I'm trying to import a dictionary variable from a function inside A.py, to my new python file B.py. However, it doesn't seem to bring it along. codedict is the variable I'm importing.
Python file A.py
import csv
def load(filename):
with open(filename, 'r') as datafile:
reader = csv.reader(datafile)
next(reader)
global codedict
codedict = sorted({k[1].lower() for k in reader})
load("Dataforcars.cvs")
In my new python file, I'm trying to bring along the dictionary.
Python file B.py
import csv
from A import load
print(codedict)
However, "codedict" is not defined in B.py.
I think this will helpful:
A.py:
import csv
def load(filename):
with open(filename, 'r') as datafile:
reader = csv.reader(datafile)
next(reader)
return sorted({k[1].lower() for k in reader})
B.py:
import csv
from A import load
codedict = load("Dataforcars.cvs")
print(codedict)
Codedict is local variable, you should return it rather than try to access it directly.
Related
I have a lot of JSON files, I put them in my folder, I want to convert them to CSV format,
Should I use import glob? ? I am a novice, how can I modify my codeļ¼
#-*-coding:utf-8-*-
import csv
import json
import sys
import codecs
def trans(path):
jsonData = codecs.open('C:/Users/jeri/Desktop/1', '*.json', 'r', 'utf-8')
# csvfile = open(path+'.csv', 'w')
# csvfile = open(path+'.csv', 'wb')
csvfile = open('C:/Users/jeri/Desktop/1.csv', 'w', encoding='utf-8', newline='')
writer = csv.writer(csvfile, delimiter=',')
flag = True
for line in jsonData:
dic = json.loads(line)
if flag:
keys = list(dic.keys())
print(keys)
flag = False
writer.writerow(list(dic.values()))
jsonData.close()
csvfile.close()
if __name__ == '__main__':
path=str(sys.argv[0])
print(path)
trans(path)
Yes using glob would be a good way to iterate through the .json files in your folder! But glob doesn't have anything to do with the reading/writing of files. After importing glob, you can use it like this:
for curr_file in glob.glob("*.json"):
# Process each file here
I see that you've used the json module to read in your code snippet. I'd say the better way to go about it is to use pandas.
df = pd.read_json()
I say this because with the pandas library, you can simply convert from .json to .csv using
df.to_csv('file_name.csv')
Combining the three together, it would look like this:
for curr_file in glob.glob("*.json"):
# Process each file here
df = pd.read_json(curr_file)
df.to_csv('file_name.csv')
Also, note that if your json has nested objects, it can't be directly converted to csv, you'll have to settle the organization of data prior to the conversion.
I need to take a csv file as a function argument and as an example code I have:
import openpyxl
from openpyxl import load_workbook
import csv
import xlrd
def supermarket(filename):
dictionary = {}
with open(filename, newline='') as filename:
read_csv = csv.reader(filename, delimiter=',')
for row in read_csv:
dictionary += row[0]
dictionary[row[0]] = row[1]
return dictionary
print(supermarket(prices1.csv))
However, when I debug the code, the traceback error says it is a NameError for which
prices1
is not defined. My professor is telling me that my argument should be able to take prices1.csv as an argument but I don't see how that's possible.
Your code is actually referring to a member csv of variable prices1, which obviously doesn't exist. Filename should actually be a string. So your code can be changed to this (assuming the csv file lies in the same directory as your working directory):
import openpyxl
from openpyxl import load_workbook
import csv
import xlrd
def supermarket(filename):
dictionary = {}
with open(filename, newline='') as filename:
read_csv = csv.reader(filename, delimiter=',')
for row in read_csv:
dictionary += row[0]
dictionary[row[0]] = row[1]
return dictionary
print(supermarket("prices1.csv"))
If it is convenience, use pandas library to handle CSV file in much more efficient way.
