#!/usr/bin/python2

import joblib
import numpy as np
import pandas as pd

df = joblib.load("/mnt/projekte/pmlcluster/cisco/trainData/multipleTaskLearning/currentData.joblib")
df = pd.concat(df["data"])
df.reset_index(inplace=True)
df.dropna(axis=0, how="any", inplace=True)
df[["duration", "bytes_down", "bytes_up"]] = df[["duration", "bytes_down", "bytes_up"]].astype(np.int)
df[["domain", "server_ip"]] = df[["domain", "server_ip"]].astype(str)
df[["server_label"]] = df[["server_label"]].astype(np.bool)
df.serverLabel = df.serverLabel.astype(np.bool)
df.virusTotalHits = df.virusTotalHits.astype(np.int)
df.trustedHits = df.trustedHits.astype(np.int)

df.to_csv("/tmp/rk/full_future_dataset.csv.gz", compression="gzip")