Update check_list

Author: breimanntools

aaanalysis/_utils/check_type.py

@@ -183,4 +183,6 @@ def check_list_like(name=None, val=None, accept_none=False, convert=True, accept
         str_error = add_str(str_error=f"'{name}' should not contain at least {min_len} elements",
                             str_add=str_add)
         raise ValueError(str_error)
+    # Check for numpy string objects and convert them to Python strings
+    val = [x.item() if hasattr(x, 'item') and isinstance(x, np.str_) else x for x in val]
     return val

aaanalysis/feature_engineering/_backend/cpp/cpp_plot_feature_map.py

@@ -269,7 +269,9 @@ def plot_feature_map(df_feat=None, df_cat=None,
                                       df_feat=df_feat.copy(),
                                       df_cat=df_cat.copy(),
                                       col_imp=col_imp,
-                                      col_cat=col_cat)
+                                      col_cat=col_cat,
+                                      start=start,
+                                      **args_len)
         ut.ticks_0(ax_bt, axis="y", **args_ticks_0)
 
     # Plot heatmap

aaanalysis/feature_engineering/_backend/cpp_run.py

@@ -86,6 +86,7 @@ def cpp_run_single(df_parts=None, split_kws=None, df_scales=None, df_cat=None, v
     # Adjust df_feat
     df_feat.reset_index(drop=True, inplace=True)
     df_feat[ut.COLS_FEAT_STAT] = df_feat[ut.COLS_FEAT_STAT].round(3)
+    df_feat[ut.COL_FEATURE] = df_feat[ut.COL_FEATURE].astype(str)
     if verbose:
         ut.print_out(f"4. CPP returns df of {len(df_feat)} unique features with general information and statistics")
     return df_feat
@@ -169,6 +170,7 @@ def cpp_run_batch(df_parts=None, split_kws=None, df_scales=None, df_cat=None, ve
     # Adjust df_feat
     df_feat.reset_index(drop=True, inplace=True)
     df_feat[ut.COLS_FEAT_STAT] = df_feat[ut.COLS_FEAT_STAT].round(3)
+    df_feat[ut.COL_FEATURE] = df_feat[ut.COL_FEATURE].astype(str)
     if verbose:
         ut.print_out(f"4. CPP returns df of {len(df_feat)} unique features with general information and statistics")
     return df_feat

aaanalysis/seq_analysis/_aalogo_plot.py

@@ -33,6 +33,7 @@ def check_parts_len(jmd_n_len=None, jmd_c_len=None, df_logo=None):
     return tmd_len, jmd_n_len, jmd_c_len
 
 
+# TODO add if target site to be positions (without P or with, e.g., kinases)
 # TODO add checks, complete docstring (consistency with cpp_plot functions!), tests for both plots
 # II Main Functions
 class AALogoPlot:

aaanalysis/seq_analysis/_backend/_aalogo/aalogo_plot.py

@@ -146,6 +146,8 @@ def multi_logo_(list_df_logo=None, target_p1_site=None, figsize_per_logo=(8, 3),
     figsize = (figsize_per_logo[0], figsize_per_logo[1] * n_plots)
     fig, axes = plt.subplots(nrows=n_plots, figsize=figsize)
     y_max = max([d.T.sum().max() for d in list_df_logo])
+    if y_label == "Probability [%]":
+        y_max *= 100
     for i, df_logo in enumerate(list_df_logo):
         name_data = list_name_data[i] if list_name_data else None
         name_data_color = list_name_data_color[i] if isinstance(list_name_data_color, list) else list_name_data_color
@@ -178,7 +180,8 @@ def multi_logo_(list_df_logo=None, target_p1_site=None, figsize_per_logo=(8, 3),
             else:
                 ax_logo.set_xticks([])
         if highlight_tmd_area:
-            ut.highlight_tmd_area(**args_parts, x_shift=-0.5, alpha=highlight_alpha, y_max=y_max)
+            ut.highlight_tmd_area(**args_parts, x_shift=-0.5,
+                                  alpha=highlight_alpha, y_max=y_max)
 
         # Adjust labels and formatting
         sns.despine(ax=ax_logo, top=True, bottom=True)