├── 01_ma_crossover.py
└── data
    └── price_aapl.pkl


/01_ma_crossover.py:
--------------------------------------------------------------------------------
 1 | # QUANT SCIENCE UNIVERSITY
 2 | # Goal: Get you started making progress with algorithmic trading
 3 | # Pro-Tip: Visualize the Moving Average Crossover Strategy (At the End)
 4 | # ****
 5 | 
 6 | # Libraries
 7 | import vectorbt as vbt
 8 | import pandas as pd
 9 | import numpy as np
10 | 
11 | # Read data
12 | price_aapl = pd.read_pickle("data/price_aapl.pkl")
13 | price_aapl
14 | 
15 | # Profit Level: Buy and Hold Strategy
16 | pf_buy_hold = vbt.Portfolio.from_holding(
17 |     close=price_aapl, 
18 |     init_cash=10_000
19 | )
20 | pf_buy_hold.total_profit()
21 | 
22 | 
23 | # 1.0 Simple Moving Average Crossover Strategy 5-20 Day (AAPL)
24 | 
25 | # 1. Define the strategy
26 | fast_ma = vbt.MA.run(price_aapl, window=5)
27 | slow_ma = vbt.MA.run(price_aapl, window=20)
28 | 
29 | entries = fast_ma.ma_crossed_above(slow_ma)
30 | exits = fast_ma.ma_crossed_below(slow_ma)
31 | 
32 | # 2. Run the strategy
33 | pf_ma_strat = vbt.Portfolio.from_signals(
34 |     close = price_aapl, 
35 |     entries=entries, 
36 |     exits=exits, 
37 |     init_cash=10_000,
38 |     fees=0.001,
39 | )
40 | 
41 | pf_ma_strat.total_profit()
42 | 
43 | pf_ma_strat.stats()
44 | 
45 | pf_ma_strat.plot().show()
46 | 
47 | # 2.0 Backtesting 100 windows for the Moving Average Crossover Strategy (AAPL) 
48 | 
49 | windows = np.arange(2, 101)
50 | fast_ma, slow_ma = vbt.MA.run_combs(
51 |     close = price_aapl, 
52 |     window=windows, 
53 |     r=2, 
54 |     short_names=['fast', 'slow']
55 | )
56 | entries = fast_ma.ma_crossed_above(slow_ma)
57 | exits = fast_ma.ma_crossed_below(slow_ma)
58 | 
59 | pf_100_ma_strats = vbt.Portfolio.from_signals(
60 |     close = price_aapl, 
61 |     entries = entries, 
62 |     exits = exits, 
63 |     size=np.inf, 
64 |     fees=0.001, 
65 |     freq='1D',
66 |     init_cash=10_000
67 | )
68 | 
69 | pf_100_ma_strats.total_profit().max()
70 | pf_100_ma_strats.total_profit().idxmax()
71 | 
72 | best_index = pf_100_ma_strats.total_profit().idxmax()
73 | 
74 | stats = pf_100_ma_strats[best_index].stats()
75 | stats
76 | 
77 | pf_100_ma_strats[best_index].plot().show()
78 | 
79 | # Conclusions ----
80 | # You can do this!
81 | # There's a lot more to learn:
82 | # - More Trading Strategies
83 | # - Risk Management
84 | # - Portfolio Optimization
85 | # - Machine Learning
86 | # - Advanced Backtesting
87 | # - Live Trading & Execution
88 | 


--------------------------------------------------------------------------------
/data/price_aapl.pkl:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/quant-science/vectorbt_backtesting/04a42bc3d75212acc1a0f9fba02b5d3035e89356/data/price_aapl.pkl


--------------------------------------------------------------------------------