I am trying to write a list to a csv file.
the following code runs and returns no error, but it doesnt work, in that it doesnt actually populate the csv file with the stuff in the list. I am probably doing it wrong because I don't understand something.
import newspaper
import os
from newspaper import article
libya_newspaperlist = []
libya_newspaper=newspaper.build('https://www.cnn.com', memoize_article=False)
for article in libya_newspaper.articles:
libya_newspaperlist.append(article.url)
import csv
os.chdir("/users/patrickharned/")
libya_newspaper.csv = "/users/patrickharned/libya_newspaper.csv"
def write_list_to_file(libya_newspaperlist):
"""Write the list to csv file."""
with open("/users/patrickharned/libya_newspaper.csv") as outfile:
outfile.write(libya_newspaperlist)
So I changed the code to this.
import newspaper
import os
from newspaper import article
libya_newspaperlist = []
libya_newspaper=newspaper.build('https://www.cnn.com', memoize_article=False)
for article in libya_newspaper.articles:
libya_newspaperlist.append(article.url)
import csv
os.chdir("/users/patrickharned/")
libya_newspaper.csv = "/users/patrickharned/libya_newspaper.csv"
with open("/users/patrickharned/libya_newspaper.csv", "w") as outfile:
outfile.write(str(libya_newspaperlist))
now it does output to the csv file, but it only outputs the first entry and wont do the rest. any suggestions?
You have to open the file in write mode:
with open("/users/patrickharned/libya_newspaper.csv", "w") as outfile:
outfile.write(libya_newspaperlist)
I am running Python 3.x. So i have been working on some code for fetching data on currencies names around the world from a currency website to get information which the code is as follows
def _fetch_currencies():
import urllib.request
import json
f = urllib.request.urlopen('http://openexchangerates.org/api/currencies.json')
charset = f.info().get_param('charset', 'utf8')
data = f.read()
decoded = json.loads(data.decode(charset))
dumps = json.dumps(decoded, indent=4)
return dumps
I then need to save it as a file locally but having some issue and cant see where.
Here is the code for saving the currencies:
def save_currencies(_fetch_currencies, filename):
sorted_currencies = sorted(decoded.items())
with open(filename, 'w') as my_csv:
csv_writer = csv.writer(my_csv, delimiter=',')
csv_writer.writerows(sorted_currencies)
They just don't seem to work together apart from when i remove the line ' dumps = json.dumps(decoded, indent=4) ' but i need that line to be able to print the file in text, how do i get around deleting this line and still be able to save and print? How do i also pick where it saves?
Any Help will be great, thank you very much anyone and everyone who answers/reads this.
I may be mistaken, but your "decoded" variable should be declared as global in both functions.
I would actually have _fetch_currencies() return a dictionary, and then I would pass that dictionary on to saved_currencies(currencies_decoded, filename). For example:
def _fetch_currencies():
import urllib.request
import json
f = urllib.request.urlopen('http://openexchangerates.org/api/currencies.json')
charset = f.info().get_param('charset', 'utf8')
data = f.read()
decoded = json.loads(data.decode(charset))
return decoded
def save_currencies(currencies_decoded, filename):
sorted_currencies = sorted(currencies_decoded.items())
with open(filename, 'w') as my_csv:
csv_writer = csv.writer(my_csv, delimiter=',')
csv_writer.writerows(sorted_currencies)
my_currencies_decoded = _fetch_currencies()
save_currencies(my_currencies_decoded, "filename.csv")
Furthermore, if you would like to save your csv file to a certain location in your filesystem, you can import os and use the os.path.join() function and provide it the FULL path. For example, to save your .csv file to a location called "/Documents/Location/Here", you can do:
import os
def save_currencies(currencies_decoded, filename):
sorted_currencies = sorted(currencies_decoded.items())
with open(os.path.join("Documents","Location","Here"), 'w') as my_csv:
csv_writer = csv.writer(my_csv, delimiter=',')
csv_writer.writerows(sorted_currencies)
You can also use a relative path, so that if you're already in directory "Documents", and you'd like to save a file in "/Documents/Location/Here", you can instead just say:
with open(os.path.join("Location", "Here"), 'w') as my_csv:
I have a Python script which modifies a CSV file to add the filename as the last column:
import sys
import glob
for filename in glob.glob(sys.argv[1]):
file = open(filename)
data = [line.rstrip() + "," + filename for line in file]
file.close()
file = open(filename, "w")
file.write("\n".join(data))
file.close()
Unfortunately, it also adds the filename to the header (first) row of the file. I would like the string "ID" added to the header instead. Can anybody suggest how I could do this?
