How can I create a nested dictionary containing info. from csv file - python

I'm working on cs50's pset6, DNA, and I want to read a csv file that looks like this:
name,AGATC,AATG,TATC
Alice,2,8,3
Bob,4,1,5
Charlie,3,2,5
And what I want to create is a nested dictionary, that would look like this:
data_dict = {
"Alice" : {
"AGATC" : 2,
"AATG" : 8,
"TATC" : 3
},
"Bob" : {
"AGATC" : 4,
"AATG" : 1,
"TATC" : 5
},
"Charlie" : {
"AGATC" : 3,
"AATG" : 2,
"TATC" : 5
}
}
So I want to use this:
with open(argv[1]) as data_file:
for i in data_file:
(Or another variation) To loop through the csv file and append to the dictionary adding all of the values so that I have a database that I can later access.

You should use python's csv.DictReader module
import csv
data_dict = {}
with open(argv[1]) as data_file:
reader = csv.DictReader(data_file)
for record in reader:
# `record` is a OrderedDict (type of dict) of column-name & value.
# Instead of creating the data pair as below:
# ```
# name = record["name"]
# data = {
# "AGATC": record["AGATC"],
# "AATG": record["AATG"],
# "TATC": record["TATC"],
# ...
# }
# data_dict[name] = data
# ```
# you can just delete the `name` column from `record`
name = record["name"]
del record["name"]
data_dict[name] = record
print(data_dict)

Using simple file read
with open(argv[1], 'r') as data_file:
line = next(data_file) # get the first line from file (i.e. header)
hdr = line.rstrip().split(',') # convert header string to comma delimited list
# ['name', 'AGATC', 'AATG', 'TATC']
data_dic = {}
for line in data_file:
line = line.rstrip().split(',')
# name and dictionary for current line
data_dic[line[0]] = {k:v for k, v in zip(hdr[1:], line[1:])}
print(data_dic)
Output
{'Alice': {'AATG': '8', 'AGATC': '2', 'TATC': '3'},
'Bob': {'AATG': '1', 'AGATC': '4', 'TATC': '5'},
'Charlie': {'AATG': '2', 'AGATC': '3', 'TATC': '5'}}

