We Keep Coding

A Python script that can navigate a .json and export a .csv based on a search term

I want to take a .json of "_PRESET..." items and their "code-state"s with "actions" that contain other "code-state"s, "appearance"s, and "switch"s and turn it into .csv produced from the actions under a given "_PRESET...", including the "code-state"s and the "actions" listed under their individual entries.
This would allow a user to enter the "_PRESET..." name and receive a 3-column .csv file containing each action's "type", name, and "value". There are of course ways to export the entire .json easily, but I can't fathom a way to navigate it like is needed.
enters "_PRESET_Config_A" for
input.json:
{
"abc_data": {
"_PRESET_Config_A": {
"properties": {
"category": "configuration",
"name": "_PRESET_Config_A",
"collection": null,
"description": ""
},
"actions": {
"EN-R9": {
"type": "code_state",
"value": "on"
}
}
},
"PN4FP": {
"properties": {
"category": "uncategorized",
"name": "PN4FP",
"collection": null,
"description": ""
},
"actions": {
"E_xxxxxx_Default": {
"type": "appearance",
"value": "M_Red"
}
}
},
"HEDIS": {
"properties": {
"category": "uncategorized",
"name": "HEDIS",
"collection": null,
"description": ""
},
"actions": {
"E_xxxxxx_Default": {
"type": "appearance",
"value": "M_Purple"
}
}
},
"_PRESET_Config_B": {
"properties": {
"category": "configuration",
"name": "_PRESET_Config_A",
"collection": null,
"description": ""
},
"actions": {
"HEDIS": {
"type": "code_state",
"value": "on"
}
}
},
"EN-R9": {
"properties": {
"category": "uncategorized",
"name": "EN-R9",
"collection": null,
"description": ""
},
"actions": {
"PN4FP": {
"type": "code_state",
"value": "on"
},
"switch_StorageBin": {
"type": "switch",
"value": "00_w_Storage_Bin_R9"
}
}
}
}
}
Desired output.csv
type,name,value
code_state,EN-R9,on
code_state,PN4FP,on
appearance,E_xxxxxx_Default,M_Red
switch,switch_StorageBin,00_w_Storage_Bin_R9

Is there a way to add curly brackets around a list of dictionaries already existing within a JSON file?

