add h5 support for pauls best config main

This commit is contained in:
2017-07-11 11:12:03 +02:00
parent 41b38de1ab
commit 522854ee0d
3 changed files with 21 additions and 16 deletions

View File

@@ -10,9 +10,8 @@ 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.virusTotalHits = df.virusTotalHits.astype(np.int8)
df.trustedHits = df.trustedHits.astype(np.int8)
df.to_csv("/tmp/rk/full_future_dataset.csv.gz", compression="gzip")