I have multiple JSON files which look like this:
foo.json:
{"Email":["abc#abc.com","aac#abc.com","asd#ac.com"]}
bar.json:
{"Work": ["Microsoft","Google","Yahoo"]}
I want to append all these together without modifying them:
I am using this for appending them:
import json
import glob
import sys
import os
read_files = glob.glob("*.json")
output_list = []
for f in read_files:
with open(f, "rb") as infile:
output_list.append(json.load(infile))
with open("merged_file.json", "wb") as outfile:
json.dump(output_list, outfile)
The output of this is:
[{"Email":["abc#abc.com","aac#abc.com","asd#ac.com"]},{"Work": ["Microsoft","Google","Yahoo"]}]
Which makes the output look different from the input. How can I not have the "[ ]" at the start and the end, with all keys in the same JSON object?
The desired output is:
{"Email":["abc#abc.com","aac#abc.com","asd#ac.com"],"Work": ["Microsoft","Google","Yahoo"]}
You are building a list, yet your expected output shows you want a JSON object (a dictionary in Python). Provided your input files have unique keys, you need to build a new dictionary:
import glob
import json
output = {}
for f in glob.glob("*.json"):
with open(f, "rb") as infile:
entry = json.load(infile)
output.update(entry)
with open("merged_file.jsonl", "wb") as outfile:
json.dump(output, outfile)
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 folder that has over 15,000 csv files. They all have different number of column names.
Most files have its first row as a column name (attribute of data) like this :
Name Date Contact Email
a b c d
a2 b2 c2 d2
What I want to do is read first row of all files, store them as a list, and write that list as new csv file.
Here is what I have done so far :
import csv
import glob
list=[]
files=glob.glob('C:/example/*.csv')
for file in files :
f = open(file)
a=[file,f.readline()]
list.append(a)
with open('test.csv', 'w') as testfile:
csv_writer = csv.writer(testfile)
for i in list:
csv_writer.writerow(i)
When I try this code, result comes out like this :
[('C:/example\\example.csv', 'Name,Date,Contact,Email\n'), ('C:/example\\example2.csv', 'Address,Date,Name\n')]
Therefore in a made csv, all attributes of each file go into second column making it look like this (for some reason, there's a empty row between) :
New CSV file made
Moreover when going through files, I have encoutered another error :
UnicodeDecodeError: 'cp949' codec can't decode byte 0xed in position 6: illegal multibyte sequence
So I included this code in first line but it didn't work saying files are invalid.
import codecs
files=glob.glob('C:/example/*.csv')
fileObj = codecs.open( files, "r", "utf-8" )
I read answers on stackflow but I couldn't find one related to my problem. I appreciate your answers.
Ok, so
import csv
import glob
list=[]
files=glob.glob('C:/example/*.csv')
for file in files :
f = open(file)
a=[file,f.readline()]
list.append(a)
here you're opening the file and then creating a list with the column headers as a string(note that means they'll look like "Column1,Column2") and the file name. So [("Filename", "Column1, Column2")]
so you're going to need to split that on the ',' like:
for file in files :
f = open(file)
a=[file] + f.readline().split(',')
Now we have:
["filename", ("Column1", "Column2")]
So it's still going to print to the file wrong. We need to concatenate the lists.
a=[file] + f.readline().split(',')
So we get:
["filename", "Column1", "Column2"]
And you should be closing each file after you open it with f.close() or use a context manager inside your loop like:
for file in files :
with open(file) as f:
a=[file] + f.readline()
list.append(a)
Better solution and how I would write it:
import csv
import glob
files = glob.glob('mydir/*.csv')
lst = list()
for file in files:
with open(file) as f:
reader = csv.reader(f)
lst.append(next(reader))
try:
with open(files,'r'.encoding='utf8') as f:
# do things
except UnicodeError:
with open(files,'r'.encoding='utf8') as f:
# do things
a little bit of tidying, proper context managing, and using csv.reader:
import csv
import glob
list=[]
files=glob.glob('C:/example/*.csv')
with open('test.csv', 'w') as testfile:
csv_writer = csv.writer(testfile)
for file in files:
with open(file, 'r') as infile:
reader = csv.reader(infile)
headers = next(reader)
lst = [file] + headers
writer.writerow(lst)
this will write a new csv with one row per infile, each row being filename, column1, column2, ...
I'm trying to read a csv file but for some reason when I ask it to print, it prints the memory address instead of the table.
Below is my result :
>>> read_table('books.csv')
['books.csv', 'boxoffice.csv', 'imdb.csv', 'olympics-locations.csv', 'olympics-results.csv', 'oscar-actor.csv', 'oscar-film.csv', 'seinfeld-episodes.csv', 'seinfeld-foods.csv']
<_csv.reader object at 0x03977C30>
This is my code :
import csv
import glob
from database import *
def read_table(name):
'''
(str) -> Table
Given a file name as a string, the function will return the file as a Table
object.
'''
# create a list that stores all comma-separate files(*.csv)
files_list = glob.glob('*.csv')
print(files_list)
# check if the desired file is in the list
if(name in files_list):
# if found, open the file for reading
with open(name) as csvfile:
readCSV = csv.reader(csvfile, delimiter = ',')
print(readCSV)
Something is false in my script ?
Try this:
for line in readCSV:
print(line)
See docs for a more complete example and explanation. Briefly csvreader returns an iterator object (a list is also an iterator).
import csv
from collections import defaultdict
col_names = defaultdict(list)
with open(filename) as f:
reader = csv.DictReader(f)
for each_row in reader:
for (i,j) in each_row.items():
col_names[i].append(j)
print(col_names[column name])
I am using the following python code to extract all of the file names from a specific csv file. It is working, but I run into a problem that the output contains two "
" at the end of each string in the list. I am looking for a way to remove it, but am having trouble because I have to remove it from each item in the list, rather than just removing it from one string:
import re
import csv
import os
with open('file.txt', 'rU') as textfile:
filetext = textfile.read()
file_list = []
file_list = [os.path.basename(fn) for fn in re.findall(r'\bFile Name:\s+.*\\.*(?=\n)', filetext)]
out_file = csv.writer(open("File-Original.csv", "wb"), delimiter='\n', quoting=csv.QUOTE_MINIMAL)
out_file.writerow(file_list)
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)