I currently have two JSONS that I want to merge into one singular JSON, additionally I want to add in a slight change.
Firstly, these are the two JSONS in question.
An intents JSON:
[
{
"ID": "G1",
"intent": "password_reset",
"examples": [
{
"text": "I forgot my password"
},
{
"text": "I can't log in"
},
{
"text": "I can't access the site"
},
{
"text": "My log in is failing"
},
{
"text": "I need to reset my password"
}
]
},
{
"ID": "G2",
"intent": "account_closure",
"examples": [
{
"text": "I want to close my account"
},
{
"text": "I want to terminate my account"
}
]
},
{
"ID": "G3",
"intent": "account_creation",
"examples": [
{
"text": "I want to open an account"
},
{
"text": "Create account"
}
]
},
{
"ID": "G4",
"intent": "complaint",
"examples": [
{
"text": "A member of staff was being rude"
},
{
"text": "I have a complaint"
}
]
}
]
and an entities JSON:
[
{
"ID": "K1",
"entity": "account_type",
"values": [
{
"type": "synonyms",
"value": "business",
"synonyms": [
"corporate"
]
},
{
"type": "synonyms",
"value": "personal",
"synonyms": [
"vanguard",
"student"
]
}
]
},
{
"ID": "K2",
"entity": "beverage",
"values": [
{
"type": "synonyms",
"value": "hot",
"synonyms": [
"heated",
"warm"
]
},
{
"type": "synonyms",
"value": "cold",
"synonyms": [
"ice",
"freezing"
]
}
]
}
]
The expected outcome is to create a JSON file that mimics this structure:
{
"intents": [
{
"intent": "password_reset",
"examples": [
{
"text": "I forgot my password"
},
{
"text": "I want to reset my password"
}
],
"description": "Reset a user password"
}
],
"entities": [
{
"entity": "account_type",
"values": [
{
"type": "synonyms",
"value": "business",
"synonyms": [
"company",
"corporate",
"enterprise"
]
},
{
"type": "synonyms",
"value": "personal",
"synonyms": []
}
],
"fuzzy_match": true
}
],
"metadata": {
"api_version": {
"major_version": "v2",
"minor_version": "2018-11-08"
}
},
"dialog_nodes": [
{
"type": "standard",
"title": "anything_else",
"output": {
"generic": [
{
"values": [
{
"text": "I didn't understand. You can try rephrasing."
},
{
"text": "Can you reword your statement? I'm not understanding."
},
{
"text": "I didn't get your meaning."
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"conditions": "anything_else",
"dialog_node": "Anything else",
"previous_sibling": "node_4_1655399659061",
"disambiguation_opt_out": true
},
{
"type": "event_handler",
"output": {
"generic": [
{
"title": "What type of account do you hold with us?",
"options": [
{
"label": "Personal",
"value": {
"input": {
"text": "personal"
}
}
},
{
"label": "Business",
"value": {
"input": {
"text": "business"
}
}
}
],
"response_type": "option"
}
]
},
"parent": "slot_9_1655398217028",
"event_name": "focus",
"dialog_node": "handler_6_1655398217052",
"previous_sibling": "handler_7_1655398217052"
},
{
"type": "event_handler",
"output": {},
"parent": "slot_9_1655398217028",
"context": {
"account_type": "#account_type"
},
"conditions": "#account_type",
"event_name": "input",
"dialog_node": "handler_7_1655398217052"
},
{
"type": "standard",
"title": "business_account",
"output": {
"generic": [
{
"values": [
{
"text": "We have notified your corporate security team, they will be in touch to reset your password."
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"parent": "node_3_1655397279884",
"next_step": {
"behavior": "jump_to",
"selector": "body",
"dialog_node": "node_4_1655399659061"
},
"conditions": "#account_type:business",
"dialog_node": "node_1_1655399028379",
"previous_sibling": "node_3_1655399027429"
},
{
"type": "standard",
"title": "intent_collection",
"output": {
"generic": [
{
"values": [
{
"text": "Thank you for confirming that you want to reset your password."
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"next_step": {
"behavior": "jump_to",
"selector": "body",
"dialog_node": "node_3_1655397279884"
},
"conditions": "#password_reset",
"dialog_node": "node_3_1655396920143",
"previous_sibling": "Welcome"
},
{
"type": "frame",
"title": "account_type_confirmation",
"output": {
"generic": [
{
"values": [
{
"text": "Thank you"
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"parent": "node_3_1655396920143",
"context": {},
"next_step": {
"behavior": "skip_user_input"
},
"conditions": "#password_reset",
"dialog_node": "node_3_1655397279884"
},
{
"type": "standard",
"title": "personal_account",
"output": {
"generic": [
{
"values": [
{
"text": "We have sent you an email with a password reset link."
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"parent": "node_3_1655397279884",
"next_step": {
"behavior": "jump_to",
"selector": "body",
"dialog_node": "node_4_1655399659061"
},
"conditions": "#account_type:personal",
"dialog_node": "node_3_1655399027429"
},
{
"type": "standard",
"title": "reset_confirmation",
"output": {
"generic": [
{
"values": [
{
"text": "Do you need assistance with anything else today?"
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"digress_in": "does_not_return",
"dialog_node": "node_4_1655399659061",
"previous_sibling": "node_3_1655396920143"
},
{
"type": "slot",
"output": {},
"parent": "node_3_1655397279884",
"variable": "$account_type",
"dialog_node": "slot_9_1655398217028",
"previous_sibling": "node_1_1655399028379"
},
{
"type": "standard",
"title": "welcome",
"output": {
"generic": [
{
"values": [
{
"text": "Hello. How can I help you?"
}
],
"response_type": "text",
"selection_policy": "sequential"
}
]
},
"conditions": "welcome",
"dialog_node": "Welcome"
}
],
"counterexamples": [],
"system_settings": {
"off_topic": {
"enabled": true
},
"disambiguation": {
"prompt": "Did you mean:",
"enabled": true,
"randomize": true,
"max_suggestions": 5,
"suggestion_text_policy": "title",
"none_of_the_above_prompt": "None of the above"
},
"human_agent_assist": {
"prompt": "Did you mean:"
},
"intent_classification": {
"training_backend_version": "v2"
},
"spelling_auto_correct": true
},
"learning_opt_out": false,
"name": "Reset Password",
"language": "en",
"description": "Basic Password Reset Request"
}
So what I am missing in my original files, is essentially:
"intents":
and for the entities file:
"entities"
at the start of each list of dictionaries.
Additionally, I would need to wrap the whole thing in curly braces to comply with json formatting.
As seen, the final goal is not just appending these two to one another but the file technically continues with some other JSON code that I have yet to write and deal with.
My question now is as follows; by what method can I either add in these words and the braces to the individual files, then combine them into a singular JSON or alternatively by what method can I read in these files and combine them with the changes all in one go?
The new output file closing on a curly brace after the entities list of dicts is an acceptable outcome for me at the time, so that I can continue to make changes and hopefully further learn from this how to do these changes in future when I get there.
TIA

