\uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc744 \uac1c\ubc1c\ud558\ub294 \ub370 \uc788\uc5b4 \uac00\uc7a5 \uc911\uc694\ud55c \uc694\uc18c \uc911 \ud558\ub098\ub294 \ub370\uc774\ud130 \ubd84\uc11d\uc785\ub2c8\ub2e4. \uc8fc\uac00 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uc5ec \uc801\uc808\ud55c \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc0dd\uc131\ud558\ub824\uba74 \ub2e4\uc591\ud55c \uae30\ubc95\uc774 \ud544\uc694\ud569\ub2c8\ub2e4. \uadf8 \uc911 \uac00\uc7a5 \uae30\ubcf8\uc801\uc774\uace0 \ub110\ub9ac \uc0ac\uc6a9\ub418\ub294 \uae30\ubc95 \uc911 \ud558\ub098\ub294 \uc774\ub3d9\ud3c9\uade0\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 \ud30c\uc774\uc36c\uc758 Pandas \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc8fc\uac00 \uc774\ub3d9\ud3c9\uade0\uc744 \uacc4\uc0b0\ud558\uace0, \uc774\ub97c \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc5d0 \uc801\uc6a9\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
\uc774\ub3d9\ud3c9\uade0(Moving Average)\uc740 \uc77c\uc815 \uae30\uac04 \ub3d9\uc548\uc758 \uc8fc\uac00 \ud3c9\uade0\uc744 \uacc4\uc0b0\ud558\uc5ec \uc8fc\uac00\uc758 \ud750\ub984\uc744 \ubd80\ub4dc\ub7fd\uac8c \ub098\ud0c0\ub0b4\ub294 \uae30\ubc95\uc785\ub2c8\ub2e4. \uc8fc\uac00\uc758 \ubcc0\ub3d9\uc131\uc774 \uc2ec\ud560 \ub54c, \uadf8 \ucd94\uc138\ub97c \uc2dd\ubcc4\ud558\ub294 \ub370 \uc720\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n
\uc8fc\ub85c SMA\uc640 EMA\ub97c \uc0ac\uc6a9\ud558\uc5ec \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc0dd\uc131\ud569\ub2c8\ub2e4. \uc774\ubc88 \uac15\uc88c\uc5d0\uc11c\ub294 SMA\ub97c \uc911\uc2ec\uc73c\ub85c \ub2e4\ub8e8\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
\uba3c\uc800, \ud30c\uc774\uc36c\uacfc Pandas\ub97c \uc124\uce58\ud574\uc57c \ud569\ub2c8\ub2e4. Anaconda\ub97c \uc0ac\uc6a9\ud558\uba74 \ud3b8\ub9ac\ud558\uac8c \uc124\uce58\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc124\uce58\uac00 \uc644\ub8cc\ub418\uba74, \ub2e4\uc74c\uacfc \uac19\uc740 \uae30\ubcf8 \uc124\uc815\uc744 \ud569\ub2c8\ub2e4:<\/p>\n
pip install pandas matplotlib yfinance<\/code><\/pre>\n3. \uc8fc\uac00 \ub370\uc774\ud130 \uac00\uc838\uc624\uae30<\/h2>\n
\uc5ec\uae30\uc11c\ub294 Yahoo Finance API\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc8fc\uac00 \ub370\uc774\ud130\ub97c \uac00\uc838\uc635\ub2c8\ub2e4. \uc774\ub97c \uc704\ud574 yfinance \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
\nimport yfinance as yf\n\n# \uc560\ud50c \uc8fc\uac00 \ub370\uc774\ud130 \uac00\uc838\uc624\uae30 (\uc608: 2020\ub144 1\uc6d4 1\uc77c\ubd80\ud130 \ucd5c\uadfc\uae4c\uc9c0)\ndata = yf.download('AAPL', start='2020-01-01', end='2023-12-31')\nprint(data.head())\n <\/code><\/pre>\n4. \uc774\ub3d9\ud3c9\uade0 \uacc4\uc0b0\ud558\uae30<\/h2>\n
\uc774\uc81c \uc8fc\uac00 \ub370\uc774\ud130\uac00 \uc900\ube44\ub418\uc5c8\uc73c\ub2c8, \uc774\ub3d9\ud3c9\uade0\uc744 \uacc4\uc0b0\ud574\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. Pandas\ub294 \uc774\ub3d9\ud3c9\uade0 \uacc4\uc0b0\uc744 \uc704\ud55c \uac04\ub2e8\ud55c \uba54\uc11c\ub4dc\ub97c \uc81c\uacf5\ud569\ub2c8\ub2e4.<\/p>\n
