I'm currently trying to make a Chromebook rental application for my high school that stores checkout information in a JSON file. Everything works except removing data from the JSON array. I found a YouTube video(link) that I thought would work as a solution, so I followed along with that. However, whenever there's more than two elements and I enter anything higher than two, it doesn't delete anything. Even worse, when I enter the number one, it deletes everything but the zero index(whenever the array has more than two elements in it).
Here's the Python code:
def view_data(): # Prints JSON Array to screen
with open(filename, "r") as f:
data = json.load(f)
i = 0
for item in data:
name = item["name"]
chromebook = item["chromebook"]
check_out = item["time&date"]
print(f"Index Number: {i}")
print(f"Name : {name}")
print(f"Chromebook : {chromebook}")
print(f"Time Of Checkout: {check_out} ")
print("\n\n")
i = i + 1
def delete_data(): # Deletes an element from the array
view_data()
new_data = []
with open(filename, "r") as f:
data = json.load(f)
data_length = len(data) - 1
print("Which index number would you like to delete?")
delete_option = input(f"Select a number 0-{data_length}: ")
i = 0
for entry in data:
if i == int(delete_option):
pass
i = + 1
else:
new_data.append(entry)
i = + 1
with open(filename, "w") as f:
json.dump(new_data, f, indent=4)
Here's the JSON file code:
[
{
"name": "Tyler",
"chromebook": "12123223",
"time&date": "Check Out Time: 13:33:22 May-11-2021"
},
{
"name": "Craig",
"chromebook": "41222224",
"time&date": "Check Out Time: 13:33:34 May-11-2021"
},
{
"name": "Bill",
"chromebook": "3235223",
"time&date": "Check Out Time: 13:33:46 May-11-2021"
}
]
For example, say the user wanted to remove the second index in the JSON array. Is there a better way to implement that in my Python script?
I'm still a fairly new and learning Python developer, and if there's any better solution I'm open to suggestions. If you need for info, I'll be active.
First question
However, whenever there's more than two elements and I enter anything higher than two, it doesn't delete anything. Even worse, when I enter the number one, it deletes everything but the zero index(whenever the array has more than two elements in it).
Inside delete_data() you have two lines reading i = + 1, which just assignes +1 (i.e., 1) to i. Thus, you're never increasing your index. You probably meant to write either i = i+1 or i += 1.
def delete_data(): # Deletes an element from the array
view_data()
new_data = []
with open(filename, "r") as f:
data = json.load(f)
data_length = len(data) - 1
print("Which index number would you like to delete?")
delete_option = input(f"Select a number 0-{data_length}: ")
i = 0
for entry in data:
if i == int(delete_option):
i += 1 # <-- here
else:
new_data.append(entry)
i += 1 # <-- and here
with open(filename, "w") as f:
json.dump(new_data, f, indent=4)
Second question: further improvements
Is there a better way to implement that in my Python script?
First, you can get rid of manually increasing i by using the builtin enumerate generator. Second, you could make your functions reusable by giving them parameters - where does the filename in your code example come from?
# view_data() should probably receive `filename` as a parameter
def view_data(filename: str): # Prints JSON Array to screen
with open(filename, "r") as f:
data = json.load(f)
# iterate over i and data simultaneously
# alternatively, you could just remove i
for i, item in enumerate(data):
name = item["name"]
chromebook = item["chromebook"]
check_out = item["time&date"]
print(f"Index Number: {i}")
print(f"Name : {name}")
print(f"Chromebook : {chromebook}")
print(f"Time Of Checkout: {check_out} ")
print("\n\n")
# not needed anymore: i = i + 1
# view_data() should probably receive `filename` as a parameter
def delete_data(filename: str): # Deletes an element from the array
view_data()
new_data = []
with open(filename, "r") as f:
data = json.load(f)
data_length = len(data) - 1
print("Which index number would you like to delete?")
delete_option = input(f"Select a number 0-{data_length}: ")
# iterate over i and data simultaneously
for i, entry in enumerate(data):
if i != int(delete_option):
new_data.append(entry)
with open(filename, "w") as f:
json.dump(new_data, f, indent=4)
Furthermore, you could replace that for-loop by a list comprehension, which some may deem more "pythonic":
new_data = [entry for i, entry in enumerate(data) if i != int(delete_option)]
There are easier ways to delete an element by index from a Python list.
