Related
I'm trying to merge both json files but I'm trying to append timestamp from file2 to corresponding frame number in file1.please guide.
JSON_FILE1
{"frameNumber":1,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":true,"bbox":{"top":157,"left":581,"height":390,"width":297},"classifications":[]}]}
{"frameNumber":2,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":390.36,"width":297.16},"classifications":[]}]}
{"frameNumber":3,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":390.72,"width":297.32},"classifications":[]}]}
{"frameNumber":4,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":391.08,"width":297.48},"classifications":[]}]}
{"frameNumber":5,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":391.44,"width":297.64},"classifications":[]}]}
JSON_FILE2
{
"frame1": "0:0:0:66",
"frame2": "0:0:0:100",
"frame3": "0:0:0:133",
"frame4": "0:0:0:166",
"frame5": "0:0:0:200"
}
expected output:
{"frameNumber":1,"frame1": "0:0:0:66",,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":true,"bbox":{"top":157,"left":581,"height":390,"width":297},"classifications":[]}]}
{"frameNumber":2, "frame2": "0:0:0:10,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":390.36,"width":297.16},"classifications":[]}]}
{"frameNumber":3,"frame3": "0:0:0:133,"classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":390.72,"width":297.32},"classifications":[]}]}
{"frameNumber":4,"frame4": "0:0:0:166","classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":391.08,"width":297.48},"classifications":[]}]}
{"frameNumber":5,"frame5": "0:0:0:200","classifications":[],"objects":[{"featureId":"ckotybs4v00033b68edh8a6o5","schemaId":"ckoto8fzm16gj0y7uesrd0nzt","title":"Person 1","value":"person_1","color":"#1CE6FF","keyframe":false,"bbox":{"top":157,"left":581,"height":391.44,"width":297.64},"classification
I tried this way but I am unable to achieve.
import json
import glob
result = []
for f in glob.glob("*.json"):
with open(f,"rb") as infile:
result.append(json.load(infile))
with open("merged_file.json","wb") as outfile:
json.dump(result,outfile)
A correct .json needs a pair of [] and than you could json.load it, iterate over ever line and do the same like below but anyway:
The easiest solution is turn every line in a dict, if the framenumber matches add the timestamp and write it back.
def fuse(file1, file2, nTargetPath):
with open(nTargetPath, "wb") as tTargetFile:
with open(file1, "rb") as tSourceFileA:
for tLineA in tSourceFileA.readlines():
tDictA = json.loads(tLineA) #loads dict from a string
tKey = "frame"+tDictA["frameNumber"] #searching the correct entry but why not name this timestampX
with open(file2, "rb") as tSourceFileB:
for tLineB in tSourceFileB.readlines():
tDictB = json.loads(tLineB )
if tKey in tDictB:
tDictA[tKey] = tDictB[tKey]
break #cause there is only one timestamp
tTargetFile.write(json.dumps(tDictA)+'\n')
This code cann easily updated by improve the file accessing for example when you know the key for the timestamp in file2 is everytime in the same row as in file1 and so on.
As was pointed out, one file is ndjson and the other file is json. You need to implement some logic to add the json to the ndjson
# https://pypi.org/project/ndjson/
# pip install ndjson
import ndjson
import json
with open('path/to/file/im_a_ndjson.ndjson') as infile:
ndjson_object = ndjson.load(infile)
with open('path/to/file/json_file2.json') as infile:
dict_object = json.load(infile)
print(type(ndjson_object[0]['frameNumber']))
# output: <class 'int'>
for key in dict_object:
# int needed as you can see above
framenumber = int(key.strip('frame'))
# find the matching ndjson object
for ndjs in ndjson_object:
if ndjs['frameNumber'] == framenumber:
# add the key/value pair
ndjs[key] = dict_object[key]
# we can break as we've found it
break
with open('path/to/file/new_ndjson.ndjson', 'w') as outfile:
ndjson.dump(ndjson_object, outfile)
I have a large (50,000+ lines) file that is a collection of json outputs from another application that i would like to read in as json and perform some analysis on. The issue is that while a single entry is valid json, I can't read the entire file in as json because each entry isn't connected.
