I have a folder with lots of *.dat files (which were created with the program IDL). I am able to take one single file, convert it to a *.csv file and save it in a different (already existing) folder:
import idlsave
import csv
input_file = idlsave.read("C:/Users/RAW/06211714.dat")
n = input_file["raw"]
with open("C:/Users/CSV/06211714.csv", "w", newline='') as f:
writer = csv.writer(f)
writer.writerows(n)
The line input_file = idlsave.read("C:/Users/RAW/06211714.dat") shows the following output:
Available variables: raw class ['numpy.recarray']
So, this works fine for just taking one file, but I am looking for a way to take all *.dat files at once and convert each of them to a *.csv file with their original name.
I was thinking of something like this, but it didn't work:
import glob
for filename in glob.glob("C:/Users/RAW/*.dat"):
for element in filename:
i = idlsave.read(element)
n = i["raw"]
with open("C:/Users/CSV/*.csv", "w", newline='') as f:
writer = csv.writer(f)
writer.writerows(n)
Can someone please give me some advice?
Thanks.
import csv
import idlsave
from os import listdir
from os.path import isfile, join, splitext
dat_folder = "/folder/to/dat/files/"
csv_folder = "/folder/to/save/new/csv/files/"
onlyfilenames = [f for f in listdir(dat_folder) if isfile(join(dat_folder,f))]
for fullfilename in onlyfilenames:
file_name, file_extension = splitext(fullfilename)
if file_extension == ".dat":
input_file = idlsave.read(dat_folder + fullfilename)
n = input_file["raw"]
with open(join(csv_folder, file_name + ".csv"), "w", newline='') as f:
writer = csv.writer(f)
writer.writerows(n)
Related
I have a python transform in code workbooks that is running this code:
import pandas as pd
def contents(dataset_with_files):
fs = dataset_with_files.filesystem()
filenames = [f.path for f in fs.ls()]
fp = fs.hadoop_path + "/" + filenames[0]
with open(fp, 'r') as f:
t = f.read()
rows = {"text": [t]}
return pd.DataFrame(rows)
But I am getting the error FileNotFoundError: [Errno 2] No such file or directory:
My understanding is that this is the correct way to access a file in the hdfs, is this a repository versus code workbooks limitation?
This documentation helped me figure it out:
https://www.palantir.com/docs/foundry/code-workbook/transforms-unstructured/
It was actually a pretty small change. If you are using the filesystem() you only need the relative path.
import pandas as pd
def contents_old(pycel_test):
fs = pycel_test.filesystem()
filenames = [f.path for f in fs.ls()]
with fs.open(filenames[0], 'r') as f:
value = ...
rows = {"values": [value]}
return pd.DataFrame(rows)
There is also this option, but I found it 10x slower.
from pyspark.sql import Row
def contents(dataset_with_files):
fs = dataset_with_files.filesystem() # This is the FileSystem object.
MyRow = Row("column")
def process_file(file_status):
with fs.open(file_status.path, 'r') as f:
...
rdd = fs.files().rdd
rdd = rdd.flatMap(process_file)
df = rdd.toDF()
return df
My code reads a bunch of json files from a directory and extract "frequency" and "attenuation" data from those files and write to a csv file. Now I want to save that csv file in a different directory. The code executes without any error but saves in the current directory. Can anyone help to resolve this issue?
import csv
import glob
import json
import os
site = 'alpha'
frequency_to_check = '196050.000'
json_dir_name = 'V:/temp/test/'
json_pattern = os.path.join(json_dir_name, '*.json')
total_files = glob.glob(json_pattern)
atten = []
timestamp = []
save_path = 'V:/python/result/'
if not os.path.isdir(save_path):
os.makedirs(save_path)
filename = f'{site}-{frequency_to_check}.csv'
with open(filename, 'w', newline='') as csv_file:
for file in total_files:
with open(file) as json_file:
output_json = json.load(json_file)
for key in output_json:
if key['start-freq'] == frequency_to_check:
csv.writer(csv_file).writerow([key['start-freq'], key['attenuation']])
save_file = os.path.join(save_path, filename)
csv_file.close()
print(f'Total files processed {len(total_files)}')
The issue as far as I can deduce is here :
csv.writer(csv_file).writerow([key['start-freq'], key['attenuation']])
csv_file is your object that is loaded into memory , and everytime this line is executed you are just writing the rows in the already open file. After that you are just creating a new path :
save_file = os.path.join(save_path, filename)
which is never really used as you close the file too.
To fix this I would suggest that you put save_path as csv file :
import csv
import glob
import json
import os
site = 'alpha'
frequency_to_check = '196050.000'
json_dir_name = 'V:/temp/test/'
json_pattern = os.path.join(json_dir_name, '*.json')
total_files = glob.glob(json_pattern)
atten = []
timestamp = []
save_path = 'V:/python/result/'
if not os.path.isdir(save_path):
os.makedirs(save_path)
filename = f'{site}-{frequency_to_check}.csv'
save_file = os.path.join(save_path, filename)
with open(save_file, 'w', newline='') as csv_file:
for file in total_files:
with open(file) as json_file:
output_json = json.load(json_file)
for key in output_json:
if key['start-freq'] == frequency_to_check:
csv.writer(csv_file).writerow([key['start-freq'], key['attenuation']])
csv_file.close()
print(f'Total files processed {len(total_files)}')
I guess this should work.
