dataset generation script

This commit is contained in:
René Knaebel 2017-06-30 10:49:49 +02:00
parent 7ae68cc30e
commit 9768f1546b

View File

@ -1,6 +1,10 @@
#!/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")