def run_pca(data, device, n_components=300, var_explained=0.85):
"""Run PCA
:param data: Dataframe of cells X genes. Typicaly multiscale space diffusion components
:param n_components: Number of principal components
:param var_explained: Include components that explain amount variance. Note
number of components = min(n_components, components explaining var_explained)
:return: PCA projections of the data and the explained variance
"""
init_components = min([n_components, data.shape[0]])
if device == "gpu":
from cuml import PCA
pca = PCA(n_components=init_components)
elif device == "cpu":
from sklearn.decomposition import PCA
pca = PCA(n_components=init_components, svd_solver='randomized')
pca.fit(data)
if pca.explained_variance_ratio_.sum() >= 0.85:
n_components = np.where(np.cumsum(pca.explained_variance_ratio_) >= var_explained)[0][0]
print(f'Running PCA with {n_components} components')
pca_projections = pca.fit_transform(data)
pca_projections = pd.DataFrame(pca_projections, index=data.index)
return pca_projections, pca.explained_variance_ratio_
def PCA_concat(df, n_components=2):
pca_float = PCA(n_components=n_components)
pca_float.fit(df[df.columns[df.dtypes == np.float32]])
scores = pca_float.transform(df[df.columns[df.dtypes == np.float32]])
scores.columns = ['PC' + str(x) for x in range(n_components)]
return cudf.concat([df, scores], axis=1)
def PCA_concat(df, components=100):
pca_float = PCA(n_components=2)
pca_float.fit(df[df.columns[df.dtypes == np.float32]])
scores = pca_float.transform(df[df.columns[df.dtypes == np.float32]])
return cudf.concat([df, scores], axis=1)