Snippet:
{"action":"Iops","idg":"2214472975167211","idx":537994,"system":"Qos","utc":"2019-07-02T11:45:09.606765Z","ver":"1.1","xQosIops":{"ActualReadOps":{"avg":0,"ct":60,"max":0,"min":0,"std":0,"tmax":29880,"tmin":29880}}}
{"action":"Latency","idg":"2214472975167211","idx":537995,"system":"Qos","utc":"2019-07-02T11:45:09.606829Z","ver":"1.1","xQosLatency":{"AverageLocalWriteLatencyUS":{"avg":0,"ct":60,"max":0,"min":0,"std":0,"tmax":29880,"tmin":29880}}}
Individually they are both valid, but what I would like to achieve is dynamically connect all of these into a single json object. It is important to note that these json responses could span multiple lines, so I can't just read in line by line. Any help would be appreciated.
You can load the contents of the file with vanilla Python (not using the json package), then use json to parse each individual line.
Example:
import json
data_fp = "/path/to/data.txt"
with open(data_fp, "r") as f:
lines = f.readlines()
# now, parse each line as a JSON string
json_object = [json.loads(l) for l in line]
# optional: dump as a JSON file
with open("/path/to/output.json", "w") as f:
json.dump(json_object, f)
Edit: if each dictionary is not necessarily limited to a single line, you could try parsing JSON for a variable number of lines until it succeeds (continuing from above example):
start_line = 0
end_line = 1
json_object = []
while end_line <= len(lines):
try:
data = json.loads("".join(lines[start_line:end_line]))
except:
end_line += 1
else:
json_object.append(data)
start_line = end_line
end_line = start_line + 1
If each line is valid JSON, you could wrap this in a script that read them in individually, and appended them to a list. Something like:
import json
data = []
with open("fakejson.txt") as data_f:
for line in data_f:
data.append(json.loads(line)
You can create a function that recognizes a json, by looking for pairs of open-close {}. See below:
def isjson(t):
for i in range(len(t)):
if t[i]=='{':
s=t[i]
c=1
n=1
while c>0:
s+=t[i+n]
if t[i+n]=='{':
c+=1
elif t[i+n]=='}':
c-=1
n+=1
return (s, i+n)
You can now load your entire file as text with the following:
with open('yourfile.txt') as f:
t=f.read()
And extact all jsons, using the above function:
d={}
n=1
while True:
d[n]=isjson(t)[0]
t=t[isjson(t)[1]+1:]
n+=1
if t.count('{')==0:
break
I have a very large JSON object that I need to split into smaller objects and write those smaller objects to file.
Sample Data
raw = '[{"id":"1","num":"2182","count":-17}{"id":"111","num":"3182","count":-202}{"id":"222","num":"4182","count":12},{"id":"33333","num":"5182","count":12}]'
Desired Output (In this example, split the data in half)
output_file1.json = [{"id":"1","num":"2182","count":-17},{"id":"111","num":"3182","count":-202}]
output_file2.json = [{"id":"222","num":"4182","count":12}{"id":"33333","num":"5182","count":12}]
Current Code
import pandas as pd
import itertools
import json
from itertools import zip_longest
def grouper(iterable, n, fillvalue=None):
args = [iter(iterable)] * n
return zip_longest(fillvalue=fillvalue, *args)
raw = '[{"id":"1","num":"2182","count":-17}{"id":"111","num":"3182","count":-202}{"id":"222","num":"4182","count":12},{"id":"33333","num":"5182","count":12}]'
#split the data into manageable chunks + write to files
for i, group in enumerate(grouper(raw, 4)):
with open('outputbatch_{}.json'.format(i), 'w') as outputfile:
json.dump(list(group), outputfile)
Current Output of first file "outputbatch_0.json"
["[", "{", "\"", "s"]
I feel like I'm making this much harder than it needs to be.