\nimport pandas as pd\n\n# 20\uc77c \uc774\ub3d9\ud3c9\uade0 \uacc4\uc0b0\ndata['SMA_20'] = data['Close'].rolling(window=20).mean()\n# 50\uc77c \uc774\ub3d9\ud3c9\uade0 \uacc4\uc0b0\ndata['SMA_50'] = data['Close'].rolling(window=50).mean()\n\nprint(data[['Close', 'SMA_20', 'SMA_50']].tail())\n <\/code><\/pre>\n5. \uc774\ub3d9\ud3c9\uade0 \ucc28\ud2b8 \uadf8\ub9ac\uae30<\/h2>\n
\uc774\uc81c matplotlib \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc774\ub3d9\ud3c9\uade0 \ucc28\ud2b8\ub97c \uadf8\ub824\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \uc8fc\uac00\uc640 \uc774\ub3d9\ud3c9\uade0\uc758 \uad00\uacc4\ub97c \uc2dc\uac01\uc801\uc73c\ub85c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
\nimport matplotlib.pyplot as plt\n\nplt.figure(figsize=(14,7))\nplt.plot(data['Close'], label='AAPL Close Price', color='blue', alpha=0.5)\nplt.plot(data['SMA_20'], label='20-Day SMA', color='orange', alpha=0.75)\nplt.plot(data['SMA_50'], label='50-Day SMA', color='green', alpha=0.75)\nplt.title('Apple Stock Price and Moving Averages')\nplt.xlabel('Date')\nplt.ylabel('Price (USD)')\nplt.legend()\nplt.show()\n <\/code><\/pre>\n6. \ub9e4\ub9e4 \uc2e0\ud638 \uc0dd\uc131\ud558\uae30<\/h2>\n
\uc774\ub3d9\ud3c9\uade0\uc744 \uc774\uc6a9\ud55c \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc0dd\uc131\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc77c\ubc18\uc801\uc73c\ub85c \ub2e8\uae30 \uc774\ub3d9\ud3c9\uade0\uc774 \uc7a5\uae30 \uc774\ub3d9\ud3c9\uade0\uc744 \uc0c1\ud5a5 \ub3cc\ud30c\ud560 \ub54c \ub9e4\uc218 \uc2e0\ud638\ub85c, \ud558\ud5a5 \ub3cc\ud30c\ud560 \ub54c \ub9e4\ub3c4 \uc2e0\ud638\ub85c \uc124\uc815\ud569\ub2c8\ub2e4.<\/p>\n
\ndata['Signal'] = 0.0 # \ucd08\uae30 \uc2e0\ud638\ub97c 0\uc73c\ub85c \uc124\uc815\n\n# \ub9e4\uc218 \uc2e0\ud638\ndata['Signal'][20:] = np.where(data['SMA_20'][20:] > data['SMA_50'][20:], 1.0, 0.0) \n# \ub9e4\ub3c4 \uc2e0\ud638\ndata['Position'] = data['Signal'].diff() # \ud3ec\uc9c0\uc158 \ubcc0\ud654 \ud655\uc778\n\nplt.figure(figsize=(14,7))\nplt.plot(data['Close'], label='Close Price', color='blue', alpha=0.5)\nplt.plot(data['SMA_20'], label='20-Day SMA', color='orange', alpha=0.75)\nplt.plot(data['SMA_50'], label='50-Day SMA', color='green', alpha=0.75)\n\n# \ub9e4\uc218 \uc2e0\ud638 \ud45c\uc2dc\nplt.plot(data[data['Position'] == 1].index, \n data['SMA_20'][data['Position'] == 1],\n '^', markersize=10, color='g', lw=0, label='Buy Signal')\n\n# \ub9e4\ub3c4 \uc2e0\ud638 \ud45c\uc2dc\nplt.plot(data[data['Position'] == -1].index, \n data['SMA_20'][data['Position'] == -1],\n 'v', markersize=10, color='r', lw=0, label='Sell Signal')\n\nplt.title('Buy & Sell Signals')\nplt.xlabel('Date')\nplt.ylabel('Price (USD)')\nplt.legend()\nplt.show()\n <\/code><\/pre>\n7. \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c \uad6c\ud604\ud558\uae30<\/h2>\n
\uc774\uc81c \uac04\ub2e8\ud55c \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc744 \uad6c\ud604\ud574\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \ub9e4\uc218 \ubc0f \ub9e4\ub3c4 \uc2e0\ud638\uac00 \ubc1c\uc0dd\ud560 \ub54c, \ub9e4\uc218\ub97c \ud560\uc9c0 \ub9e4\ub3c4\ud560\uc9c0\ub97c \uacb0\uc815\ud558\ub294 \ub85c\uc9c1\uc744 \ucd94\uac00\ud569\ub2c8\ub2e4. \uc774 \uc608\uc81c\uc5d0\uc11c\ub294 \uac00\uc0c1\uc758 \uc790\uae08 10,000\ub2ec\ub7ec\ub97c \uc0ac\uc6a9\ud558\uc5ec \ub9e4\ub9e4\ub97c \uc218\ud589\ud55c\ub2e4\uace0 \uac00\uc815\ud569\ub2c8\ub2e4.<\/p>\n
