Develop Reference

List of linked tuple to nested dict

I have a list of tuples. This could look like this:
tuple_list = [
('species', 'flower'),
('flower', 'dorsal flower'),
('dorsal flower', 'pink'),
('pink', 'white'),
('pink', 'greenish'),
('species', 'branch'),
]
Note: The tuples are not in order and in this example, they could also vary in order. The 'deepness' can also vary.
I would like to create a dict of dict that would look like this:
dod = {'species': {'branch':{},'flower': {'dorsal flower':{'pink': {'white':{}}, 'greenish':{}}}}}
In this case I want the species at top level, as it has no items that 'contain' species'. E.g. species contains 'flower' and 'branch' and so on.
I feel this entire process can be wrapped in a simple recursive function (e.g. yield from) instead of writing an elaborative for loop that iterates over all values.
In the end, I want to use this function to create a list of lists that contains the proper values as a list (Kudos to #Stef for this function):
def undict_to_lists(d, acc = []):
if d == {}:
yield acc
else:
for k, v in d.items():
yield from undict_to_tuples(v, acc + [k,])
This would result in the following:
print(list(undict_to_lists(dod)))
[['species', 'branch'],
['species', 'flower', 'dorsal flower', 'pink', 'white'],
['species', 'flower', 'dorsal flower', 'greenish']]
Thanks for thinking along! All suggestions are welcome.

You could first create a dictionary key (with {} as value) for each key that occurs in the input. Then iterate those tuples to find the value that corresponds to the start key, and populate the sub dictionary with the end key, and the subdictionary that corresponds to that end key.
Finally, derive which is the root by excluding all those nodes that are children.
tuple_list = [('species', 'flower'), ('flower', 'dorsal flower'), ('dorsal flower', 'pink'),('pink', 'white'),('pink', 'greenish'),('species', 'branch')]
d = { key: {} for pair in tuple_list for key in pair }
for start, end in tuple_list:
d[start][end] = d[end]
root = None
for key in set(d.keys()).difference(end for _, end in tuple_list):
root = d[key]
print(root)

tuple_list = [
('species', 'flower'),
('flower', 'dorsal flower'),
('dorsal flower', 'pink'),
('pink', 'white'),
('pink', 'greenish'),
('species', 'branch'),
]
# Create the nested dict, using a "master" dict
# to quickly look up nodes in the nested dict.
nested_dict, master_dict = {}, {}
for a, b in tuple_list:
if a not in master_dict:
nested_dict[a] = master_dict[a] = {}
master_dict[a][b] = master_dict[b] = {}
# Flatten into lists.
def flatten_dict(d):
if not d:
return [[]]
return [[k] + f for k, v in d.items() for f in flatten_dict(v)]
print(flatten_dict(nested_dict))
#[['species', 'flower', 'dorsal flower', 'pink', 'white'],
# ['species', 'flower', 'dorsal flower', 'pink', 'greenish'],
# ['species', 'branch']]

Here's another alternative (loosely based on #trincot answer) that uses a defaultdict to simplify the code slightly and which figures out the root of the tree as it goes through the list of tuples:
from collections import defaultdict
d = defaultdict(dict)
root = tuple_list[0][0] # first parent value
for parent, child in tuple_list:
d[parent][child] = d[child]
if root == child:
root = parent
result = { root : d[root] }
Output:
{
"species": {
"branch": {},
"flower": {
"dorsal flower": {
"pink": {
"greenish": {},
"white": {}
}
}
}
}
}

Alternative :
def find_node( tree, parent, child ):
if parent in tree:
tree[parent][child] = {}
return True
for node in tree.values():
if find_node( node, parent, child ):
return True
# new node
tree[parent] = { child : {} }
root = {}
for parent, child in tuple_list:
find_node( root, parent, child )

How to iterate through a set in a constraint?