Related

How do I converted my textfile to a nested json in python

I have a text file which I want to convert to a nested json structure. The text file is :
Report_for Reconciliation
Execution_of application_1673496470638_0001
Spark_version 2.4.7-amzn-0
Java_version 1.8.0_352 (Amazon.com Inc.)
Start_time 2023-01-12 09:45:13.360000
Spark Properties:
Job_ID 0
Submission_time 2023-01-12 09:47:20.148000
Run_time 73957ms
Result JobSucceeded
Number_of_stages 1
Stage_ID 0
Number_of_tasks 16907
Number_of_executed_tasks 16907
Completion_time 73207ms
Stage_executed parquet at RawDataPublisher.scala:53
Job_ID 1
Submission_time 2023-01-12 09:48:34.177000
Run_time 11525ms
Result JobSucceeded
Number_of_stages 2
Stage_ID 1
Number_of_tasks 16907
Number_of_executed_tasks 0
Completion_time 0ms
Stage_executed parquet at RawDataPublisher.scala:53
Stage_ID 2
Number_of_tasks 300
Number_of_executed_tasks 300
Completion_time 11520ms
Stage_executed parquet at RawDataPublisher.scala:53
Job_ID 2
Submission_time 2023-01-12 09:48:46.908000
Run_time 218358ms
Result JobSucceeded
Number_of_stages 1
Stage_ID 3
Number_of_tasks 1135
Number_of_executed_tasks 1135
Completion_time 218299ms
Stage_executed parquet at RawDataPublisher.scala:53
I want the output to be :
{
"Report_for": "Reconciliation",
"Execution_of": "application_1673496470638_0001",
"Spark_version": "2.4.7-amzn-0",
"Java_version": "1.8.0_352 (Amazon.com Inc.)",
"Start_time": "2023-01-12 09:45:13.360000",
"Job_ID 0": {
"Submission_time": "2023-01-12 09:47:20.148000",
"Run_time": "73957ms",
"Result": "JobSucceeded",
"Number_of_stages": "1",
"Stage_ID 0”: {
"Number_of_tasks": "16907",
"Number_of_executed_tasks": "16907",
"Completion_time": "73207ms",
"Stage_executed": "parquet at RawDataPublisher.scala:53"
"Stage": "parquet at RawDataPublisher.scala:53",
},
},
}
I tried defaultdict method but it was generating a json with values as list which was not acceptable to make a table on it. Here's what I did:
import json
from collections import defaultdict
INPUT = 'demofile.txt'
dict1 = defaultdict(list)
def convert():
with open(INPUT) as f:
for line in f:
command, description = line.strip().split(None, 1)
dict1[command].append(description.strip())
OUTPUT = open("demo1file.json", "w")
json.dump(dict1, OUTPUT, indent = 4, sort_keys = False)
and was getting this:
"Report_for": [ "Reconciliation" ],
"Execution_of": [ "application_1673496470638_0001" ],
"Spark_version": [ "2.4.7-amzn-0" ],
"Java_version": [ "1.8.0_352 (Amazon.com Inc.)" ],
"Start_time": [ "2023-01-12 09:45:13.360000" ],
"Job_ID": [
"0",
"1",
"2", ....
]]]
I just want to convert my text to the above json format so that I can build a table on top of it.
There's no way, python or one of it's libraries can figure out your nesting requirements, if a flat text is being given as an input. How should it know Stages are inside Jobs...for example.
You will have to programmatically tell your application how it works.
I hacked an example which should work, you can go from there (assuming input_str is what you posted as your file content):
# define your nesting structure
nesting = {'Job_ID': {'Stage_ID': {}}}
upper_nestings = []
upper_nesting_keys = []
# your resulting dictionary
result_dict = {}
# your "working" dictionaries
current_nesting = nesting
working_dict = result_dict
# parse each line of the input string
for line_str in input_str.split('\n'):
# key is the first word, value are all consecutive words
line = line_str.split(' ')
# if key is in nesting, create new sub-dict, all consecutive entries are part of the sub-dict
if line[0] in current_nesting.keys():
current_nesting = current_nesting[line[0]]
upper_nestings.append(line[0])
upper_nesting_keys.append(line[1])
working_dict[line_str] = {}
working_dict = working_dict[line_str]
else:
# if a new "parallel" or "upper" nesting is detected, reset your nesting structure
if line[0] in upper_nestings:
nests = upper_nestings[:upper_nestings.index(line[0])]
keys = upper_nesting_keys[:upper_nestings.index(line[0])]
working_dict = result_dict
for nest in nests:
working_dict = working_dict[' '.join([nest, keys[nests.index(nest)]])]
upper_nestings = upper_nestings[:upper_nestings.index(line[0])+1]
upper_nesting_keys = upper_nesting_keys[:upper_nestings.index(line[0])]
upper_nesting_keys.append(line[1])
current_nesting = nesting
for nest in upper_nestings:
current_nesting = current_nesting[nest]
working_dict[line_str] = {}
working_dict = working_dict[line_str]
continue
working_dict[line[0]] = ' '.join(line[1:])
print(result_dict)
Results in:
{
'Report_for': 'Reconciliation',
'Execution_of': 'application_1673496470638_0001',
'Spark_version': '2.4.7-amzn-0',
'Java_version': '1.8.0_352 (Amazon.com Inc.)',
'Start_time': '2023-01-12 09:45:13.360000',
'Spark': 'Properties: ',
'Job_ID 0': {
'Submission_time': '2023-01-12 09:47:20.148000',
'Run_time': '73957ms',
'Result': 'JobSucceeded',
'Number_of_stages': '1',
'Stage_ID 0': {
'Number_of_tasks': '16907',
'Number_of_executed_tasks': '16907',
'Completion_time': '73207ms',
'Stage_executed': 'parquet at RawDataPublisher.scala:53'
}
},
'Job_ID 1': {
'Submission_time': '2023-01-12 09:48:34.177000',
'Run_time': '11525ms',
'Result': 'JobSucceeded',
'Number_of_stages': '2',
'Stage_ID 1': {
'Number_of_tasks': '16907',
'Number_of_executed_tasks': '0',
'Completion_time': '0ms',
'Stage_executed': 'parquet at RawDataPublisher.scala:53'
},
'Stage_ID 2': {
'Number_of_tasks': '300',
'Number_of_executed_tasks': '300',
'Completion_time': '11520ms',
'Stage_executed': 'parquet at RawDataPublisher.scala:53'
}
},
'Job_ID 2': {
'Submission_time':
'2023-01-12 09:48:46.908000',
'Run_time': '218358ms',
'Result': 'JobSucceeded',
'Number_of_stages': '1',
'Stage_ID 3': {
'Number_of_tasks': '1135',
'Number_of_executed_tasks': '1135',
'Completion_time': '218299ms',
'Stage_executed': 'parquet at RawDataPublisher.scala:53'
}
}
}
and should pretty much be generically usable for all kinds of nesting definitions from a flat input. Let me know if it works for you!

