Develop Reference

How do I turn JSON Objects into a dict?

Working on a freshwater fish conservation project. I scraped a JSON file that looks like this:
{
"fish": [
{
"id": 0,
"n": "NO INFORMATION",
"a": "NONE",
"i": "none.png"
},
{
"id": 1,
"n": "Hampala barb",
"a": "Hampala macrolepidota",
"i": "hampala.png"
},
{
"id": 2,
"n": "Giant snakehead",
"a": "Channa micropeltes",
"i": "toman.png"
},
{
"id": 3,
"n": "Clown featherback",
"a": "Chitala ornata",
"i": "belida.png"
}
]
}
And I'm trying to extract the keys "id" and "a" into a python dictionary like this:
fish_id = {
0 : "NONE",
1 : "Hampala macrolepidota",
2 : "Channa micropeltes",
3 : "Chitala ornata"
}

import json
data = """{
"fish": [
{
"id": 0,
"n": "NO INFORMATION",
"a": "NONE",
"i": "none.png"
},
{
"id": 1,
"n": "Hampala barb",
"a": "Hampala macrolepidota",
"i": "hampala.png"
},
{
"id": 2,
"n": "Giant snakehead",
"a": "Channa micropeltes",
"i": "toman.png"
},
{
"id": 3,
"n": "Clown featherback",
"a": "Chitala ornata",
"i": "belida.png"
}
]
}"""
data_dict = json.loads(data)
fish_id = {}
for item in data_dict["fish"]:
fish_id[item["id"]] = item["a"]
print(fish_id)

First create a fish.json file and get your JSON file;
with open('fish.json') as json_file:
data = json.load(json_file)
Then, take your fishes;
fish1 = data['fish'][0]
fish2 = data['fish'][1]
fish3 = data['fish'][2]
fish4 = data['fish'][3]
After that take only values for each, because you want to create a dictionary only from values;
value_list1=list(fish1.values())
value_list2=list(fish2.values())
value_list3=list(fish3.values())
value_list4=list(fish4.values())
Finally, create fish_id dictionary;
fish_id = {
f"{value_list1[0]}" : f"{value_list1[2]}",
f"{value_list2[0]}" : f"{value_list2[2]}",
f"{value_list3[0]}" : f"{value_list3[2]}",
f"{value_list4[0]}" : f"{value_list4[2]}",
}
if you run;
print(fish_id)
Result will be like below, but if you can use for loops, it can be more effective.
{'0': 'NONE', '1': 'Hampala macrolepidota', '2': 'Channa micropeltes', '3': 'Chitala ornata'}

Replace all the keys in nested dictionary and merge duplicate keys in python

I have a nested dictionary that represents parent-child relationships. For example:
{
"45273425f5abc05b->s":
{
"12864f455e7c86bb->s": {
"12864f455e7c86bbexternal_call->c": {}
}
},
"c69aead72fcd6ec1->d":
{
"8ade76728bdddf27->d": {
"8ade76728bdddf27external_call->i": {}
},
"b29f07de47c5841f->d": {
"107bec1baede1bff->l": {
"e14ebabea4785c3f->l": {
"e14ebabea4785c3fexternal_call->r": {}
},
"e36b35daa794bd50->l": {
"e36b35daa794bd50external_call->a": {}
}
},
"b29f07de47c5841fexternal_call->l": {}
},
"1906ef2c2897ac01->d": {
"1906ef2c2897ac01external_call->e": {}
}
}
}
I want to do two things with this dictionary. Firstly I want to remove everything before and including "->" i.e I want to update the keys. Secondly, after renaming there will be duplicate values in the nested dictionary. for example the second element in the dictionary. If there are two keys with the same name I want to merge them into one. So, the result will look like the following:
{
"s":
{
"s": {
"c"
}
},
"d":
{
"d": {
"i",
"l": {
"l": {
"r",
"a"
}
},
"e"
}
}
}
How can I achieve this? I have written this code so far.
def alter_dict(nested_dict):
new_dict = {}
for k, v in nested_dict.items():
if isinstance(v, dict):
v = alter_dict(v)
new_key = k.split("->")[1]
new_dict[new_key] = v
return new_dict
It works for a simple one like the first element but doesn't work for the second one. It loses some information. The purpose of this is to create a graph with the dictionary.