assuming the raw should be a valid json string (I included the missing commas), here is a simple, but working solution.
import json
raw = '[{"id":"1","num":"2182","count":-17},{"id":"111","num":"3182","count":-202},{"id":"222","num":"4182","count":12},{"id":"33333","num":"5182","count":12}]'
json_data = json.loads(raw)
def split_in_files(json_data, amount):
step = len(json_data) // amount
pos = 0
for i in range(amount - 1):
with open('output_file{}.json'.format(i+1), 'w') as file:
json.dump(json_data[pos:pos+step], file)
pos += step
# last one
with open('output_file{}.json'.format(amount), 'w') as file:
json.dump(json_data[pos:], file)
split_in_files(json_data, 2)
if raw is valid json. the saving part is not detailed.
import json
raw = '[{"id":"1","num":"2182","count":-17},{"id":"111","num":"3182","count":-202},{"id":"222","num":"4182","count":12},{"id":"33333","num":"5182","count":12}]'
raw_list = eval(raw)
raw__zipped = list(zip(raw_list[0::2], raw_list[1::2]))
for item in raw__zipped:
with open('a.json', 'w') as f:
json.dump(item, f)
If you need the exactly half of the data you can use slicing:
import json
raw = '[{"id":"1","num":"2182","count":-17},{"id":"111","num":"3182","count":-202},{"id":"222","num":"4182","count":12},{"id":"33333","num":"5182","count":12}]'
json_data = json.loads(raw)
size_of_half = len(json_data)/2
print json_data[:size_of_half]
print json_data[size_of_half:]
In shared code basic cases are not handled like what if length is odd etc, In short You can do everything that you can do with list.
I am very new to Json files. If I have a json file with multiple json objects such as following:
{"ID":"12345","Timestamp":"20140101", "Usefulness":"Yes",
"Code":[{"event1":"A","result":"1"},…]}
{"ID":"1A35B","Timestamp":"20140102", "Usefulness":"No",
"Code":[{"event1":"B","result":"1"},…]}
{"ID":"AA356","Timestamp":"20140103", "Usefulness":"No",
"Code":[{"event1":"B","result":"0"},…]}
…
I want to extract all "Timestamp" and "Usefulness" into a data frames:
Timestamp Usefulness
0 20140101 Yes
1 20140102 No
2 20140103 No
…
Does anyone know a general way to deal with such problems?
Update: I wrote a solution that doesn't require reading the entire file in one go. It's too big for a stackoverflow answer, but can be found here jsonstream.
You can use json.JSONDecoder.raw_decode to decode arbitarily big strings of "stacked" JSON (so long as they can fit in memory). raw_decode stops once it has a valid object and returns the last position where wasn't part of the parsed object. It's not documented, but you can pass this position back to raw_decode and it start parsing again from that position. Unfortunately, the Python json module doesn't accept strings that have prefixing whitespace. So we need to search to find the first non-whitespace part of your document.
from json import JSONDecoder, JSONDecodeError
import re
NOT_WHITESPACE = re.compile(r'\S')
def decode_stacked(document, pos=0, decoder=JSONDecoder()):
while True:
match = NOT_WHITESPACE.search(document, pos)
if not match:
return
pos = match.start()
try:
obj, pos = decoder.raw_decode(document, pos)
except JSONDecodeError:
# do something sensible if there's some error
raise
yield obj
s = """
{"a": 1}
[
1
,
2
]
"""
for obj in decode_stacked(s):
print(obj)
prints:
{'a': 1}
[1, 2]
Use a json array, in the format:
[
{"ID":"12345","Timestamp":"20140101", "Usefulness":"Yes",
"Code":[{"event1":"A","result":"1"},…]},
{"ID":"1A35B","Timestamp":"20140102", "Usefulness":"No",
"Code":[{"event1":"B","result":"1"},…]},
{"ID":"AA356","Timestamp":"20140103", "Usefulness":"No",
"Code":[{"event1":"B","result":"0"},…]},
...
