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

Video and more...

Browse Source
This commit is contained in:
valentin 2020-04-07 18:46:31 +02:00
parent 14e6bcce9a
commit 99ed3d4427
5 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
01_data_analysis.py
View File

@ -20,7 +20,7 @@ from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFromModel from sklearn.feature_selection import SelectFromModel
print("Loading dataset in memory [ ... ]") print("Loading dataset in memory [ ... ]")
files = pd.read_csv('dataset_clean.txt',delimiter=',', low_memory=False) files = pd.read_csv('dataset/dataset_clean.txt',delimiter=',', low_memory=False)
print("Loading dataset in memory [ DONE ]") print("Loading dataset in memory [ DONE ]")
print("Dataset basic infos:") print("Dataset basic infos:")

2
02_draft_preparation_work.py
View File

@ -20,7 +20,7 @@ from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFromModel from sklearn.feature_selection import SelectFromModel
print("Loading dataset in memory [ ... ]") print("Loading dataset in memory [ ... ]")
files = pd.read_csv('dataset_clean.txt',delimiter=',', low_memory=False) files = pd.read_csv('dataset/dataset_clean.txt',delimiter=',', low_memory=False)
print("Loading dataset in memory [ DONE ]") print("Loading dataset in memory [ DONE ]")
# =-=-=-=-=-=-=-= Data Prepare Work =-=-=-=-=-=-= # =-=-=-=-=-=-=-= Data Prepare Work =-=-=-=-=-=-=

10
04_detect_from_oneline_csv.py
View File

@ -121,18 +121,18 @@ def predict_one_line(model,line):
# - At the end, print the prediction accuracy result # - At the end, print the prediction accuracy result
res = [] res = []
#nb_malware_to_test = 50 nb_malware_to_test = 50
nb_malware_to_test = 34199 #nb_malware_to_test = 34199
good_ans = 0 good_ans = 0
for i in range(34179,nb_malware_to_test): #for i in range(34179,nb_malware_to_test):
#for i in range(nb_malware_to_test): for i in range(nb_malware_to_test):
print(" =-=-=-= Prediction {} out of {} ({}%) [ ERT ~ {} min ] =-=-=-=".format(i, nb_malware_to_test, round((i/nb_malware_to_test)*100,1), round(((nb_malware_to_test-i)*1.2)/60,1))) print(" =-=-=-= Prediction {} out of {} ({}%) [ ERT ~ {} min ] =-=-=-=".format(i, nb_malware_to_test, round((i/nb_malware_to_test)*100,1), round(((nb_malware_to_test-i)*1.2)/60,1)))
features = file_to_test.values[i,] features = file_to_test.values[i,]
features_list = features.tolist() features_list = features.tolist()
features_array = [features_list] features_array = [features_list]
features = np.array(features_array) features = np.array(features_array)
res.append(predict_one_line(saved_model, features)) res.append(predict_one_line(saved_model, features))
if res[i-34179] == file_to_test.values[i,][54]: if res[i] == file_to_test.values[i,][54]:
good_ans +=1 good_ans +=1
print(features) print(features)
print(res) print(res)

4
06_extract_features_and_predict.py
View File

@ -199,8 +199,8 @@ def predict_from_features(features, model):
X_unknown = features_numpy X_unknown = features_numpy
X_unknown_columns = selected_features X_unknown_columns = selected_features
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)
ans = model.predict([features]) #ans = model.predict([features])
return ans[0] return ans[0]
if __name__ == "__main__": if __name__ == "__main__":

BIN
tenamortech_malware_scanner_website_ihm.mp4 Normal file
View File

Binary file not shown.