Given li = ["a", "b", "c"], you can delete element 1 ("b") by index in (at least) the following ways:
li.pop(1) # pop takes an index (defaults to last) and removes and returns the element at that index
del li[1] # the del keyword will also remove an element from a list
So, here's some updated code:
def view_data(): # Prints JSON Array to screen
with open(filename, "r") as f:
data = json.load(f)
i = 0
for item in data:
name = item["name"]
chromebook = item["chromebook"]
check_out = item["time&date"]
print(f"Index Number: {i}")
print(f"Name : {name}")
print(f"Chromebook : {chromebook}")
print(f"Time Of Checkout: {check_out} ")
print("\n\n")
i = i + 1
def delete_data(): # Deletes an element from the array
view_data()
with open(filename, "r") as f:
data = json.load(f)
data_length = len(data) - 1
print("Which index number would you like to delete?")
delete_option = input(f"Select a number 0-{data_length}: ")
del data[int(delete_option)] # or data.pop(int(delete_option))
with open(filename, "w") as f:
json.dump(data, f, indent=4)
import json
data = json.loads(jsonString) #convert json string to object
delete_option = input(f"Select a number 0-{data_length}: ")
del data[int(delete_option)]
Related
def editselection():
#this converts the text in the files into a list in a list
with open("stocks", "r") as stocks:
for line in stocks:
stripped_line = line.strip()
line_list = stripped_line.split()
list_of_items.append(line_list)
itemselection = input('Choice: ')
if itemselection.isalpha() == True:
ManageStock()
elif itemselection == '':
ManageStock()
itemselection = int(itemselection)
os.system('clear')
#the square brackets are the indexes so for example if they select 0, the first item turned into a list would be known as specific item
specificitem = list_of_items[itemselection]
changeitem(specificitem)
return specificitem
I'm trying to call the variable 'specificitem' to the function AddItem()
def AddToCart(specificitem):
os.system('clear')
number = 0
os.system('clear')
print ("""Here is the current stock
--------------------------
Name, Price, Quantity
--------------------------
""")
with open ('stocks', 'r') as stocks:
for i in stocks:
number = str(number)
print (number+'.' , i)
number = int(number)
number = number + 1
#this converts the text in the files into a list in a list
with open("stocks", "r") as stocks:
for line in stocks:
stripped_line = line.strip()
line_list = stripped_line.split()
list_of_items.append(line_list)
itemselection = input('Choice: ')
if itemselection.isalpha() == True:
AddToCart()
if itemselection == '':
MakeASale()
itemselection = int(itemselection)
#the square brackets are the indexes so for example if they select 0, the first item turned into a list would be known as specific item
quantity = input('How many would you like? ')
chosenitem2 = list_of_items[itemselection]
with open ('cart' , 'a') as cart:
chosenitem2 = str(chosenitem2)
cart.write(chosenitem2 + '\n')
with open("cart", "r") as cart:
for line in cart:
stripped_line = line.strip()
line_list = stripped_line.split()
list_of_cart.append(line_list)
with open ("cart" , "r+") as cart:
data = cart.read()
data = data.replace(chosenitem2[2], quantity)
cart.close
cart = open('cart' , 'wt')
cart.write(data)
cart.close()
with open ("stocks" , "r+") as stocks:
data = stocks.read()
data = data.replace(specificitem[2], chosenitem2[2])
stocks.close
stocks = open('stocks' , 'wt')
stocks.write(data)
stocks.close()
print(chosenitem2)
though it comes up with AddToCart() missing 1 required positional argument: 'specificitem'
I'm trying to use the variable from editselection to edit the quantity for example when the user enters a value it adds it to the file cart and 'subtracts' if you will from the file stocks, the use of global is unavailable due to the fact that I'll just get marked down. I've been stuck on this for 2 days now
In the first function write (function name)editselection.(variable name)specificitem=(value)list_of_items[itemselection]
And on the second function call the variable for example like this:
print(editselection.specificitem)
And this will print the value of the variable.