\ninitial_capital = 10000\nshares = 0\ncash = initial_capital\n\nfor i in range(len(data)):\n if data['Position'][i] == 1: # \ub9e4\uc218 \uc2e0\ud638\n shares = cash \/\/ data['Close'][i] # \uad6c\ub9e4\ud560 \uc8fc\uc2dd \uc218 \uacc4\uc0b0\n cash -= shares * data['Close'][i] # \uc790\uc0b0\uc5d0\uc11c \uc8fc\uc2dd \uad6c\ub9e4 \ube44\uc6a9 \ucc28\uac10\n elif data['Position'][i] == -1: # \ub9e4\ub3c4 \uc2e0\ud638\n cash += shares * data['Close'][i] # \uc790\uc0b0\uc5d0 \uc8fc\uc2dd \ud310\ub9e4 \uc218\uc775 \ucd94\uac00\n shares = 0 # \ubaa8\ub4e0 \uc8fc\uc2dd \ub9e4\ub3c4\n \nfinal_value = cash + shares * data['Close'].iloc[-1] # \ucd5c\uc885 \uc790\uc0b0 \uacc4\uc0b0\nprint(f'Initial Capital: ${initial_capital} -> Final Value: ${final_value}')\n <\/code><\/pre>\n8. \uc131\uacfc \ubd84\uc11d<\/h2>\n
\uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc758 \uc131\uacfc\ub97c \ubd84\uc11d\ud558\uae30 \uc704\ud574, \ucd5c\uc885 \uc218\uc775\ub960\uacfc \uc2b9\ub960\uc744 \uacc4\uc0b0\ud574\ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc544\ub798 \ucf54\ub4dc\ub294 \uc774 \uc2dc\uc2a4\ud15c\uc744 \ud1b5\ud55c \uc131\uacfc\ub97c \ud3c9\uac00\ud558\ub294 \uac04\ub2e8\ud55c \ubc29\ubc95\uc785\ub2c8\ub2e4.<\/p>\n
\ntrades = data['Position'].diff() # \ub9e4\ub9e4 \uc2e0\ud638 \ud655\uc778\nsuccessful_trades = trades[trades == 1].count() # \ub9e4\ub3c4 \uc2e0\ud638 \uce74\uc6b4\ud2b8\nwin_trades = trades[trades == -1].count() # \ub9e4\uc218 \uc2e0\ud638 \uce74\uc6b4\ud2b8\nwin_ratio = (successful_trades \/ (successful_trades + win_trades)) * 100\n\nprint(f'Total Trades: {successful_trades + win_trades}, Winning Trades: {successful_trades}, Win Ratio: {win_ratio}%')\n <\/code><\/pre>\n9. \uacb0\ub860<\/h2>\n
\uc774\ubc88 \uac15\uc88c\uc5d0\uc11c\ub294 \ud30c\uc774\uc36c\uc758 Pandas \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc8fc\uac00 \uc774\ub3d9\ud3c9\uade0\uc744 \uacc4\uc0b0\ud558\uace0, \uc774\ub97c \uae30\ubc18\uc73c\ub85c \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc0dd\uc131\ud558\uace0 \uac04\ub2e8\ud55c \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc744 \uad6c\ud604\ud574 \ubcf4\uc558\uc2b5\ub2c8\ub2e4. \uc774\ub3d9\ud3c9\uade0\uc740 \uae30\ubcf8\uc801\uc778 \uae30\ubc95\uc774\uc9c0\ub9cc, \uc774\ub97c \uc801\uc808\ud788 \ud65c\uc6a9\ud558\uc5ec \ub354 \ubcf5\uc7a1\ud55c \uc790\ub3d9\ub9e4\ub9e4 \uc804\ub7b5\uc73c\ub85c \ubc1c\uc804\uc2dc\ud0ac \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ud5a5\ud6c4\uc5d0\ub294 \uc9c0\uc218 \uc774\ub3d9\ud3c9\uade0(EMA)\uc774\ub098 \ub2e4\ub978 \uae30\uc220\uc801 \uc9c0\ud45c\ub97c \ud65c\uc6a9\ud55c \uc804\ub7b5\ub3c4 \uace0\ub824\ud574\ubcf4\uba74 \uc88b\uc2b5\ub2c8\ub2e4. \uadf8\ub7fc \uc5ec\ub7ec\ubd84\uc758 \uc131\uacf5\uc801\uc778 \uc790\ub3d9\ub9e4\ub9e4\ub97c \uae30\uc6d0\ud569\ub2c8\ub2e4!<\/p>\n
10. \ucc38\uace0 \uc790\ub8cc<\/h2>\n