Update app.py

app.py

@@ -3,17 +3,12 @@
 
 # In[2]:
 
-
 import gradio as gr
 
-
+import os
 import pandas as pd
 from math import sqrt;
 import numpy as np
-from sklearn import preprocessing
-from sklearn.metrics import accuracy_score,log_loss
-from sklearn.model_selection import train_test_split
-
 import matplotlib.pyplot as plt
 import seaborn as sns 
 import joblib
@@ -21,6 +16,15 @@ import joblib
 import tensorflow as tf
     
 def malware_detection_DL (results, malicious_traffic, benign_traffic):
+    plt.clf()
+    if os.path.exists("accplot.png"):
+        os.remove("accplot.png")
+    else:
+        pass
+    if os.path.exists("lossplot.png"):
+        os.remove("lossplot.png")
+    else:
+        pass  
     malicious_dataset = pd.read_csv(malicious_traffic)  #Importing Datasets 
     benign_dataset = pd.read_csv(benign_traffic)
     # Removing duplicated rows from benign_dataset (5380 rows removed)
@@ -35,13 +39,13 @@ def malware_detection_DL (results, malicious_traffic, benign_traffic):
     reduced_y = df['isMalware']
     reduced_x = df.drop(['isMalware'], axis=1);
     # Splitting datasets into training and test data
-    x_train, x_test, y_train, y_test = train_test_split(reduced_x, reduced_y, test_size=0.2, random_state=42)
+    #x_train, x_test, y_train, y_test = train_test_split(reduced_x, reduced_y, test_size=0.2, random_state=42)
    
     #scale data between 0 and 1
-    min_max_scaler = preprocessing.MinMaxScaler()
-    x_scale = min_max_scaler.fit_transform(reduced_x)
+    #min_max_scaler = preprocessing.MinMaxScaler()
+    #x_scale = min_max_scaler.fit_transform(reduced_x)
     # Splitting datasets into training and test data
-    x_train, x_test, y_train, y_test = train_test_split(x_scale, reduced_y, test_size=0.2, random_state=42)
+    #x_train, x_test, y_train, y_test = train_test_split(x_scale, reduced_y, test_size=0.2, random_state=42)
     #type of layers in ann model is sequential, dense and uses relu activation 
     ann = tf.keras.models.Sequential()
     model = tf.keras.Sequential([
@@ -54,10 +58,10 @@ def malware_detection_DL (results, malicious_traffic, benign_traffic):
     model.compile(optimizer ='adam', 
         loss = 'binary_crossentropy',
         metrics = ['accuracy'])
-       
-        #does not output epochs and gives evalutaion of validation data and history of losses and accuracy, epochs lowered to 10 from 150 for speed in displaying plot
-    history = model.fit(x_train, y_train, batch_size=32, epochs = 30,verbose=0, validation_data=(x_test, y_test))
-    _, accuracy = model.evaluate(x_train, y_train)
+        #model.fit(x_train, y_train, batch_size=32, epochs = 150, validation_data=(x_test, y_test))
+        #does not output epochs and gives evalutaion of validation data and history of losses and accuracy
+    history = model.fit(reduced_x, reduced_y,validation_split=0.33, batch_size=32, epochs = 10,verbose=0)
+    _, accuracy = model.evaluate(reduced_x, reduced_y)
         #return history.history
     if results=="Accuracy":
         #summarize history for accuracy
@@ -67,7 +71,8 @@ def malware_detection_DL (results, malicious_traffic, benign_traffic):
         plt.ylabel('accuracy')
         plt.xlabel('epoch')
         plt.legend(['train', 'test'], loc='upper left')
-        return plt.show()
+        plt.savefig('accplot.png')
+        return "accplot.png",accuracy
     else:
         # summarize history for loss
         plt.plot(history.history['loss'])
@@ -76,7 +81,8 @@ def malware_detection_DL (results, malicious_traffic, benign_traffic):
         plt.ylabel('loss')
         plt.xlabel('epoch')
         plt.legend(['train', 'test'], loc='upper left')
-        return plt.show()
+        plt.savefig('lossplot.png')
+        return 'lossplot.png',accuracy
     
     
     
@@ -84,9 +90,9 @@ iface = gr.Interface(
     malware_detection_DL, [gr.inputs.Dropdown(["Accuracy","Loss"], label="Result Type"),
                                      gr.inputs.Dropdown(["malicious_flows.csv"], label = "Malicious traffic in .csv"),
                            gr.inputs.Dropdown(["sample_benign_flows.csv"], label="Benign Traffic in .csv")
-                          ], "plot",
+                          ],["image","text"],
     
     
 )
 
-iface.launch(enable_queue =True)
+iface.launch(share=True)