This is called a function variable (or something like this)
i have a task to do and i got stuck because whatever i do it does't seem to work.
So i have to csv files.
First called persons_file and it contains header line: id, name, surname.
And visits_file containing id, person_id, site.
I have to write a function called merge that gets to files as arguments (both StrionIO type) and returns list of dictionaries with number of visits for each users:
[ {
"id": (person's id),
"name": (person's name),
"surname": (person's surname),
"visits": (number of visits)
} ]
I came up with this and i don't know where my mistake is.
import io
def merge(persons_file,visits_file):
line_counter = 0
return_list = []
list_of_person_ids = []
visits = 0
for row in visits_file:
if line_counter == 0:
line_counter+=1
continue
list_of_person_ids.append(row.split(',')[1])
line_counter = 0
for row in persons_file:
if line_counter == 0:
line_counter+=1
continue
help_dict = {}
split_row = row.split(',')
help_dict['id'] = split_row[0]
help_dict['name'] = split_row[1]
help_dict['surname'] = split_row[2][:len(split_row[2])-1]
if split_row[0] in list_of_person_ids:
visits = list_of_person_ids.count(split_row[0])
help_dict['visits'] = str(visits)
return_list.append(help_dict)
visits=0
return return_list
file1 = open('persons_file.csv' , mode='r')
file2 = open('visits_file.csv' , mode='r')
persons_file_arg = io.StringIO(file1.read())
visits_file_arg = io.StringIO(file2.read())
list_of_visits = merge(persons_file_arg,visits_file_arg)
for i in list_of_visits:
print(i)
file1.close()
file2.close()
I will be glad if anyone could help me.
What is the issue? Is it the output that is not what you expected, or are you getting an exception? Your code seems like it should achieve the result you want, but I have a couple suggestions to make that could simplify things.
Look into collections.Counter you could then call count_of_visits_by_person_id = Counter(list_of_person_ids) to get a result of the form:
{person_id: number_of_visits, ...}. You could then use this to simply look up the number of visits in your next for loop. e.g.:
from collections import Counter
...
count_of_visits_by_person_id = Counter(list_of_person_ids)
for row in persons_file:
if line_counter == 0:
line_counter += 1
continue
help_dict = {}
split_row = row.split(',')
help_dict['id'] = split_row[0]
help_dict['name'] = split_row[1]
help_dict['surname'] = split_row[2][:-1]
# [:len(split_row[2]) - 1] is equivalent to [:-1]
# I assume you are stripping whitespace from the right side,
# which can also be accomplished using split_row[2].rstrip()
if split_row[0] in count_of_visits_by_person_id:
visits = count_of_visits_by_person_id[split_row[0]]
else:
visits = 0
help_dict['visits'] = str(visits)
return_list.append(help_dict)
The generally simpler and safer way to open files is using the with statement. Here is an example:
with open('visits_file.csv', mode='r') as visits_file:
row = visits_file.readline()
while row:
row = visits_file.readline() # Skips the first line
list_of_person_ids.append(row.split(',')[1])
I am trying to convert multiple .txt file to "table-like" data (with columns and rows). Each .txt file should be considered as a new column.
Consider below content of the .txt file:
File1.txt
Hi there
How are you doing?
What is your name?
File2.txt
Hi
Great!
Oliver, what's yours?