]
Then import it into your python code
import json
with open('file.json') as json_file:
data = json.load(json_file)
Now the content of data is an array with dictionaries representing each of the elements.
You can access it easily, i.e:
data[0]["ID"]
So, as was mentioned in a couple comments containing the data in an array is simpler but the solution does not scale well in terms of efficiency as the data set size increases. You really should only use an iterable object when you want to access a random item in the array, otherwise, generators are the way to go. Below I have prototyped a reader function which reads each json object individually and returns a generator.
The basic idea is to signal the reader to split on the carriage character "\n" (or "\r\n" for Windows). Python can do this with the file.readline() function.
import json
def json_reader(filename):
with open(filename) as f:
for line in f:
yield json.loads(line)
However, this method only really works when the file is written as you have it -- with each object separated by a newline character. Below I wrote an example of a writer that separates an array of json objects and saves each one on a new line.
def json_writer(file, json_objects):
with open(file, "w") as f:
for jsonobj in json_objects:
jsonstr = json.dumps(jsonobj)
f.write(jsonstr + "\n")
You could also do the same operation with file.writelines() and a list comprehension:
...
json_strs = [json.dumps(j) + "\n" for j in json_objects]
f.writelines(json_strs)
...
And if you wanted to append the data instead of writing a new file just change open(file, "w") to open(file, "a").
In the end I find this helps a great deal not only with readability when I try and open json files in a text editor but also in terms of using memory more efficiently.
On that note if you change your mind at some point and you want a list out of the reader, Python allows you to put a generator function inside of a list and populate the list automatically. In other words, just write
lst = list(json_reader(file))
Added streaming support based on the answer of #dunes:
import re
from json import JSONDecoder, JSONDecodeError
NOT_WHITESPACE = re.compile(r"[^\s]")
def stream_json(file_obj, buf_size=1024, decoder=JSONDecoder()):
buf = ""
ex = None
while True:
block = file_obj.read(buf_size)
if not block:
break
buf += block
pos = 0
while True:
match = NOT_WHITESPACE.search(buf, pos)
if not match:
break
pos = match.start()
try:
obj, pos = decoder.raw_decode(buf, pos)
except JSONDecodeError as e:
ex = e
break
else:
ex = None
yield obj
buf = buf[pos:]
if ex is not None:
raise ex
I have problem with changing a dict value and saving the dict to a text file (the format must be same), I only want to change the member_phone field.
My text file is the following format:
memberID:member_name:member_email:member_phone
and I split the text file with:
mdict={}
for line in file:
x=line.split(':')
a=x[0]
b=x[1]
c=x[2]
d=x[3]
e=b+':'+c+':'+d
mdict[a]=e
When I try change the member_phone stored in d, the value has changed not flow by the key,
def change(mdict,b,c,d,e):
a=input('ID')
if a in mdict:
d= str(input('phone'))
mdict[a]=b+':'+c+':'+d
else:
print('not')
and how to save the dict to a text file with same format?
Python has the pickle module just for this kind of thing.
These functions are all that you need for saving and loading almost any object:
import pickle
with open('saved_dictionary.pkl', 'wb') as f:
pickle.dump(dictionary, f)
with open('saved_dictionary.pkl', 'rb') as f:
loaded_dict = pickle.load(f)
In order to save collections of Python there is the shelve module.
Pickle is probably the best option, but in case anyone wonders how to save and load a dictionary to a file using NumPy:
import numpy as np
# Save
dictionary = {'hello':'world'}
np.save('my_file.npy', dictionary)
# Load
read_dictionary = np.load('my_file.npy',allow_pickle='TRUE').item()
print(read_dictionary['hello']) # displays "world"
FYI: NPY file viewer
We can also use the json module in the case when dictionaries or some other data can be easily mapped to JSON format.
import json
# Serialize data into file:
json.dump( data, open( "file_name.json", 'w' ) )
# Read data from file:
data = json.load( open( "file_name.json" ) )
This solution brings many benefits, eg works for Python 2.x and Python 3.x in an unchanged form and in addition, data saved in JSON format can be easily transferred between many different platforms or programs. This data are also human-readable.
