Edit pickle-csv converter script

README.md

@@ -142,15 +142,15 @@ Aggregates data from `../data/test1k.pkl` by cluster information in `../data/tes
 
 Helper function to transform a pickle into a csv file, for easier importing into e.g. Excel.
 
-* `-i PATH`: The path for the python "pickle" file which contains the dataset.
-* `-o PATH`: The path for the csv file to store the dataset in; if omitted prints to `stdout`.
+* `input`: The path for the python "pickle" file which contains the dataset.
+* `output`: The path for the csv file to store the dataset in; if omitted, or `-`, prints to `stdout`.
 * `-r`: Include row names/index labels in csv. This may be essential for proper exporting of some datasets
 * `-v`: Output extra information, including dimensions of dataset.
 
 Example:
 
 ```bash
-python pickletocsv.py -i ../data/test1kagg.pkl | less
+python pickletocsv.py ../data/test1kagg.pkl | less
 ```
 
 Reads file at `../data/test1kagg.pkl` and views it in the UNIX pager `less`.

py/pickletocsv.py

@@ -1,13 +1,16 @@
-from argparse import ArgumentParser
+from argparse import ArgumentParser, FileType
 from sys import stdout
 import pandas as p
 
 def main():
     parser = ArgumentParser(description='Transform a "pickle" to a csv file')
-    parser.add_argument("-i", "--input",  dest="input",      help = "input pickle path",  metavar="PATH", required = True)
-    parser.add_argument("-o", "--output", dest="output",     help = "output csv path", metavar="PATH")
-    parser.add_argument("-r", "--row-names", dest = "rownames", help = "include row names in csv; if ommitted prints to stdout", action = "store_true")
-    parser.add_argument("-v", "--verbose", dest = "verbose", action ="store_true")
+    parser.add_argument(dest="input",      help = "input pickle path", type = FileType('rb'))
+    parser.add_argument(dest="output",  nargs="?",   help = "output csv path", type = FileType('w'))
+    parser.add_argument("-r", "--row-names", dest = "rownames", help = "include row names in csv; "
+                        "needed to faithfully reproduce some dataframes. "
+                        "Use -v to check information about dataframe", action = "store_true")
+    parser.add_argument("-v", "--verbose", dest = "verbose", action ="store_true", 
+                        help="print information about dataframe and process")
     args = parser.parse_args()
 
     if args.output is None:
@@ -24,6 +27,9 @@ def main():
 
     ptc.to_csv(args.output, index = args.rownames)
 
+    args.input.close()
+    args.output.close()
+
 
 if __name__ == "__main__":
     main()