python - python pandas中的相对强度指数

Question

我是 Pandas 新手。计算 Pandas RSI指标中相对强度部分的最佳方法是什么？到目前为止，我得到了以下信息:

from pylab import *
import pandas as pd
import numpy as np



def Datapull(Stock):
    try:
        df = (pd.io.data.DataReader(Stock,'yahoo',start='01/01/2010'))
        return df
        print 'Retrieved', Stock
        time.sleep(5)
    except Exception, e:
        print 'Main Loop', str(e)


def RSIfun(price, n=14):
    delta = price['Close'].diff()
    #-----------
    dUp=
    dDown=

    RolUp=pd.rolling_mean(dUp, n)
    RolDown=pd.rolling_mean(dDown, n).abs()

    RS = RolUp / RolDown
    rsi= 100.0 - (100.0 / (1.0 + RS))
    return rsi

Stock='AAPL'
df=Datapull(Stock)
RSIfun(df)

到目前为止，我做得对吗？我在等式的差异部分遇到问题，您将向上和向下的计算分开

Answer 1

请务必注意，定义 RSI 的方法有多种。它通常至少以两种方式定义:使用上述简单移动平均线 (SMA)，或使用指数移动平均线 (EMA)。这是一个代码片段，它计算 RSI 的各种定义并绘制它们以进行比较。我在取差后丢弃了第一行，因为根据定义它总是 NaN。

请注意，使用 EMA 时必须小心:因为它包含一个可以追溯到数据开头的内存，所以结果取决于您从哪里开始!出于这个原因，通常人们会在开始时添加一些数据，比如 100 个时间步长，然后切断前 100 个 RSI 值。

在下图中，可以看到使用 SMA 和 EMA 计算的 RSI 之间的差异:SMA 往往更敏感。请注意，基于 EMA 的 RSI 在第一个时间步(这是原始周期的第二个时间步，由于丢弃了第一行)具有其第一个有限值，而基于 SMA 的 RSI 在第一个时间步具有其第一个有限值第 14 个时间步。这是因为默认情况下 rolling_mean() 仅在有足够的值填充窗口时才返回有限值。

import datetime
from typing import Callable

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pandas_datareader.data as web

# Window length for moving average
length = 14

# Dates
start, end = '2010-01-01', '2013-01-27'

# Get data
data = web.DataReader('AAPL', 'yahoo', start, end)
# Get just the adjusted close
close = data['Adj Close']

# Define function to calculate the RSI
def calc_rsi(over: pd.Series, fn_roll: Callable) -> pd.Series:
    # Get the difference in price from previous step
    delta = over.diff()
    # Get rid of the first row, which is NaN since it did not have a previous row to calculate the differences
    delta = delta[1:] 

    # Make the positive gains (up) and negative gains (down) Series
    up, down = delta.clip(lower=0), delta.clip(upper=0).abs()

    roll_up, roll_down = fn_roll(up), fn_roll(down)
    rs = roll_up / roll_down
    rsi = 100.0 - (100.0 / (1.0 + rs))

    # Avoid division-by-zero if `roll_down` is zero
    # This prevents inf and/or nan values.
    rsi[:] = np.select([roll_down == 0, roll_up == 0, True], [100, 0, rsi])
    rsi.name = 'rsi'

    # Assert range
    valid_rsi = rsi[length - 1:]
    assert ((0 <= valid_rsi) & (valid_rsi <= 100)).all()
    # Note: rsi[:length - 1] is excluded from above assertion because it is NaN for SMA.

    return rsi

# Calculate RSI using MA of choice
# Reminder: Provide ≥ `1 + length` extra data points!
rsi_ema = calc_rsi(close, lambda s: s.ewm(span=length).mean())
rsi_sma = calc_rsi(close, lambda s: s.rolling(length).mean())
rsi_rma = calc_rsi(close, lambda s: s.ewm(alpha=1 / length).mean())  # Approximates TradingView.

# Compare graphically
plt.figure(figsize=(8, 6))
rsi_ema.plot(), rsi_sma.plot(), rsi_rma.plot()
plt.legend(['RSI via EMA/EWMA', 'RSI via SMA', 'RSI via RMA/SMMA/MMA (TradingView)'])
plt.show()