Update prediction.py

prediction.py

@@ -5,17 +5,31 @@ import pickle
 def run():
 # Load All Files
 
-    with open('pipeline_model.pkl', 'rb') as file:
-        full_process = pickle.load(file)
-
-    file_path = "/Users/ryantrisnadi/Desktop/first_project1/p1-ftds017-hck-g5-ryantrisnadi/_P1G5_Set_1_Ryan_Trisnadi.csv"
+    file_path = "https://drive.google.com/file/d/1iAlO-jScEJBa4_RaNGR7G_-xaUKKECGz/view?usp=sharing"
     df_original = pd.read_csv(file_path)
 
-    index_columns = ['limit_balance', 'sex', 'education_level', 'marital_status', 'age',
-                 'pay_0', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6', 'bill_amt_1',
-                 'bill_amt_2', 'bill_amt_3', 'bill_amt_4', 'bill_amt_5', 'bill_amt_6',
-                 'pay_amt_1', 'pay_amt_2', 'pay_amt_3', 'pay_amt_4', 'pay_amt_5',
-                 'pay_amt_6', 'default_payment_next_month'] 
+    index_columns = [    
+    "The film was good and had a great story.",
+    "This movie is like nothing I've seen before.",
+    "One of the best films I've seen in a long time.",
+    "Would definitely recommend this great movie.",
+    "The story in this film is captivating.",
+    "I would see this movie again.",
+    "A good time watching this film.",
+    "Great performances make this movie memorable.",
+    "The film's plot was like no other.",
+    "Time well spent watching this great film.",
+    "This movie was really bad.",
+    "I wouldn't watch this film again.",
+    "Even though it's a film, I didn't like it.",
+    "The movie was one of the worst I've seen.",
+    "Bad acting ruined the film for me.",
+    "I really disliked this movie.",
+    "Would not recommend this film to anyone.",
+    "The plot was confusing and not good.",
+    "Even though I like movies, this one was terrible.",
+    "Not a good use of time watching this movie."
+    ] 
     df_data_dummy = df_original[index_columns].copy()
     
     st.write('In the following is the result of the data you have input : ')
@@ -33,11 +47,11 @@ def run():
         st.write('Client kemungkinan gagal bayar utang')
         st.metric(label="Here is a prediction: ", value = y_pred_inf[0])
 
-    # If your data is a classification, you can follow the example below 
-        # if y_pred_inf[0] == 0:
-        #     st.write('Pasien tidak terkena jantung')
-        #     st.markdown("[Cara Cegah Serangan Jantung](https://www.siloamhospitals.com/informasi-siloam/artikel/cara-cegah-serangan-jantung-di-usia-muda)")
+        # Make predictions of IMDB dataset
+        predictions = loaded_lstm.predict(new_texts)
+        print('Predictions: ', predictions)
 
-        # else:
-        #     st.write('Pasien kemungkinan terkena jantung')
-        #     st.markdown("[Cara Hidup Sehat Sehabis Terkena Serangan Jantung](https://lifestyle.kompas.com/read/2021/11/09/101744620/7-pola-hidup-sehat-setelah-mengalami-serangan-jantung?page=all)")
+        # Apply threshold for binary classification
+        threshold = 0.5
+        predicted_classes = (predictions > threshold).astype(int)
+        print('Predicted Classes: ', predicted_classes)