Read Dictionary and write to a text file - python

I have a dictionary now:
data = [{'position': 1, 'name':'player1:', 'number': 524}, {'position':2, 'name': 'player2:','number': 333}]
(just list two group of number first to simplify the problem)
I want to read and print it in the order of positions: "position 1", "position 2" ... "position n" in a text or csv file.
something like:
position name number
1 player1 524
2 player2 333
I tried:
data = [{'position': 1, 'name':'player1', 'number': 524}, {'position':2, 'name': 'player2:','number': 333}]
keys = data[0].keys()
with open(output.csv", 'r') as output_file:
dict_writer = csv.DictWriter(output_file, keys)
dict_writer.writeheader()
dict_writer.writerows(data)
Seems like I should create a csv instead of open it first. Also, is there any better ways? Thanks.

The easiest thing to do would probably be to read it into a pandas Dataframe and then write it to a csv.
import pandas as pd
data = [
{
'position': 1,
'name':'player1',
'number': 524
}, {
'position': 2,
'name': 'player2',
'number': 333
}
]
df = pd.DataFrame.from_records(data, columns=['position', 'name', 'number'])
df = df.sort_values('position')
df.to_csv('data.csv')

use pandas
import pandas as pd
data = [
{
'position': 1,
'name':'player1:',
'number': 524
}, {
'position':2,
'name':'player2:',
'number': 333
}
]
df = pd.DataFrame.from_records(data, columns=['position', 'name', 'number'])
df = df.sort_values('position')
df.head()

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!

Flattening multi nested json into a pandas dataframe

I'm trying to flatten this json response into a pandas dataframe to export to csv.
It looks like this:
j = [
{
"id": 401281949,
"teams": [
{
"school": "Louisiana Tech",
"conference": "Conference USA",
"homeAway": "away",
"points": 34,
"stats": [
{"category": "rushingTDs", "stat": "1"},
{"category": "puntReturnYards", "stat": "24"},
{"category": "puntReturnTDs", "stat": "0"},
{"category": "puntReturns", "stat": "3"},
],
}
],
}
]
...Many more items in the stats area.
If I run this and flatten to the teams level:
multiple_level_data = pd.json_normalize(j, record_path =['teams'])
I get:
school conference homeAway points stats
0 Louisiana Tech Conference USA away 34 [{'category': 'rushingTDs', 'stat': '1'}, {'ca...
How do I flatten it twice so that all of the stats are on their own column in each row?
If I do this:
multiple_level_data = pd.json_normalize(j, record_path =['teams'])
multiple_level_data = multiple_level_data.explode('stats').reset_index(drop=True)
multiple_level_data=multiple_level_data.join(pd.json_normalize(multiple_level_data.pop('stats')))
I end up with multiple rows instead of more columns:
You can try:
df = pd.DataFrame(j).explode("teams")
df = pd.concat([df, df.pop("teams").apply(pd.Series)], axis=1)
df["stats"] = df["stats"].apply(lambda x: {d["category"]: d["stat"] for d in x})
df = pd.concat(
[
df,
df.pop("stats").apply(pd.Series),
],
axis=1,
)
print(df)
Prints:
id school conference homeAway points rushingTDs puntReturnYards puntReturnTDs puntReturns
0 401281949 Louisiana Tech Conference USA away 34 1 24 0 3
can you try this:
multiple_level_data = pd.json_normalize(j, record_path =['teams'])
multiple_level_data = multiple_level_data.explode('stats').reset_index(drop=True)
multiple_level_data=multiple_level_data.join(pd.json_normalize(multiple_level_data.pop('stats')))
#convert rows to columns.
multiple_level_data=multiple_level_data.set_index(multiple_level_data.columns[0:4].to_list())
dfx=multiple_level_data.pivot_table(values='stat',columns='category',aggfunc=list).apply(pd.Series.explode).reset_index(drop=True)
multiple_level_data=multiple_level_data.reset_index().drop(['stat','category'],axis=1).drop_duplicates().reset_index(drop=True)
multiple_level_data=multiple_level_data.join(dfx)
Output:
school
conference
homeAway
points
puntReturnTDs
puntReturnYards
puntReturns
rushingTDs
0
Louisiana Tech
Conference USA
away
34
0
24
3
1
Instead of calling explode() on an output of a json_normalize(), you can explicitly pass the paths to the meta data for each column in a single json_normalize() call. For example, ['teams', 'school'] would be one path, ['teams', 'conference'] is another path, etc. This will create a long dataframe similar to what you already have.
Then you can call pivot() to reshape this output into the correct shape.
# normalize json
df = pd.json_normalize(
j, record_path=['teams', 'stats'],
meta=['id', *(['teams', c] for c in ('school', 'conference', 'homeAway', 'points'))]
)
# column name contains 'teams' prefix; remove it
df.columns = [c.split('.')[1] if '.' in c else c for c in df]
# pivot the intermediate result
df = (
df.astype({'points': int, 'id': int})
.pivot(['id', 'school', 'conference', 'homeAway', 'points'], 'category', 'stat')
.reset_index()
)
# remove index name
df.columns.name = None
df

