Develop Reference

python according to the same value combining dictionary

i have a list of dict like this
[
{'id': 'A123',
'feature': {'name': 'jack', 'age' : '18' },
'create_time': '2022-5-17 10:29:47',
'is_fast': False},
{'id': 'A123',
'feature': {'gender': 'male'},
'create_time': '2022-5-17 10:29:47',
'is_fast': False},
{'id': 'A123',
'habit': {'name': 'read'},
'create_time': '2022-5-15 10:29:45',
'is_fast': False},
{'id': 'A456',
'feature': {'name': 'rose'},
'create_time': '2022-4-15 10:29:45',
'is_fast': False},
{'id': 'A456',
'habit': {'name': 'sport'},
'create_time': '2022-3-15 10:29:45',
'is_fast': False}
]
But I want to merge the same "id" values ​​together using something function
The desired output is as follows
[
{'id': 'A123',
'feature': {'name': 'jack', 'age' : '18' ,'gender': 'male'},
'habit': {'name': 'read'},
'create_time': '2022-5-19 10:29:47', #Get the latest time based on the same id
'is_fast': False},
{'id': 'A456',
'feature': {'name': 'rose'},
'habit': {'name': 'sport'},
'create_time': '2022-4-15 10:29:45',
'is_fast': False},
]
How can I merge the same "id" values ​​according to these dictionaries..

This should get you started... I put some inline notes to explain what the code is doing. You still need to implement a date time comparison.
def merge_dicts(lst):
final = {} # results
for row in lst: # iterate through list
if row['id'] not in final: # if current item id hasnt been seen
final[row['id']] = row # assign it to results with id as the key
else:
record = final[row['id']] # otherwise compare to data already stored
for k,v in row.items(): #iterate through dictionary items
if k not in record: # if key not in results
record[k] = v # add the key and value
continue
if record[k] == v: continue # if they are already equal move on
if isinstance(v, dict): # if its a dictionary
record[k].update(v) # update the dictionary
else: # must be date time sequence so do some datetime comparison
"""Do some date comparison and assign correct date"""
return [v for k,v in final.items()] # convert to list
print(merge_dicts(lst))
output:
[
{
'id': 'A123',
'feature': {'name': 'jack', 'age': '18', 'gender': 'male'},
'create_time': '2022-5-17 10:29:47',
'is_fast': False,
'habit': {'name': 'read'}
},
{
'id': 'A456',
'feature': {'name': 'rose'},
'create_time': '2022-4-15 10:29:45',
'is_fast': False,
'habit': {'name': 'sport'}
}
]

You can use the dict.setdefault method to initialize sub-dicts under keys that don't already exist to avoid cluttering up your code with conditional statements that test the existence of keys:
merged = {}
for d in lst:
s = merged.setdefault(d['id'], d)
for k, v in d.items():
if isinstance(v, dict):
s.setdefault(k, v).update(v)
elif v > s[k]: # the dates/times in the input follow alphabetical order
s[k] = v # later dates/times takes precedence
print(list(merged.values()))
Demo: https://replit.com/#blhsing/BlandCarelessPolygons#main.py

Why only last element is printing while using function [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
I need to get the value for business' name and append it to a list.
I need to get the value policies and append to a list after checking parent.
if parent is Marketing name has to added to level1.
if parent is Advertising name has to added to level2.
if some place Business is [] I need to pass None instead of Null List
Also need to check key exists or not for some keys there is a chance of missing policies, business
dictionary is below
If in the list contains same elements example 'Business':['Customer', Customer] then only one element has to take
searchtest = [
{'_index': 'newtest',
'_type': '_doc',
'_id': '100',
'_score': 1.0,
'_source': {'id': '100',
'name': 'A',
'policies': [
{
'id': '332',
'name': 'Second division',
'parent': 'Marketing'},
{'id': '3323', 'name':
'First division',
'parent': 'Marketing'}
]
}
},
{'_index': 'newtest',
'_type': '_doc',
'_id': '101',
'_score': 1.0,
'_source': {
'id': '101',
'name': 'B',
'Business': [{'id': '9'}, {'id': '10', 'name': 'Customer'}],
'policies': [{'id': '332', 'name': 'Second division', 'parent': 'Marketing'}, {'id': '3323', 'name': 'First division', 'parent': 'Advertising'}]}}]`
Code is below
def business(searchtest):
for el in searchtest:
Business_List = []
if 'Business' in el['_source']:
for j in el['_source']['Business']:
if 'name' in j:
Business_List.append(j['name'])
else:
Business_List.extend([])
return Business_List
def policy(searchtest):
for el in searchtest:
level1= []
if 'policies' in el['_source']:
for j in el['_source']['policies']:
if 'parent' in j:
if 'Marketing' in j['parent'] :
level1.append(j['name'])
else:
level1.extend([])
level2= []
if 'policies' in el['_source']:
for j in el['_source']['policies']:
if 'parent' in j:
if 'Advertising' in j['parent']:
level2.append(j['name'])
else:
level2.extend([])
return [level1, level2]
def data_product(searchtest):
resp = []
for el in searchtest:
d = {
'id' : el['_source']['id'],
'name' : el['_source']['name'],
'Business' : business(searchtest),
'level1' : policy(searchtest)[0],
'level2' : policy(searchtest)[1]
}
resp.append(d)
return resp
if __name__ == "__main__":
import pprint
pp = pprint.PrettyPrinter(4)
pp.pprint(data_product(searchtest))
My output
[ { 'Business': [],
'id': '101',
'level1': ['Second division'],
'level2': ['First division'],
'name': 'B'}]
Expected out
[ { 'Business': [],
'id': '100',
'level1': ['Second division','First division'],
'level2': [],
'name': 'A'},
{ 'Business': ['Customer'],
'id': '101',
'level1': ['Second division'],
'level2': ['First division'],
'name': 'B'}]
if resp.append(d) is put inside the loop then only one id is repeating?

