Remove all occurences of a value from a nested dictionary - python

I have a nested dictionary as the following.
myDict= {
"id": 10,
"state": "MY LIST",
"Stars":
{
"BookA": {
"id": 10,
"state": "new book",
"Mystery": {
"AuthorA":
{
"id": "100",
"state": "thriller"
},
"AuthorB":
{
"id": "112",
"state": "horror"
}
},
"Thriller": {
"Store1":
{
"id": "300",
"state": "Old"
}
}
}
}
}
I want to return a dictionary which has all of the "state": "text" removed. So that means, I want to remove all the "state" fields and have an output as below.
I want it to be generic method as the dictionary could be nested on many levels.
myDict=
{
id: 10,
"Stars":
{
"BookA": {
"id": 10
"Mystery": {
"AuthorA":
{
"id": "100"
},
"AuthorB":
{
"id": "112"
}
},
"Thriller": {
"Store1":
{
"id": "300"
}
}
}
}
I tried the following but it doesnt seem to work. It only removes the "state": "MY LIST". May someone help me to resolve the issue?
def get(self):
removelist= ["state"]
new_dict = {}
for key, item in myDict.items():
if key not in removelist:
new_dict.update({key: item})
return new_dict
It doesnt remove all the "state" values.

You can use a DFS:
def remove_keys(d, keys):
if isinstance(d, dict):
return {k: remove_keys(v, keys) for k, v in d.items() if k not in keys}
else:
return d
The idea is to remove recursively the keys from subtrees: for every subtree that is a nested dict, return a dict without the keys to remove, using a dict comprehension; for every leaf (that is a single value), just return the value.
Test:
from pprint import pprint
pprint(remove_keys(myDict, ['state']))
Output:
{'Stars': {'BookA': {'Mystery': {'AuthorA': {'id': '100'},
'AuthorB': {'id': '112'}},
'Thriller': {'Store1': {'id': '300'}},
'id': 10}},
'id': 10}

The problem is you aren't handling the nested dictionaries.
def get(self):
removelist= ["state"]
new_dict = {}
for key, item in myDict.items():
if key not in removelist:
new_dict.update({key: item})
if isinstance(item, dict):
# You'll need to handle this use case.
return new_dict
To elaborate, lets look back at your dictionary:
myDict= {
"id": 10, # int
"state": "MY LIST", # string
"Stars": { # dictionary
"BookA": {
"id": 10, # int
"state": "new book", # string
"Mystery": { # dictionary
"AuthorA": {
"id": "100",
"state": "thriller"
},
"AuthorB": {
"id": "112",
"state": "horror"
}
},
"Thriller": {
"Store1": {
"id": "300",
"state": "Old"
}
}
}
}
}
I commented in the types for clarity. Your code is currently parsing myDict and ignoring the key "state". Once you hit the value "Stars", you need to parse that dictionary to also ignore the key "state".

Related

Pythonic way to transform/flatten JSON containing nested table-as-list-of-dicts structures

Suppose I have a table represented in JSON as a list of dicts, where the keys of each item are the same:
J = [
{
"symbol": "ETHBTC",
"name": "Ethereum",
:
},
{
"symbol": "LTC",
"name": "LiteCoin"
:
},
And suppose I require efficient lookup, e.g. symbols['ETHBTC']['name']
I can transform with symbols = { item['name']: item for item in J }, producing:
{
"ETHBTC": {
"symbol": "ETHBTC",
"name": "Ethereum",
:
},
"LTCBTC": {
"symbol": "LTCBTC",
"name": "LiteCoin",
:
},
(Ideally I would also remove the now redundant symbol field).
However, what if each item itself contains a "table-as-list-of-dicts"?
Here's a fuller minimal example (I've removed lines not pertinent to the problem):
J = {
"symbols": [
{
"symbol":"ETHBTC",
"filters":[
{
"filterType":"PRICE_FILTER",
"minPrice":"0.00000100",
},
{
"filterType":"PERCENT_PRICE",
"multiplierUp":"5",
},
],
},
{
"symbol":"LTCBTC",
"filters":[
{
"filterType":"PRICE_FILTER",
"minPrice":"0.00000100",
},
{
"filterType":"PERCENT_PRICE",
"multiplierUp":"5",
},
],
}
]
}
So the challenge is to transform this structure into:
J = {
"symbols": {
"ETHBTC": {
"filters": {
"PRICE_FILTER": {
"minPrice": "0.00000100",
:
}
I can write a flatten function:
def flatten(L:list, key) -> dict:
def remove_key_from(D):
del D[key]
return D
return { D[key]: remove_key_from(D) for D in L }
Then I can flatten the outer list and loop through each key/val in the resulting dict, flattening val['filters']:
J['symbols'] = flatten(J['symbols'], key="symbol")
for symbol, D in J['symbols'].items():
D['filters'] = flatten(D['filters'], key="filterType")
Is it possible to improve upon this using glom (or otherwise)?
Initial transform has no performance constraint, but I require efficient lookup.
I don't know if you'd call it pythonic but you could make your function more generic using recursion and dropping key as argument. Since you already suppose that your lists contain dictionaries you could benefit from python dynamic typing by taking any kind of input:
from pprint import pprint
def flatten_rec(I) -> dict:
if isinstance(I, dict):
I = {k: flatten_rec(v) for k,v in I.items()}
elif isinstance(I, list):
I = { list(D.values())[0]: {k:flatten_rec(v) for k,v in list(D.items())[1:]} for D in I }
return I
pprint(flatten_rec(J))
Output:
{'symbols': {'ETHBTC': {'filters': {'PERCENT_PRICE': {'multiplierUp': '5'},
'PRICE_FILTER': {'minPrice': '0.00000100'}}},
'LTCBTC': {'filters': {'PERCENT_PRICE': {'multiplierUp': '5'},
'PRICE_FILTER': {'minPrice': '0.00000100'}}}}}
Since you have different transformation rules for different keys, you can keep a list of the key names that require "grouping" on:
t = ['symbol', 'filterType']
def transform(d):
if (m:={a:b for a, b in d.items() if a in t}):
return {[*m.values()][0]:transform({a:b for a, b in d.items() if a not in m})}
return {a:b if not isinstance(b, list) else {x:y for j in b for x, y in transform(j).items()} for a, b in d.items()}
import json
print(json.dumps(transform(J), indent=4))
{
"symbols": {
"ETHBTC": {
"filters": {
"PRICE_FILTER": {
"minPrice": "0.00000100"
},
"PERCENT_PRICE": {
"multiplierUp": "5"
}
}
},
"LTCBTC": {
"filters": {
"PRICE_FILTER": {
"minPrice": "0.00000100"
},
"PERCENT_PRICE": {
"multiplierUp": "5"
}
}
}
}
}

