This short script converts the Excel files from the supplementary materials of Schich et al. to CSV text files (compressed with gzip).

In [ ]:
import pandas as pd

fnames = ["SchichDataS1_FB.xlsx", "SchichDataS2_AKL.xlsx",
          "SchichDataS3_ULAN.xlsx", "SchichDataS4_WCEN.xlsx"]

for fi in fnames:
    print fi
    data = pd.read_excel(fi)
    data = data.convert_objects(convert_numeric=True)
    out_name = fi.replace(".xlsx", ".csv.gz")
    out = gzip.open(out_name, "w")
    data.to_csv(out, encoding="utf-8")
    out.close()