def predict(self, domains, probability=False):
"""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 0.010
1 0.924
Name: dga_probability, dtype: decimal
"""
df = cudf.DataFrame({"domain": domains})
domains_len = df["domain"].count()
temp_df = utils.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", axis=1)
input, seq_lengths = self._create_variables(temp_df)
del temp_df
model_result = self.model(input, seq_lengths)
if probability:
model_result = model_result[:, 0]
preds = torch.sigmoid(model_result)
preds = preds.view(-1).tolist()
df["preds"] = preds
else:
preds = model_result.data.max(1, keepdim=True)[1]
preds = preds.view(-1).tolist()
df["preds"] = preds
df = df.sort_index()
return df["preds"]
def predict(self, domains, probability=False, truncate=100):
"""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
:param truncate: Truncate string to n number of characters.
:type truncate: int
Examples
--------
>>> dd.predict(['nvidia.com', 'dgadomain'])
0 0.010
1 0.924
Name: dga_probability, dtype: decimal
"""
log.debug("Initiating model inference ...")
self.model.eval()
df = cudf.DataFrame({"domain": domains})
log.debug('Truncate domains to width: {}'.format(truncate))
df['domain'] = df['domain'].str.slice_replace(truncate, repl='')
temp_df = utils.str2ascii(df, 'domain')
# 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", axis=1)
input, seq_lengths = self._create_variables(temp_df)
del temp_df
model_result = self.model(input, seq_lengths)
if probability:
model_result = model_result[:, 0]
preds = torch.sigmoid(model_result)
preds = preds.view(-1).tolist()
df["preds"] = preds
else:
preds = model_result.data.max(1, keepdim=True)[1]
preds = preds.view(-1).tolist()
df["preds"] = preds
df = df.sort_index()
return df["preds"]
def __preprocess(self, df, truncate):
df['domain'] = df['domain'].str.slice_replace(truncate, repl='')
df = utils.str2ascii(df, 'domain')
return df
def __preprocess(self, df):
df = utils.str2ascii(df, df.shape[0])
return df
def test_str2ascii():
actual_output_df = utils.str2ascii(test_input_df, 'domain')
assert actual_output_df.equals(expected_output_df)
def __preprocess(self, df):
df = utils.str2ascii(df, 'domain')
return df