with_file(quant_spec, specs_file)
#Quantile group by Degree, Work
quant_spec = df.groupby(['Degree', 'Work']).quantile('Salary',
0.01).specs()
script_dir = os.path.dirname(__file__)
with open(
os.path.join(script_dir,
'../../inst/specs/quantile_specs_two_columns.json'),
'r') as specs_file:
compare_specs_with_file(quant_spec, specs_file)
def test_datamation_groupby():
df = small_salary().df
df = DatamationFrame(df)
# Group by Degree
mean = df.groupby('Degree').mean()
assert "groupby" in mean.operations
assert "mean" in mean.operations
assert len(mean.states) == 2
assert df.equals(mean.states[0])
assert mean.Salary.Masters == 90.22633400617633
assert mean.Salary.PhD == 88.24560612632195
# median
median = df.groupby('Degree').median()
assert "groupby" in median.operations
assert "median" in median.operations
assert len(median.states) == 2
assert df.equals(median.states[0])
assert median.Salary.Masters == 91.13211765489541
assert median.Salary.PhD == 86.40630845562555
# sum
sum = df.groupby('Degree').sum()
assert "groupby" in sum.operations
assert "sum" in sum.operations
assert len(sum.states) == 2
assert df.equals(sum.states[0])
assert sum.Salary.Masters == 6496.296048444696
assert sum.Salary.PhD == 2470.8769715370145
# product
product = df.groupby('Degree').prod()
assert "groupby" in product.operations
assert "product" in product.operations
assert len(product.states) == 2
assert df.equals(product.states[0])
assert product.Salary.PhD == 2.9426590692781414e+54
assert product.Salary.Masters == 5.892246828184284e+140
# Group by Work
mean = df.groupby('Work').mean()
assert "groupby" in mean.operations
assert "mean" in mean.operations
assert len(mean.states) == 2
assert df.equals(mean.states[0])
assert mean.Salary.Academia == 85.01222196154829
assert mean.Salary.Industry == 91.48376118136609