added neural net

app.py

@@ -2,7 +2,8 @@ import gradio as gr
 import pandas as pd
 import joblib
 
-model = joblib.load('decision_tree.pkl')
+treemodel = joblib.load('decision_tree.pkl')
+nnmodel = joblib.load('neural_network.pkl')
 
 def onehot(df, column):
     df = df.copy()
@@ -12,8 +13,7 @@ def onehot(df, column):
     return df
 
 
-def dataframe(file_obj):
-    df = pd.read_csv(file_obj.name)
+def dataframe(df):
     df = onehot(df, column='type')
 
     #if the 'type' column doesn't have value 'CASH_OUT' then add a column 'type_CASH_OUT' with value 0
@@ -33,27 +33,45 @@ def dataframe(file_obj):
         df['type_PAYMENT'] = 0
     
     df = df.drop(['nameOrig','nameDest','isFraud'], axis=1)
-    print(df.shape)
-    y_pred = model.predict(df)
-    
+    return df
+
+def tree(file_obj):
+    df = pd.read_csv(file_obj.name)
+    df = dataframe(df)
+    y_pred = treemodel.predict(df)
     pred_df = pd.DataFrame(y_pred, columns = ['predictedFraud'])
     #append the predictions to the original dataframe
     df_original = pd.read_csv(file_obj.name)
     pred_df = pd.concat([df_original, pred_df], axis=1)
-    print(type(pred_df))
-    print(pred_df.shape)
-#     clr = classification_report(y_test, y_pred, target_names=['Not Fraud','Fraud'])
-#     return 'Classification Report:\n'+ clr
     return pred_df
 
+def nn(file_obj):
+    nn_df = pd.read_csv(file_obj.name)
+    nn_df = dataframe(nn_df)
+    y_prednn = nnmodel.predict(nn_df)
+    pred_dfnn = pd.DataFrame(y_prednn, columns = ['predictedFraud'])
+    #append the predictions to the original dataframe
+    df_originalnn = pd.read_csv(file_obj.name)
+    pred_dfnn = pd.concat([df_originalnn, pred_dfnn], axis=1)
+    return pred_dfnn
+
 file = gr.components.File(file_count="single", type="file", label="Fisierul CSV cu tranzactii", optional=False)
-y_pred_df = gr.components.Dataframe(max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="predictedFraud - Predictii bazate pe modelul de clasificare isFraud - Etichetele reale")
-interface_csv = gr.Interface(
-                            fn=dataframe, 
+tree_output = gr.components.Dataframe(max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="predictedFraud - Predictii bazate pe modelul de clasificare isFraud - Etichetele reale")
+nn_output = gr.components.Dataframe(max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="predictedFraud - Predictii bazate pe modelul de clasificare isFraud - Etichetele reale")
+tree_interface = gr.Interface(
+                            fn=tree, 
+                            inputs=file, 
+                            outputs=tree_output,
+                            title="Fraud Detection - DECISION TREE EXPERT SYSTEM",
+                            description='<h2>Sistem expert bazat pe un model de clasificare pentru detectarea fraudelor in tranzactii bancare.<h2><h3>predictedFraud - Predictii bazate pe modelul de clasificare. isFraud - Etichetele reale<h3>'
+                            )
+
+nn_interface = gr.Interface(
+                            fn=nn, 
                             inputs=file, 
-                            outputs=y_pred_df,
-                            title="Fraud Detection - EXPERT SYSTEM",
-                            description='<h2>Sistem expert bazat pe un model de clasificare pentru detectarea fraudelor in tranzactii bancare.<h2><h3>predictedFraud - Predictii bazate pe modelul de clasificare. isFraud - Etichetele reale<h3><blockquote class="imgur-embed-pub" lang="en" data-id="J1aOKXd"><a href="https://imgur.com/J1aOKXd">View post on imgur.com</a></blockquote>'
+                            outputs=nn_output,
+                            title="Fraud Detection - NEURAL NETWORK EXPERT SYSTEM",
+                            description='<h2>Sistem expert bazat pe un model de clasificare pentru detectarea fraudelor in tranzactii bancare.<h2><h3>predictedFraud - Predictii bazate pe modelul de clasificare. isFraud - Etichetele reale<h3>'
                             )
 
-interface_csv.launch(inline=False)
+gr.Parallel(tree_interface, nn_interface).launch()

neural_network.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3addbf26362e78236b30a97ff690e7c4a21f1f4fe3dfed88f42cf91bd68a5e9e
+size 92390