Cleanup figures

pf2rnaseq/figures/figureCC1.py

@@ -19,30 +19,19 @@
 
 def makeFigure():
     """Get a list of the axis objects and create a figure."""
-    ax, f = getSetup((20, 4), (1, 3))
+    ax, f = getSetup((6, 6), (2, 2))
     subplotLabel(ax)
 
     X = anndata.read_h5ad("/opt/extra-storage/CRC/GSE178341/crc10x_full_50cmp.h5ad")
 
-    samples_only_df = sample_names_only(X, "HistologicGradeSimple")
-
-
-    # grouping_hgsgs = pd.Series(samples_only_df["HistologicGradeSimple"].to_numpy())
-
-    # for i in grouping_hgsgs:
-    #     print(i)
-    # print(grouping_hgsgs)
-    # print(np.unique(grouping_hgsgs))
-    # plot_condition_factors(X, ax[0], condition_label="PID", cond_group_labels=grouping_hgsgs, groupConditions=True)
+    samples_names = sample_names_only(X, "HistologicGradeSimple")
 
 
-
-    # plot_condition_factors(X, ax[0], condition_label="HistologicGradeSimpleGradeSimple"), X.obs["MMRStatus"], groupConditions=True)
-    # plot_eigenstate_factors(X, ax[1])
-    # plot_gene_factors(X, ax[2])
-    # plot_factor_weight(X, ax[3])
-
-    # plot_labels_pacmap(X, "time", ax[4])
+    plot_condition_factors(X, ax[0], condition_label="PID", cond_group_labels=pd.Series(samples_names), groupConditions=True)
+    ax[0].yaxis.set_ticklabels([])
+    plot_eigenstate_factors(X, ax[1])
+    plot_gene_factors(X, ax[2])
+    ax[2].yaxis.set_ticklabels([])
 
 
     return f
@@ -51,22 +40,20 @@ def makeFigure():
 def sample_names_only(X: anndata.AnnData, label: str):
     """Obtain samples once only with corresponding observations"""
     samples = X.obs
-    print(samples)
-
     unique_idx = np.unique(samples["condition_unique_idxs"])
+    label_samples = []
 
-    label_samples = np.empty(len(unique_idx), dtype=str)
-    for i in range(20): 
+    for i in range(len(unique_idx)): 
         samples_idx = samples.loc[samples["condition_unique_idxs"] == i]
-        print(samples_idx[label])
-        print(np.unique(samples_idx[label]))
-        label_samples[i] = str(np.unique(samples_idx[label]))
-
-    print(label_samples)
-
 
-
-    # df_samples = samples.drop_duplicates(subset="condition_unique_idxs")
-    # df_samples = df_samples.sort_values("condition_unique_idxs")
+        if pd.isna(samples_idx[label].to_numpy()).any() == True:
+            samples_idx_np = samples_idx[label].to_numpy()
+            label_wo_nan = np.unique(samples_idx_np[~pd.isna(samples_idx_np)])
+            label_w_nan = label_wo_nan + "-NaN"
+            label_samples.append(label_w_nan[0])
+        else:
+            label_no_nan = np.unique(samples_idx[label])
+            label_samples.append(label_no_nan[0])
 
-    # return df_samples
+
+    return label_samples