def test_compute_pca_less_components_than_features(self):
# test pca when we have less components than features
df = pd.DataFrame({'a': range(100)})
for i in range(100):
df[i] = df['a'] * i
(components, variance) = Analyzer.compute_pca(df, df.columns)
assert_equal(len(components.columns), 100)
assert_equal(len(variance.columns), 100)
def test_compute_pca_less_components_than_features(self):
# test pca when we have less components than features
df = pd.DataFrame({'a': range(100)})
for i in range(100):
df[i] = df['a'] * i
(components, variance) = Analyzer.compute_pca(df, df.columns)
assert_equal(len(components.columns), 100)
assert_equal(len(variance.columns), 100)
def test_compute_pca_less_samples_than_features(self):
# test pca when we have less samples than
# features. In this case the number of components
# equals to the number of samples.
df = pd.DataFrame({'a': range(50)})
for i in range(100):
df[i] = df['a'] * i
(components, variance) = Analyzer.compute_pca(df, df.columns)
assert_equal(len(components.columns), 50)
assert_equal(len(variance.columns), 50)
def test_compute_pca_less_samples_than_features(self):
# test pca when we have less samples than
# features. In this case the number of components
# equals to the number of samples.
dfs = []
# to avoid inserting too many columns,
# we create a list of data frames and then
# concatenate them together
for i in range(1, 101):
dfs.append(pd.DataFrame({i: pd.Series(range(50)) * i}))
df = pd.concat(dfs, axis=1)
(components, variance) = Analyzer.compute_pca(df, df.columns)
assert_equal(len(components.columns), 50)
assert_equal(len(variance.columns), 50)