Scikit Learn 股票投资：p18

▌前言

在视频p17中，我们从quandl.com中重新获取了新的股票数据，这个数据更加准确，有利于我们做预测。本视频主要是将yahoo页面提取的数据替换为quandl获得的数据，并计算对应股票一年后的股价，从而回测得出股票是否优于大盘。

▌视频

▌视频出处

视频系列：Scikit-learn Machine Learning with Python and SKlearn

本视频出处：Scikit Learn Machine Learning for investing Tutorial with Python p. 18

哔哩哔哩：Scikit Learn Machine Learning for investing Tutorial with Python p. 18

▌内容

我们将修改视频p12中的代码。
首先，在def Key_Stats中的sp500_df = pd.DataFrame.from_csv("SPY.csv")下添加stock_prices.csv文件的读取。

sp500_df = pd.DataFrame.from_csv("SPY.csv")
#读取quandl下载的股票数据
stock_df = pd.DataFrame.from_csv("stock_prices.csv")

获取sp500一年后的价格：

one_year_later = int(unix_time + 31536000)

        #从spy中获取sp500对应一年后的时间点的adj close
        try:
          sp500_1y = datetime.fromtimestamp(one_year_later).strftime('%Y-%m-%d')
          row = sp500_df[(sp500_df.index == sp500_1y)]
          sp500_1y_value = float(row["Adj Close"])
        except Exception as e:
          try:
            sp500_1y = datetime.fromtimestamp(one_year_later - 259200).strftime('%Y-%m-%d')
            row = sp500_df[(sp500_df.index == sp500_1y)]
            sp500_1y_value = float(row["Adj Close"])
          except Exception as e:
            print("S&P 500 1 year later: exception:",str(e))

然后，将用正则表达式获取stock price 部分删除，改为读取csv中的股票价格, 并获取一年后的价格。

#获取stock对应一年后的时间点的adj close
try:
  stock_price_1y = datetime.fromtimestamp(one_year_later).strftime('%Y-%m-%d')
  row = stock_df[(stock_df.index == stock_price_1y)][ticker.upper()]
  stock_1y_value = round(float(row),2)
except Exception as e:
  try:
    stock_price_1y = datetime.fromtimestamp(one_year_later - 259200).strftime('%Y-%m-%d')
    row = stock_df[(stock_df.index == stock_price_1y)][ticker.upper()]
    stock_1y_value = round(float(row),2)
  except Exception as e:
    print("stock price 1 year later: exception:",str(e))

#获取stock对应的时间点的adj close
try:
  stock_price = datetime.fromtimestamp(unix_time).strftime('%Y-%m-%d')
  row = stock_df[(stock_df.index == stock_price)][ticker.upper()]
  stock_price = round(float(row),2)
except Exception as e:
  try:
    stock_price = datetime.fromtimestamp(unix_time - 259200).strftime('%Y-%m-%d')
    row = stock_df[(stock_df.index == stock_price)][ticker.upper()]
    stock_price = round(float(row),2)
  except Exception as e:
    print("stock price: exception:",str(e))

最后就是修改stock_p_change和sp500_p_change的表达式, 保留2位小数：

stock_p_change = round((((stock_1y_value - stock_price) / stock_price) * 100), 2)
sp500_p_change = round((((sp500_1y_value - sp500_value) / sp500_value) * 100), 2)

最后，我们需要生成两个csv文件，一个是不包含N/A，一个是包含N/A，用作往后的测试。运行时，把#去掉。

#if value_list.count("N/A") > 0:
#if value_list.count("N/A") > 15:

然后对应文件名改为：

#df.to_csv("key_stats_acc_perf_NO_NA.csv")
#df.to_csv("key_stats_acc_perf_WITH_NA.csv")

▌源代码

import pandas as pd
import os
import time
from datetime import datetime
import re
from time import mktime
import matplotlib
import matplotlib.pyplot as plt
from matplotlib import style
style.use("dark_background")