JSON is only a string format, you can it load in a language structure, in python that is list and dict, do what you need then dump it back, so you don't "add strings" and "add brackets", on modify the structure
file = 'intents.txt'
intents = json.load(open(file)) # load a list
file = 'entities.txt'
entities = json.load(open(file)) # load a list
# create a dict
content = {
"intents": intents,
"entities": entities
}
json.dump(content, open(file, "w"))

If you're reading all the json in as a string, you can just prepend "{'intents':" to the start and append a closing "}".
myJson = "your json string"
myWrappedJson = '{"intents":' + myJson + "}"

Why am I receiving an error when attempting to parse JSON object within for loop?

Everything with my script runs fine until I try to run it through a for loop. Specifically, when I attempt to index a specific array within the object. Before I get to the The script is intended to grab the delivery date for each tracking number in my list.
This is my script:
import requests
import json
TrackList = ['1Z3X756E0310496105','1ZX0373R0303581450','1ZX0373R0103574417']
url = 'https://onlinetools.ups.com/rest/Track'
para1 = '...beginning of JSON request string...'
para2 = '...end of JSON request string...'
for TrackNum in TrackList:
parameters = para1+TrackNum+para2
resp = requests.post(url = url, data = parameters, verify=False)
data = json.loads(resp.text)
DelDate = data['TrackResponse']['Shipment']['Package'][0]['Activity'][0]['Date']
print(DelDate)
JSON API Response (if needed):
{
"TrackResponse": {
"Response": {
"ResponseStatus": {
"Code": "1",
"Description": "Success"
},
"TransactionReference": {
"CustomerContext": "Analytics Inquiry"
}
},
"Shipment": {
"InquiryNumber": {
"Code": "01",
"Description": "ShipmentIdentificationNumber",
"Value": "1ZX0373R0103574417"
},
"Package": {
"Activity": [
{
"ActivityLocation": {
"Address": {
"City": "OKLAHOMA CITY",
"CountryCode": "US",
"PostalCode": "73128",
"StateProvinceCode": "OK"
},
"Code": "M3",
"Description": "Front Desk",
"SignedForByName": "CUMMINGS"
},
"Date": "20190520",
"Status": {
"Code": "9E",
"Description": "Delivered",
"Type": "D"
},
"Time": "091513"
},
{
"ActivityLocation": {
"Address": {
"City": "Oklahoma City",
"CountryCode": "US",
"StateProvinceCode": "OK"
},
"Description": "Front Desk"
},
"Date": "20190520",
"Status": {
"Code": "OT",
"Description": "Out For Delivery Today",
"Type": "I"
},
"Time": "085943"
},
{
"ActivityLocation": {
"Address": {
"City": "Oklahoma City",
"CountryCode": "US",
"StateProvinceCode": "OK"
},
"Description": "Front Desk"
},
"Date": "20190520",
"Status": {
"Code": "DS",
"Description": "Destination Scan",
"Type": "I"
},
"Time": "011819"
},
{
"ActivityLocation": {
"Address": {
"City": "Oklahoma City",
"CountryCode": "US",
"StateProvinceCode": "OK"
},
"Description": "Front Desk"
},
"Date": "20190519",
"Status": {
"Code": "AR",
"Description": "Arrival Scan",
"Type": "I"
},
"Time": "235100"
},
{
"ActivityLocation": {
"Address": {
"City": "DFW Airport",
