def test_cdf(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
# Test CDF
cdf = model.cumulative_distribution(sampled_data)
assert (0 <= cdf).all() and (cdf <= 1).all()
# Test CDF increasing function
for column in sampled_data.columns:
sorted_data = sampled_data.sort_values(column)
other_columns = data.columns.to_list()
other_columns.remove(column)
row = sorted_data.sample(1).iloc[0]
for column in other_columns:
sorted_data[column] = row[column]
cdf = model.cumulative_distribution(sorted_data)
diffs = np.diff(
cdf
) + 0.001 # Add tolerance to avoid floating precision issues.
assert (diffs >= 0).all()
def test_cdf(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
# Test CDF
cdf = model.cumulative_distribution(sampled_data)
assert (0 < cdf).all() and (cdf < 1).all()
# Test CDF increasing function
for column in sampled_data.columns:
sorted_data = sampled_data.sort_values(column)
other_columns = data.columns.to_list()
other_columns.remove(column)
row = sorted_data.sample(1).iloc[0]
for column in other_columns:
sorted_data[column] = row[column]
cdf = model.cumulative_distribution(sorted_data)
assert (np.diff(cdf) >= 0).all()
def test_to_dict_from_dict(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
params = model.to_dict()
model2 = GaussianMultivariate.from_dict(params)
pdf = model.probability_density(sampled_data)
pdf2 = model2.probability_density(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
cdf = model.cumulative_distribution(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
def test_save_load(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = GaussianMultivariate.load(path_to_model)
pdf = model.probability_density(sampled_data)
pdf2 = model2.probability_density(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
cdf = model.cumulative_distribution(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
def copula_based(X,Y):
"""
Calculate joint PDF/CDF using copula
"""
import pandas as pd
from copulas.multivariate import GaussianMultivariate
# fit gaussian copula
data=pd.DataFrame(list(zip(X,Y)),columns=['P','T'])
dist=GaussianMultivariate()
dist.fit(data)
sampled=dist.sample(1)
sampled.at[0,'P']=np.mean(X)
sampled.at[0,'T']=np.mean(Y)
# find pdf/cdf at mean value
pdf=dist.pdf(sampled)
cdf=dist.cumulative_distribution(sampled)
return [pdf,cdf]
def _gaussian(self, dataset):
"""
For the given dataset, this runs "everything but the kitchen sink" (i.e.
every feature of GaussianMultivariate that is officially supported) and
makes sure it doesn't crash.
"""
model = GaussianMultivariate({
dataset.columns[0]: GaussianKDE() # Use a KDE for the first column
})
model.fit(dataset)
for N in [10, 100, 50]:
assert len(model.sample(N)) == N
sampled_data = model.sample(10)
pdf = model.probability_density(sampled_data)
cdf = model.cumulative_distribution(sampled_data)
# Test Save/Load from Dictionary
config = model.to_dict()
model2 = GaussianMultivariate.from_dict(config)
for N in [10, 100, 50]:
assert len(model2.sample(N)) == N
pdf2 = model2.probability_density(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = GaussianMultivariate.load(path_to_model)
for N in [10, 100, 50]:
assert len(model2.sample(N)) == N
pdf2 = model2.probability_density(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
