Update app.py

app.py

@@ -45,3 +45,47 @@ st.pyplot(fig)
 data_training = pd.DataFrame(df["Close"][0:int(len(df)*0.70)])
 data_testing = pd.DataFrame(df["Close"][int(len(df)*0.70):int(len(df))])
 
+#Scaling
+scaler = MinMaxScaler(feature_range=(0,1))
+data_training_arr = scaler.fit_transform(data_training)
+
+#Split data in x_train and y_train
+x_train = []
+y_train = []
+for i in range(100, data_training_arr.shape[0]):
+    x_train.append(data_training_arr[i-100: i])
+    y_train.append(data_training_arr[i, 0])
+x_train, y_train = np.array(x_train), np.array(y_train)
+
+#Load the model
+model = load_model("keras_model.h5")
+
+past_100_days = data_training.tail(100)
+final_test_df = past_100_days._append(data_testing, ignore_index=True)
+input_data = scaler.fit_transform(final_test_df)
+
+#Split data in x_test and y_test
+x_test = []
+y_test = []
+
+for i in range(100, input_data.shape[0]):
+    x_test.append(input_data[i-100: i])
+    y_test.append(input_data[i, 0])
+    
+x_test, y_test = np.array(x_test), np.array(y_test)
+
+y_predicted = model.predict(x_test)
+
+sc = scaler.scale_
+scale_factor = 1/sc[0]
+
+y_predicted = y_predicted * scale_factor
+y_test = y_test * scale_factor
+
+plt.figure(figsize=(12,6))
+plt.plot(y_test, 'blue', label="Original Stock Price")
+plt.plot(y_predicted, 'red', label="Predicted Stock Price")
+plt.xlabel('Time')
+plt.ylabel('Price')
+plt.legend()
+plt.show()