I would like to iterate through a set in a constraint. I have built an abstract model. Let's assume the following dictionaries for the instance:
dict_Nodes = {None: ['N1', 'N2']}
dict_Nodes_ArcsOut = {'N1': ['N1N4', 'N1N3'], 'N2': ['N2N5', 'N2N7']}
dict_Time = {None: [0, 1, 2]}
dict_Arcs = {None: ['N1N4', 'N1N3', 'N2N5', 'N2N7']}
However, as I am constructing an abstract model the data should not really matter.
I want to say that the variable in node N1 is the same value as in the arcs N1N4 and N1N3. For the abstract model I created several sets:
from pyomo.environ import AbstractModel, Param, minimize, Var, Constraint,\
SolverFactory, Set, Objective, NonNegativeReals, Reals, Binary, ConstraintList
model = AbstractModel()
model.Set_Nodes = Set()
model.Set_Arcs = Set()
model.Set_Time = Set()
model.Set_Nodes_ArcsOut = Set(model.Set_Nodes)
model.Var_Arc = Var(model.Set_Arcs, model.Set_Time, within=NonNegativeReals)
model.Var_Node = Var(model.Set_Nodes, model.Set_Time, within=NonNegativeReals)
Looking at the data I would like to say that:
Var_Arc['N1N4'] = Var_Node['N1']
Var_Arc['N1N3'] = Var_Node['N1']
Var_Arc['N2N5'] = Var_Node['N2']
Var_Arc['N2N7'] = Var_Node['N2']
To implement the constraint I tried the following two options:
def Arc_rule(model, node, t):
for arc in model.Set_Nodes_ArcsOut[node]:
return model.Var_Arc[arc, t] == model.Var_Node[node, t]
model.ArcInTemp_rule = Constraint(model.Set_Nodes, model.Set_Time, rule=ArcInTemp_rule)
This option only takes the first position of the list. This is probably caused by the return which stops the iteration.
Option 2:
def _init(model):
for t in model.Set_Time:
for node in model.Set_Nodes_ArcsOut:
yield model.Var_Arcs_TempIn[model.Set_Nodes_ArcsOut[node], t] == model.Var_Nodes_TempMix[node, t]
model.init_conditions = ConstraintList(rule=_init)
This does not work and I get the following error: TypeError: unhashable type: '_InsertionOrderSetData'.
I do not understand because I can do this operation if I do a summation. However, iteration seems to be impossible with an abstract model.

I rephrased the problem and illustrated it based on the pyomo example. The tryRule is what I needed:
import pyomo.environ as pyo
model = pyo.AbstractModel()
model.Nodes = pyo.Set()
model.Arcs = pyo.Set(dimen=2)
def NodesOut_init(m, node):
for i, j in m.Arcs:
if i == node:
yield j
model.NodesOut = pyo.Set(model.Nodes, initialize=NodesOut_init)
def NodesIn_init(m, node):
for i, j in m.Arcs:
if j == node:
yield i
model.NodesIn = pyo.Set(model.Nodes, initialize=NodesIn_init)
model.Flow = pyo.Var(model.Arcs, domain=pyo.NonNegativeReals)
model.NodeFlow = pyo.Var(model.Nodes, domain=pyo.NonNegativeReals)
model.FlowCost = pyo.Param(model.Arcs)
model.Demand = pyo.Param(model.Nodes)
model.Supply = pyo.Param(model.Nodes)
def Obj_rule(m):
return pyo.summation(m.FlowCost, m.Flow)
model.Obj = pyo.Objective(rule=Obj_rule, sense=pyo.minimize)
def tryRule(m, i, j):
return m.Flow[i, j] == m.NodeFlow[i]
model.tryRule = pyo.Constraint(model.Arcs, rule=tryRule)
def FlowBalance_rule(m, node):
return m.Supply[node] \
+ sum(m.Flow[i, node] for i in m.NodesIn[node]) \
- m.Demand[node] \
- sum(m.Flow[node, j] for j in m.NodesOut[node]) \
== 0
model.FlowBalance = pyo.Constraint(model.Nodes, rule=FlowBalance_rule)
dict_data = {
None: {
'Nodes': {None: ['CityA', 'CityB', 'CityC']},
'Arcs': {None: [('CityA', 'CityB'), ('CityA', 'CityC'), ('CityC', 'CityB')]},
'FlowCost': {
('CityA', 'CityB'): 1.4,
('CityA', 'CityC'): 2.7,
('CityC', 'CityB'): 1.6,
},
'Demand': {
'CityA': 0,
'CityB': 1,
'CityC': 1,
},
'Supply': {
'CityA': 2,
'CityB': 0,
'CityC': 0,
}
}
}
# create instance
instance = model.create_instance(dict_data)
instance.pprint()
The result for the rule is:
tryRule : Size=3, Index=Arcs, Active=True
Key : Lower : Body : Upper : Active
('CityA', 'CityB') : 0.0 : Flow[CityA,CityB] - NodeFlow[CityA] : 0.0 : True
('CityA', 'CityC') : 0.0 : Flow[CityA,CityC] - NodeFlow[CityA] : 0.0 : True
('CityC', 'CityB') : 0.0 : Flow[CityC,CityB] - NodeFlow[CityC] : 0.0 : True

