def predict(self, domains):
"""This function accepts cudf series of domains as an argument to classify domain names as benign/malicious and returns the learned label for each object in the form of cudf series.
:param domains: List of domains.
:type domains: cudf.Series
:return: Predicted results with respect to given domains.
:rtype: cudf.Series
Examples
--------
>>> dd.predict(['nvidia.com', 'dgadomain'])
0 0
1 1
Name: is_dga, dtype: int64
"""
df = cudf.DataFrame({"domain": domains})
domains_len = df["domain"].count()
temp_df = du.str2ascii(df, domains_len)
# Assigning sorted domains index to return learned labels as per the given input order.
df.index = temp_df.index
df["domain"] = temp_df["domain"]
temp_df = temp_df.drop("domain")
input, seq_lengths = self.__create_variables(temp_df)
del temp_df
model_result = self.model(input, seq_lengths)
pred = model_result.data.max(1, keepdim=True)[1]
type_ids = pred.view(-1).tolist()
df["is_dga"] = type_ids
df = df.sort_index()
return df["is_dga"]
def __get_partitioned_dfs(self, df, batch_size):
"""Partition one dataframe to multiple small dataframes based on a given batch size.
:param df: Contains domains and it's types.
:type df: cudf.DataFrame
:param batch_size: Number of records has to be in each partitioned dataframe.
:type batch_size: int
"""
dataset_len = df["domain"].count()
df = du.str2ascii(df, dataset_len)
prev_chunk_offset = 0
partitioned_dfs = []
while prev_chunk_offset < dataset_len:
curr_chunk_offset = prev_chunk_offset + batch_size
chunk = df.iloc[prev_chunk_offset:curr_chunk_offset:1]
partitioned_dfs.append(chunk)
prev_chunk_offset = curr_chunk_offset
return partitioned_dfs, dataset_len
def test_str2ascii():
actual_output_df = du.str2ascii(test_input_df, test_domains_len)
assert actual_output_df.equals(expected_output_df)