Save and load dict to file:
def save_dict_to_file(dic):
f = open('dict.txt','w')
f.write(str(dic))
f.close()
def load_dict_from_file():
f = open('dict.txt','r')
data=f.read()
f.close()
return eval(data)
As Pickle has some security concerns and is slow (source), I would go for JSON, as it is fast, built-in, human-readable, and interchangeable:
import json
data = {'another_dict': {'a': 0, 'b': 1}, 'a_list': [0, 1, 2, 3]}
# e.g. file = './data.json'
with open(file, 'w') as f:
json.dump(data, f)
Reading is similar easy:
with open(file, 'r') as f:
data = json.load(f)
This is similar to this answer, but implements the file handling correctly.
If the performance improvement is still not enough, I highly recommend orjson, fast, correct JSON library for Python build upon Rust.
I'm not sure what your first question is, but if you want to save a dictionary to file you should use the json library. Look up the documentation of the loads and puts functions.
I would suggest saving your data using the JSON format instead of pickle format as JSON's files are human-readable which makes your debugging easier since your data is small. JSON files are also used by other programs to read and write data. You can read more about it here
You'll need to install the JSON module, you can do so with pip:
pip install json
# To save the dictionary into a file:
json.dump( data, open( "myfile.json", 'w' ) )
This creates a json file with the name myfile.
# To read data from file:
data = json.load( open( "myfile.json" ) )
This reads and stores the myfile.json data in a data object.
For a dictionary of strings such as the one you're dealing with, it could be done using only Python's built-in text processing capabilities.
(Note this wouldn't work if the values are something else.)
with open('members.txt') as file:
mdict={}
for line in file:
a, b, c, d = line.strip().split(':')
mdict[a] = b + ':' + c + ':' + d
a = input('ID: ')
if a not in mdict:
print('ID {} not found'.format(a))
else:
b, c, d = mdict[a].split(':')
d = input('phone: ')
mdict[a] = b + ':' + c + ':' + d # update entry
with open('members.txt', 'w') as file: # rewrite file
for id, values in mdict.items():
file.write(':'.join([id] + values.split(':')) + '\n')
I like using the pretty print module to store the dict in a very user-friendly readable form:
import pprint
def store_dict(fname, dic):
with open(fname, "w") as f:
f.write(pprint.pformat(dic, indent=4, sort_dicts=False))
# note some of the defaults are: indent=1, sort_dicts=True
Then, when recovering, read in the text file and eval() it to turn the string back into a dict:
def load_file(fname):
try:
with open(fname, "r") as f:
dic = eval(f.read())
except:
dic = {}
return dic
Unless you really want to keep the dictionary, I think the best solution is to use the csv Python module to read the file.
Then, you get rows of data and you can change member_phone or whatever you want ;
finally, you can use the csv module again to save the file in the same format
as you opened it.
Code for reading:
import csv
with open("my_input_file.txt", "r") as f:
reader = csv.reader(f, delimiter=":")
lines = list(reader)
Code for writing:
with open("my_output_file.txt", "w") as f:
writer = csv.writer(f, delimiter=":")
writer.writerows(lines)
Of course, you need to adapt your change() function:
def change(lines):
a = input('ID')
for line in lines:
if line[0] == a:
d=str(input("phone"))
line[3]=d
break
else:
print "not"
I haven't timed it but I bet h5 is faster than pickle; the filesize with compression is almost certainly smaller.
import deepdish as dd
dd.io.save(filename, {'dict1': dict1, 'dict2': dict2}, compression=('blosc', 9))
file_name = open("data.json", "w")
json.dump(test_response, file_name)
file_name.close()
or use context manager, which is better:
with open("data.json", "w") as file_name:
json.dump(test_response, file_name)