I have a json object: users.json
{
"1" :
{ "name" : "Jason" } ,
"2" :
{ "name" : "Alex" }
}
I have a python function which takes as input a name and should return the "id". For example if I pass 'Jason', it should return '1' and if I pass 'Alex' it should return '2'. I know this is a simple question but I am really stuck...(and a bit lazy to study python dictionnaries...) Here is what I have so far
def __init__(self):
self.users_file = 'users.json'
def read_users_file(self):
with open(self.users_file) as users_file:
return json.load(users_file)
def get_user_id(self, name):
data = self.read_users_file()
values = data.values()
for val in data.values():
if(name == val.get('name')):
print('user found!')
Thanks!
data = {
"1":
{"name": "Jason"},
"2":
{"name": "Alex"}
}
name = 'Jason'
for key in d:
if (d[key]['name'] == name):
print(key) ## output 1
or in more Pythonic way:
for key, value in data.items():
if name == value['name']:
print(key)
Related
I have this simplified dict:
{
{
"birthPlace" : "london"
},
"hello": "hello",
"birthPlace" : "rome"
}
And I want to make the value of birthPlace uppercase: how? I tried
smallalphabetDict={}
for key, value in myjson.items():
smallalphabetDict[key.upper()] = value
It doesn't work
This changes all the values of a dict to uppercase, if the value is a string:
d = {......}
for k in d:
if type(d[k]) == str: d[k] = d[k].upper()
I have mongodb document as an array and need to create json file in python.
mongodb document looks like
db.mappedfields.insertMany(
[
{ sourceAttribute: "first_name",
domainAttribute: "First_Name"},
{ sourceAttribute: "last_name",
domainAttribute: "Last_Name"}
]
Code tried
class create_dict(dict):
def __init__(self):
self = dict()
def add(self, key, value):
self[key] = value
mydict = create_dict()
i = 1
for key in mycol.find():
mydict.add(i, ({key['sourceAttribute']:key['domainAttribute']}))
i = i+1
json_data = json.dumps(mydict, indent=2, sort_keys=True)
Output getting
{
"1": {
"first_name": "First_Name"
},
"2": {
"last_name": "Last_Name"
}
}
Expected Output
{
"first_name": "First_Name",
"last_name": "Last_Name"
}
import json
import pymongo
class create_dict(dict):
# __init__ function
def __init__(self):
self = dict()
# Function to add key:value
def add(self, key, value):
self[key] = value
mydict = create_dict()
i = 1
for key in mycol.find():
mydict.add(i, ({key['input']:key['output']}))
i = i+1
json_data = json.dumps(mydict, indent=2, sort_keys=True)
json_data1 = json.loads(json_data)
dictlist = []
for key, value in json_data1.items():
dictlist.append(value)
print(dictlist)
result = {}
for d in dictlist:
result.update(d)
print(result)
I have a JSON object like so, and I need to extract the name value of any object, using the id. I have tried many different iterations of this but I can't seem to get anything to work. Any general pointers would be much appreciated. Thank you.
{
"weeks":[
{
"1":[
{
"name":"Stackoverflow Question",
"description":"Have you ever asked a question on StackoverFlow?",
"date":"11/25/2019",
"id":"whewhewhkahfasdjkhgjks"
},
{
"name":"I Can't Believe It's Not Butter!",
"description":"Can you believe it? I sure can't.",
"date":"11/25/2019",
"id":"agfasdgasdgasdgawe"
}
]
},
{
"2":[
{
"name":"Hello World",
"description":"A hello world.",
"date":"12/02/2019",
"id":"aewgasdgewa"
},
{
"name":"Testing 123",
"description":"Sometimes people don't say it be like it is but it do.",
"date":"12/04/2019",
"id":"asdgasdgasdgasd"
}
]
}
]
}
Hope you need to find the name based on id, then try out the code below,
def get_name(data, id):
for week in data['weeks']:
for i in week:
for j in week[i]:
if j['id'] == id:
return j['name']
return None
get_name(data, 'asdgasdgasdgasd')
output
'Testing 123'
Not sure if this is what you are looking for
for week in a["weeks"]:
for k, v in week.values():
print(v['name'])
considering the variable a your dict.