I have created a simple method, that accepts the file and and integer (the file number from another method):
def txtFileToJson(text_file, column):
data = defaultdict(list)
i = int(1)
with open(text_file) as f:
data[column].append(column)
for line in f:
i = i + 1
for line in re.split(r'[\n\r]+', line):
data[column] = line
with open("output.txt", 'a+') as f:
f.write(json.dumps(data))
So above method will run two times (one time for each file, and append the data).
This is the output.txt file after I have run my script:
{"1": "What is your name?"}{"2": "Oliver, what's yours?"}
As you can see, I can only get it to create a new for each file I have, and then add the entire line.
[{
"1": [{
"1": "Hi there",
"2": "How are you doing?",
"3": "\n"
"4": "What is your name?"
},
"2": [{
"1": "Hi"
"2": "Great!",
"3": "\n",
"4": "Oliver, what's yours?"
},
}]
Update:
OK, so I played around a bit and got a bit closer:
myDict = {str(column): []}
i = int(1)
with open(text_file) as f:
for line in f:
# data[column].append(column)
match = re.split(r'[\n\r]+', line)
if match:
myDict[str(column)].append({str(i): line})
i = i + 1
with open(out_file, 'a+') as f:
f.write(json.dumps(myDict[str(column)]))
That gives me below output:
[{"1": "Hi there\n"}, {"2": "How are you doing?\n"}, {"3": "\n"}, {"4": "What is your name?"}]
[{"1": "Hi\n"}, {"2": "Great!\n"}, {"3": "\n"}, {"4": "Oliver, what's yours?"}]
But as you can see, now I have multiple JSON root elements.
Solution
Thanks to jonyfries, I did this:
data = defaultdict(list)
for path in images.values():
column = column + 1
data[str(column)] = txtFileToJson(path, column)
saveJsonFile(path, data)
And then added a new method to save the final combined list:
def saveJsonFile(text_file, data):
basename = os.path.splitext(os.path.basename(text_file))
dir_name = os.path.dirname(text_file) + "/"
text_file = dir_name + basename[0] + "1.txt"
out_file = dir_name + 'table_data.txt'
with open(out_file, 'a+') as f:
f.write(json.dumps(data))
You're creating a new dictionary within the function itself. So each time you pass a text file in it will create a new dictionary.
The easiest solution seems to be returning the dictionary created and add it to an existing dictionary.
def txtFileToJson(text_file, column):
myDict = {str(column): []}
i = int(1)
with open(text_file) as f:
for line in f:
# data[column].append(column)
match = re.split(r'[\n\r]+', line)
if match:
myDict[str(column)].append({str(i): line})
i = i + 1
with open(out_file, 'a+') as f:
f.write(json.dumps(myDict[str(column)]))
return myDict
data = defaultdict(list)
data["1"] = txtFileToJson(text_file, column)
data["2"] = txtFileToJson(other_text_file, other_column)
def read(text_file):
data, i = {}, 0
with open(text_file) as f:
for line in f:
i = i + 1
data['row_%d'%i] = line.rstrip('\n')
return data
res = {}
for i, fname in enumerate([r'File1.txt', r'File2.txt']):
res[i] = read(fname)
with open(out_file, 'w') as f:
json.dump(res, f)
First, if I understand you are trying to get as output a dictionary of dictionaries, then let me observe that what I understand to be your desired output seems to be enclosing the whole thing within a list, Furthermore, you have unbalanced open and closed list brackets within the dictionaries, which I will ignore, as I will the enclosing list.
I think you need something like:
#!python3
import json
import re
def processTxtFile(text_file, n, data):
d = {}
with open(text_file) as f:
i = 0
for line in f:
for line in re.split(r'[\n\r]+', line):
i = i + 1
d[str(i)] = line
data[str(n)] = d
data = dict()
processTxtFile('File1.txt', 1, data)
processTxtFile('File2.txt', 2, data)
with open("output.txt", 'wt') as f:
f.write(json.dumps(data))
If you really need the nested dictionaries to be enclosed within a list, then replace
data[str(n)] = d
with:
data[str(n)] = [d]
I am trying to create 5 lists out of 1 data file, the error I keep getting states that "airlines is not defined", yet it is the first thing I define in the function, how is this possible? What should I do to correctly create a list of airlines, arrival times, departure times, prices, and flight number?
