I am getting a dict of users and their information
{'Username': 'username', 'Attributes': [{'Name': 'sub', 'Value': 'userSub'}, {'Name': 'email', 'Value': 'email'}
I want to restructure this into an array of objects
ex) [{username: 'username', sub: 'userSub', email: 'email'}, {username: 'secondUsername', sub: 'secondSub'...}]
How do I accomplish this without manually putting in every value, as there may be different Attributes for each user
I have this so far
for user in response['Users']:
userList.append({
'username': user['Username'],
user['Attributes'][0]['Name']: user['Attributes'][0]['Value'],
})
This will return the correct structure, but I need to dynamically add the user attributes instead of manually putting in each index or string value
I would initially create each dict with just its username key, then use the update method to add the remaining keys.
from operator import itemgetter
get_kv_pairs = itemgetter('Name', 'Value')
# e.g.
# get_kv_pairs({'Name': 'sub', 'Value': 'userSub'}) == ('sub', 'userSub')
user_list = []
for user in response['Users']:
d = {'username': user['Username']}
kv_pairs = map(get_kv_pairs, user['Attributes'])
d.update(kv_pairs)
user_list.append(d)
Related
After creating a dictionary like {'key': {'key': {'key': 'value'}}}, I ran into issues trying to set the value for the higher depth key. After updating one of these values, the values for the remainder values (of other keys) were also updated.
Here's my Python code:
times = ["09:00", "09:30", "10:00", "10:30"]
courts = ["1", "2"]
daytime_dict = dict.fromkeys(times)
i = 0
for time in times:
daytime_dict[times[i]] = dict.fromkeys(["username"])
i += 1
courts_dict = dict.fromkeys(courts)
k = 0
for court in courts:
courts_dict[courts[k]] = daytime_dict
k += 1
day_info = [('name', '09:00', 1), ('name', '09:30', 1)]
for info in day_info:
info_court = str(info[2])
time = info[1]
# Here I am trying to set the value for courts_dict['1']['09:00']["username"] to be 'name',
# but the value for courts_dict['2']['09:00']["username"] and courts_dict['3']['09:00']["username"] is also set to 'name'
# What am I doing wrong? How can I only update the value for where the court is '1'?
courts_dict[info_court][time]["username"] = info[0]
I desire to get this:
{'1': {'09:00': {'username': 'name'},
'09:30': {'username': 'name'},
'10:00': {'username': None},
'10:30': {'username': None}},
'2': {'09:00': {'username': None},
'09:30': {'username': None},
'10:00': {'username': None},
'10:30': {'username': None}}
But I'm getting this:
{'1': {'09:00': {'username': 'name'},
'09:30': {'username': 'name'},
'10:00': {'username': None},
'10:30': {'username': None}},
'2': {'09:00': {'username': 'name'},
'09:30': {'username': 'name'},
'10:00': {'username': None},
'10:30': {'username': None}}
(See how court_dict['2']['09:00']['username'] and court_dict['2']['09:30']['username'] are both being updated when I only wish to update values from court_dict['1'])
Logically, I can't understand why both values are updated when I update the courts_dict (how I did in the last line of code), and not just one. Since info_court is "1", I thought only the "username" for that court would be updated.
What did I do wrong?
Logically, I can't understand why both values are updated when I update the courts_dict
For the dictionary objects you are using you are assigning the same object references as values, hence why you are seeing "both values are updated". You may want to rework your code using copy or deepcopy:
https://docs.python.org/3/library/copy.html
Assignment statements in Python do not copy objects, they create bindings between a target and an object. For collections that are mutable or contain mutable items, a copy is sometimes needed so one can change one copy without changing the other.
I'm receiving many CSV-files that contain orders for different products. Those CSV-files need to be "converted" into a specific JSON-structure.
Each row of the CSV-file represents the order of one product. This means that if I would order two products, the CSV would contain two rows.
A simplified version of the CSV-file may look like this (please note the orderId "111" in the first and third row):
orderId,itemNumber,itemName,name,street
111,123,testitem,john doe,samplestreet 1
222,345,anothertestitem,jane doe,samplestreet 1
111,345,anothertestitem,john doe,samplestreet 1
My current solution works but I think I'm overcomplicating things.
