valentin/big_data_projet
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Pipelines regroup

Browse Source
This commit is contained in:
valentin 2020-04-04 22:28:14 +02:00
parent a1bdae4dab
commit 36f9d7e098
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
04_detect_from_oneline_csv.py
View File

@ -66,13 +66,16 @@ class ManualFeatureSelector(TransformerMixin):
# =-=-=-=-=-=-= Pipelines =-=-=-=-=-=-= # =-=-=-=-=-=-= Pipelines =-=-=-=-=-=-=
# - This pipeline select usefull features - # - This pipeline select usefull features -
pipeline_features_selection = Pipeline([ #pipeline_features_selection = Pipeline([
('features_remap', ManualFeatureSelector()), # ('features_remap', ManualFeatureSelector()),
]) #])
# - This pipeline use the imputer and scales the values - # - This pipeline use the imputer and scales the values -
# -- Tried to regroup both pipelines, seems to work for now ... --
# -- TODO If no issues, don't forget to remove the upper commented pipeline
pipeline = Pipeline([ pipeline = Pipeline([
('features_remap', ManualFeatureSelector()),
('imputer', SimpleImputer(strategy="median")), ('imputer', SimpleImputer(strategy="median")),
('std_scaler', StandardScaler()), ('std_scaler', StandardScaler()),
]) ])
@ -95,7 +98,8 @@ saved_model = joblib.load("models/malware_classifier_1.pkl")
# - Use np.array([['info1', 'info2', 'infox']]) to build the 'line' variable - # - Use np.array([['info1', 'info2', 'infox']]) to build the 'line' variable -
def predict_one_line(model,line): def predict_one_line(model,line):
X_unknown = full_pipeline(line) #X_unknown = full_pipeline(line)
X_unknown = pipeline.fit_transform(line)
X_unknown_columns = ['Characteristics', 'DllCharacteristics', 'SectionsMaxEntropy', 'MajorSubsystemVersion', 'Machine', 'Subsystem', 'ResourcesMaxEntropy', 'ResourcesMinEntropy', 'VersionInformationSize', ' MajorOperatingSystemVersion', 'ResourcesMeanEntropy', 'SectionsMeanEntropy'] X_unknown_columns = ['Characteristics', 'DllCharacteristics', 'SectionsMaxEntropy', 'MajorSubsystemVersion', 'Machine', 'Subsystem', 'ResourcesMaxEntropy', 'ResourcesMinEntropy', 'VersionInformationSize', ' MajorOperatingSystemVersion', 'ResourcesMeanEntropy', 'SectionsMeanEntropy']
X_unknown = pd.DataFrame(X_unknown, columns=X_unknown_columns) X_unknown = pd.DataFrame(X_unknown, columns=X_unknown_columns)
ans = model.predict(X_unknown) ans = model.predict(X_unknown)