USAir,1269,6:15,10:57,210
Delta,5138,16:20,22:10,212
UNITED,6001,14:12,20:50,217
Delta,5054,12:30,20:22,227
UNITED,5949,9:30,14:43,264
JetBlue,1075,17:00,20:06,280
Delta,1263,6:00,11:30,282
Delta,3824,9:00,14:45,282
USAir,1865,16:55,21:33,300
USAir,3289,18:55,23:41,300
USAir,1053,8:00,13:02,300
USAir,2689,12:55,18:09,300
USAir,3973,9:25,14:00,302
USAir,3267,11:30,16:13,302
USAir,3609,13:25,18:28,302
USAir,3863,15:35,20:54,302
USAir,3826,17:45,23:19,302
USAir,1927,7:00,12:53,302
Delta,3601,12:00,17:29,307
Delta,4268,7:15,12:46,307
UNITED,4676,6:00,10:45,321
UNITED,4103,11:00,16:16,321
USAir,3139,11:51,16:29,332
JetBlue,475,7:30,10:42,340
USAir,3267,11:30,18:15,367
UNITED,2869,16:55,21:33,406
UNITED,2865,6:15,10:57,406
UNITED,2729,8:00,13:02,406
UNITED,2645,7:00,12:53,445
and the code I am using is
def getFlights():
airlines = []
flightNums = []
depTimes = []
arriveTimes = []
prices = []
fname = input("Enter name of data file: ")
infile = open(fname, 'r')
line = infile.readline()
line = line.strip()
while line != "":
line = line.strip()
airline, flightNum, depTime, arriveTime, price = line.split(',')
airlines.append(airline)
flightNums.append(flightNum)
depTimes.append(depTime)
arriveTimes.append(arriveTime)
prices.append(price)
line = infile.readline()
line = line.strip()
infile.close()
return airlines, flightNums, depTimes, arriveTimes, prices
getFlights()
print(airlines, flightNums, depTimes, arriveTimes, prices)
Local variables inside a function are not accessible outside of the function call. If you want to use the returned values of getFlights you must assign them to variables in the calling context.
(airlines, flightNums, depTimes, arriveTimes, prices) = getFlights()
print(airlines, flightNums, depTimes, arriveTimes, prices)
What b4hand has said is correct, however, the Pythonic way of doing this is using csv.reader and a with statement, eg:
import csv
filename = input('Enter filename: ')
with open(filename, 'rb') as fin:
csvin = csv.reader(fin)
airlines, flightNums, depTimes, arriveTimes, prices = zip(*csvin)
I am doing text processing and using 'readline()' function as follows:
ifd = open(...)
for line in ifd:
while (condition)
do something...
line = ifd.readline()
condition = ....
#Here when the condition becomes false I need to rewind the pointer so that the 'for' loop read the same line again.
ifd.fseek() followed by readline is giving me a '\n' character. How to rewind the pointer so that the whole line is read again.
>>> ifd.seek(-1,1)
>>> line = ifd.readline()
>>> line
'\n'
Here is my code
labtestnames = sorted(tmp)
#Now read each line in the inFile and write into outFile
ifd = open(inFile, "r")
ofd = open(outFile, "w")
#read the header
header = ifd.readline() #Do nothing with this line. Skip
#Write header into the output file
nl = "mrn\tspecimen_id\tlab_number\tlogin_dt\tfluid"
offset = len(nl.split("\t"))
nl = nl + "\t" + "\t".join(labtestnames)
ofd.write(nl+"\n")
lenFields = len(nl.split("\t"))
print "Reading the input file and converting into modified file for further processing (correlation analysis etc..)"