Currently, I'm iterating over each CSV-row and create the JSON-structure where I use a helper-function that will either add the order or append a list that contains ordered items like so:
def add_orderitem(orderitem, order, all_orders):
""" Adds an ordered product to the order or "create" a new order if it doesn't exist """
for row in all_orders:
# Order already exists
if any(order["orderNumber"] == value for field, value in row.items()):
print(f"Order '{order['orderNumber']}' already exists, adding product #{orderitem['sku']}")
row["orderItems"].append(orderitem)
return all_orders
# New order
print(f"New Order found, creating order '{order['orderNumber']}' and adding product #{orderitem['sku']}")
all_orders.append(order)
order["orderItems"].append(orderitem)
return all_orders
def parse_orders():
""" Converts CSV-orders into JSON """
results = []
orders = read_csv("testorder.csv") # helper-function returns CSV-dictreader (list of dicts)
for order in orders:
# Create basic structure
orderdata = {
"orderNumber": order["orderId"],
"address": {
"name": order["orderId"],
"street": order["street"]
},
"orderItems": [] # <-- this will be filled later
}
# Extract product-information that will be inserted in above 'orderItems' list
product = {
"sku": order["itemNumber"],
"name": order["itemName"]
}
# Add order to final list or add item if order already exists
results = add_orderitem(product, orderdata, results)
return results
def main():
from pprint import pprint
parsed_orders = parse_orders()
pprint(parsed_orders)
if __name__ == "__main__":
main()
The skript works fine, the output below is what I'm expecting:
New Order found, creating order '111' and adding product #123
New Order found, creating order '222' and adding product #345
Order '111' already exists, adding product #345
[{'address': {'name': '111', 'street': 'samplestreet 1'},
'orderItems': [{'name': 'testitem', 'sku': '123'},
{'name': 'anothertestitem', 'sku': '345'}],
'orderNumber': '111'},
{'address': {'name': '222', 'street': 'samplestreet 1'},
'orderItems': [{'name': 'anothertestitem', 'sku': '345'}],
'orderNumber': '222'}]
Is there a way, to do this "smarter"?
Imo a namedtuple and a groupby would make your code clearer:
from collections import namedtuple
from itertools import groupby
# csv data or file
data = """orderId,itemNumber,itemName,name,street
111,123,testitem,john doe,samplestreet 1
222,345,anothertestitem,jane doe,samplestreet 1
111,345,anothertestitem,john doe,samplestreet 1
"""
# the Order tuple
Order = namedtuple('Order', 'orderId itemNumber itemName name street')
# load the csv into orders
orders = [Order(*values) for line in data.split("\n")[1:] if line for values in [line.split(",")]]
# and group it by orderId
orders = sorted(orders, key = lambda order: order.orderId)
# group it by orderId
output = list()
for key, values in groupby(orders, key=lambda order: order.orderId):
items = list(values)
dct = {"address": {"name": items[0].name, "street": items[0].street},
"orderItems": [{"name": item.itemName, "sku": item.itemNumber} for item in items]}
output.append(dct)
print(output)
This yields
[{'address': {'name': 'john doe', 'street': 'samplestreet 1'}, 'orderItems': [{'name': 'testitem', 'sku': '123'}, {'name': 'anothertestitem', 'sku': '345'}]},
{'address': {'name': 'jane doe', 'street': 'samplestreet 1'}, 'orderItems': [{'name': 'anothertestitem', 'sku': '345'}]}]
You could even put it in a great comprehension but that would not make it more readable.
I'm receiving following data from DynamoDB as a response to client scan API call.
Data = [{'id': {'S': '5'},
'FirstName': {'S': 'Prashanth'},
'LastName': {'S': 'Wadeyar'},
'ClientName': {'S': 'Test'}}]
I want to handle this response and get the output as
{'FirstName':'Prashanth', 'LastName': 'Wadeyar', 'ClientName': 'Test'}
I can handle it by separating it like
for field_obj in data:
obj = (field_obj['FirstName'])
but to get value of Firstname, Key 'S' may differ for each object. like boolean string, list etc.
is there a easy way to get the key and value pairs.
