col_meta=col_df,
col_sort_class=["from_class"],
row_colors=CLASS_COLOR_DICT,
row_meta=row_df,
row_sort_class=["to_class"],
plot_type="heatmap",
sizes=(0.5, 0.5),
tick_rot=45,
)
stashfig("log-full-heat" + basename)
# %% [markdown]
# # Screeplots
if plot_embed:
screeplot(hist_mat.astype(float), title="Raw hist mat (full)")
stashfig("scree-raw-mat" + basename)
screeplot(log_mat, title="Log hist mat (full)")
stashfig("scree-log-mat" + basename)
# %% [markdown]
# # Pairplots
if plot_embed:
pca = PCA(n_components=6)
embed = pca.fit_transform(log_mat)
loadings = pca.components_.T
pg = pairplot(
embed,
labels=to_class.values,
palette=CLASS_COLOR_DICT,
height=5,
# sym_adj, class_labels, side_labels = preprocess_graph(
# sym_adj, class_labels, side_labels
# )
# n_verts = sym_adj.shape[0]
# print(f"Removed {old_n_verts - n_verts} nodes")
# %% [markdown]
# # Embedding
n_verts = mg.n_verts
sym_adj = mg.adj
side_labels = mg["Hemisphere"]
class_labels = mg["Merge Class"]
latent, laplacian = lse(sym_adj, N_COMPONENTS, regularizer=None, ptr=PTR)
latent_dim = latent.shape[1] // 2
screeplot(
laplacian,
title=f"Laplacian scree plot, R-DAD (ZG2 = {latent_dim} + {latent_dim})")
print(f"ZG chose dimension {latent_dim} + {latent_dim}")
plot_latent = np.concatenate(
(latent[:, :3], latent[:, latent_dim:latent_dim + 3]), axis=-1)
pairplot(plot_latent, labels=side_labels)
# take the mean for the paired cells, making sure to add back in the unpaired cells
sym_latent = (latent[:n_pairs] + latent[n_pairs:2 * n_pairs]) / 2
sym_latent = np.concatenate((sym_latent, latent[2 * n_pairs:]))
latent = sym_latent
# make new labels
side_labels = np.concatenate((n_pairs * ["P"], side_labels[2 * n_pairs:]))
# this is assuming that the class labels are perfectly matches left right, probs not
col_meta=meta,
col_colors="merge_class",
col_sort_class=["merge_class"],
col_palette=CLASS_COLOR_DICT,
col_ticks=False,
col_class_order="group_mean_visit",
col_item_order="mean_visit",
)
stashfig("log_hop_hist")
# %% [markdown]
# ## Scree plots
from src.visualization import screeplot
screeplot(all_hop_hist, show_first=40)
stashfig("scree-first-40")
screeplot(all_hop_hist, show_first=None)
stashfig("scree-all")
screeplot(np.log10(all_hop_hist + 1), show_first=100)
screeplot(np.log10(all_hop_hist + 1), show_first=100, cumulative=True)
# %% [markdown]
# ##
from graspy.cluster import AutoGMMCluster
agmm = AutoGMMCluster(
min_components=2,
max_components=50,
affinity=["euclidean", "manhattan"],
embed[left_inds] = embed[left_inds] @ R # %% [markdown] # ## joint = np.concatenate((embed, full_hop_hist.T), axis=1) from graspy.plot import pairplot from sklearn.decomposition import PCA from sklearn.decomposition import TruncatedSVD from sklearn.preprocessing import StandardScaler from src.visualization import screeplot joint = StandardScaler(with_mean=False, with_std=True).fit_transform(joint) screeplot(joint) embedder = TruncatedSVD(n_components=4) joint_embed = embedder.fit_transform(joint) pg = pairplot(joint_embed, labels=meta["merge_class"].values, palette=CLASS_COLOR_DICT) pg._legend.remove() # %% meta["inds"] = range(len(meta)) left_inds = meta[meta["left"]]["inds"] right_inds = meta[meta["right"]]["inds"] lp_inds, rp_inds = get_paired_inds(meta) results = crossval_cluster(
)
stashfig("edgesum-scatter")
edgesum_mat = calc_edgesums(color_adjs)
in_cols = ["In " + n for n in GRAPH_TYPES]
out_cols = ["Out " + n for n in GRAPH_TYPES]
cols = np.array(in_cols + out_cols)
edgesum_df = pd.DataFrame(data=edgesum_mat, columns=cols)
figsize = (20, 20)
sns.clustermap(edgesum_df, figsize=figsize)
plt.title("Edgesum matrix, single linkage euclidean dendrograms", loc="center")
screeplot(edgesum_mat, cumulative=False, title="Edgesum matrix screeplot")
plt.ylim((0, 0.5))
pca = PCA(n_components=3)
edgesum_pcs = pca.fit_transform(edgesum_mat)
var_exp = np.sum(pca.explained_variance_ratio_)
pairplot(
edgesum_pcs, height=5, alpha=0.3, title=f"Edgesum PCs, {var_exp} variance explained"
)
pairplot(
edgesum_pcs,
labels=class_labels,
height=5,
alpha=0.3,
