Update app.py

app.py

@@ -6,22 +6,19 @@ import gradio as gr
 import matplotlib.pyplot as plt
 from sklearn.preprocessing import MinMaxScaler
 
-# Function to get stock data
+# Function to fetch stock data from Yahoo Finance
 def fetch_stock_data(ticker, start_date, end_date):
     stock_data = yf.download(ticker, start=start_date, end=end_date)
+    if stock_data.empty:
+        return None
     return stock_data
 
-# Prepare the dataset for LSTM
+# Function to prepare the data for LSTM
 def prepare_data(data):
-    # Scaling data
     scaler = MinMaxScaler(feature_range=(0, 1))
-    scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1,1))
+    scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1, 1))
 
-    # Create training and testing sets (80% train, 20% test)
-    train_size = int(len(scaled_data) * 0.8)
-    train_data, test_data = scaled_data[:train_size], scaled_data[train_size:]
-
-    # Create sequences for LSTM (last 60 days used to predict the next one)
+    # Create sequences for LSTM
     def create_sequences(data, time_step=60):
         X, y = [], []
         for i in range(len(data) - time_step - 1):
@@ -29,12 +26,16 @@ def prepare_data(data):
             y.append(data[i + time_step])
         return np.array(X), np.array(y)
 
+    # Train-test split (80% train, 20% test)
+    train_size = int(len(scaled_data) * 0.8)
+    train_data, test_data = scaled_data[:train_size], scaled_data[train_size:]
+
     X_train, y_train = create_sequences(train_data)
     X_test, y_test = create_sequences(test_data)
 
     return X_train, y_train, X_test, y_test, scaler
 
-# Building the LSTM model
+# Function to build LSTM model
 def build_lstm_model(input_shape):
     model = tf.keras.Sequential([
         tf.keras.layers.LSTM(50, return_sequences=True, input_shape=(input_shape[1], 1)),
@@ -42,22 +43,21 @@ def build_lstm_model(input_shape):
         tf.keras.layers.Dense(25),
         tf.keras.layers.Dense(1)
     ])
-
     model.compile(optimizer='adam', loss='mean_squared_error')
     return model
 
-# Training the model
+# Function to train the LSTM model
 def train_model(X_train, y_train):
     model = build_lstm_model(X_train.shape)
     model.fit(X_train, y_train, batch_size=1, epochs=1)
     return model
 
-# Make predictions
+# Function to make predictions using the trained model
 def make_predictions(model, X_test, scaler):
     predictions = model.predict(X_test)
     return scaler.inverse_transform(predictions)
 
-# Calculate metrics for buy/sell decisions
+# Function to calculate the metrics (percentage change, highest, lowest, buy/sell)
 def calculate_metrics(data, predictions):
     start_value = data['Close'][0]
     end_value = predictions[-1][0]
@@ -70,61 +70,68 @@ def calculate_metrics(data, predictions):
 
     return percentage_change, highest_value, lowest_value, decision
 
-# Plot historical vs predicted
+# Function to plot the graph of historical vs predicted data
 def plot_graph(data, predictions, ticker):
-    plt.figure(figsize=(12,6))
-    plt.plot(data.index, data['Close'], label="Historical")
-    plt.plot(data.index[len(data) - len(predictions):], predictions, label="Predicted")
+    plt.figure(figsize=(12, 6))
+    plt.plot(data.index, data['Close'], label="Historical Prices", color='blue')
+    plt.plot(data.index[len(data) - len(predictions):], predictions, label="Predicted Prices", color='red')
     plt.title(f'{ticker} Stock Price Prediction')
     plt.xlabel('Date')
-    plt.ylabel('Price')
+    plt.ylabel('Price (USD)')
     plt.legend()
     plt.grid(True)
     plt.show()
 
-# Gradio app function
+# Gradio interface function
 def stock_predictor(ticker, start_date, end_date):
     stock_data = fetch_stock_data(ticker, start_date, end_date)
-    
-    if len(stock_data) == 0:
+
+    if stock_data is None or len(stock_data) == 0:
         return "Error: No data found. Please select a valid date range."
-    
+
+    # Prepare data for LSTM
     X_train, y_train, X_test, y_test, scaler = prepare_data(stock_data)
-    
+
+    # Train the model
     model = train_model(X_train, y_train)
-    
+
+    # Make predictions
     predictions = make_predictions(model, X_test, scaler)
-    
+
+    # Calculate buy/sell decision and metrics
     percentage_change, highest_value, lowest_value, decision = calculate_metrics(stock_data, predictions)
-    
+
+    # Plot the historical vs predicted data
     plot_graph(stock_data, predictions, ticker)
-    
+
+    # Return the calculated metrics
     return {
-        "Percentage Change": percentage_change,
-        "Highest Value": highest_value,
-        "Lowest Value": lowest_value,
+        "Percentage Change": f"{percentage_change:.2f}%",
+        "Highest Value": f"${highest_value:.2f}",
+        "Lowest Value": f"${lowest_value:.2f}",
         "Prediction (Buy/Sell)": decision
     }
 
-# Define stock tickers for dropdown
+# List of stock tickers for the dropdown
 tickers = ['AAPL', 'GOOGL', 'AMZN', 'MSFT', 'TSLA', 'NFLX', 'NVDA', 'META', 'BABA', 'INTC']
 
-# Gradio interface
+# Gradio interface design
 gr_interface = gr.Interface(
     fn=stock_predictor,
     inputs=[
         gr.Dropdown(choices=tickers, label="Select Stock Ticker"),
-        gr.Date(label="Start Date"),
-        gr.Date(label="End Date")
+        gr.inputs.Date(label="Start Date"),
+        gr.inputs.Date(label="End Date")
     ],
     outputs=[
         gr.Label(label="Percentage Change"),
         gr.Label(label="Highest Value"),
         gr.Label(label="Lowest Value"),
         gr.Label(label="Prediction (Buy/Sell)"),
-        gr.Plot(label="Stock Performance")
     ],
-    title="Stock Prediction App"
+    title="Stock Prediction App",
+    description="This app predicts stock prices and helps users decide whether to buy or sell."
 )
 
+# Launch the Gradio interface
 gr_interface.launch()