Create app.py

app.py

@@ -0,0 +1,116 @@
+# app.py
+import tensorflow as tf
+import yfinance as yf
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from datetime import datetime
+from sklearn.preprocessing import MinMaxScaler
+import gradio as gr
+
+# Function to get stock data
+def get_stock_data(ticker, start, end):
+    data = yf.download(ticker, start=start, end=end)
+    return data
+
+# Function to process data and make predictions
+def predict_stock(ticker, start, end):
+    data = get_stock_data(ticker, start, end)
+    
+    # Scale the data
+    scaler = MinMaxScaler(feature_range=(0, 1))
+    scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1, 1))
+    
+    # Preparing data for LSTM model (last 60 days as input)
+    def create_dataset(dataset, time_step=60):
+        X, y = [], []
+        for i in range(time_step, len(dataset)):
+            X.append(dataset[i-time_step:i, 0])
+            y.append(dataset[i, 0])
+        return np.array(X), np.array(y)
+
+    # Split the data
+    train_size = int(len(scaled_data) * 0.8)
+    train_data = scaled_data[0:train_size]
+    test_data = scaled_data[train_size:]
+
+    # Create training and testing datasets
+    X_train, y_train = create_dataset(train_data)
+    X_test, y_test = create_dataset(test_data)
+
+    # Reshape for LSTM input
+    X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
+    X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
+
+    # Build LSTM model
+    model = tf.keras.Sequential([
+        tf.keras.layers.LSTM(50, return_sequences=True, input_shape=(X_train.shape[1], 1)),
+        tf.keras.layers.LSTM(50, return_sequences=False),
+        tf.keras.layers.Dense(25),
+        tf.keras.layers.Dense(1)
+    ])
+    
+    model.compile(optimizer='adam', loss='mean_squared_error')
+    model.fit(X_train, y_train, batch_size=32, epochs=10)
+
+    # Predict on test data
+    predictions = model.predict(X_test)
+    predictions = scaler.inverse_transform(predictions)
+
+    # Calculate buy/sell signal (simple strategy: if predicted > current, buy; else, sell)
+    current_price = data['Close'][-1]
+    predicted_price = predictions[-1][0]
+    buy_sell_signal = "Buy" if predicted_price > current_price else "Sell"
+    
+    # Calculate key statistics
+    percentage_change = (current_price - data['Close'][0]) / data['Close'][0] * 100
+    highest_value = data['High'].max()
+    lowest_value = data['Low'].min()
+
+    return {
+        "prediction": predicted_price,
+        "buy_sell_signal": buy_sell_signal,
+        "percentage_change": percentage_change,
+        "highest_value": highest_value,
+        "lowest_value": lowest_value,
+        "historical_data": data['Close'].to_list(),
+        "predicted_data": predictions.tolist()
+    }
+
+# Gradio interface
+def predict_interface(ticker, start_date, end_date):
+    result = predict_stock(ticker, start_date, end_date)
+    return {
+        "Buy/Sell Signal": result["buy_sell_signal"],
+        "Predicted Value": result["prediction"],
+        "Percentage Change": result["percentage_change"],
+        "Highest Value": result["highest_value"],
+        "Lowest Value": result["lowest_value"],
+        "Historical Chart": gr.Plot(plt.plot(result["historical_data"], label="Historical"), plt.plot(result["predicted_data"], label="Predicted"))
+    }
+
+# Stock tickers for testing
+tickers = ['AAPL', 'MSFT', 'GOOGL', 'AMZN', 'TSLA', 'FB', 'NFLX', 'NVDA', 'BA', 'NKE']
+
+# Create Gradio UI
+interface = gr.Interface(
+    fn=predict_interface,
+    inputs=[
+        gr.Dropdown(tickers, label="Stock Ticker"),
+        gr.Date(label="Start Date"),
+        gr.Date(label="End Date")
+    ],
+    outputs=[
+        gr.Textbox(label="Buy/Sell Signal"),
+        gr.Textbox(label="Predicted Value"),
+        gr.Textbox(label="Percentage Change"),
+        gr.Textbox(label="Highest Value"),
+        gr.Textbox(label="Lowest Value"),
+        gr.Plot(label="Stock Performance")
+    ],
+    title="Stock Prediction App",
+    description="Select stock ticker, start date, and end date to predict stock value and get a buy/sell signal."
+)
+
+if __name__ == "__main__":
+    interface.launch()