my whole code with change
searchtest = [{'_index': 'newtest',
'_type': '_doc',
'_id': '100',
'_score': 1.0,
'_source': {'id': '100',
'name': 'A',
'policies': [{'id': '332',
'name': 'Second division',
'parent': 'Marketing'},
{'id': '3323', 'name': 'First division', 'parent': 'Marketing'}]}},
{'_index': 'newtest',
'_type': '_doc',
'_id': '101',
'_score': 1.0,
'_source': {'id': '101',
'name': 'B',
'Business': [{'id': '9'}, {'id': '10', 'name': 'Customer'}],
'policies': [{'id': '332',
'name': 'Second division',
'parent': 'Marketing'},
{'id': '3323', 'name': 'First division', 'parent': 'Advertising'}]}}]
def business(el):
Business_List = []
# for el in searchtest:
if 'Business' in el['_source']:
for j in el['_source']['Business']:
if 'name' in j:
Business_List.append(j['name'])
else:
Business_List.extend([])
return Business_List
def policy(searchtest):
for el in searchtest:
level1 = []
if 'policies' in el['_source']:
for j in el['_source']['policies']:
if 'parent' in j:
if 'Marketing' in j['parent']:
level1 .append(j['name'])
else:
level1 .extend([])
level2 = []
if 'policies' in el['_source']:
for j in el['_source']['policies']:
if 'parent' in j:
if 'Advertising' in j['parent']:
level2.append(j['name'])
else:
level2.extend([])
return [level1, level1 ]
def data_product(searchtest):
resp = []
for el in searchtest:
d = {
'id': el['_source']['id'],
'name': el['_source']['name'],
'Business': business(el),
'level1': policy(searchtest)[0],
'level2': policy(searchtest)[1]
}
resp.append(d)
return resp
if __name__ == "__main__":
import pprint
pp = pprint.PrettyPrinter(4)
pp.pprint(data_product(searchtest))
output:
[ { 'Business': [],
'id': '100',
'level1': ['Second division'],
'level2': ['First division'],
'name': 'A'},
{ 'Business': ['Customer'],
'id': '101',
'level1': ['Second division'],
'level2': ['First division'],
'name': 'B'}]

How to iterate over a JSON array and get values for a key which itself is a JSON object

I have been trying to do something simple yet something hard for me to solve it!
I have a json object that looks like:
jsonObject = {
'attributes': {
'192': { <--- This can be changed times to times meaning different number
'id': '192',
'code': 'hello',
'label': 'world',
'options': [
{
'id': '211',
'label': '5'
},
{
'id': '1202',
'label': '8.5'
},
{
'id': '54',
'label': '9'
},
{
'id': '1203',
'label': '9.5'
},
{
'id': '58',
'label': '10'
}
]
}
},
'template': '12345',
'basePrice': '51233',
'oldPrice': '51212',
'productId': 'hello',
}
and what I want to do is to get the values from options (To have both id and label saved into a list)
For now I only managed to do:
for att, value in jsonObject.items():
print(f"{att} - {value}"
How can I get the label and id?

You can try the following code:
attr = jsonObject['attributes']
temp = list(attr.values())[0] # It is same as "temp = attr['192']", but you said '192' can be changed.
options = temp['options']
for option in options:
print(f"id: {option['id']}, label: {option['label']}")

Retrieve only certain keys and values from a dictionary, nested inside a list

I've been stuck on this for hours.. I want to retrieve only ONE individuals keys and values from a dictionary that is nested inside of a list.
GAMERS = [{
'name': 'Fatboi',
'parent': 'Dick Van Dyke',
'game': 'Dark Souls 3',
'weight': '420 lbs'
},
{
'name': 'Justin',
'parent': 'Heather Blueberry',
'game': 'Tetris',
'weight': '180 lbs'
},
{
'name': 'jerkhead',
'parent': 'none',
'games': 'Hello Kitty',
'weight': '240 lbs'
},{
'name': 'Tumor',
'parent': 'Jack Black',
'games': 'Trying to live',
'weight': '150 lbs'
}]
So for instance I want to get Justins information printed only, nobody elses. Any insights?

