def wpca_decomposition(data):
weights = 0. + np.isfinite(data)
kwds = {'weights': weights}
pca = WPCA(n_components=1).fit(data, **kwds)
eigen_samples = pca.transform(data)[:,0]
eigen_genes = pca.components_[0,:]
return eigen_genes, eigen_samples
def get_pca(input_: Array,
learn_input: Array,
learn_weight_vec: Opt[Array],
n_comp_list: Iterable[int],
err_printer: Callable[[Array, Array, str], None] = None,
normalize_x: bool = True,
normalize_z: bool = False) -> LinearAnalyzer:
""" The last from ``n_comp_list`` would be returned. """
def expl(pca_):
return np.round(np.sum(pca_.explained_variance_ratio_), 2)
n_comp_list = list(n_comp_list)
x = x_normalized = learn_input # (~6000, ~162)
weight_vec = learn_weight_vec
μ_x: Union[Array, int] = 0
σ_x: Union[Array, int] = 1
if normalize_x:
x_normalized, μ_x, σ_x = get_x_normalized_μ_σ(x, weight_vec)
weight_vec_as_mat = weights_matrix(weight_vec,
x) if (weight_vec is not None) else None
for j, i in enumerate(n_comp_list):
pca = ClassWPCA(i)
pca.fit(x_normalized, weights=weight_vec_as_mat)
z: Array = pca.transform(x_normalized)
inverse_transform_matrix, μ_z, σ_z = get__inverse_transform_matrix__μ_z__σ_z(
z, weight_vec, normalize_z, x_normalized)
an = LinearAnalyzer(n=pca.n_components,
analyzer=pca,
x=input_,
μ_x=μ_x,
σ_x=σ_x,
μ_z=μ_z,
σ_z=σ_z,
inverse_transform_matrix=inverse_transform_matrix,
normalize_x=normalize_x,
normalize_z=normalize_z)
if err_printer is not None:
pref = f"Expl = {expl(pca)}, PC N = {pca.n_components}, "
err_printer(input_, an.x_rec, pref)
if (j + 1) == len(n_comp_list):
break
else:
raise ValueError('Empty n_comp_list')
return an
def component_removal(data, n_comp):
mean = data.mean(axis=1)
data = data.sub(mean, axis=0)
dataT = data.T.values
weights = 0 + np.isfinite(dataT)
kwds = {'weights': weights}
pca = WPCA(n_components=30).fit(dataT, **kwds) #Fit data to model
reconstruction = np.dot(
pca.transform(dataT)[:, n_comp:], pca.components_[n_comp:, :])
reconst_df = pd.DataFrame(data=reconstruction.T,
columns=data.columns,
index=data.index)
reconst_df = reconst_df.add(mean, axis=0)
return reconst_df
def weighted_PCA(df, n_pc=1, standardize=True):
'''
Function for performing the PCA, using sklearn.
df - Dataframe with expression values
'''
x = df.values.T #Set x as transpose of only the numerical values of the dataframe
if standardize:
standardizer = StandardScaler()
x2 = standardizer.fit_transform(
x
) #Standardize the data (center to mean and scale to unit variance)
else:
x2 = x
x2 = np.nan_to_num(
x2
) #Change back NaN values to 0, so array is accepted by the PCA function
weights = 0 + np.isfinite(x)
kwds = {'weights': weights}
n_pcs = min(df.shape[0], n_pc)
pca = WPCA(n_components=n_pcs).fit(x2, **kwds) #Fit data to model
expl = pca.explained_variance_ratio_
x3 = pca.transform(
x2, **kwds
) #Transform the data (apply dimensionality reduciton) and set x3 as principal components
out_df = pd.DataFrame(
x3.T, index=list(range(1, n_pcs + 1)), columns=df.columns
).T #Create dataframe with vlues from the PCA and set columnindex as the PC number
cont = pd.DataFrame(index=df.index)
for i in range(n_pcs):
cont.loc[:, f'PC{i+1} contribution'] = pca.components_[i]**2
cont.sort_values(by='PC1 contribution', ascending=False, inplace=True)
while n_pcs < n_pc:
expl = np.append(expl, float('NaN'))
n_pcs += 1
out_df.loc[:, str(n_pcs)] = float('NaN')
return out_df, expl, cont