You can use recursion:
import json
from collections import defaultdict
def merge(d):
r = defaultdict(list)
for i in d:
for a, b in i.items():
r[a.split('->')[-1]].append(b)
return {a:merge(b) for a, b in r.items()}
data = {'45273425f5abc05b->s': {'12864f455e7c86bb->s': {'12864f455e7c86bbexternal_call->c': {}}}, 'c69aead72fcd6ec1->d': {'8ade76728bdddf27->d': {'8ade76728bdddf27external_call->i': {}}, 'b29f07de47c5841f->d': {'107bec1baede1bff->l': {'e14ebabea4785c3f->l': {'e14ebabea4785c3fexternal_call->r': {}}, 'e36b35daa794bd50->l': {'e36b35daa794bd50external_call->a': {}}}, 'b29f07de47c5841fexternal_call->l': {}}, '1906ef2c2897ac01->d': {'1906ef2c2897ac01external_call->e': {}}}}
print(json.dumps(merge([data]), indent=4))
Output:
{
"s": {
"s": {
"c": {}
}
},
"d": {
"d": {
"i": {},
"l": {
"l": {
"r": {},
"a": {}
}
},
"e": {}
}
}
}

How to convert json to csv when there are multiple nested structures in json? [duplicate]

I'm struggling with this problem. I have a JSON file and needs ti put it out to CSV, its fine if the structure is kind of flat with no deep nested items.
But in this case the nested RACES is messing me up.
How would I go about getting the data in a format like this:
VENUE, COUNTRY, ITW, RACES__NO, RACES__TIME
for each object and each race in the object?
{
"1": {
"VENUE": "JOEBURG",
"COUNTRY": "HAE",
"ITW": "XAD",
"RACES": {
"1": {
"NO": 1,
"TIME": "12:35"
},
"2": {
"NO": 2,
"TIME": "13:10"
},
"3": {
"NO": 3,
"TIME": "13:40"
},
"4": {
"NO": 4,
"TIME": "14:10"
},
"5": {
"NO": 5,
"TIME": "14:55"
},
"6": {
"NO": 6,
"TIME": "15:30"
},
"7": {
"NO": 7,
"TIME": "16:05"
},
"8": {
"NO": 8,
"TIME": "16:40"
}
}
},
"2": {
"VENUE": "FOOBURG",
"COUNTRY": "ABA",
"ITW": "XAD",
"RACES": {
"1": {
"NO": 1,
"TIME": "12:35"
},
"2": {
"NO": 2,
"TIME": "13:10"
},
"3": {
"NO": 3,
"TIME": "13:40"
},
"4": {
"NO": 4,
"TIME": "14:10"
},
"5": {
"NO": 5,
"TIME": "14:55"
},
"6": {
"NO": 6,
"TIME": "15:30"
},
"7": {
"NO": 7,
"TIME": "16:05"
},
"8": {
"NO": 8,
"TIME": "16:40"
}
}
}, ...
}
I would like to output this to CSV like this:
VENUE, COUNTRY, ITW, RACES__NO, RACES__TIME
JOEBERG, HAE, XAD, 1, 12:35
JOEBERG, HAE, XAD, 2, 13:10
JOEBERG, HAE, XAD, 3, 13:40
...
...
FOOBURG, ABA, XAD, 1, 12:35
FOOBURG, ABA, XAD, 2, 13:10
So first I get the correct keys:
self.keys = self.data.keys()
keys = ["DATA_KEY"]
for key in self.keys:
if type(self.data[key]) == dict:
for k in self.data[key].keys():
if k not in keys:
if type(self.data[key][k]) == unicode:
keys.append(k)
elif type(self.data[key][k]) == dict:
self.subkey = k
for sk in self.data[key][k].values():
for subkey in sk.keys():
subkey = "%s__%s" % (self.subkey, subkey)
if subkey not in keys:
keys.append(subkey)
Then add the data:
But how?
This should be a fun one for you skilled forloopers. ;-)

I'd collect keys only for the first object, then assume that the rest of the format is consistent.
The following code also limits the nested object to just one; you did not specify what should happen when there is more than one. Having two or more nested structures of equal length could work (you'd 'zip' those together), but if you have structures of differing length you need to make an explicit choice how to handle those; zip with empty columns to pad, or to write out the product of those entries (A x B rows, repeating information from A each time you find a B entry).
import csv
from operator import itemgetter
with open(outputfile, 'wb') as outf:
writer = None # will be set to a csv.DictWriter later
for key, item in sorted(data.items(), key=itemgetter(0)):
row = {}
nested_name, nested_items = '', {}
for k, v in item.items():
if not isinstance(v, dict):
row[k] = v
else:
assert not nested_items, 'Only one nested structure is supported'
nested_name, nested_items = k, v
if writer is None:
# build fields for each first key of each nested item first
fields = sorted(row)
# sorted keys of first item in key sorted order
nested_keys = sorted(sorted(nested_items.items(), key=itemgetter(0))[0][1])
fields.extend('__'.join((nested_name, k)) for k in nested_keys)
writer = csv.DictWriter(outf, fields)
writer.writeheader()
for nkey, nitem in sorted(nested_items.items(), key=itemgetter(0)):
row.update(('__'.join((nested_name, k)), v) for k, v in nitem.items())
writer.writerow(row)
For your sample input, this produces:
COUNTRY,ITW,VENUE,RACES__NO,RACES__TIME
HAE,XAD,JOEBURG,1,12:35
HAE,XAD,JOEBURG,2,13:10
HAE,XAD,JOEBURG,3,13:40
HAE,XAD,JOEBURG,4,14:10
HAE,XAD,JOEBURG,5,14:55
HAE,XAD,JOEBURG,6,15:30
HAE,XAD,JOEBURG,7,16:05
HAE,XAD,JOEBURG,8,16:40
ABA,XAD,FOOBURG,1,12:35
ABA,XAD,FOOBURG,2,13:10
ABA,XAD,FOOBURG,3,13:40
ABA,XAD,FOOBURG,4,14:10
ABA,XAD,FOOBURG,5,14:55
ABA,XAD,FOOBURG,6,15:30
ABA,XAD,FOOBURG,7,16:05
ABA,XAD,FOOBURG,8,16:40