Have a look at the official csv module.
Here are a few minor notes on your current code:
It's a bad idea to use file as a variable name, since that shadows the built-in type.
You can close the file objects automatically by using the with syntax.
Don't you want to add an extra column in the header line, called something like Filename, rather than just omitting a column in the first row?
If your filenames have commas (or, less probably, newlines) in them, you'll need to make sure that the filename is quoted - just appending it won't do.
That last consideration would incline me to use the csv module instead, which will deal with the quoting and unquoting for you. For example, you could try something like the following code:
import glob
import csv
import sys
for filename in glob.glob(sys.argv[1]):
data = []
with open(filename) as finput:
for i, row in enumerate(csv.reader(finput)):
to_append = "Filename" if i == 0 else filename
data.append(row+[to_append])
with open(filename,'wb') as foutput:
writer = csv.writer(foutput)
for row in data:
writer.writerow(row)
That may quote the data slightly differently from your input file, so you might want to play with the quoting options for csv.reader and csv.writer described in the documentation for the csv module.
As a further point, you might have good reasons for taking a glob as a parameter rather than just the files on the command line, but it's a bit surprising - you'll have to call your script as ./whatever.py '*.csv' rather than just ./whatever.py *.csv. Instead, you could just do:
for filename in sys.argv[1:]:
... and let the shell expand your glob before the script knows anything about it.
One last thing - the current approach you're taking is slightly dangerous, in that if anything fails when writing back to the same filename, you'll lose data. The standard way of avoiding this is to instead write to a temporary file, and, if that was successful, rename the temporary file over the original. So, you might rewrite the whole thing as:
import csv
import sys
import tempfile
import shutil
for filename in sys.argv[1:]:
tmp = tempfile.NamedTemporaryFile(delete=False)
with open(filename) as finput:
with open(tmp.name,'wb') as ftmp:
writer = csv.writer(ftmp)
for i, row in enumerate(csv.reader(finput)):
to_append = "Filename" if i == 0 else filename
writer.writerow(row+[to_append])
shutil.move(tmp.name,filename)
You can try:
data = [file.readline().rstrip() + ",id"]
data += [line.rstrip() + "," + filename for line in file]
You can try changing your code, but using the csv module is recommended. This should give you the result you want:
import sys
import glob
import csv
filename = glob.glob(sys.argv[1])[0]
yourfile = csv.reader(open(filename, 'rw'))
csv_output=[]
for row in yourfile:
if len(csv_output) != 0: # skip the header
row.append(filename)
csv_output.append(row)
yourfile = csv.writer(open(filename,'w'),delimiter=',')
yourfile.writerows(csv_output)
Use the CSV module that comes with Python.
import csv
import sys
def process_file(filename):
# Read the contents of the file into a list of lines.
f = open(filename, 'r')
contents = f.readlines()
f.close()
# Use a CSV reader to parse the contents.
reader = csv.reader(contents)
# Open the output and create a CSV writer for it.
f = open(filename, 'wb')
writer = csv.writer(f)
# Process the header.
header = reader.next()
header.append('ID')
writer.writerow(header)
# Process each row of the body.
for row in reader:
row.append(filename)
writer.writerow(row)
# Close the file and we're done.
f.close()
# Run the function on all command-line arguments. Note that this does no
# checking for things such as file existence or permissions.
map(process_file, sys.argv[1:])
You can run this as follows:
blair#blair-eeepc:~$ python csv_add_filename.py file1.csv file2.csv
you can use fileinput to do in place editing
import sys
import glob
import fileinput
for filename in glob.glob(sys.argv[1]):
for line in fileinput.FileInput(filename,inplace=1) :
if fileinput.lineno()==1:
print line.rstrip() + " ID"
else
print line.rstrip() + "," + filename