Is the structure fixed, or can the depth of the JSON differ from the example?
This one would work as well if there are more or lesser hierarchies.
It basically searches in each dictionary inside a JSON-like structure for the field_name and returns the value of the argument output_name.
Maybe it helps you when your data structure changes :)
data = {
"weeks":[
{
"1":[
{
"name":"Stackoverflow Question",
"description":"Have you ever asked a question on StackoverFlow?",
"date":"11/25/2019",
"id":"whewhewhkahfasdjkhgjks"
},
{
"name":"I Can't Believe It's Not Butter!",
"description":"Can you believe it? I sure can't.",
"date":"11/25/2019",
"id":"agfasdgasdgasdgawe"
}
]
},
{
"2":[
{
"name":"Hello World",
"description":"A hello world.",
"date":"12/02/2019",
"id":"aewgasdgewa"
},
{
"name":"Testing 123",
"description":"Sometimes people don't say it be like it is but it do.",
"date":"12/04/2019",
"id":"asdgasdgasdgasd"
}
]
}
]
}
def extract_name(data, field_name: str, matching_value: str, output_name: str):
"""
:param data: json-like datastructure in which you want to search
:param field_name: the field name with which you want to match
:param matching_value: the value you want to match
:param output_name: the name of the value which you want to get
:return:
"""
if isinstance(data, list):
for item in data:
res = _inner_extract_name(item, field_name, matching_value, output_name)
if res is not None:
return res
elif isinstance(data, dict):
for item in data.values():
res = _inner_extract_name(item, field_name, matching_value, output_name)
if res is not None:
return res
def _inner_extract_name(item, field_name, matching_value, output_name):
if isinstance(item, dict):
res = extract_name(item, field_name, matching_value, output_name)
if field_name in item:
if item[field_name] == matching_value:
if output_name in item:
return item[output_name]
else:
res = extract_name(item, field_name, matching_value, output_name)
return res
if __name__ == "__main__":
name = extract_name(data, "id", "aewgasdgewa", "name")
print(name)
``
Background
For some background, I'm trying to create a tool that converts worksheets into API calls using Python 3.5
For the conversion of the table cells to the schema needed for the API call, I've started down the path of using javascript like syntax for the headers used in the spreadsheet. e.g:
Worksheet Header (string)
dict.list[0].id
Python Dictionary
{
"dict":
"list": [
{"id": "my cell value"}
]
}
It's also possible that the header schema could have nested arrays/dicts:
one.two[0].three[0].four.five[0].six
And I also need to append to the object after it has been created as I go through each header.
What I've tried
add_branch
Based on https://stackoverflow.com/a/47276490/2903486 I am able to get nested dictionaries setup using values like one.two.three.four and I'm able to append to the existing dictionary as I go through the rows but I've been unable to add in support for arrays:
def add_branch(tree, vector, value):
key = vector[0]
tree[key] = value \
if len(vector) == 1 \
else add_branch(tree[key] if key in tree else {},
vector[1:],
value)
return tree
file = Worksheet(filePath, sheet).readRow()
rowList = []
for row in file:
rowObj = {}
for colName, rowValue in row.items():
rowObj.update(add_branch(rowObj, colName.split("."), rowValue))
rowList.append(rowObj)
return rowList
My own version of add_branch
import re, json
def branch(tree, vector, value):
"""
Used to convert JS style notation (e.g dict.another.array[0].id) to a python object
Originally based on https://stackoverflow.com/a/47276490/2903486
"""
# Convert Boolean
if isinstance(value, str):
value = value.strip()
if value.lower() in ['true', 'false']:
value = True if value.lower() == "true" else False
# Convert JSON
try:
value = json.loads(value)
except:
pass
key = vector[0]
arr = re.search('\[([0-9]+)\]', key)
if arr:
arr = arr.group(0)
key = key.replace(arr, '')
arr = arr.replace('[', '').replace(']', '')
newArray = False
if key not in tree:
tree[key] = []
tree[key].append(value \
if len(vector) == 1 \
else branch({} if key in tree else {},
vector[1:],
value))
else:
isInArray = False
for x in tree[key]:
if x.get(vector[1:][0], False):
isInArray = x[vector[1:][0]]
if isInArray:
tree[key].append(value \
if len(vector) == 1 \
else branch({} if key in tree else {},
vector[1:],
value))
else:
tree[key].append(value \
if len(vector) == 1 \
else branch({} if key in tree else {},
vector[1:],
value))
if len(vector) == 1 and len(tree[key]) == 1:
tree[key] = value.split(",")
else:
tree[key] = value \
if len(vector) == 1 \
else branch(tree[key] if key in tree else {},
vector[1:],
value)
return tree
What still needs help
My branch solution works pretty well actually now after adding in some things but I'm wondering if I'm doing something wrong/messy here or if theres a better way to handle where I'm editing nested arrays (my attempt started in the if IsInArray section of the code)
I'd expect these two headers to edit the last array, but instead I end up creating a duplicate dictionary on the first array:
file = [{
"one.array[0].dict.arrOne[0]": "1,2,3",
"one.array[0].dict.arrTwo[0]": "4,5,6"
}]
rowList = []
for row in file:
rowObj = {}
for colName, rowValue in row.items():
rowObj.update(add_branch(rowObj, colName.split("."), rowValue))
rowList.append(rowObj)
return rowList
Outputs:
[
{
"one": {
"array": [
{
"dict": {
"arrOne": [
"1",
"2",
"3"
]
}
},
{
"dict": {
"arrTwo": [
"4",
"5",
"6"
]
}
}
]
}
}
]
Instead of:
[
{
"one": {
"array": [
{
"dict": {
"arrOne": [
"1",
"2",
"3"
],
"arrTwo": [
"4",
"5",
"6"
]
}
}
]
}
}
]
So I'm not sure if there are any caveats in this solution, but this appears to work for some of the use cases i'm throwing at it:
import json, re
def build_job():
def branch(tree, vector, value):
# Originally based on https://stackoverflow.com/a/47276490/2903486
# Convert Boolean
if isinstance(value, str):
value = value.strip()
if value.lower() in ['true', 'false']:
value = True if value.lower() == "true" else False
# Convert JSON
try:
value = json.loads(value)
except:
pass
key = vector[0]
arr = re.search('\[([0-9]+)\]', key)
if arr:
# Get the index of the array, and remove it from the key name
arr = arr.group(0)
key = key.replace(arr,'')
arr = int(arr.replace('[','').replace(']',''))
if key not in tree:
# If we dont have an array already, turn the dict from the previous
# recursion into an array and append to it
tree[key] = []
tree[key].append(value \
if len(vector) == 1 \
else branch({} if key in tree else {},
vector[1:],
value))
else:
# Check to see if we are inside of an existing array here
isInArray = False
for i in range(len(tree[key])):
if tree[key][i].get(vector[1:][0], False):
isInArray = tree[key][i][vector[1:][0]]
if isInArray and arr < len(tree[key]) \
and isinstance(tree[key][arr], list):
# Respond accordingly by appending or updating the value
tree[key][arr].append(value \
if len(vector) == 1 \
else branch(tree[key] if key in tree else {},
vector[1:],
value))
else:
# Make sure we have an index to attach the requested array to
while arr >= len(tree[key]):
tree[key].append({})
# update the existing array with a dict
tree[key][arr].update(value \
if len(vector) == 1 \
else branch(tree[key][arr] if key in tree else {},
vector[1:],
value))
# Turn comma deliminated values to lists
if len(vector) == 1 and len(tree[key]) == 1:
tree[key] = value.split(",")
else:
# Add dictionaries together
tree.update({key: value \
if len(vector) == 1 \
else branch(tree[key] if key in tree else {},
vector[1:],
value)})
return tree
file = [{
"one.array[0].dict.dont-worry-about-me": "some value",
"one.array[0].dict.arrOne[0]": "1,2,3",
"one.array[0].dict.arrTwo[1]": "4,5,6",
"one.array[1].x.y[0].z[0].id": "789"
}]
rowList = []
for row in file:
rowObj = {}
for colName, rowValue in row.items():
rowObj.update(branch(rowObj, colName.split("."), rowValue))
rowList.append(rowObj)
return rowList
print(json.dumps(build_job(), indent=4))
Result:
[
{
"one": {
"array": [
{
"dict": {
"dont-worry-about-me": "some value",
"arrOne": [
"1",
"2",
"3"
],
"arrTwo": [
"4",
"5",
"6"
]
}
},
{
"x": {
"y": [
{
"z": [
{
"id": 789
}
]
}
]
}
}
]
}
}
]
I am looking to write a recursive function:
arguments: d, dictionary
result: list of dictionaries
def expand_dictionary(d):
return []
The function recursively goes through a dictionary and flattens nested objects using an _, in addition it expands out nested lists into the array, and includes the parent label.