"CountryCode": "US",
"StateProvinceCode": "TX"
},
"Description": "Front Desk"
},
"Date": "20190519",
"Status": {
"Code": "DP",
"Description": "Departure Scan",
"Type": "I"
},
"Time": "195500"
},
{
"ActivityLocation": {
"Address": {
"City": "DFW Airport",
"CountryCode": "US",
"StateProvinceCode": "TX"
},
"Description": "Front Desk"
},
"Date": "20190517",
"Status": {
"Code": "OR",
"Description": "Origin Scan",
"Type": "I"
},
"Time": "192938"
},
{
"ActivityLocation": {
"Address": {
"CountryCode": "US"
},
"Description": "Front Desk"
},
"Date": "20190517",
"Status": {
"Code": "MP",
"Description": "Order Processed: Ready for UPS",
"Type": "M"
},
"Time": "184621"
}
],
"PackageWeight": {
"UnitOfMeasurement": {
"Code": "LBS"
},
"Weight": "2.00"
},
"ReferenceNumber": [
{
"Code": "01",
"Value": "8472745558"
},
{
"Code": "01",
"Value": "5637807:1007379402:BN81-17077A:1"
},
{
"Code": "01",
"Value": "5637807"
}
],
"TrackingNumber": "1ZX0373R0103574417"
},
"PickupDate": "20190517",
"Service": {
"Code": "001",
"Description": "UPS Next Day Air"
},
"ShipmentAddress": [
{
"Address": {
"AddressLine": "S 600 ROYAL LN",
"City": "COPPELL",
"CountryCode": "US",
"PostalCode": "750193827",
"StateProvinceCode": "TX"
},
"Type": {
"Code": "01",
"Description": "Shipper Address"
}
},
{
"Address": {
"City": "OKLAHOMA CITY",
"CountryCode": "US",
"PostalCode": "73128",
"StateProvinceCode": "OK"
},
"Type": {
"Code": "02",
"Description": "ShipTo Address"
}
}
],
"ShipmentWeight": {
"UnitOfMeasurement": {
"Code": "LBS"
},
"Weight": "2.00"
},
"ShipperNumber": "X0373R"
}
}
}
Below is the error I receive:
Traceback (most recent call last):
File "/Users/***/Library/Preferences/PyCharmCE2019.1/scratches/UPS_API.py", line 15, in <module>
DelDate = data['TrackResponse']['Shipment']['Package'][0]['Activity'][0]['Date']
KeyError: 0

You're trying to index "Package" at index 0, but it's an object not an array. So you should be accessing ['Package']['Activity']

just take away the [0] because there is no [1] or [2]

issue in Elastic Search Term Aggregation

In elastic search aggregation query I need to get all the movies watched by the user who watches the movie "Frozen". This is how my Result source
{
"_index": "user",
"_type": "user",
"_id": "ovUowmUBREWOv-CU-4RT",
"_version": 4,
"_score": 1,
"_source": {
"movies": [
"Angry birds 1",
"PINNOCCHIO",
"Frozen",
"Hotel Transylvania 3"
],
"user_id": 86
}
}
This is the query I'm using.
{
"query": {
"match": {
"movies": "Frozen"
}
},
"size": 0,
"aggregations": {
"movies_like_Frozen": {
"terms": {
"field": "movies",
"min_doc_count": 1
}
}
}
}
The result I got in the bucket is correct, but the movie names are splits by white space like this
"buckets": [
{
"key": "3",
"doc_count": 2
},
{
"key": "hotel",
"doc_count": 2
},
{
"key": "transylvania",
"doc_count": 2
},
{
"key": "1",
"doc_count": 1
},
{
"key": "angry",
"doc_count": 1
},
{
"key": "birds",
"doc_count": 1
}
]
How can I get buckets with "Angry birds 1", "Hotel Transylvania 3" as result.
Please help.