Remove keys but keep values from dictionary

Let's say I have this dictionary:
{
"id": "132-sd-sa-23-a-1",
"data": {
"lastUpdated": { "S": "2020-07-22T21:39:20Z" },
"profile": {
"M": {
"address": { "L": [] },
"fakeField": { "S": "someValue" },
"someKey": { "M": { "firstName": { "S": "Test" } } }
}
},
"groups": {
"L": [{ "S": "hello world!" }]
}
}
}
How can I remove the "M", "S", "L", etc. keys from the dictionary but keep the values. So it would turn into this:
{
"id": "132-sd-sa-23-a-1",
"data": {
"lastUpdated": "2020-07-22T21:39:20Z",
"profile": {
"address": [],
"fakeField": "someValue",
"someKey": { "firstName": "Test" }
},
"groups": ["hello world!"]
}
}
I could turn the dictionary into a string, loop through it, and remove what's necessary but that doesn't seem efficient or fast. I can't save the original list as the output that I'm hoping for initially so I need to convert it myself.
Sounds like a job for recursion:
def unsml(obj):
if isinstance(obj, dict):
if len(obj) == 1:
(key, value), *_ = obj.items() # get the only key and value
if key in "SML":
return unsml(value)
return {
key: unsml(value) if isinstance(value, dict) else value
for key, value
in obj.items()
}
elif isinstance(obj, list):
return [unsml(value) for value in obj]
return obj
Then just do new_dict = unsml(old_dict).

How do I extract keys from a dictionary that has {"key":[{"A":"1"},{"B":"2"}]?

I have a python dictionary,
dict = {
"A": [{
"264": "0.1965"
}, {
"289": "0.1509"
}, {
"192": "0.1244"
}]
}
I have a collection in mongoDB that has,
{
"_id": ObjectId("5d5a7f474c55b68a873f9602"),
"A": [{
"264": "0.5700"
}, {
"175": "0.321"
}
}
{
"_id": ObjectId("5d5a7f474c55b68a873f9610"),
"B": [{
"152": "0.2826"
}, {
"012": "0.1234"
}
}
}
I want to see if the key "A" from dict is available in mongodb. If yes, I want to loop over the keys in the list i.e.
[{
"264": "0.19652049960139123"
}, {
"289": "0.1509138215380371"
}, {
"192": "0.12447470015715734"
}]
}
and check if 264 is available in mongodb and update the key value else append.
Expected output in mongodb:
{
"_id": ObjectId("5d5a7f474c55b68a873f9602"),
"A": [{
"264": "0.1965"
}, {
"175": "0.321"
}, {
"289": "0.1509"
}, {
"192": "0.1244"
}
}
{
"_id": ObjectId("5d5a7f474c55b68a873f9610"),
"B": [{
"152": "0.2826"
},{
"012": "0.1234"
}
}
The value for key 264 is updated. Kindly help.
Assuming you are looking for the python part and not the mongoDB, try:
for k,v in dict['A'].items(): #k is key, v is value
process_entry(k, v) #do what you want with the database
assuming your mongodb collection is called your_collection
data= your_collection.find_one({'A':{'$exists':1}})
if data:
#loop over the keys
for item in data['A']:
#check whether a certain key is available
if 'some_key' not in item:
do_something()# update