Printing from nested dictionary

How to print either 1 specific value, or a select key2 values for all key1 from a nested dictionary? The lines in my code display nothing.
Foe example, how to print (a single value):
Canon-PS-G7-X-Mark-II`
or (select key2 values for all key1):
Canon-PS-G7-X-Mark-II
Nikon-D5
Sony-alpha9
The dictionary (part of it) and code
config = {
'g7': {},
'd5': {},
'a9': {},
}
config['g7']['cam_name'] = ('Canon-PS-G7-X-Mark-II')
config['d5']['cam_name'] = ('Nikon-D5')
config['a9']['cam_name'] = ('Sony-alpha9')
camtype = """
1 camera:
(config['g7']['cam_name'])
all cameras
(config[.]['cam_name'])
"""
print(camtype)

try below code:
config = {
'g7': {},
'd5': {},
'a9': {},
}
config['g7']['cam_name'] = ('Canon-PS-G7-X-Mark-II')
config['d5']['cam_name'] = ('Nikon-D5')
config['a9']['cam_name'] = ('Sony-alpha9')
camtype = """
1 camera:
({0})
all cameras
({1})
"""
single_camera = config['g7']['cam_name']
all_camera = ', '.join([config[k]['cam_name'] for k in config])
print(camtype.format(single_camera, all_camera))
output:
1 camera:
(Canon-PS-G7-X-Mark-II)
all cameras
(['Canon-PS-G7-X-Mark-II', 'Nikon-D5', 'Sony-alpha9'])

I am sure someone else can do better than I.
config = {
'g7': {},
'd5': {},
'a9': {},
}
config['g7']['cam_name'] = ('Canon-PS-G7-X-Mark-II')
config['d5']['cam_name'] = ('Nikon-D5')
config['a9']['cam_name'] = ('Sony-alpha9')
camtype = """1 camera: %s""" %(config['g7']['cam_name']) #search up python print function
allcam = [ value['cam_name'] for key, value in config.items()] #creates list with all cameras
str_allcam = "all cameras " + ', '.join( str(p) for p in allcam) # prints all cameras with a comma seperator
print(camtype +"\n" + str_allcam) # outputs a two lines because of newline seperator

Search for a value in a nested dictionary python

Search for a value and get the parent dictionary names (keys):
Dictionary = {dict1:{
'part1': {
'.wbxml': 'application/vnd.wap.wbxml',
'.rl': 'application/resource-lists+xml',
},
'part2':
{'.wsdl': 'application/wsdl+xml',
'.rs': 'application/rls-services+xml',
'.xop': 'application/xop+xml',
'.svg': 'image/svg+xml',
},
'part3':{...}, ...
dict2:{
'part1': { '.dotx': 'application/vnd.openxmlformats-..'
'.zaz': 'application/vnd.zzazz.deck+xml',
'.xer': 'application/patch-ops-error+xml',}
},
'part2':{...},
'part3':{...},...
},...
In above dictionary I need to search values like: "image/svg+xml". Where, none of the values are repeated in the dictionary. How to search the "image/svg+xml"? so that it should return the parent keys in a dictionary { dict1:"part2" }.
Please note: Solutions should work unmodified for both Python 2.7 and Python 3.3.