In elasticsearch 6.x, every text field is analyzed implicitly. To override this, you need to create a mapping for text type fields as not_analyzed in an index, then insert documents in it.
In your case,
{
"mappings": {
"user": {
"properties": {
"movies": {
"type": "text",
"index": "not_analyzed",
"fields": {
"keyword": {
"type": "text",
"index": "not_analyzed"
}
}
},
"user_id": {
"type": "long"
}
}
}
}
}
Hope it works.

"object mapping [prices] can't be changed from nested to non-nested" on Bulk Python

I'm trying to insert a doc in ElasticSearch but every time i try to insert in python, its return me an error. But if i try to insert from Kibana or cUrl, its succeed.
I already tried the elasticserach-dsl but i've got the same error.
(Sorry for my bad english, i'm from brazil :D)
Error i've got:
elasticsearch.helpers.BulkIndexError: ((...)'status': 400, 'error': {'type':
'illegal_argument_exception', 'reason': "object mapping [prices] can't be changed from nested to non-nested"}}}])
My code:
from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk
doc = [{
"_index": "products",
"_type": "test_products",
"_source": {
[...]
"prices": {
"latest": {
"value": 89,
"when": 1502795602848
},
"old": [
{
"value": 0,
"when": 1502795602848
}
]
},
"sizes": [
{
"name": "P",
"available": True
},
{
"name": "M",
"available": True
}
],
"created": "2017-08-15T08:13:22.848284"
}
}]
bulk(self.es, doc, index="products")
My ES mapping:
{
"test_products": {
"mappings": {
"products": {
"properties": {
"approved": {
"type": "boolean"
},
"available": {
"type": "boolean"
},
"brand": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"buyClicks": {
"type": "integer"
},
"category": {
"type": "keyword"
},
"code": {
"type": "keyword"
},
"color": {
"type": "nested",
"properties": {
"name": {
"type": "keyword"
},
"value": {
"type": "keyword"
}
}
},
"created": {
"type": "date"
},
"description": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"gender": {
"type": "keyword"
},
"images": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"likes": {
"type": "integer"
},
"link": {
"type": "keyword"
},
"name": {
"type": "text",
"term_vector": "yes",
"analyzer": "nGram_analyzer",
"search_analyzer": "whitespace_analyzer"
},
"prices": {
"type": "nested",
"properties": {
"latest": {
"type": "nested",
"properties": {
"value": {
"type": "long"
},
"when": {
"type": "date",
"format": "dd-MM-yyyy||epoch_millis"
}
}
},
"old": {
"type": "nested",
"properties": {
"value": {
"type": "long"
},
"when": {
"type": "date",
"format": "dd-MM-yyyy||epoch_millis"
}
}
}
}
},
"redirectClicks": {
"type": "integer"
},
"sizes": {
"type": "nested",
"properties": {
"available": {
"type": "boolean"
},
"name": {
"type": "keyword"
},
"quantity": {
"type": "integer"
}
}
},
"slug": {
"type": "keyword"
},
"store": {
"type": "keyword"
},
"subCategories": {
"type": "nested",
"properties": {
"name": {
"type": "keyword"
},
"value": {
"type": "keyword"
}
}
},
"tags": {
"type": "text",
"fields": {
"raw": {
"type": "text",
"term_vector": "yes",
"analyzer": "nGram_analyzer",
"search_analyzer": "whitespace_analyzer"
}
}
},
"thumbnails": {
"type": "keyword"
}
}
}
}
}
}