output every attribute, value in an uneven JSON object

I have a very long and uneven JSON object and I want to output every attribute, value for the end points (leaves) of the object.
For instance, it could look like this:
data = {
"Response": {
"Version": "2.0",
"Detail": {
"TransactionID": "Ib410c-2",
"Timestamp": "04:00"
},
"Transaction": {
"Severity": "Info",
"ID": "2222",
"Text": "Success"
},
"Detail": {
"InquiryDetail": {
"Value": "804",
"CountryISOAlpha2Code": "US"
},
"Product": {
"ID": "PRD",
"Org": {
"Header": {
"valuer": "804"
},
"Location": {
"Address": [
{
"CountryISOAlpha2Code": "US",
"Address": [
{
"Text": {
"#Value": 2,
"$": "Hill St"
}
}
]
}
]
}
}
}
}
}
}
I want to output each potential leaf. It can output the (final attribute or the entire path) and the value.
I know I just need to add something to this:
data = json.loads(inputFile)
small = repeat(data)
for attribute,value in small.iteritems():
print attribute,value
You could use recursion:
def print_leaf_keyvalues(d):
for key, value in d.iteritems():
if hasattr(value, 'iteritems'):
# recurse into nested dictionary
print_leaf_keyvalues(value)
else:
print key, value
Demo on your sample data:
>>> print_leaf_keyvalues(data)
Version 2.0
valuer 804
Address [{'CountryISOAlpha2Code': 'US', 'Address': [{'Text': {'#Value': 2, '$': 'Hill St'}}]}]
ID PRD
CountryISOAlpha2Code US
Value 804
Text Success
Severity Info
ID 2222
This will not handle the list value of Address however. You can always add an additional test for sequences and iterate and recurse again.

Manipulating data structures in Python

I have data in JSON format:
data = {"outfit":{"shirt":"red,"pants":{"jeans":"blue","trousers":"khaki"}}}
I'm attempting to plot this data into a decision tree using InfoVis, because it looks pretty and interactive. The problem is that their graph takes JSON data in this format:
data = {id:"nodeOutfit",
name:"outfit",
data:{},
children:[{
id:"nodeShirt",
name:"shirt",
data:{},
children:[{
id:"nodeRed",
name:"red",
data:{},
children:[]
}],
}, {
id:"nodePants",
name:"pants",
data:{},
children:[{
id:"nodeJeans",
name:"jeans",
data:{},
children:[{
id:"nodeBlue",
name:"blue",
data:{},
children[]
},{
id:"nodeTrousers",
name:"trousers",
data:{},
children:[{
id:"nodeKhaki",
name:"khaki",
data:{},
children:[]
}
}
Note the addition of 'id', 'data' and 'children' to every key and value and calling every key and value 'name'. I feel like I have to write a recursive function to add these extra values. Is there an easy way to do this?
Here's what I want to do but I'm not sure if it's the right way. Loop through all the keys and values and replace them with the appropriate:
for name, list in data.iteritems():
for dict in list:
for key, value in dict.items():
#Need something here which changes the value for each key and values
#Not sure about the syntax to change "outfit" to name:"outfit" as well as
#adding id:"nodeOutfit", data:{}, and 'children' before the value
Let me know if I'm way off.
Here is their example http://philogb.github.com/jit/static/v20/Jit/Examples/Spacetree/example1.html
And here's the data http://philogb.github.com/jit/static/v20/Jit/Examples/Spacetree/example1.code.html
A simple recursive solution:
data = {"outfit":{"shirt":"red","pants":{"jeans":"blue","trousers":"khaki"}}}
import json
from collections import OrderedDict
def node(name, children):
n = OrderedDict()
n['id'] = 'node' + name.capitalize()
n['name'] = name
n['data'] = {}
n['children'] = children
return n
def convert(d):
if type(d) == dict:
return [node(k, convert(v)) for k, v in d.items()]
else:
return [node(d, [])]
print(json.dumps(convert(data), indent=True))
note that convert returns a list, not a dict, as data could also have more then one key then just 'outfit'.
output:
[
{
"id": "nodeOutfit",
"name": "outfit",
"data": {},
"children": [
{
"id": "nodeShirt",
"name": "shirt",
"data": {},
"children": [
{
"id": "nodeRed",
"name": "red",
"data": {},
"children": []
}
]
},
{
"id": "nodePants",
"name": "pants",
"data": {},
"children": [
{
"id": "nodeJeans",
"name": "jeans",
"data": {},
"children": [
{
"id": "nodeBlue",
"name": "blue",
"data": {},
"children": []
}
]
},
{
"id": "nodeTrousers",
"name": "trousers",
"data": {},
"children": [
{
"id": "nodeKhaki",
"name": "khaki",
"data": {},
"children": []
}
]
}
]
}
]
}
]

Categories