Pandas csv to json

I have this code i`ts work but i wont get another result
parser.add_argument('-f', '--fields', help='csv fields', type=lambda s: [str(item) for item in s.split(',')])
fields = parser.parse_args().fields
print(fields)
df = pd.read_csv('data/file.csv', usecols=fields)
print(df.to_json(orient='index'))
Run command python main.py --fields date,campaign,clicks
Result:
['date', 'campaign', 'clicks']
{"0":{"date":"2022-01-06","campaign":"retageting APAC","clicks":1}}
It should return the data in JSON format in a "data" envelope.
Need result:
['date', 'campaign', 'clicks']
{"data":[{"date":"2022-01-06","campaign":"retageting APAC","clicks":1}]}
How to do this?
Create dictionary with orient='records' first and then convert to json by json.dumps:
import json
d = {"0":{"date":"2022-01-06","campaign":"retageting APAC","clicks":1}}
df = pd.DataFrame.from_dict(d, orient='index')
print({"data":df.to_dict(orient='records')})
{'data': [{'date': '2022-01-06', 'campaign': 'retageting APAC', 'clicks': 1}]}
print(json.dumps({"data":df.to_dict(orient='records')}))
{"data": [{"date": "2022-01-06", "campaign": "retageting APAC", "clicks": 1}]}

Json file not formatted correctly when writing json differences with pandas and numpy

I am trying to compare two json and then write another json with columns names and with differences as yes or no. I am using pandas and numpy
The below is sample files i am including actually, these json are dynamic, that mean we dont know how many key will be there upfront
Input files:
fut.json
[
{
"AlarmName": "test",
"StateValue": "OK"
}
]
Curr.json:
[
{
"AlarmName": "test",
"StateValue": "OK"
}
]
Below code I have tried:
import pandas as pd
import numpy as np
with open(r"c:\csv\fut.json", 'r+') as f:
data_b = json.load(f)
with open(r"c:\csv\curr.json", 'r+') as f:
data_a = json.load(f)
df_a = pd.json_normalize(data_a)
df_b = pd.json_normalize(data_b)
_, df_a = df_b.align(df_a, fill_value=np.NaN)
_, df_b = df_a.align(df_b, fill_value=np.NaN)
with open(r"c:\csv\report.json", 'w') as _file:
for col in df_a.columns:
df_temp = pd.DataFrame()
df_temp[col + '_curr'], df_temp[col + '_fut'], df_temp[col + '_diff'] = df_a[col], df_b[col], np.where((df_a[col] == df_b[col]), 'No', 'Yes')
#[df_temp.rename(columns={c:'Missing'}, inplace=True) for c in df_temp.columns if df_temp[c].isnull().all()]
df_temp.fillna('Missing', inplace=True)
with pd.option_context('display.max_colwidth', -1):
_file.write(df_temp.to_json(orient='records'))
Expected output:
[
{
"AlarmName_curr": "test",
"AlarmName_fut": "test",
"AlarmName_diff": "No"
},
{
"StateValue_curr": "OK",
"StateValue_fut": "OK",
"StateValue_diff": "No"
}
]
Coming output: Not able to parse it in json validator, below is the problem, those [] should be replaed by ',' to get right json dont know why its printing like that
[{"AlarmName_curr":"test","AlarmName_fut":"test","AlarmName_diff":"No"}][{"StateValue_curr":"OK","StateValue_fut":"OK","StateValue_diff":"No"}]
Edit1:
Tried below as well
_file.write(df_temp.to_json(orient='records',lines=True))
now i get json which is again not parsable, ',' is missing and unless i add , between two dic and [ ] at beginning and end manually , its not parsing..
[{"AlarmName_curr":"test","AlarmName_fut":"test","AlarmName_diff":"No"}{"StateValue_curr":"OK","StateValue_fut":"OK","StateValue_diff":"No"}]
Honestly pandas is overkill for this... however
load dataframes as you did
concat them as columns. rename columns
do calcs and map boolean to desired Yes/No
to_json() returns a string so json.loads() to get it back into a list/dict. Filter columns to get to your required format
import json
data_b = [
{
"AlarmName": "test",
"StateValue": "OK"
}
]
data_a = [
{
"AlarmName": "test",
"StateValue": "OK"
}
]
df_a = pd.json_normalize(data_a)
df_b = pd.json_normalize(data_b)
df = pd.concat([df_a, df_b], axis=1)
df.columns = [c+"_curr" for c in df_a.columns] + [c+"_fut" for c in df_a.columns]
df["AlarmName_diff"] = df["AlarmName_curr"] == df["AlarmName_fut"]
df["StateValue_diff"] = df["StateValue_curr"] == df["StateValue_fut"]
df = df.replace({True:"Yes", False:"No"})
js = json.loads(df.loc[:,(c for c in df.columns if c.startswith("Alarm"))].to_json(orient="records"))
js += json.loads(df.loc[:,(c for c in df.columns if c.startswith("State"))].to_json(orient="records"))
js
output
[{'AlarmName_curr': 'test', 'AlarmName_fut': 'test', 'AlarmName_diff': 'Yes'},
{'StateValue_curr': 'OK', 'StateValue_fut': 'OK', 'StateValue_diff': 'Yes'}]

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