Update app.py

app.py

@@ -2,21 +2,18 @@ import streamlit as st
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
-from tensorflow.keras.models import Sequential
-from tensorflow.keras.layers import Dense, LSTM
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.metrics import mean_squared_error
-import tensorflow as tf
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
 import io
 
-# 函數定義
-def create_dataset(dataset, look_back=1):
-    dataX, dataY = [], []
-    for i in range(len(dataset)-look_back-1):
-        a = dataset[i:(i+look_back), 0]
-        dataX.append(a)
-        dataY.append(dataset[i + look_back, 0])
-    return np.array(dataX), np.array(dataY)
+def create_features(data, look_back=1):
+    X, y = [], []
+    for i in range(len(data) - look_back):
+        X.append(data[i:(i + look_back)])
+        y.append(data[i + look_back])
+    return np.array(X), np.array(y)
 
 def train_and_predict(file):
     # 載入和預處理數據
@@ -27,50 +24,42 @@ def train_and_predict(file):
     scaler = MinMaxScaler(feature_range=(0, 1))
     dataset = scaler.fit_transform(dataset)
     
-    # 分割訓練集和測試集
-    train_size = int(len(dataset) * 0.67)
-    test_size = len(dataset) - train_size
-    train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
+    # 創建特徵和目標
+    look_back = 3
+    X, y = create_features(dataset, look_back)
     
-    # 重塑為 X=t 和 Y=t+1
-    look_back = 1
-    trainX, trainY = create_dataset(train, look_back)
-    testX, testY = create_dataset(test, look_back)
-    trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
-    testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
+    # 分割訓練集和測試集
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
     
-    # 創建和訓練 LSTM 網絡
-    model = Sequential()
-    model.add(LSTM(4, input_shape=(1, look_back)))
-    model.add(Dense(1))
-    model.compile(loss='mean_squared_error', optimizer='adam')
-    model.fit(trainX, trainY, epochs=50, batch_size=1, verbose=0)
+    # 創建和訓練模型
+    model = LinearRegression()
+    model.fit(X_train, y_train)
     
     # 進行預測
-    trainPredict = model.predict(trainX)
-    testPredict = model.predict(testX)
+    train_predict = model.predict(X_train)
+    test_predict = model.predict(X_test)
     
     # 反轉預測
-    trainPredict = scaler.inverse_transform(trainPredict)
-    trainY = scaler.inverse_transform([trainY])
-    testPredict = scaler.inverse_transform(testPredict)
-    testY = scaler.inverse_transform([testY])
+    train_predict = scaler.inverse_transform(train_predict.reshape(-1, 1))
+    y_train = scaler.inverse_transform(y_train.reshape(-1, 1))
+    test_predict = scaler.inverse_transform(test_predict.reshape(-1, 1))
+    y_test = scaler.inverse_transform(y_test.reshape(-1, 1))
     
     # 計算 RMSE
-    trainScore = np.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
-    testScore = np.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
+    train_score = np.sqrt(mean_squared_error(y_train, train_predict))
+    test_score = np.sqrt(mean_squared_error(y_test, test_predict))
     
     # 準備繪圖數據
-    trainPredictPlot = np.empty_like(dataset)
-    trainPredictPlot[:, :] = np.nan
-    trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
-    testPredictPlot = np.empty_like(dataset)
-    testPredictPlot[:, :] = np.nan
-    testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict
+    train_predict_plot = np.empty_like(dataset)
+    train_predict_plot[:, :] = np.nan
+    train_predict_plot[look_back:len(train_predict)+look_back, :] = train_predict
+    test_predict_plot = np.empty_like(dataset)
+    test_predict_plot[:, :] = np.nan
+    test_predict_plot[len(train_predict)+(look_back*2)+1:len(dataset)-1, :] = test_predict
     
-    return scaler.inverse_transform(dataset), trainPredictPlot, testPredictPlot, trainScore, testScore
+    return scaler.inverse_transform(dataset), train_predict_plot, test_predict_plot, train_score, test_score
 
-st.title("LSTM Stock Price Prediction")
+st.title("Stock Price Prediction")
 
 uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
 
@@ -104,11 +93,11 @@ else:
     st.info("Please upload a CSV file to start the prediction.")
 
 st.markdown("""
-This application uses an LSTM (Long Short-Term Memory) neural network to predict stock prices based on historical data.
+This application uses a simple linear regression model to predict stock prices based on historical data.
 
 To use:
 1. Upload a CSV file containing historical stock price data.
-2. The app will train an LSTM model on this data and make predictions.
+2. The app will train a model on this data and make predictions.
 3. You'll see a graph showing the original data and predictions, along with RMSE scores for training and test sets.
 
 Note: The CSV file should have the stock prices in the second column.