Changeset 34441 for main

Timestamp:

2020-10-05T12:49:05+13:00 (4 years ago)

Author:

davidb

Message:

Further refactoring

File:

• main/trunk/model-sites-dev/mars/collect/deam/MERGE-CSV-FEATURES-AND-AV-FILES.py (modified) (8 diffs)

main/trunk/model-sites-dev/mars/collect/deam/MERGE-CSV-FEATURES-AND-AV-FILES.py

@@ -4 +4 @@
 from __future__ import division
 from __future__ import print_function
+from __future__ import with_statement
+
 
 import csv
@@ -9 +11 @@
 from collections import OrderedDict
 
-def csv_features_to_dict(csv_filename):
+def csv_load_features_to_dict(csv_filename):
     csv_features_file = open(csv_filename,"r")
-    csv_features_reader = csv.reader(csv_features_file, delimiter=',', quotechar='"')
 
-    csv_features_dict = {}
+    try:
+        csv_features_reader = csv.reader(csv_features_file, delimiter=',', quotechar='"')
 
-    line_count = 0
-    header_row = None
+        csv_features_dict = {}
+        
+        line_count = 0
+        header_row = None
+        
+        for row in csv_features_reader:
+            if line_count == 0:
+                row.pop(0)
+                header_row = row
+            else:
+                full_file_id = row[0]
+                
+                pat = re.compile('^import/(\\d+).json$')
+                mat = pat.match(full_file_id)
+                song_id = int(mat.group(1))
 
-    for row in csv_features_reader:
-        if line_count == 0:
-            row.pop(0)
-            header_row = row
-        else:
-            full_file_id = row[0]
+                row.pop(0)
+                row_ordered_dict = OrderedDict()
+                
+                for i in range(0, len(header_row)):
+                    field = header_row[i];
+                    value = row[i];
+                    
+                    row_ordered_dict[field] = value
+                
+                csv_features_dict[song_id] = row_ordered_dict
 
-            pat = re.compile('^import/(\\d+).json$')
-            mat = pat.match(full_file_id)
-            song_id = int(mat.group(1))
+            line_count += 1
 
-            row.pop(0)
-            row_ordered_dict = OrderedDict()
+    finally:
+        csv_features_file.close()
+        return csv_features_dict
 
-            for i in range(0, len(header_row)):
-                field = header_row[i];
-                value = row[i];
+def csv_load_groundtruth_to_dict(csv_filename):
 
-                row_ordered_dict[field] = value
+    # Written in the 'with' style that automatically closes the open()
+    with open(csv_filename,"r") as csv_file:
+        csv_reader = csv.reader(csv_file, delimiter=',')
+
+        csv_gt_dict = {}
+
+        line_count = 0
+        header_row = None
+
+        for row in csv_reader:
+            if line_count == 0:
+                row.pop(0)
+                header_row = row
+            else:
+                song_id = int(row[0])
+                row.pop(0)
+
+                row_ordered_dict = OrderedDict()
+
+                for i in range(0, len(row)):
+                    field = header_row[i];
+                    value = row[i];
+
+                    row_ordered_dict[field] = value
                 
-            csv_features_dict[song_id] = row_ordered_dict
+                csv_gt_dict[song_id] = row_ordered_dict
 
-        line_count += 1
-
-    return csv_features_dict
-
-def csv_groundtruth_to_dict(csv_filename):
-
-    csv_file = open(csv_filename)
-    csv_reader = csv.reader(csv_file, delimiter=',')
-
-    csv_gt_dict = {}
-
-    line_count = 0
-    header_row = None
-
-    for row in csv_reader:
-        if line_count == 0:
-            row.pop(0)
-            header_row = row
-        else:
-            song_id = int(row[0])
-            row.pop(0)
-
-            row_ordered_dict = OrderedDict()
-
-            for i in range(0, len(row)):
-                field = header_row[i];
-                value = row[i];
-
-                row_ordered_dict[field] = value
-                
-            csv_gt_dict[song_id] = row_ordered_dict
-
-        line_count += 1
+            line_count += 1
 
     return csv_gt_dict
@@ -98 +105 @@
     
 
-def ordered_dict_features_to_array(songkey_combined_dict):
+def ordered_dict_features_to_list(songkey_combined_dict):
     
-    features_array = []
+    features_list = []
 
     header = []
@@ -111 +118 @@
         header.append(feature_key)
 
-    features_array.append(header)
+    features_list.append(header)
 
     # Now move on to processing each of the song_key_id entries
@@ -127 +134 @@
 
 
-        features_array.append(row)
+        features_list.append(row)
 
-    return features_array
+    return features_list
         
 
-def csv_save_combined_features(csv_filename,combined_features_array):
+def csv_save_combined_features(csv_filename,combined_features_list):
     csv_features_file = open(csv_filename,"w",newline="")
     csv_features_writer = csv.writer(csv_features_file, delimiter=',', quotechar='"')
 
-    csv_features_writer.writerows(combined_features_array);
+    csv_features_writer.writerows(combined_features_list);
 
 
@@ -157 +164 @@
 
 
-csv_features_dict = csv_features_to_dict(csv_input_filename)
+csv_features_dict = csv_load_features_to_dict(csv_input_filename)
 
-arousal_groundtruth_dict = csv_groundtruth_to_dict(arousal_csv_filename)
-valence_groundtruth_dict = csv_groundtruth_to_dict(valence_csv_filename)
+arousal_groundtruth_dict = csv_load_groundtruth_to_dict(arousal_csv_filename)
+valence_groundtruth_dict = csv_load_groundtruth_to_dict(valence_csv_filename)
 
 print_songkey_dict("Arousal Ground-truth",arousal_groundtruth_dict)
@@ -170 +177 @@
 print_songkey_dict("Essentia Features",csv_features_dict,1)
 
-combined_features_array = ordered_dict_features_to_array(csv_features_dict)
+combined_features_list = ordered_dict_features_to_list(csv_features_dict)
 
 
@@ -177 +184 @@
 print("* Saving combined CSV data to: " + csv_output_filename)
 print("****")
-csv_save_combined_features(csv_output_filename,combined_features_array)
+csv_save_combined_features(csv_output_filename,combined_features_list)