我就不用AI、ML模型预测股价，来点不一样的！

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import datetime
from scipy import stats
pd.options.mode.chained_assignment = None  # default='warn'

def load_db(file):
    fix_price = lambda x: float(str(x).replace(',',''))
    df = pd.read_csv(file)
    # clean data
    if 'Price' in df.columns:
        df.rename(columns={"Price":"Close"}, inplace=True)
    cols = []
    if 'Change %' in df.columns:
        cols.append('Change %')
    if 'Vol.' in df.columns:
        cols.append('Vol.')
    df.drop(cols, axis=1, inplace=True)
    try:
        df['Date'] = pd.to_datetime(df['Date'], format="%b %d, %Y")
    except:
        df['Date'] = pd.to_datetime(df['Date'])
    df['Open'] = df['Open'].apply(fix_price)
    df['High'] = df['High'].apply(fix_price)
    df['Low'] = df['Low'].apply(fix_price)
    df['Close'] = df['Close'].apply(fix_price)
    # This is the tricky part!!!
    # Calculate how far did price go from Open for each day!
    df['MaxHigh'] = df['High']/df['Open']
    df['MaxLow'] = df['Low']/df['Open']
    df['MaxClose'] = df['Close']/df['Open']
    # I will use prices beginning 2014
    return df[df['Date']>='2014-01-01']

sym = "GBP_USD"
period = "1d"
file = "./{} {}.csv".format(period, sym)
db = load_db(file).reset_index(drop=True)
db.tail()

def show_min_max(df):
    # find max and min values for High
    max_high = (df['MaxHigh'].max()-1)*100
    min_high = (df['MaxHigh'].min()-1)*100

    # find max and min values for Low
    max_low = (df['MaxLow'].max()-1)*100
    min_low = (df['MaxLow'].min()-1)*100

    # find max and min values for Close
    max_close = (df['MaxClose'].max()-1)*100
    min_close = (df['MaxClose'].min()-1)*100

    print("OpenToHigh\nMax: {:.2f}%\nMin: {:.2f}%\n".format(max_high, min_high))
    print("OpenToLow\nMax: {:.2f}%\nMin: {:.2f}%\n".format(max_low, min_low))
    print("OpenToClose\nMax: {:.2f}%\nMin: {:.2f}%\n".format(max_close, min_close))

show_min_max(db)

OpenToHigh
Max: 3.08%
Min: -0.05%

OpenToLow
Max: 0.00%
Min: -11.07%

OpenToClose
Max: 3.06%
Min: -8.02%

def prob(df, col, p):
    # I'm using percentile here
    lp = np.percentile(df[col].dropna(), p)
    fig, ax = plt.subplots(figsize=(20,10))
    plt.plot_date(df['Date'], df[col], ls='-', fmt='')
    ax.xaxis.set_tick_params(rotation=30, labelsize=10)
    ax.axhline(lp, color='r')
    return lp

prb = 95
col = 'MaxHigh' # Let's find prb% of High (100-prb)
days = 100 # This is the testing size. So we will test last 100 days and exclude them from the calculation.
p = prob(df[:-days], col, 100-prb)

# get the current bar's open price
open_price = df['Open'].iloc[-1]
prediction = open_price * p
ticks = abs(open_price-(p*open_price))
monthly = 22 * ticks # 22 trading days in a month
mp = int(monthly / 0.0001)
print("Open Price: {:.5f}\nPrediction: {:.5f}\nProbability: {}%\nTicks: {:.5f}\nMonthly Ticks: {:.5f} ({} pips)".format(open_price, prediction, prb, ticks, monthly, mp))

Open Price: 1.26940
Prediction: 1.26998
Probability: 95%
Ticks: 0.00058
Monthly Ticks: 0.01279 (127 pips)

# Create a prediction column for each day and multiply it with the value we have got from out model.
d = df[-days:] # get unseen data from our dataset
# p: value we have got from out model
d['HighPredicts'] = d['Open'] * p
total = len(d)
# if the High price of the day cross over our prediction, we will win!!!
won = len(d[d['High']>d['HighPredicts']])
hit_rate = won*100/total
print("Hit rate {:.2f}% of {} trades!".format(hit_rate, total))