Here's a simple recursive version:
def getpath(nested_dict, value, prepath=()):
for k, v in nested_dict.items():
path = prepath + (k,)
if v == value: # found value
return path
elif hasattr(v, 'items'): # v is a dict
p = getpath(v, value, path) # recursive call
if p is not None:
return p
Example:
print(getpath(dictionary, 'image/svg+xml'))
# -> ('dict1', 'part2', '.svg')
To yield multiple paths (Python 3 only solution):
def find_paths(nested_dict, value, prepath=()):
for k, v in nested_dict.items():
path = prepath + (k,)
if v == value: # found value
yield path
elif hasattr(v, 'items'): # v is a dict
yield from find_paths(v, value, path)
print(*find_paths(dictionary, 'image/svg+xml'))

This is an iterative traversal of your nested dicts that additionally keeps track of all the keys leading up to a particular point. Therefore as soon as you find the correct value inside your dicts, you also already have the keys needed to get to that value.
The code below will run as-is if you put it in a .py file. The find_mime_type(...) function returns the sequence of keys that will get you from the original dictionary to the value you want. The demo() function shows how to use it.
d = {'dict1':
{'part1':
{'.wbxml': 'application/vnd.wap.wbxml',
'.rl': 'application/resource-lists+xml'},
'part2':
{'.wsdl': 'application/wsdl+xml',
'.rs': 'application/rls-services+xml',
'.xop': 'application/xop+xml',
'.svg': 'image/svg+xml'}},
'dict2':
{'part1':
{'.dotx': 'application/vnd.openxmlformats-..',
'.zaz': 'application/vnd.zzazz.deck+xml',
'.xer': 'application/patch-ops-error+xml'}}}
def demo():
mime_type = 'image/svg+xml'
try:
key_chain = find_mime_type(d, mime_type)
except KeyError:
print ('Could not find this mime type: {0}'.format(mime_type))
exit()
print ('Found {0} mime type here: {1}'.format(mime_type, key_chain))
nested = d
for key in key_chain:
nested = nested[key]
print ('Confirmation lookup: {0}'.format(nested))
def find_mime_type(d, mime_type):
reverse_linked_q = list()
reverse_linked_q.append((list(), d))
while reverse_linked_q:
this_key_chain, this_v = reverse_linked_q.pop()
# finish search if found the mime type
if this_v == mime_type:
return this_key_chain
# not found. keep searching
# queue dicts for checking / ignore anything that's not a dict
try:
items = this_v.items()
except AttributeError:
continue # this was not a nested dict. ignore it
for k, v in items:
reverse_linked_q.append((this_key_chain + [k], v))
# if we haven't returned by this point, we've exhausted all the contents
raise KeyError
if __name__ == '__main__':
demo()
Output:
Found image/svg+xml mime type here: ['dict1', 'part2', '.svg']
Confirmation lookup: image/svg+xml

Here is a solution that works for a complex data structure of nested lists and dicts
import pprint
def search(d, search_pattern, prev_datapoint_path=''):
output = []
current_datapoint = d
current_datapoint_path = prev_datapoint_path
if type(current_datapoint) is dict:
for dkey in current_datapoint:
if search_pattern in str(dkey):
c = current_datapoint_path
c+="['"+dkey+"']"
output.append(c)
c = current_datapoint_path
c+="['"+dkey+"']"
for i in search(current_datapoint[dkey], search_pattern, c):
output.append(i)
elif type(current_datapoint) is list:
for i in range(0, len(current_datapoint)):
if search_pattern in str(i):
c = current_datapoint_path
c += "[" + str(i) + "]"
output.append(i)
c = current_datapoint_path
c+="["+ str(i) +"]"
for i in search(current_datapoint[i], search_pattern, c):
output.append(i)
elif search_pattern in str(current_datapoint):
c = current_datapoint_path
output.append(c)
output = filter(None, output)
return list(output)
if __name__ == "__main__":
d = {'dict1':
{'part1':
{'.wbxml': 'application/vnd.wap.wbxml',
'.rl': 'application/resource-lists+xml'},
'part2':
{'.wsdl': 'application/wsdl+xml',
'.rs': 'application/rls-services+xml',
'.xop': 'application/xop+xml',
'.svg': 'image/svg+xml'}},
'dict2':
{'part1':
{'.dotx': 'application/vnd.openxmlformats-..',
'.zaz': 'application/vnd.zzazz.deck+xml',
'.xer': 'application/patch-ops-error+xml'}}}
d2 = {
"items":
{
"item":
[
{
"id": "0001",
"type": "donut",
"name": "Cake",
"ppu": 0.55,
"batters":
{
"batter":
[
{"id": "1001", "type": "Regular"},
{"id": "1002", "type": "Chocolate"},
{"id": "1003", "type": "Blueberry"},
{"id": "1004", "type": "Devil's Food"}
]
},
"topping":
[
{"id": "5001", "type": "None"},
{"id": "5002", "type": "Glazed"},
{"id": "5005", "type": "Sugar"},
{"id": "5007", "type": "Powdered Sugar"},
{"id": "5006", "type": "Chocolate with Sprinkles"},
{"id": "5003", "type": "Chocolate"},
{"id": "5004", "type": "Maple"}
]
},
...
]
}
}
pprint.pprint(search(d,'svg+xml','d'))
>> ["d['dict1']['part2']['.svg']"]
pprint.pprint(search(d2,'500','d2'))
>> ["d2['items']['item'][0]['topping'][0]['id']",
"d2['items']['item'][0]['topping'][1]['id']",
"d2['items']['item'][0]['topping'][2]['id']",
"d2['items']['item'][0]['topping'][3]['id']",
"d2['items']['item'][0]['topping'][4]['id']",
"d2['items']['item'][0]['topping'][5]['id']",
"d2['items']['item'][0]['topping'][6]['id']"]