json to dictionary in python

This is my json file input.
{"Report":{"id":101,"type":"typeA","Replist":[{"rptid":"r001","subrpt":{"subid":74,"subname":"name1","subval":113},"RelsubList":[{"Relid":8,"Relsubdetails":{"Rel_subname":"name8","Rel_Subval":65}},{"Relid":5,"Relsubdetails":{"Rel_subname":"name5","Rel_Subval":40}}],"fldA":30,"fldB":23}]}}
...
I am writing python program to convert the input into the below format in my dictionary.
I am new to python.
Expected output:
out: {"id": "101", "type": "typeA", "rptid": "r001", "subrpt_subid": "74", "subrpt_subname": "name1", "subrpt_subval":"113","Relid":"8","Rel_subname":"name8","Rel_Subval":"65","Relid":"5","Rel_subname":"name5","Rel_Subval":"40","fldA":"30","fldB":"23"
I used the following logic to convert the output till subrpt.
Current output:
out: {'id': '101', 'type': 'typeA', 'rptid': 'r001', 'subrpt_subid': '74', 'subrpt_subname': 'name1', 'subrpt_subval': '113'}
But I am struggling to get the logic of RelsubList(it looks like it has both list and dictionary[{}] ).
please help me to get the logic for the same.
import json
list1 = []
dict1 = {}
dict2 = {}
data_file = "samp1.json"
file = open(data_file)
for line in file:
json_line = json.loads(line)
json_line = json_line["Report"]
dict1["id"]=str(json_line["id"])
dict1["type"] = str(json_line["type"])
json_line = json_line["Replist"]
dict1["rptid"]= str(json_line[0]["rptid"])
dict1["subrpt_subid"] = str(json_line[0]["subrpt"]["subid"])
dict1["subrpt_subname"] = str(json_line[0]["subrpt"]["subname"])
dict1["subrpt_subval"] = str(json_line[0]["subrpt"]["subval"])
print("out:", dict1)
Some of your logic is confusing to me, i.e. why are you doing json.loads(line) in every loop?
Anyway, the following should get you the logic for RealsubList:
import json
f = open("data.json")
data = json.load(f)
for line in data:
relsublist = data["Report"]["Replist"][0]["RelsubList"]
print(relsublist)
Results in:
[{'Relid': 8, 'Relsubdetails': {'Rel_subname': 'name8', 'Rel_Subval': 65}}, {'Relid': 5, 'Relsubdetails': {'Rel_subname': 'name5', 'Rel_Subval': 40}}]
The reason for the [0] index after ["Replist"] is Replist contains an array of nested dictionaries, so you need to call it out by index. In this case its only a single array, so it would be 0

