Pickle to csv

README.md

@@ -137,3 +137,20 @@ python agg.py -i ../data/test1k.pkl -c ../data/test1kclustable.pkl -o ../data/te
 ```
 
 Aggregates data from `../data/test1k.pkl` by cluster information in `../data/test1kclustable.pkl`, save in `../data/test1kagg.pkl`.
+
+### `pickletocsv.py`
+
+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.
+* `-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
+```
+
+Reads file at `../data/test1kagg.pkl` and views it in the UNIX pager `less`.

py/pickletocsv.py

@@ -0,0 +1,29 @@
+from argparse import ArgumentParser
+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")
+    args = parser.parse_args()
+
+    if args.output is None:
+        args.output = stdout
+
+    if args.verbose:
+        print("Reading pickle")
+
+    ptc = p.read_pickle(args.input)
+
+    if args.verbose:
+        print(ptc.info())
+        print("Saving as csv")
+
+    ptc.to_csv(args.output, index = args.rownames)
+
+
+if __name__ == "__main__":
+    main()