mini updates for x-labels on figures

stats_figures/create_edges_figures.py

@@ -15,17 +15,17 @@
 
 
 # specify params
-names = [ 'tkgl-polecat', 'tkgl-icews',  'tkgl-smallpedia', 'tkgl-wikidata', 'thgl-myket', 'thgl-github', 'thgl-forum', 'thgl-software']
+names = ['thgl-github', 'tkgl-polecat', 'tkgl-icews',  'tkgl-smallpedia', 'tkgl-wikidata', 'thgl-myket',  'thgl-forum', 'thgl-software']
 granularity ={} #for labels
 granularity['tkgl-polecat'] = 'days'
 granularity['tkgl-icews'] = 'days'
 granularity['tkgl-smallpedia'] = 'years'
 granularity['tkgl-wikidata'] = 'years'
 granularity['tkgl-yago'] = 'years'
-granularity['thgl-myket'] = 'sec.'
-granularity['thgl-github'] = 'sec.'
-granularity['thgl-software'] = 'sec.'
-granularity['thgl-forum'] = 'sec.'
+granularity['thgl-myket'] = 's.'
+granularity['thgl-github'] = 's.'
+granularity['thgl-software'] = 's.'
+granularity['thgl-forum'] = 's.'
 
 # colors from tgb logo
 colortgb = '#60ab84'
@@ -74,23 +74,8 @@
             capthick=1
             elinewidth=1
         ts_discretized_mean, ts_discretized_sum, ts_discretized_min, ts_discretized_max, start_indices, end_indices, mid_indices = du.discretize_values(n_edges_list, num_bars)
-        # different version of the figures
-        # plt.figure()
-        # plt.tick_params(axis='both', which='major', labelsize=labelsize)
-        # # plt.bar(mid_indices, ts_discretized_mean, width=(len(n_edges_list) // num_bars), label ='Mean Value', color =colortgb)
-        # plt.step(mid_indices, ts_discretized_mean, where='mid', linestyle='-', label ='Mean Value', color=colortgb)
-        # plt.scatter(mid_indices, ts_discretized_min, label ='min value')
-        # plt.scatter(mid_indices, ts_discretized_max, label ='max value')
-        # plt.xlabel(f'Timestep [{granularity[dataset_name]}] from {start_date} to {end_date}', fontsize=fontsize)
-        # plt.ylabel('Number of Edges', fontsize=fontsize)
-        # plt.legend()
-        # #plt.title(dataset_name+ ' - Number of Edges aggregated across multiple timesteps')
-        # save_path = (os.path.join(figs_dir, f"num_edges_discretized_{num_bars}_{dataset_name}.png"))
-        # plt.savefig(save_path, bbox_inches='tight')
-        # save_path = (os.path.join(figs_dir, f"num_edges_discretized_{num_bars}_{dataset_name}.pdf"))
-        # plt.savefig(save_path, bbox_inches='tight')
-
 
+        # line chart
         plt.figure()
         plt.tick_params(axis='both', which='major', labelsize=labelsize)
         mins = np.array(ts_discretized_min)
@@ -100,16 +85,18 @@
         plt.step(mid_indices, ts_discretized_mean, where='mid', linestyle='-', label ='Mean Value', color=colortgb, linewidth=2)
         #plt.scatter(mid_indices, ts_discretized_mean, label ='Mean Value', color=colortgb)
         plt.errorbar(mid_indices, maxs, yerr=[maxs-mins, maxs-maxs], fmt='none', alpha=0.9, color='grey',capsize=capsize, capthick=capthick, elinewidth=elinewidth, label='Min-Max Range')
-        plt.xlabel(f'Timestep [{granularity[dataset_name]}] from {start_date} to {end_date}', fontsize=fontsize)
+        plt.xlabel(f'Ts. [{granularity[dataset_name]}] from {start_date} to {end_date}', fontsize=fontsize)
         plt.ylabel('Number of Edges', fontsize=fontsize)
         plt.legend()
+        plt.tight_layout()
         #plt.title(dataset_name+ ' - Number of Edges aggregated across multiple timesteps')
         plt.show()
         save_path2 = (os.path.join(figs_dir,f"num_edges_discretized_{num_bars}_{dataset_name}2.png"))
         plt.savefig(save_path2, bbox_inches='tight')
         save_path2 = (os.path.join(figs_dir,f"num_edges_discretized_{num_bars}_{dataset_name}2.pdf"))
         plt.savefig(save_path2, bbox_inches='tight')
 
