Changeset 34908

Timestamp:

2021-02-21T15:06:11+13:00 (3 years ago)

Author:

davidb

Message:

Name change to better reflect what the script does

File:

• main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/voting-excel/xlsx-fromcountry-jsonmetadata.py (moved) (moved from main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/voting-excel/xlsx-fromcountry-csvmetadata.py ) (6 diffs)

main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/prepare/voting-excel/xlsx-fromcountry-jsonmetadata.py

@@ -7 +7 @@
 import sys
 import json
+#import csv
 
 import argparse
@@ -39 +40 @@
     # Debug output
     #
-    for data_hashmap in data_hashmap_array_finals:
-        print(data_hashmap.get('From country'), data_hashmap.get('Year'), data_hashmap.get('Points'), "(Points to " + data_hashmap.get('To country') + ")")
+    # for data_hashmap in data_hashmap_array_finals:
+    #    print(data_hashmap.get('From country'), data_hashmap.get('Year'), data_hashmap.get('Points'), "(Points to " + data_hashmap.get('To country') + ")")
 
 
@@ -67 +68 @@
     country_group.append(prev_data_hashmap)        
     country_groups.append(country_group)
+
+    # Debug output
+    
+    for from_country_voting_array in country_groups:
+        # from_country_voting_array => Votes case by given country (in given year) to other countries
+
+        from_country_name = from_country_voting_array[0].get('From country')
+        print(from_country_name+":")
+
+        for to_country_entry in from_country_voting_array:
+            print("  ", to_country_entry.get('Year'), to_country_entry.get('Points'),
+                  " ("+to_country_entry.get('Jury or Televoting')+") ",
+                  " Points to " + to_country_entry.get('To country'))
+
 
     return country_groups
@@ -90 +105 @@
     # }
 
+
+
+    # Scan all voting to build up complete list of all countries that
+    # either cast of received votes
+
+    all_from_countries_year = []
+    all_to_countries_tj     = []
+    
+    for from_country_voting_array in country_groups:
+        from_country = from_country_voting_array[0].get('From country')
+        year = from_country_voting_array[0].get('Year')
+
+        ### Remove spaces!!!
+        from_country_year = from_country + "-" + year
+
+        all_from_countries_year[from_country_year] = 1
+        
+        for to_country_entry in from_country_voting_array:
+            to_country = to_country_entry.get('To country')
+            vote_type = to_country_entry.get('Jury or Televoting')
+
+            to_country_vote_type = to_country+"-"+vote_type
+            
+            all_to_countries[to_country_vote_type] = 1
+
+
+    from_country_to_hashmap = []
+    
+    
+    for to_country_entry in from_country_voting_array:
+        print("  ", to_country_entry.get('Year'), to_country_entry.get('Points'),
+                  " ("+to_country_entry.get('Jury or Televoting')+") ",
+                  " Points to " + to_country_entry.get('To country'))
+            
+
+    csv_header_array = sorted(all_to_countries_tj.keys())
+
+            
+    csv_ofile = open(csv_filename, 'wb')
+
+    csv_wr  = csv.writer(csv_ofile, quoting=csv.QUOTE_ALL)
+
+            
+#            csv_wr.writerow(filtered_utf8_row)
+
+    
+
+    csv_ofile.close()
+    
     fileset_array = []
     
@@ -136 +200 @@
     id_year = to_country_year_votes[0].get('Year');
     id = id_to_country + str(id_year);
-    filename_id = id + "\\.nul"
+<    filename_id = id + "\\.nul"
 
     fileset = {
@@ -151 +215 @@
 
     parser = argparse.ArgumentParser()
+    parser.add_argument('--sheetname', help="The name of the sheet within the Excel file to extractc data from")
+    parser.add_argument('--voting-type', choices=['J','T'], help="Filter to only J=Jury or T=Tele cast votes")
     parser.add_argument('input-file.xlsx')
     parser.add_argument('output-file.csv', nargs='?')
-    parser.add_argument('--sheetname')
     
     args = parser.parse_args()
 
+    sheetname = getattr(args,'sheetname');
+    if (csv_output_filename == None):
+        csv_output_filename = os.path.splitext(excel_input_filename)[0]+'.csv'
+
+    voting_type = getattr(args,'voting-type');
+    
     excel_input_filename = getattr(args,'input-file.xlsx');
     csv_output_filename = getattr(args,'output-file.csv');
-    sheetname = getattr(args,'sheetname');
-    
-    if (csv_output_filename == None):
-        csv_output_filename = os.path.splitext(excel_input_filename)[0]+'.csv'
+    
         
     worksheet = xlsxutil.load_xslx_sheet(excel_input_filename,sheetname)
 
     data_hashmap_array = xlsxutil.convert_worksheet_to_hashmaps(worksheet)
-
-    print("Number of data rows: " + str(len(data_hashmap_array)))
-
-    
-    from_country_year_voting_groups = create_from_country_voting_groups(data_hashmap_array)
+    
+    print("Number of data rows in Excel file: " + str(len(data_hashmap_array)))
+
+    # Filter down to just the voting results concerning finals
+    data_hashmap_array_finals = list(filter(xlsxutil.filter_finalist_votes, data_hashmap_array))
+
+    print("Number of finalist voting data rows: " + str(len(data_hashmap_array_finals)))
+
+    if voting_type != None:
+        # Further filter down by the type of voting results cast
+        if (voting_type == "J"):
+            data_hashmap_array_finals = list(filter(xlsxutil.filter_jury_votes, data_hashmap_array_finals))
+            print("Number Jury cast data rows: " + str(len(data_hashmap_array_finals)))
+        else:
+            # Must be "T"
+            data_hashmap_array_finals = list(filter(xlsxutil.filter_tele_votes, data_hashmap_array_finals))
+            print("Number Jury cast data rows: " + str(len(data_hashmap_array_finals)))
+
+
+
+    from_country_year_voting_groups = create_from_country_voting_groups(data_hashmap_array_finals)
 
     # Debug output
     #
-    print(from_country_year_voting_groups)
+    #print(from_country_year_voting_groups)
     
     # Next step is to express the grouped from-country voting data
-    # in the Greenstone JSON metadata format:
-    
-
+    # as a CSV file in the form used by Greenstone's CSVPlugin
+    
     
 #    directory_metadata = []