Here are two similar quick and dirty ways of doing this type of operation. The function find_parent_dict1 uses list comprehension but if you are uncomfortable with that then find_parent_dict2 uses the infamous nested for loops.
Dictionary = {'dict1':{'part1':{'.wbxml':'1','.rl':'2'},'part2':{'.wbdl':'3','.rs':'4'}},'dict2':{'part3':{'.wbxml':'5','.rl':'6'},'part4':{'.wbdl':'1','.rs':'10'}}}
value = '3'
def find_parent_dict1(Dictionary):
for key1 in Dictionary.keys():
item = {key1:key2 for key2 in Dictionary[key1].keys() if value in Dictionary[key1][key2].values()}
if len(item)>0:
return item
find_parent_dict1(Dictionary)
def find_parent_dict2(Dictionary):
for key1 in Dictionary.keys():
for key2 in Dictionary[key1].keys():
if value in Dictionary[key1][key2].values():
print {key1:key2}
find_parent_dict2(Dictionary)

Traverses a nested dict looking for a particular value. When success is achieved the full key path to the value is printed. I left all the comments and print statements for pedagogical purposes (this isn't production code!)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Jan 24 17:16:46 2022
#author: wellington
"""
class Tree(dict):
"""
allows autovivification as in Perl hashes
"""
def __missing__(self, key):
value = self[key] = type(self)()
return value
# tracking the key sequence when seeking the target
key_list = Tree()
# dict storing the target success result
success = Tree()
# example nested dict of dicts and lists
E = {
'AA':
{
'BB':
{'CC':
{
'DD':
{
'ZZ':'YY',
'WW':'PP'
},
'QQ':
{
'RR':'SS'
},
},
'II':
{
'JJ':'KK'
},
'LL':['MM', 'GG', 'TT']
}
}
}
def find_keys_from_value(data, target):
"""
recursive function -
given a value it returns all the keys in the path to that value within
the dict "data"
there are many paths and many false routes
at the end of a given path if success has not been achieved
the function discards keys to get back to the next possible path junction
"""
print(f"the number of keys in the local dict is {len(data)}")
key_counter = 0
for key in data:
key_counter += 1
# if target has been located stop iterating through keys
if success[target] == 1:
break
else:
# eliminate prior key from path that did not lead to success
if key_counter > 1:
k_list.pop()
# add key to new path
k_list.append(key)
print(f"printing k_list after append{k_list}")
# if target located set success[target] = 1 and exit
if key == target or data[key] == target:
key_list[target] = k_list
success[target] = 1
break
# if the target has not been located check to see if the value
# associated with the new key is a dict and if so return to the
# recursive function with the new dict as "data"
elif isinstance(data[key], dict):
print(f"\nvalue is dict\n {data[key]}")
find_keys_from_value(data[key], target)
# check to see if the value associated with the new key is a list
elif isinstance(data[key], list):
# print("\nv is list\n")
# search through the list
for i in data[key]:
# check to see if the list element is a dict
# and if so return to the recursive function with
# the new dict as "data
if isinstance(i, dict):
find_keys_from_value(i, target)
# check to see if each list element is the target
elif i == target:
print(f"list entry {i} is target")
success[target] = 1
key_list[target] = k_list
elif i != target:
print(f"list entry {i} is not target")
print(f"printing k_list before pop_b {k_list}")
print(f"popping off key_b {key}")
# so if value is not a key and not a list and not the target then
# discard the key from the key list
elif data[key] != target:
print(f"value {data[key]} is not target")
print(f"printing k_list before removing key_before {k_list}")
print(f"removing key_c {key}")
k_list.remove(key)
# select target values
values = ["PP", "SS", "KK", "TT"]
success = {}
for target in values:
print(f"\nlooking for target {target}")
success[target] = 0
k_list = []
find_keys_from_value(E, target)
print(f"\nprinting key_list for target {target}")
print(f"{key_list[target]}\n")
print("\n****************\n\n")

