rene/ma_cisco_malware
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

dataset generation script

Browse Source
This commit is contained in:
René Knaebel 2017-06-30 10:49:49 +02:00
parent 7ae68cc30e
commit 9768f1546b
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/make_csv_dataset.py
View File

@ -1,6 +1,10 @@
#!/usr/bin/python2 #!/usr/bin/python2
import joblib import joblib
import pandas as pd
datafile = joblib.load("/mnt/projekte/pmlcluster/cisco/trainData/multipleTaskLearning/currentData.joblib") datafile = joblib.load("/mnt/projekte/pmlcluster/cisco/trainData/multipleTaskLearning/currentData.joblib")
user_flows = datafile["data"] 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")