PYTHON JSONtoDICT help needed - It appears python is interpreting my json-dictionary conversion as a list

The following code is giving me the error:
Traceback (most recent call last): File "AMZGetPendingOrders.py", line 66, in <module>
item_list.append(item['SellerSKU']) TypeError: string indices must be integers
The code:
from mws import mws
import time
import json
import xmltodict
access_key = 'xx' #replace with your access key
seller_id = 'yy' #replace with your seller id
secret_key = 'zz' #replace with your secret key
marketplace_usa = '00'
orders_api = mws.Orders(access_key, secret_key, seller_id)
orders = orders_api.list_orders(marketplaceids=[marketplace_usa], orderstatus=('Pending'), fulfillment_channels=('MFN'), created_after='2018-07-01')
#save as XML file
filename = 'c:order.xml'
with open(filename, 'w') as f:
f.write(orders.original)
#ConvertXML to JSON
dictString = json.dumps(xmltodict.parse(orders.original))
#Write new JSON to file
with open("output.json", 'w') as f:
f.write(dictString)
#Read JSON and parse our order number
with open('output.json', 'r') as jsonfile:
data = json.load(jsonfile)
#initialize blank dictionary
id_list = []
for order in data['ListOrdersResponse']['ListOrdersResult']['Orders']['Order']:
id_list.append(order['AmazonOrderId'])
#This "gets" the orderitem info - this code actually is similar to the initial Amazon "get" though it has fewer switches
orders_api = mws.Orders(access_key, secret_key, seller_id)
#opens and empties the orderitem.xml file
open('c:orderitem.xml', 'w').close()
#iterated through the list of AmazonOrderIds and writes the item information to orderitem.xml
for x in id_list:
orders = orders_api.list_order_items(amazon_order_id = x)
filename = 'c:orderitem.xml'
with open(filename, 'a') as f:
f.write(orders.original)
#ConvertXML to JSON
amz_items_pending = json.dumps(xmltodict.parse(orders.original))
#Write new JSON to file
with open("pending.json", 'w') as f:
f.write(amz_items_pending)
#read JSON and parse item_no and qty
with open('pending.json', 'r') as jsonfile1:
data1 = json.load(jsonfile1)
#initialize blank dictionary
item_list = []
for item in data1['ListOrderItemsResponse']['ListOrderItemsResult']['OrderItems']['OrderItem']:
item_list.append(item['SellerSKU'])
#print(item)
#print(id_list)
#print(data1)
#print(item_list)
time.sleep(10)
I don't understand why Python thinks this is a list and not a dictionary. When I print id_list it looks like a dictionary (curly braces, single quotes, colons, etc)
print(data1) shows my dictionary
{
'ListOrderItemsResponse':{
'#xmlns':'https://mws.amazonservices.com/Orders/201 3-09-01',
'ListOrderItemsResult':{
'OrderItems':{
'OrderItem':{
'QuantityOrdered ':'1',
'Title':'Delta Rothko Rolling Bicycle Stand',
'ConditionId':'New',
'Is Gift':'false',
'ASIN':'B00XXXXTIK',
'SellerSKU':'9934638',
'OrderItemId':'49 624373726506',
'ProductInfo':{
'NumberOfItems':'1'
},
'QuantityShipped':'0',
'C onditionSubtypeId':'New'
}
},
'AmazonOrderId':'112-9XXXXXX-XXXXXXX'
},
'ResponseM etadata':{
'RequestId':'8XXXXX8-0866-44a4-96f5-XXXXXXXXXXXX'
}
}
}
Any ideas?
because you are iterating over each key value in dict:
{'QuantityOrdered ': '1', 'Title': 'Delta Rothko Rolling Bicycle Stand', 'ConditionId': 'New', 'Is Gift': 'false', 'ASIN': 'B00XXXXTIK', 'SellerSKU': '9934638', 'OrderItemId': '49 624373726506', 'ProductInfo': {'NumberOfItems': '1'}, 'QuantityShipped': '0', 'C onditionSubtypeId': 'New'}
so first value in item will be 'QuantityOrdered ' and you are trying to access this string as if it is dictionary
you can just do:
id_list.append(data1['ListOrderItemsResponse']['ListOrderItemsResult']['OrderItems']['OrderItem']['SellerSKU']))
and avoid for loop in dictionary
I guess you are trying to iterate OrderItems and finding their SellerSKU values.
for item in data1['ListOrderItemsResponse']['ListOrderItemsResult']['OrderItems']:
item_list.append(item['SellerSKU'])