+        # bar chart
         plt.figure()
         plt.tick_params(axis='both', which='major', labelsize=labelsize)
         mins = np.array(ts_discretized_min)
@@ -130,6 +117,7 @@
 
 
         try:
+            # try log scale
             plt.figure()
             plt.tick_params(axis='both', which='major', labelsize=labelsize)
             mins = np.array(ts_discretized_min)

stats_figures/create_relation_figures.py

@@ -17,13 +17,16 @@
 
 
 # specify params
+# which datasets
 names = [ 'tkgl-polecat', 'tkgl-icews', 'tkgl-wikidata', 'tkgl-smallpedia','tkgl-polecat'] #'tkgl-polecat','tkgl-smallpedia',  'tkgl-yago',  'tkgl-icews' ,'tkgl-smallpedia','thgl-myket','tkgl-yago',  'tkgl-icews','thgl-github', 'thgl-forum', 'tkgl-wikidata']
+# which methods for the mrr_per_rel figures
 methods = ['recurrency', 'regcn', 'cen'] #'recurrency'
 colortgb = '#60ab84' #tgb logo colors
 colortgb2 = '#eeb641'
 colortgb3 = '#dd613a'
 head_tail_flag = False # if true, the head and tail of the relation are shown in the plot, otherwise just the mean across both directions
 
+# pie chart colors
 colors = [colortgb,colortgb2,colortgb3]  # from tgb logo
 colors2= ['#8e0152', '#c51b7d', '#de77ae', '#f1b6da', '#fde0ef', '#f7f7f7', '#e6f5d0', '#b8e186', '#7fbc41', '#4d9221', '#276419']
 # from https://colorbrewer2.org/#type=diverging&scheme=PiYG&n=11 color blind friendly 
@@ -43,6 +46,7 @@
 plot_values_list = []
 plot_names_multi_line_list =[]
 for dataset_name in names:
+    print('dataset_name:', dataset_name)
     # some directory stuff
     modified_dataset_name = dataset_name.replace('-', '_')
     current_dir = os.path.dirname(os.path.abspath(__file__))
@@ -59,7 +63,7 @@
     if not os.path.exists(stats_dir):
         os.makedirs(stats_dir)
 
-    ### A pie charts #plot top k relations accordung to the number of occurences plus a slice for "others"
+    ### A) pie charts #plot top k relations accordung to the number of occurences plus a slice for "others"
     plot_names = list(stats_df['rel_string_word'].iloc[:k]) 
     plot_values = list(stats_df['number_total_occurences'].iloc[:k])
     all_others = np.sum(stats_df['number_total_occurences'].iloc[k:]) #slice for "others" (sum of all other relations occurences)
@@ -107,7 +111,7 @@
     if dataset_name == 'tkgl-wikidata': #then we do not want to plot the mrr for the relations
         continue
 
-    ### B plot the mrr for each relation for each method, different color for different number of occurences or for different recurrency degree
+    ### B) plot the mrr for each relation for each method, different color for different number of occurences or for different recurrency degree
 
     # prepare the dataframe: only take the top ten relations according to number of occurences and sort by recurrency degree
     # we use selected_df_sorted to plot the relations in the order of recurrency degree
@@ -195,8 +199,7 @@
     plt.savefig(save_path, bbox_inches='tight')
     save_path = (os.path.join(figs_dir, f"rel_mrrperrel_recdeg_{dataset_name}.pdf"))
     plt.savefig(save_path, bbox_inches='tight')
-    print('saved')
-
+    print('saved in ', save_path)
 
     # version 2) colors are the number of occurences
     plt.figure()
@@ -220,7 +223,8 @@
     save_path = (os.path.join(figs_dir, f"rel_mrrperrel_occ_{dataset_name}.png"))
     plt.savefig(save_path, bbox_inches='tight')
 
-    ### now we plot all sorts of correlation matrix. I specify different columns for the different plots    
+
+    ### C) plot all sorts of correlation matrix. I specify different columns for the different plots    
     df = stats_df[['recurrency_degree', 'direct_recurrency-degree', 'recurrency_tail', 'recurrency_head', 'regcn_tail', 'regcn_head', 'cen_tail', 'cen_head']]
     corrmat= df.corr()
     f = plt.figure(figsize=(19, 15))