If you don't want to bring external dependencies you can use Table class as described here.
import boto3
dynamodb = boto3.resource('dynamodb')
table = dynamodb.Table('users')
response = table.get_item(
Key={
'username': 'janedoe',
'last_name': 'Doe'
}
)
item = response['Item']
print(item)
Expected Output:
{u'username': u'janedoe',
u'first_name': u'Jane',
u'last_name': u'Doe',
u'account_type': u'standard_user',
u'age': Decimal('25')}
But my personal preference everytime I hear about Python and DynamoDB is to use PynamoDB: https://pynamodb.readthedocs.io/en/latest/ which is sort of an ORM for DynamoDB.
Above answer from Mayank seems to work well, but I also wanted to map fields I want to return in a list. Hence I mapped field and then was able to get the result I was looking for
FIELD_MAP = ['firstName', 'lastName',
'clientName']
for field_obj in response['Items']:
for key in FIELD_MAP:
if field_obj.get(key):
obj = (field_obj.get(key))
for i in obj:
value = obj[i]
db_result.append({key: value})
print(db_result)
Something like this could work, where you don't need to care about the internal keys(S in your case):
In [1018]: d = {}
In [1016]: for i in Data:
...: for k,v in i.items():
...: if k != 'id':
...: if isinstance(v, dict):
...: for j, val in v.items():
...: d[k] = val
...:
In [1024]: d
Out[1024]: {'FirstName': 'Prashanth', 'LastName': 'Wadeyar', 'ClientName': 'Test'}
I have created a dictionary and filled it with dictionaries by using two for-each loops.
y = {'Name': {'User0': 'Alicia', 'User1': 'Lea', 'User2': 'Jan', 'User3': 'Kot', 'User4': 'Jarvis'},
'Password': {'User0': 'kokos', 'User1': 'blbec ', 'User2': 'morous', 'User3': 'mnaumnau', 'User4': 'Trav3_liK'}}
Each user has a name and a password. It would be much easier to set my data like this:
y = {UserX : ["Name", "Password"], ... }
Is there any way I can "unify" my previous code?
Supposing User and Password dicts have the same users:
y = {
user_id: (name, y['Password'][user_id])
for user_id, name in y['Name'].items()
}
I have a database schema in Postgres that looks like this (in pseudo code):
users (table):
pk (field, unique)
name (field)
permissions (table):
pk (field, unique)
permission (field, unique)
addresses (table):
pk (field, unique)
address (field, unique)
association1 (table):
user_pk (field, foreign_key)
permission_pk (field, foreign_key)
association2 (table):
user_pk (field, foreign_key)
address_pk (field, foreign_key)
Hopefully this makes intuitive sense. It's a users table that has a many-to-many relationship with a permissions table as well as a many-to-many relationship with an addresses table.
In Python, when I perform the correct SQLAlchemy query incantations, I get back results that look something like this (after converting them to a list of dictionaries in Python):
results = [
{'pk': 1, 'name': 'Joe', 'permission': 'user', 'address': 'home'},
{'pk': 1, 'name': 'Joe', 'permission': 'user', 'address': 'work'},
{'pk': 1, 'name': 'Joe', 'permission': 'admin', 'address': 'home'},
{'pk': 1, 'name': 'Joe', 'permission': 'admin', 'address': 'work'},
{'pk': 2, 'name': 'John', 'permission': 'user', 'address': 'home'},
]
So in this contrived example, Joe is both a user and and an admin. John is only a user. Both Joe's home and work addresses exist in the database. Only John's home address exists.
So the question is, does anybody know the best way to go from these SQL query 'results' to the more compact 'desired_results' below?
desired_results = [
{
'pk': 1,
'name': 'Joe',
'permissions': ['user', 'admin'],
'addresses': ['home', 'work']
},
{
'pk': 2,
'name': 'John',
'permissions': ['user'],
'addresses': ['home']
},
]
Additional information required: Small list of dictionaries describing the 'labels' I would like to use in the desired_results for each of the fields that have many-to-many relationships.
relationships = [
{'label': 'permissions', 'back_populates': 'permission'},
{'label': 'addresses', 'back_populates': 'address'},
]
Final consideration, I've put together a concrete example for the purposes of this question, but in general I'm trying to solve the problem of querying SQL databases in general, assuming an arbitrary amount of relationships. SQLAlchemy ORM solves this problem well, but I'm limited to using SQLAlchemy Core; so am trying to build my own solution.