I am trying to convert csv files in a folder to a single json file. Below code does the job, but the issue is, json file has the first csv written several times. Below is the code i tried. I guess i am going wrong with assigning the data variable. Help me fix it
import csv, json, os
dir_path = 'C:/Users/USER/Desktop/output_files'
inputfiles = [file for file in os.listdir(dir_path) if file.endswith('.csv')]
outputfile = "data_backup1.json"
for file in inputfiles:
filepath = os.path.join(dir_path, file)
data = {}
with open(filepath, "r") as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
id = row['ID']
data[id] = row
with open(outputfile, "a") as jsonfile:
jsonfile.write(json.dumps(data, indent=4))
Expected output: Json file needs to have each csv written only once into it.
if your .csv files and all of the rows do have different ['ID']s, your assigned dictionary keys should be unique. In this case, your dictionary is growing with one entry per reader .csv row.
You have to change the indentation of the jsonfile.write() function as shown below to produce just one .json file. To sort your entries you could add sort_keys=True in this function.
for file in inputfiles:
filepath = os.path.join(dir_path, file)
data = {}
with open(filepath, "r") as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
id = row['ID']
data[id] = row
with open(outputfile, "a") as jsonfile:
jsonfile.write(json.dumps(data, indent=4, sort_keys=True))
I'm trying to make a simple command line script with Python code that generates a CSV when it scans the contents of a directory, but I'm not sure if I'm doing it correctly, cause I keep getting errors. Can someone tell me what the heck I'm doing wrong?
import sys
import argparse
import os
import string
import fnmatch
import csv
from string import Template
from os import path
from os.path import basename
header = ["Title","VersionData","PathOnClient","OwnerId","FirstPublishLocationId","RecordTypeId","TagsCsv"]
if not sys.argv.len < 2:
with open(sys.argv[1], 'w') as f:
writer = csv.DictWriter(f, fieldnames = header, delimiter=',')
writer.writeheader()
if os.path.isdir(sys.argv[2]):
for d in os.scandir(sys.argv[2]):
row = Template('"$title","$path","$path"') #some default values in the template were omitted here
writer.writerow(row.substitute(title=basename(d.path)), path=path.abspath(d.path))
Right off the bat, csvwriter.writerow(row) takes only one argument. You need to wrap your arguments inside brackets and then join with comma.
Moreover, you cannot call other functions within the row object, which is what you are trying to do with row.substitute(args) etc.
Figured it out. For anyone else needing a quick CSV listing of folders, here's the code I got to work:
#!/usr/bin/env python3
import sys, os, csv
from string import Template
from pathlib import PurePath, PureWindowsPath
from os.path import basename
header = ["Title","Path","","","","",""] # insert what header you need, if any
if not len(sys.argv) < 2:
with open(sys.argv[1], 'w') as f:
writer = csv.DictWriter(f, fieldnames=header, dialect='excel', delimiter=',', quoting=csv.QUOTE_ALL)
writer.writeheader()
initPath = os.path.abspath(sys.argv[2])
if sys.platform.startswith('linux') or sys.platform.startswith('cygwin') or sys.platform.startswith('darwin'):
p = PurePath(initPath)
else:
if sys.platform.startswith('win32'):
p = PureWindowsPath(initPath)
if os.path.isdir(str(p)) and not str(p).startswith('.'):
for d in os.scandir(str(p)):
srow = Template('"$title","$path", "","","",""')
#s = srow.substitute({'title': basename(d.path), 'path': os.path.abspath(d.path)) #
#print(s) # this is for testing if the content produces what's expected
row = {'Title': basename(d.path), 'Path': os.path.abspath(d.path)} # the dictionary must have the same number of entries as the number of header fields your CSV is going to contain.
writer.writerow(row)
I would like to import a csv file into python with FileChooser and display it as dataframe. Here is the code and it didn't work. Thanks for your kind help.
def get_open_filename(self):
filename = None
chooser = gtk.FileChooserDialog("Open File...", self.window,
gtk.FILE_CHOOSER_ACTION_OPEN,
(gtk.STOCK_CANCEL, gtk.RESPONSE_CANCEL,
gtk.STOCK_OPEN, gtk.RESPONSE_OK))
response = chooser.run()
if response == gtk.RESPONSE_OK:
with open(chooser.get_filename(), 'rb') as csvfile:
don = DataFrame.from_csvfile(csvfile) ## I am confused here !!!
print don
chooser.destroy()
return filename
I believe from_csv file takes a filename not a file, using these docs
Try replacing
with open(chooser.get_filename(), 'rb') as csvfile:
don = DataFrame.from_csvfile(csvfile) ## I am confused here !!!
print don
with
don = DataFrame.from_csvfile(chooser.get_filename())
print don