#!/usr/bin/python2

import joblib
import pandas as pd

datafile = joblib.load("/mnt/projekte/pmlcluster/cisco/trainData/multipleTaskLearning/currentData.joblib")
user_flows = datafile["data"]
df = pd.concat(user_flows)
df.reset_index(inplace=True)
df.to_csv("/tmp/rk/full_dataset.csv.gz", compression="gzip")