#获取数据的具体路径
path = "../intraQuarter"

def Key_Stats(
    gather=[
      "Total Debt/Equity",
      'Trailing P/E',
      'Price/Sales',
      'Price/Book',
      'Profit Margin',
      'Operating Margin',
      'Return on Assets',
      'Return on Equity',
      'Revenue Per Share',
      'Market Cap',
      'Enterprise Value',
      'Forward P/E',
      'PEG Ratio',
      'Enterprise Value/Revenue',
      'Enterprise Value/EBITDA',
      'Revenue',
      'Gross Profit',
      'EBITDA',
      'Net Income Avl to Common ',
      'Diluted EPS',
      'Earnings Growth',
      'Revenue Growth',
      'Total Cash',
      'Total Cash Per Share',
      'Total Debt',
      'Current Ratio',
      'Book Value Per Share',
      'Cash Flow',
      'Beta',
      'Held by Insiders',
      'Held by Institutions',
      'Shares Short (as of',
      'Short Ratio',
      'Short % of Float',
      'Shares Short (prior '
    ]
  ):

  statspath = path+'/_KeyStats'
  #os模块提供的walk方法很强大，能够把给定的目录下的所有目录和文件遍历出来。
  #方法：os.walk(path),遍历path，返回一个对象，他的每个部分都是一个三元组,('目录x'，[目录x下的目录list]，目录x下面的文件)
  stock_list = [x[0] for x in os.walk(statspath)]
  df = pd.DataFrame(
    columns = [
      'Date',
      'Unix',
      'Ticker',
      'Price',
      'stock_p_change',
      'SP500',
      'sp500_p_change',
      'Difference',
      ##############
      'DE Ratio',
      'Trailing P/E',
      'Price/Sales',
      'Price/Book',
      'Profit Margin',
      'Operating Margin',
      'Return on Assets',
      'Return on Equity',
      'Revenue Per Share',
      'Market Cap',
      'Enterprise Value',
      'Forward P/E',
      'PEG Ratio',
      'Enterprise Value/Revenue',
      'Enterprise Value/EBITDA',
      'Revenue',
      'Gross Profit',
      'EBITDA',
      'Net Income Avl to Common ',
      'Diluted EPS',
      'Earnings Growth',
      'Revenue Growth',
      'Total Cash',
      'Total Cash Per Share',
      'Total Debt',
      'Current Ratio',
      'Book Value Per Share',
      'Cash Flow',
      'Beta',
      'Held by Insiders',
      'Held by Institutions',
      'Shares Short (as of',
      'Short Ratio',
      'Short % of Float',
      'Shares Short (prior ',                                
      ##############
      'Status'
    ]
  )

  sp500_df = pd.DataFrame.from_csv("SPY.csv")
  #读取quandl下载的股票数据
  stock_df = pd.DataFrame.from_csv("stock_prices.csv")

  ticker_list = []
  #stock_list[1:] -- 主要作用是跳过根目录intraQuarter
  for each_dir in stock_list[1:]:
    #os.listdir(each_dir)：列出each_dir下的目录和文件
    each_file = os.listdir(each_dir)

    # ticker = each_dir.split("\\")[1] # Windows only
    # ticker = each_dir.split("/")[1] # this didn't work so do this:
    ticker = os.path.basename(os.path.normpath(each_dir))
    # print(ticker) # uncomment to verify
    ticker_list.append(ticker)

    # starting_stock_value = False
    # starting_sp500_value = False

    if len(each_file) > 0:
      for file in each_file:
        date_stamp = datetime.strptime(file, '%Y%m%d%H%M%S.html')
        unix_time = time.mktime(date_stamp.timetuple())
        full_file_path = each_dir+'/'+file
        source = open(full_file_path,'r').read()
        try:
          value_list = []
          for each_data in gather:
            try:
              regex = re.escape(each_data) + r'.*?(\d{1,8}\.\d{1,8}M?B?|N/A)%?</td>'
              value = re.search(regex, source)
              value = (value.group(1))
              if "B" in value:
                value = float(value.replace("B",''))*1000000000
              elif "M" in value:
                value = float(value.replace("M",''))*1000000
              value_list.append(value)
            except Exception as e:
              value = "N/A"
              value_list.append(value)