format into json with array that belong to a certain parent

I have result set of rows in a database that all relate to each other through a parent child relationship
Each row is represented as follows objectid, id, parent, child, name, level so when I read an example from the database in my program it looks like this
Organization1
Component1
Department1
Sections1
Sections2
Department2
Sections3
Component2
Department3
Sections4
Sections5
Department4
Sections6
Where Organizations has many departments and departments has many Components and Components has many sections
my code thus far looks like this and that works but I need to put it into json format and the json format has to look like the below
for v in result:
level = v[5]
child = v[3]
parent = v[2]
if level == 0:
OrgDic['InstID'] = v[4]
OrgDic['Child'] = v[3]
OrgDic['Parent'] = v[2]
Organizations.append(InstDic)
OrgDic = {}
if level == 1:
ComponentsDic['CollegeID'] = v[4]
ComponentsDic['Child'] = v[3]
ComponentsDic['Parent'] = v[2]
Components.append(CollegeDic)
ComponentsDic = {}
if level == 2:
DepartmentDic['DepartmentID'] = v[4]
DepartmentDic['Child'] = v[3]
DepartmentDic['Parent'] = v[2]
Departments.append(DepartmentDic)
DepartmentDic = {}
if level == 3:
SectionDic['SubjectID'] = v[4]
SectionDic['Child'] = v[3]
SectionDic['Parent'] = v[2]
Sections.append(SubjectDic)
SectionDic = {}
for w in :
print w['Organization']
for x in Components:
if w['Child'] == x['Parent']:
print x['Components']
for y in Departments:
if x['Child'] == y['Parent']:
print y['Deparments']
for z in Sections:
if y['Child'] == z['Parent']:
print z['Sections']
JSON FORMAT
{
"Eff_Date": "08/02/2013",
"Tree":
[
{
"OrganizationID": "Organization1",
"Components":
[
{"ComponentID": "Component1",
"Departments":
[
{"DepartmentID": "Dep1",
"Sections":
[
{"SectionID": "Section1"},
{"SectionID": "Section2"}
]},
{"DepartmentID": "Dep2",
"Sections":
[
{"SectionID": "Section3"}
]}
]}
]
}

basically, all you have to do is dump the json after your first snippet (given that snippet does correctly create the tree you exposed, I did not thoroughly check it, but it looks coherent):
import json
print json.dumps({"Eff_Date": "08/02/2013", "Tree":Organizations})
and tada!

I was able to do it the following way
data[]
data.append([-1, 0 ,"name1", 0])
data.append([0,1, "name2", 1])
data.append([1, 2, "name3", 1])
data.append([2 ,3, "name4", 2])
data.append([2 ,4, "name5" ,2])
data.append([1 ,5, "name6", 2])
data.append([5, 6, "name7", 3])
data.append([5, 7, "name8",1])
data.append([5, 7, "name9",2])
def listToDict(input):
root = {}
lookup = {}
for parent_id, id, name, attr in input:
if parent_id == -1:
root['name'] = name;
lookup[id] = root
else:
node = {'name': name}
lookup[parent_id].setdefault('children', []).append(node)
lookup[id] = node
return root
result = listToDict(data)
print result
print json.dumps(result)
In my case my data was a result set from a database so I had to loop through it as follows
for v in result:
values = [v[2], v[3], v[4], v[5]]
pc.append(values)