Update
Here's an answer, but I'm not sure it's the best / most efficient solution. Can anyone come up with something better?
# step 1: generate set of keys that will be replaced by new keys in desired_result
back_populates = set(rel['back_populates'] for rel in relationships)
# step 2: delete from results keys generated in step 1
intermediate_results = [
{k: v for k, v in res.items() if k not in back_populates}
for res in results]
# step 3: eliminate duplicates
intermediate_results = [
dict(t)
for t in set([tuple(ires.items())
for ires in intermediate_results])]
# step 4: add back information from deleted fields but in desired form
for ires in intermediate_results:
for rel in relationships:
ires[rel['label']] = set([
res[rel['back_populates']]
for res in results
if res['pk'] == ires['pk']])
# done
desired_results = intermediate_results
Iterating over the groups of partial entries looks like a job for itertools.groupby.
But first lets put relationships into a format that is easier to use, prehaps a back_populates:label dictionary?
conversions = {d["back_populates"]:d['label'] for d in relationships}
Next because we will be using itertools.groupby it will need a keyfunc to distinguish between the different groups of entries.
So given one entry from the initial results, this function will return a dictionary with only the pairs that will not be condensed/converted
def grouper(entry):
#each group is identified by all key:values that are not identified in conversions
return {k:v for k,v in entry.items() if k not in conversions}
Now we will be able to traverse the results in groups something like this:
for base_info, group in itertools.groupby(old_results, grouper):
#base_info is dict with info unique to all entries in group
for partial in group:
#partial is one entry from results that will contribute to the final result
#but wait, what do we add it too?
The only issue is that if we build our entry from base_info it will confuse groupby so we need to make an entry to work with:
entry = {new_field:set() for new_field in conversions.values()}
entry.update(base_info)
Note that I am using sets here because they are the natural container when all contence are unique,
however because it is not json-compatible we will need to change them into lists at the end.
Now that we have an entry to build we can just iterate through the group to add to each new field from the original
for partial in group:
for original, new in conversions.items():
entry[new].add(partial[original])
then once the final entry is constructed all that is left is to convert the sets back into lists
for new in conversions.values():
entry[new] = list(entry[new])
And that entry is done, now we can either append it to a list called new_results but since this process is essentially generating results it would make more sense to put it into a generator
making the final code look something like this:
import itertools
results = [
{'pk': 1, 'name': 'Joe', 'permission': 'user', 'address': 'home'},
{'pk': 1, 'name': 'Joe', 'permission': 'user', 'address': 'work'},
{'pk': 1, 'name': 'Joe', 'permission': 'admin', 'address': 'home'},
{'pk': 1, 'name': 'Joe', 'permission': 'admin', 'address': 'work'},
{'pk': 2, 'name': 'John', 'permission': 'user', 'address': 'home'},
]
relationships = [
{'label': 'permissions', 'back_populates': 'permission'},
{'label': 'addresses', 'back_populates': 'address'},
]
#first we put the "relationships" in a format that is much easier to use.
conversions = {d["back_populates"]:d['label'] for d in relationships}
def grouper(entry):
#each group is identified by all key:values that are not identified in conversions
return {k:v for k,v in entry.items() if k not in conversions}
def parse_results(old_results, conversions=conversions):
for base_info, group in itertools.groupby(old_results, grouper):
entry = {new_field:set() for new_field in conversions.values()}
entry.update(base_info)
for partial in group: #for each entry in the original results set
for original, new in conversions.items(): #for each field that will be condensed
entry[new].add(partial[original])
#convert sets back to lists so it can be put back into json
for new in conversions.values():
entry[new] = list(entry[new])
yield entry
Then the new_results can be gotten like this:
>>> new_results = list(parse_results(results))
>>> from pprint import pprint #for demo purpose
>>> pprint(new_results,width=50)
[{'addresses': ['home', 'work'],
'name': 'Joe',
'permissions': ['admin', 'user'],
'pk': 1},
{'addresses': ['home'],
'name': 'John',
'permissions': ['user'],
'pk': 2}]