How can I put excel data to the dictionary?

I wanna put excel data to the dictionary.
Excel is
views.py is
#coding:utf-8
from django.shortcuts import render
import xlrd
book3 = xlrd.open_workbook('./data/excel.xlsx')
sheet3 = book3.sheet_by_index(0)
large_item = None
data_dict = {}
for row_index in range(1,sheet3.nrows):
rows3 = sheet3.row_values(row_index)
large_item = rows3[1] or large_item
data_dict = rows3
Now when I printed out print(data_dict),['', '4', '10', 'Karen', ''] was shown.Before,I wrote data_dict.extend(rows3) in place of data_dict = rows3,but in that time dict has not extend error happens.My ideal output is
data_dict = {
1: {
user_id: 1,
name_id: 1,
name: Blear,
age: 40,
man: false,
employee: leader,
},
2: {
user_id: 2,
name_id: 5,
・
       ・
       ・
},
・
       ・
       ・
}
How should I write to achieve my goal?
Your problem is :
data_dict = rows3
This doesn't add rows3 to data_dict, this set is value. So data_dict is equal to the last row.
To add element to a dict you need to do this:
data_dict[KEY] = VALUE
Your key will be the row index.
Now, you want another dict like VALUE
{
user_id: 1,
name_id: 1,
name: Blear,
age: 40,
man: false,
employee: leader,
}
So for each row you need to construct this dict, use headers and cell value to do it.
I don't test this code, it's just to give you an idea to how to do it.
#coding:utf-8
from django.shortcuts import render
import xlrd
book3 = xlrd.open_workbook('./data/excel.xlsx')
sheet3 = book3.sheet_by_index(0)
headers = sheet3.row_values(0)
large_item = None
data_dict = {}
for row_index in range(1,sheet3.nrows):
rows3 = sheet3.row_values(row_index)
large_item = rows3[1] or large_item
# Create dict with headers and row values
row_data = {}
for idx_col,value in enumerate(rows3):
header_value = headers[idx_col]
# Avoid to add empty column. A column in your example
if header_value:
row_data[headers[idx_col]] = value
# Add row_data to your data_dict with
data_dict[row_index] = row_data
You can use python's library pandas for an easy solution:
from pandas import *
xls = ExcelFile('your_excel_file.xls')
df = xls.parse(xls.sheet_names[0])
df.to_dict()

