I have a table in a JSON whereby I need an entire row to be deleted/ filtered based on the condition if "Disposition (Non Open Market)" in "transactionType" then delete/ filter entry in all columns. Below is what my JSON file looks like:
{
"lastDate":{
"0":"11\/22\/2022",
"1":"10\/28\/2022",
"2":"10\/17\/2022",
"3":"10\/15\/2022",
"4":"10\/15\/2022",
"5":"10\/15\/2022",
"6":"10\/15\/2022",
"7":"10\/03\/2022",
"8":"10\/03\/2022",
"9":"10\/03\/2022",
"10":"10\/01\/2022",
"11":"10\/01\/2022",
"12":"10\/01\/2022",
"13":"10\/01\/2022",
"14":"10\/01\/2022",
"15":"10\/01\/2022",
"16":"10\/01\/2022",
"17":"10\/01\/2022",
"18":"08\/17\/2022",
"19":"08\/08\/2022",
"20":"08\/05\/2022",
"21":"08\/05\/2022",
"22":"08\/03\/2022",
"23":"05\/06\/2022",
"24":"05\/04\/2022"
},
"transactionType":{
"0":"Sell",
"1":"Automatic Sell",
"2":"Automatic Sell",
"3":"Disposition (Non Open Market)",
"4":"Option Execute",
"5":"Disposition (Non Open Market)",
"6":"Option Execute",
"7":"Automatic Sell",
"8":"Sell",
"9":"Automatic Sell",
"10":"Disposition (Non Open Market)",
"11":"Option Execute",
"12":"Disposition (Non Open Market)",
"13":"Option Execute",
"14":"Disposition (Non Open Market)",
"15":"Option Execute",
"16":"Disposition (Non Open Market)",
"17":"Option Execute",
"18":"Automatic Sell",
"19":"Automatic Sell",
"20":"Disposition (Non Open Market)",
"21":"Option Execute",
"22":"Automatic Sell",
"23":"Disposition (Non Open Market)",
"24":"Automatic Sell"
},
"sharesTraded":{
"0":"20,200",
"1":"176,299",
"2":"8,053",
"3":"6,399",
"4":"13,136",
"5":"8,559",
"6":"16,612",
"7":"167,889",
"8":"13,250",
"9":"176,299",
"10":"177,870",
"11":"365,600",
"12":"189,301",
"13":"365,600",
"14":"184,461",
"15":"365,600",
"16":"189,301",
"17":"365,600",
"18":"96,735",
"19":"15,366",
"20":"16,530",
"21":"31,896",
"22":"25,000",
"23":"1,276",
"24":"25,000"
}
}
My current code is the attempt to delete/ filter out an entry if the value is "Disposition (Non Open Market)":
import json
data = json.load(open("AAPL22_institutional_table_MRKTVAL.json"))
modified = lambda feature: 'Disposition (Non Open Market)' not in feature['transactionType']
data2 = filter(modified, data)
open("AAPL22_institutional_table_MRKTVAL.json", "w").write(
json.dumps(data2, indent=4))
The preferred output JSON (showing the entry being deleted on all 3 columns):
{
"lastDate":{
"0":"11\/22\/2022",
"1":"10\/28\/2022",
"2":"10\/17\/2022",
"4":"10\/15\/2022",
"6":"10\/15\/2022",
"7":"10\/03\/2022",
"8":"10\/03\/2022",
"9":"10\/03\/2022",
"11":"10\/01\/2022",
"13":"10\/01\/2022",
"15":"10\/01\/2022",
"17":"10\/01\/2022",
"18":"08\/17\/2022",
"19":"08\/08\/2022",
"21":"08\/05\/2022",
"22":"08\/03\/2022",
"24":"05\/04\/2022"
},
"transactionType":{
"0":"Sell",
"1":"Automatic Sell",
"2":"Automatic Sell",
"4":"Option Execute",
"6":"Option Execute",
"7":"Automatic Sell",
"8":"Sell",
"9":"Automatic Sell",
"11":"Option Execute",
"13":"Option Execute",
"15":"Option Execute",
"17":"Option Execute",
"18":"Automatic Sell",
"19":"Automatic Sell",
"21":"Option Execute",
"22":"Automatic Sell",
"24":"Automatic Sell"
},
"sharesTraded":{
"0":"20,200",
"1":"176,299",
"2":"8,053",
"4":"13,136",
"6":"16,612",
"7":"167,889",
"8":"13,250",
"9":"176,299",
"11":"365,600",
"13":"365,600",
"15":"365,600",
"17":"365,600",
"18":"96,735",
"19":"15,366",
"21":"31,896",
"22":"25,000",
"24":"25,000"
}
}
CodePudding user response:
I was able to remove according to value by appending the keys that have the string value to a list and then simply removing it
import json
data = json.load(open("AAPL22_institutional_table_MRKTVAL.json"))
delete_keys = []
for value in data['transactionType']:
if data['transactionType'][value] == 'Disposition (Non Open Market)':
delete_keys.append(value)
print(delete_keys)
for key in delete_keys:
del data['transactionType'][key]
del data['lastDate'][key]
del data['sharesTraded'][key]
print(data)
open("AAPL22_institutional_table_MRKTVAL.json", "w").write(
json.dumps(data, indent=4))
CodePudding user response:
data = {
"lastDate":{
"0":"11\/22\/2022",
"1":"10\/28\/2022",
"2":"10\/17\/2022",
"3":"10\/15\/2022",
"4":"10\/15\/2022",
"5":"10\/15\/2022",
"6":"10\/15\/2022",
"7":"10\/03\/2022",
"8":"10\/03\/2022",
},
"transactionType":{
"0":"Sell",
"1":"Automatic Sell",
"2":"Automatic Sell",
"3":"Disposition (Non Open Market)",
"4":"Option Execute",
"5":"Disposition (Non Open Market)",
"6":"Option Execute",
"7":"Automatic Sell",
"8":"Sell",
},
"sharesTraded":{
"0":"20,200",
"1":"176,299",
"2":"8,053",
"3":"6,399",
"4":"13,136",
"5":"8,559",
"6":"16,612",
"7":"167,889",
"8":"13,250",
}
}
for k,v in data["transactionType"].copy().items():
if v == "Disposition (Non Open Market)":
for key in data: # Remove the key from all other nested dictionaries
del data[key][k]
print(data)