Hit rate 96.00% of 100 trades!

col = 'MaxLow' 
p = prob(df[:-days], col, prb)
# get the current bar's open price
open_price = df['Open'].iloc[-1]
prediction = open_price * p
ticks = abs(open_price-(p*open_price))
monthly = 22 * ticks
mp = int(monthly / 0.0001)
print("Open Price: {:.5f}\nPrediction: {:.5f}\nProbability: {}%\nTicks: {:.5f}\nMonthly Ticks: {:.5f} ({} pips)".format(open_price, prediction, prb, ticks, monthly, mp))

Open Price: 1.26940
Prediction: 1.26880
Probability: 95%
Ticks: 0.00060
Monthly Ticks: 0.01316 (131 pips)

d = df[-days:]
d['LowPredicts'] = d['Open'] * p
total = len(d)
# if Low of the day cross under our prediction, we will win!!!
won = len(d[d['Low']<d['LowPredicts']])
hit_rate = won*100/total
print("Hit rate {:.2f}% of {} trades!".format(hit_rate, total))

Hit rate 92.00% of 100 trades!

col = 'MaxClose' # Let's find 75% of Low but this time we will just use prb instead of 100-prb
max_close = prob(df[df['MaxClose']>1], col, 100-prb) # only for green bars
min_close = prob(df[df['MaxClose']<1], col, prb) # only for red bars
# get the current bar's open price
open_price = df['Open'].iloc[-1]
prediction_max = open_price * max_close
prediction_min = open_price * min_close
print("Open Price: {:.5f}\nPrediction: {:.5f} - {:.5f}\nProbability: {}%".format(open_price, prediction_min, prediction_max, prb))                                             
print("Low ticks: {:.5f}".format(open_price-prediction_min))
print("High ticks: {:.5f}".format(prediction_max-open_price))

Open Price: 1.26940
Prediction: 1.26901 - 1.26973
Probability: 95%
Low ticks: 0.00039
High ticks: 0.00033

# Create a prediction column for each day
d = df[-days:]
d['CloseLowPredicts'] = d['Open'] * min_close
d['CloseHighPredicts'] = d['Open'] * max_close
total = len(d)

# We are predicting a level we can make money. In this article, we are not trying to predict actual closing price
# That's why we are going to try to take profit!

# if Low of the day cross under our prediction, we will win!!!
low_won = len(d[d['Low']<d['CloseLowPredicts']])

# if High of the day cross over our prediction, we will win!!!
high_won = len(d[d['High']>d['CloseHighPredicts']])
low_hit_rate = low_won*100/total
high_hit_rate = high_won*100/total
print("Hit rate {:.2f}% for Low - {:.2f}% for High".format(low_hit_rate, high_hit_rate))

Hit rate 94.00% for Low - 98.00% for High

def prob_ma(df, col, p, is_low=False):
    # I'm using percentile here
    df['MA1'] = df['Close'].rolling(5).mean()
    df['MA2'] = df['Close'].rolling(220).mean()
    if is_low:
        cond = df['MA2']>df['MA1']
    else:
        cond = df['MA1']>df['MA2']
    lp = np.percentile(df[col][cond].dropna(), p)
    return lp, len(df[col][cond].dropna())

col = 'MaxHigh' # Let's find 75% of High (100-prb)
days = 100 # This is the testing size. So we will test last 100 days and exclude them from the calculation.
p, trades = prob_ma(df[:-days], col, 100-prb)
# get the current bar's open price
open_price = df['Open'].iloc[-1]
prediction = open_price * p
ticks = abs(open_price-(p*open_price))
monthly = 22 * ticks # 22 trading days in a month
mp = int(monthly / 0.0001)
print("Trades: {}/{}\nOpen Price: {:.5f}\nPrediction: {:.5f}\nProbability: {}%\nTicks: {:.5f}\nMonthly Ticks: {:.5f} ({} pips)".format(trades, len(df[:-days]), open_price, prediction, prb, ticks, monthly, mp))

Trades: 286/1025
Open Price: 1.26940
Prediction: 1.27023
Probability: 95%
Ticks: 0.00083
Monthly Ticks: 0.01833 (183 pips)