recursively collect string blocks in python

I have a custom data file formatted like this:
{
data = {
friends = {
max = 0 0,
min = 0 0,
},
family = {
cars = {
van = "honda",
car = "ford",
bike = "trek",
},
presets = {
location = "italy",
size = 10,
travelers = False,
},
version = 1,
},
},
}
I want to collect the blocks of data, meaning string between each set of {} while maintaining a hierarhcy. This data is not a typical json format so that is not a possible solution.
My idea was to create a class object like so
class Block:
def __init__(self, header, children):
self.header = header
self.children = children
Where i would then loop through the data line by line 'somehow' collecting the necessary data so my resulting output would like something like this...
Block("data = {}", [
Block("friends = {max = 0 0,\n min = 0 0,}", []),
Block("family = {version = 1}", [...])
])
In short I'm looking for help on ways I can serialize this into useful data I can then easily manipulate. So my approach is to break into objects by using the {} as dividers.
If anyone has suggestions on ways to better approach this I'm all up for ideas. Thank you again.
So far I've just implemented the basic snippets of code
class Block:
def __init__(self, content, children):
self.content = content
self.children = children
def GetBlock(strArr=[]):
print len(strArr)
# blocks = []
blockStart = "{"
blockEnd = "}"
with open(filepath, 'r') as file:
data = file.readlines()
blocks = GetBlock(strArr=data)
You can create a to_block function that takes the lines from your file as an iterator and recursively creates a nested dictionary from those. (Of course you could also use a custom Block class, but I don't really see the benefit in doing so.)
def to_block(lines):
block = {}
for line in lines:
if line.strip().endswith(("}", "},")):
break
key, value = map(str.strip, line.split(" = "))
if value.endswith("{"):
value = to_block(lines)
block[key] = value
return block
When calling it, you have to strip the first line, though. Also, evaluating the "leafs" to e.g. numbers or strings is left as an excercise to the reader.
>>> to_block(iter(data.splitlines()[1:]))
{'data': {'family': {'version': '1,',
'cars': {'bike': '"trek",', 'car': '"ford",', 'van': '"honda",'},
'presets': {'travelers': 'False,', 'size': '10,', 'location': '"italy",'}},
'friends': {'max': '0 0,', 'min': '0 0,'}}}
Or when reading from a file:
with open("data.txt") as f:
next(f) # skip first line
res = to_block(f)
Alternatively, you can do some preprocessing to transform that string into a JSON(-ish) string and then use json.loads. However, I would not go all the way here but instead just wrap the values into "" (and replace the original " with ' before that), otherwise there is too much risk to accidentally turning a string with spaces into a list or similar. You can sort those out once you've created the JSON data.
>>> data = data.replace('"', "'")
>>> data = re.sub(r'= (.+),$', r'= "\1",', data, flags=re.M)
>>> data = re.sub(r'^\s*(\w+) = ', r'"\1": ', data, flags=re.M)
>>> data = re.sub(r',$\s*}', r'}', data, flags=re.M)
>>> json.loads(data)
{'data': {'family': {'version': '1',
'presets': {'size': '10', 'travelers': 'False', 'location': "'italy'"},
'cars': {'bike': "'trek'", 'van': "'honda'", 'car': "'ford'"}},
'friends': {'max': '0 0', 'min': '0 0'}}}
You can also do with ast or json with the help of regex substitutions.
import re
a = """{
data = {
friends = {
max = 0 0,
min = 0 0,
},
family = {
cars = {
van = "honda",
car = "ford",
bike = "trek",
},
presets = {
location = "italy",
size = 10,
travelers = False,
},
version = 1,
},
},
}"""
#with ast
a = re.sub("(\w+)\s*=\s*", '"\\1":', a)
a = re.sub(":\s*((?:\d+)(?: \d+)+)", lambda x:':[' + x.group(1).replace(" ", ",") + "]", a)
import ast
print ast.literal_eval(a)
#{'data': {'friends': {'max': [0, 0], 'min': [0, 0]}, 'family': {'cars': {'car': 'ford', 'bike': 'trek', 'van': 'honda'}, 'presets': {'travelers': False, 'location': 'italy', 'size': 10}, 'version': 1}}}
#with json
import json
a = re.sub(",(\s*\})", "\\1", a)
a = a.replace(":True", ":true").replace(":False", ":false").replace(":None", ":null")
print json.loads(a)
#{u'data': {u'friends': {u'max': [0, 0], u'min': [0, 0]}, u'family': {u'cars': {u'car': u'ford', u'bike': u'trek', u'van': u'honda'}, u'presets': {u'travelers': False, u'location': u'italy', u'size': 10}, u'version': 1}}}

Categories

Resources