Automated Entry & Exit Signals w/ Python

I created a Python script that pulls realtime market pricing data from AlphaVantage and uses specific entry and exit position signals off of my custom superposition bands indicator I’ve created.
import pandas as pd
from alpha_vantage.timeseries import TimeSeries
import matplotlib.pyplot as plt
import numpy as np
import datetime

api_key = [enter_your_api_key]

def get_stock_data(symbol, interval='5min', size='compact'):
    ts = TimeSeries(key=api_key, output_format='pandas')
    data, meta_data = ts.get_intraday(symbol=symbol, interval=interval, outputsize=size)
    df = data.rename(columns=lambda x: x.split(' ')[-1])  # Remove space in column names
    df.index = pd.to_datetime(df.index)
    return df

def calculate_superposition_bands(df, length=20, multiplier=1.5):
    df['Middle_Band'] = df['close'].rolling(window=length).mean()
    df['ATR'] = df['high'] - df['low']
    df['Upper_Band'] = df['Middle_Band'] + multiplier * df['ATR']
    df['Lower_Band'] = df['Middle_Band'] - multiplier * df['ATR']
    return df

def generate_signals(df, atr_multiplier=0.5):
    df['ATR'] = df['high'] - df['low']
    df['Buy_Signal'] = ((df['close'] > df['Lower_Band']) & (df['close'].shift(1) <= df['Lower_Band'].shift(1))).astype(int)
    df['Sell_Signal'] = ((df['close'] > df['Middle_Band']) & (df['close'].shift(1) <= df['Middle_Band'].shift(1))
                        & (df['close'] >= df['close'].shift(1) + atr_multiplier * df['ATR'].shift(1))).astype(int)
    return df

def plot_superposition_bands(df, symbol, threshold=10, rolling_window=5):
    df_smoothed = df.copy()
    df_smoothed['close'] = df['close'].rolling(window=rolling_window).mean()

    plt.figure(figsize=(12, 6))
    plt.plot(df_smoothed.index, df_smoothed['close'], label='Close Price (Smoothed)', color='black')
    plt.plot(df.index, df['Middle_Band'], label='Middle Band', color='blue')
    plt.plot(df.index, df['Upper_Band'], label='Upper Band', color='red', linestyle='--')
    plt.plot(df.index, df['Lower_Band'], label='Lower Band', color='green', linestyle='--')
    plt.scatter(df[df['Buy_Signal'] == 1].index, df[df['Buy_Signal'] == 1]['close'], label='Buy Signal', marker='^', color='green')
    plt.scatter(df[df['Sell_Signal'] == 1].index, df[df['Sell_Signal'] == 1]['close'], label='Sell Signal', marker='v', color='red')
    plt.title(f'Superposition Bands Analysis for {symbol}')
    plt.xlabel('Date (MST)')
    plt.ylabel('Price')
    plt.legend()

    # Set y-axis range with a threshold to exclude extreme values
    plt.ylim([df_smoothed['close'].min() - threshold, df_smoothed['close'].max() + threshold])

    # Display relevant trading hours on x-axis
    trading_hours = pd.date_range('09:30', '16:00', freq='30min')
    plt.xticks(trading_hours, trading_hours.strftime('%H:%M'))

    plt.show()

def monitor_stock(symbol):
    df = get_stock_data(symbol)
    df = calculate_superposition_bands(df)
    df = generate_signals(df)
    plot_superposition_bands(df, symbol)

# Example: Monitor the stock with the symbol 'TSLA'
monitor_stock('TSLA')