Add update_categories script (#741)

README.md

@@ -53,6 +53,7 @@ Or if you're comfortable with json files, here is how it would look like:
 {
   "Contributors": [""],
   "Source": [""],
+  "URL": [""],
   "Categories": [""],
   "Reasoning": [""],
   "Definition": [""],

src/test_all.py

@@ -29,6 +29,7 @@
 # read all the tasks and make sure that they're following the right pattern
 tasks_path = 'tasks/'
 
+#TODO: We need to add URL here after updating the tasks
 expected_keys = [
     "Definition",
     "Input_language",

src/update_category_assignment.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+import json
+import pandas as pd
+from collections import OrderedDict
+
+tasks_path = 'tasks/'
+meta = pd.read_csv("Natural Instructions V2 Exps - tasks review 0323 (final).csv").values
+key_order = ("Contributors","Source","URL","Categories","Reasoning","Definition","Input_language","Output_language","Instruction_language","Domains","Positive Examples","Negative Examples","Instances")
+
+def ordered(d, key_order):
+    return OrderedDict([(key, d[key]) for key in key_order])
+
+for row in range(len(meta)):
+        file = meta[row][0] + '.json'
+        file_path = tasks_path + file
+        with open(file_path, 'r') as f:
+            try:
+                data = json.load(f)
+            except:
+                with open(file_path, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+
+        data['Categories'] = [meta[row][5]]
+        data['Source'] = [meta[row][2]]        
+        data['URL'] = [meta[row][3]]     
+
+        data = ordered(data, key_order)
+        with open(file_path, 'w', encoding='utf-8') as outfile:
+            json.dump(data, outfile, indent=4,ensure_ascii=False)