Think of creating a relational model from a document.
Here is an example input and output:
original_object = {
"id" : 1,
"name" : {
"first" : "Alice",
"last" : "Sample"
},
"cities" : [
{
"id" : 55,
"name" : "New York"
},
{
"id" : 60,
"name" : "Chicago"
}
],
"teachers" : [
{
"id" : 2
"name" : "Bob",
"classes" : [
{
"id" : 13,
"name" : "math"
},
{
"id" : 16,
"name" : "spanish"
}
]
}
]
}
expected_output = [
{
"id" : 1,
"name_first" : "Alice",
"name_last" : "Sample"
},
{
"_parent_object" : "cities",
"id" : 55,
"name" : "New York"
},
{
"_parent_object" : "cities",
"id" : 60,
"name" : "Chicago"
},
{
"parent_object" :"teachers",
"id" : 2,
"name" : "Bob"
},
{
"parent_object" :"teachers_classes",
"id" : 13,
"name" : "math"
},
{
"parent_object" :"teachers_classes",
"id" : 16,
"name" : "spanish"
}
]
the code currently being used for flattening is:
def flatten_dictionary(d):
def expand(key, value):
if isinstance(value, dict):
return [ (key + '_' + k, v) for k, v in flatten_dictionary(value).items() ]
else:
#If value is null or empty array don't include it
if value is None or value == [] or value == '':
return []
return [ (key, value) ]
items = [ item for k, v in d.items() for item in expand(k, v) ]
return dict(items)
That will do
def expand_dictionary(d,name=None,l=None):
obj = {}
if l == None:
l = [obj]
else:
l.append(obj)
prefix = (name+'_'if name else '')
if prefix: obj['_parent_object'] = name
for i, v in d.iteritems():
if isinstance(v, list):
map(lambda x:expand_dictionary(x,prefix+i,l),v)
elif isinstance(v, dict):
obj.update(flatten_dictionary({i: v}))
else:
obj[i] = v
return l
After working through it a bit here is what I have come up with. Probably can be significantly optimized. Based on #paulo-scardine's comment I added the parent primary key to keep the relational model. Would love to hear optimization thoughts.
def expand_dictionary(original_object, object_name, objects=None):
if objects is None:
objects = []
def flatten_dictionary(dictionary):
def expand(key, value):
if isinstance(value, dict):
return [ (key + '_' + k, v) for k, v in flatten_dictionary(value).items() ]
else:
#If value is null or empty array don't include it
if value is None or value == [] or value == '':
return []
return [ (key, value) ]
items = [ item for k, v in dictionary.items() for item in expand(k, v) ]
return dict(items)
original_object_root = flatten_dictionary(original_object).copy()
original_object_root['_meta_object_name'] = object_name
for key,value in original_object_root.copy().items():
if isinstance(value, dict):
flatten_dictionary(value, objects)
if isinstance(value, list):
original_object_root.pop(key)
for nested_object in value:
nested_object['_meta_parent_foreign_key'] = original_object_root['id']
nested_object['_meta_object_name'] = object_name + "_" + key
expand_dictionary(nested_object, object_name + "_" + key, objects)
objects.append(original_object_root)
return objects