You can pass the key which you want and push it to separate list.
GAMERS = [{
'name': 'Fatboi',
'parent': 'Dick Van Dyke',
'game': 'Dark Souls 3',
'weight': '420 lbs'
},
{
'name': 'Justin',
'parent': 'Heather Blueberry',
'game': 'Tetris',
'weight': '180 lbs'
},{
'name': 'jerkhead',
'parent': 'none',
'games': 'Hello Kitty',
'weight': '240 lbs'
}]
def get_key_pair_list(input_dict, key):
new_list = []
for item in input_dict:
my_dict = {}
if key in item.keys():
my_dict[key] = item[key]
new_list.append(my_dict)
return new_list
print(get_key_pair_list(GAMERS, 'name'))
Output:
[{'name': 'Fatboi'}, {'name': 'Justin'}, {'name': 'jerkhead'}]
Comprehensive way:
key = 'name'
my_list = [{key, item[key]} for item in GAMERS if key in item.keys() ]
print(my_list)
output:
[{'name', 'Fatboi'}, {'name', 'Justin'}, {'name', 'jerkhead'}]

You want to filter the list and grab the first value that matches a predicate. Make sure to handle the case where the item doesnt exist!
filtered_info = (
item for item in GAMERS if item['name'] == 'Justin'
)
justin_info = next(filtered_info, None)
if justin_info is not None:
print(justin_info)

Find all occurrence of keys in nested python dict

I have a dictionary like this:
a = {'compatibility': {'schema': ['attribute_variables/evar44',
'event42',
'container_visitors'],
'status': 'valid',
'supported_features': ['function_and',
'function_attr',
'function_container',
'function_event',
'function_event-exists',
'function_streq'],
'supported_products': ['o', 'data_warehouse', 'discover'],
'supported_schema': ['warehouse', 'n'],
'validator_version': '1.1.11'},
'definition': {'container': {'context': 'visitors',
'func': 'container',
'pred': {'func': 'and',
'preds': [{'description': 'e42',
'evt': {'func': 'event', 'name': 'metrics/event42'},
'func': 'event-exists'},
{'description': 'v44',
'func': 'streq',
'str': '544',
'val': {'func': 'attr', 'name': 'variables/evar44'}}]}},
'func': 'segment',
'version': [1, 0, 0]},
'description': '',
'id': 's2165c30c946ebceb',
'modified': '12',
'name': 'Apop',
'owner': {'id': 84699, 'login': 'max', 'name': 'Max'},
'reportSuiteName': 'App',
'rsid': 'test',
'siteTitle': 'App',
'tags': []}
I would like to extract the values of every key "description", "func", and "str"/"num" and return these values in one DataFrame of these dict.
I tried it with this code, but I wasn´t able to get every value und struggeld to put the values in one DataFrame.
def findkeys(node, kv):
if isinstance(node, list):
for i in node:
for x in findkeys(i, kv):
yield x
elif isinstance(node, dict):
if kv in node:
yield node[kv]
for j in node.values():
for x in findkeys(j, kv):
yield x
For my example the output I would like to have:
pd.DataFrame(np.array([['e42', 'event', 'NaN'], ['v44', 'streq', '544']]),
columns=['description', 'funk', 'str/num'])

The code below collect the values of the "interesting" keys into a dict.
from collections import defaultdict
a = {'compatibility': {'schema': ['attribute_variables/evar44',
'event42',
'container_visitors'],
'status': 'valid',
'supported_features': ['function_and',
'function_attr',
'function_container',
'function_event',
'function_event-exists',
'function_streq'],
'supported_products': ['o', 'data_warehouse', 'discover'],
'supported_schema': ['warehouse', 'n'],
'validator_version': '1.1.11'},
'definition': {'container': {'context': 'visitors',
'func': 'container',
'pred': {'func': 'and',
'preds': [{'description': 'e42',
'evt': {'func': 'event', 'name': 'metrics/event42'},
'func': 'event-exists'},
{'description': 'v44',
'func': 'streq',
'str': '544',
'val': {'func': 'attr', 'name': 'variables/evar44'}}]}},
'func': 'segment',
'version': [1, 0, 0]},
'description': '',
'id': 's2165c30c946ebceb',
'modified': '12',
'name': 'Apop',
'owner': {'id': 84699, 'login': 'max', 'name': 'Max'},
'reportSuiteName': 'App',
'rsid': 'test',
'siteTitle': 'App',
'tags': []}
def walk_dict(d, interesting_keys, result, depth=0):
for k, v in sorted(d.items(), key=lambda x: x[0]):
if isinstance(v, dict):
walk_dict(v, interesting_keys, result, depth + 1)
elif isinstance(v,list):
for entry in v:
if isinstance(entry, dict):
walk_dict(entry, interesting_keys, result, depth + 1)
else:
if k in interesting_keys:
result[k].append(v)
result = defaultdict(list)
walk_dict(a, ["description", "func", "str", "num"], result)
print(result)
output
defaultdict(<class 'list'>, {'func': ['container', 'and', 'event', 'event-exists', 'streq', 'attr', 'segment'], 'description': ['e42', 'v44', ''], 'str': ['544']})