Recursively search and modify complex object (dict of ists of dicts)

I have a complex object.
Currently it is Dict of Lists of Dicts. But could change in the future while still only using lists and dictionaries.
I would like to find all list elements or dictionary values with type "datetime" and change them to string.
The recursive search seems to be working but can't figure out how to write the modified value back to the corresponding (dict val or list item).
def mod_complex(c_obj):
if isinstance(c_obj, datetime.datetime):
print(c_obj)
c_obj = str(c_obj) ???
elif isinstance(c_obj, list):
for v in c_obj:
mod_complex(v)
elif isinstance(c_obj, dict):
for k, v in c_obj.items():
mod_complex(v)

You have simple way that consists in returning a new object, each sub-object also being a new one etc.
This look like this:
def mod_complex(c_obj):
if isinstance(c_obj, int):
return c_obj*2
elif isinstance(c_obj, list):
return [mod_complex(v) for v in c_obj]
elif isinstance(c_obj, dict):
return {f"new {k}": mod_complex(v) for k, v in c_obj.items()}
ob = {
"1st list": [
{ "A": 1, "B": 2 },
{ "C": 3, "D": 4 },
],
"2nd list": [
{ "E": 5, "F": 6 },
{ "G": 7, "H": 8 },
]
}
print(mod_complex(ob))
Which prints:
{
"new 1st list": [
{ "new A": 2, "new B": 4 },
{ "new C": 6, "new D": 8 }
],
"new 2nd list": [
{ "new E": 10, "new F": 12 },
{ "new G": 14, "new H": 16 }
]
}
The advantage of this is that you are sure that nothing will be mutated, and therefore print(ob) outputs:
{
"1st list": [
{ "A": 1, "B": 2 },
{ "C": 3, "D": 4 },
],
"2nd list": [
{ "E": 5, "F": 6 },
{ "G": 7, "H": 8 },
]
}

def mod_complex(c_obj):
if isinstance(c_obj, datetime.datetime):
print(c_obj)
return str(c_obj)
elif isinstance(c_obj, list):
for i, v in enumerate(c_obj):
c_obj[i] = mod_complex(v)
elif isinstance(c_obj, dict):
for k, v in c_obj.items():
c_obj[k] = mod_complex(v)
return c_obj

Nested list into a hierarchical dict

I have a nested list that I need to convert into a hierarchical dictionary. However I am a bit confused how to achieve it in a clean pythonic way. Here's a somewhat ugly sample code that I have come up with. How to improve it?
from itertools import tee,izip
import json
L=[(1,2,3,4,5),(1,2,7),(2,3,5),(3,4,5,6)]
def pairs(iterable):
a,b = tee(iterable)
b.next()
return izip(a,b)
def innerfunc(pairs,d):
try:
pair = pairs.next()
item, nextitem = pair
except StopIteration:
return
if item in d:
innerfunc(pairs,d[item])
else:
d[item]= {}
{nextitem : innerfunc(pairs,d[item])}
def outerfunc(matrix):
result_dict={}
for row in matrix:
iter_pairs = pairs(row+(0,))
innerfunc(iter_pairs,result_dict)
return result_dict
print json.dumps(outerfunc(L), sort_keys=True, indent=4)
Output:
{
"1": {
"2": {
"3": {
"4": {
"5": {}
}
},
"7": {}
}
},
"2": {
"3": {
"5": {}
}
},
"3": {
"4": {
"5": {
"6": {}
}
}
}
}

You can do that quite succinctly using recursion:
def append_path(root, paths):
if paths:
child = root.setdefault(paths[0], {})
append_path(child, paths[1:])
# Example usage
root = {}
for p in [(1,2,3,4,5),(1,2,7),(2,3,5),(3,4,5,6)]:
append_path(root, p)
# Print results
import json
print json.dumps(root, indent=4)
Output:
{
"1": {
"2": {
"3": {
"4": {
"5": {}
}
},
"7": {}
}
},
"2": {
"3": {
"5": {}
}
},
"3": {
"4": {
"5": {
"6": {}
}
}
}
}