prevTup = (0,0,0)
rowComplete = 0
k=0
for line in ifd:
k=k+1
if (k==200): break
items = line.rstrip("\n").split("\t")
if((items[0] =='')):
continue
newline= list('' for i in range(lenFields))
newline[0],newline[1],newline[3],newline[2],newline[4] = items[0], items[1], items[3], items[2], items[4]
ltests = []
ltvals = []
while(cmp(prevTup, (items[0], items[1], items[3])) == 0): # If the same mrn, lab_number and specimen_id then fill the same row. else create a new row.
ltests.append(items[6])
ltvals.append(items[7])
pos = ifd.tell()
line = ifd.readline()
prevTup = (items[0], items[1], items[3])
items = line.rstrip("\n").split("\t")
rowComplete = 1
if (rowComplete == 1): #If the row is completed, prepare newline and write into outfile
indices = [labtestnames.index(x) for x in ltests]
j=0
ifd.seek(pos)
for i in indices:
newline[i+offset] = ltvals[j]
j=j+1
if (rowComplete == 0): #
currTup = (items[0], items[1], items[3])
ltests = items[6]
ltvals = items[7]
pos = ifd.tell()
line = ifd.readline()
items = line.rstrip("\n").split("\t")
newTup = (items[0], items[1], items[3])
if(cmp(currTup, newTup) == 0):
prevTup = currTup
ifd.seek(pos)
continue
else:
indices = labtestnames.index(ltests)
newline[indices+offset] = ltvals
ofd.write(newline+"\n")
The problem can be handled more simply using itertools.groupby. groupby can cluster all the contiguous lines that deal with the same mrn, specimen_id, and lab_num.
The code that does this is
for key, group in IT.groupby(reader, key = mykey):
where reader iterates over the lines of the input file, and mykey is defined by
def mykey(row):
return (row['mrn'], row['specimen_id'], row['lab_num'])
Each row from reader is passed to mykey, and all rows with the same key are clustered together in the same group.
While we're at it, we might as well use the csv module to read each line into a dict (which I call row). This frees us from having to deal with low-level string manipulation like line.rstrip("\n").split("\t") and instead of referring to columns by index numbers (e.g. row[3]) we can write code that speaks in higher-level terms such as row['lab_num'].
import itertools as IT
import csv
inFile = 'curious.dat'
outFile = 'curious.out'
def mykey(row):
return (row['mrn'], row['specimen_id'], row['lab_num'])
fieldnames = 'mrn specimen_id date lab_num Bilirubin Lipase Calcium Magnesium Phosphate'.split()
with open(inFile, 'rb') as ifd:
reader = csv.DictReader(ifd, delimiter = '\t')
with open(outFile, 'wb') as ofd:
writer = csv.DictWriter(
ofd, fieldnames, delimiter = '\t', lineterminator = '\n', )
writer.writeheader()
for key, group in IT.groupby(reader, key = mykey):
new = {}
row = next(group)
for key in ('mrn', 'specimen_id', 'date', 'lab_num'):
new[key] = row[key]
new[row['labtest']] = row['result_val']
for row in group:
new[row['labtest']] = row['result_val']
writer.writerow(new)
yields
mrn specimen_id date lab_num Bilirubin Lipase Calcium Magnesium Phosphate
4419529 1614487 26.2675 5802791G 0.1
3319529 1614487 26.2675 5802791G 0.3 153 8.1 2.1 4
5713871 682571 56.0779 9732266E 4.1
This seems to be a perfect use case for yield expressions. Consider the following example that prints lines from a file, repeating some of them at random:
def buflines(fp):
r = None
while True:
r = yield r or next(fp)
if r:
yield None
from random import randint
with open('filename') as fp:
buf = buflines(fp)
for line in buf:
print line
if randint(1, 100) > 80:
print 'ONCE AGAIN::'
buf.send(line)
Basically, if you want to process an item once again, you send it back to the generator. On the next iteration you will be reading the same item once again.