2017-06-30 10:12:20 +02:00
|
|
|
#!/usr/bin/python2
|
|
|
|
|
|
|
|
|
|
import joblib
|
2017-06-30 10:49:49 +02:00
|
|
|
import pandas as pd
|
2017-06-30 10:12:20 +02:00
|
|
|
|
|
|
|
|
datafile = joblib.load("/mnt/projekte/pmlcluster/cisco/trainData/multipleTaskLearning/currentData.joblib")
|
|
|
|
|
user_flows = datafile["data"]
|
2017-06-30 10:49:49 +02:00
|
|
|
df = pd.concat(user_flows)
|
|
|
|
|
df.reset_index(inplace=True)
|
|
|
|
|
df.to_csv("/tmp/rk/full_dataset.csv.gz", compression="gzip")
|