          #从spy中获取sp500对应时间点的adj close
          try:
            sp500_date = datetime.fromtimestamp(unix_time).strftime('%Y-%m-%d')
            row = sp500_df[(sp500_df.index == sp500_date)]
            sp500_value = float(row["Adj Close"])
          except:
            sp500_date = datetime.fromtimestamp(unix_time-259200).strftime('%Y-%m-%d')
            row = sp500_df[(sp500_df.index == sp500_date)]
            sp500_value = float(row["Adj Close"])

          one_year_later = int(unix_time + 31536000)

          #从spy中获取sp500对应一年后的时间点的adj close
          try:
            sp500_1y = datetime.fromtimestamp(one_year_later).strftime('%Y-%m-%d')
            row = sp500_df[(sp500_df.index == sp500_1y)]
            sp500_1y_value = float(row["Adj Close"])
          except Exception as e:
            try:
              sp500_1y = datetime.fromtimestamp(one_year_later - 259200).strftime('%Y-%m-%d')
              row = sp500_df[(sp500_df.index == sp500_1y)]
              sp500_1y_value = float(row["Adj Close"])
            except Exception as e:
              print("S&P 500 1 year later: exception:",str(e))

          #获取stock对应一年后的时间点的adj close
          try:
            stock_price_1y = datetime.fromtimestamp(one_year_later).strftime('%Y-%m-%d')
            row = stock_df[(stock_df.index == stock_price_1y)][ticker.upper()]
            stock_1y_value = round(float(row),2)
          except Exception as e:
            try:
              stock_price_1y = datetime.fromtimestamp(one_year_later - 259200).strftime('%Y-%m-%d')
              row = stock_df[(stock_df.index == stock_price_1y)][ticker.upper()]
              stock_1y_value = round(float(row),2)
            except Exception as e:
              print("stock price 1 year later: exception:",str(e))

          #获取stock对应的时间点的adj close
          try:
            stock_price = datetime.fromtimestamp(unix_time).strftime('%Y-%m-%d')
            row = stock_df[(stock_df.index == stock_price)][ticker.upper()]
            stock_price = round(float(row),2)
          except Exception as e:
            try:
              stock_price = datetime.fromtimestamp(unix_time - 259200).strftime('%Y-%m-%d')
              row = stock_df[(stock_df.index == stock_price)][ticker.upper()]
              stock_price = round(float(row),2)
            except Exception as e:
              print("stock price: exception:",str(e))

          stock_p_change = round((((stock_1y_value - stock_price) / stock_price) * 100), 2)
          sp500_p_change = round((((sp500_1y_value - sp500_value) / sp500_value) * 100), 2)

          difference = stock_p_change - sp500_p_change

          if difference > 0:
            status = "outperform"
          else:
            status = "underperform"

          # if value_list.count("N/A") > 0:
          if value_list.count("N/A") > 15:
            pass
          else:
            df = df.append(
              {
                'Date':date_stamp,
                'Unix':unix_time,
                'Ticker':ticker,
                'Price':stock_price,
                'stock_p_change':stock_p_change,
                'SP500':sp500_value,
                'sp500_p_change':sp500_p_change,
                'Difference':difference,
                'DE Ratio':value_list[0],
                #'Market Cap':value_list[1],
                'Trailing P/E':value_list[1],
                'Price/Sales':value_list[2],
                'Price/Book':value_list[3],
                'Profit Margin':value_list[4],
                'Operating Margin':value_list[5],
                'Return on Assets':value_list[6],
                'Return on Equity':value_list[7],
                'Revenue Per Share':value_list[8],
                'Market Cap':value_list[9],
                'Enterprise Value':value_list[10],
                'Forward P/E':value_list[11],
                'PEG Ratio':value_list[12],
                'Enterprise Value/Revenue':value_list[13],
                'Enterprise Value/EBITDA':value_list[14],
                'Revenue':value_list[15],
                'Gross Profit':value_list[16],
                'EBITDA':value_list[17],
                'Net Income Avl to Common ':value_list[18],
                'Diluted EPS':value_list[19],
                'Earnings Growth':value_list[20],
                'Revenue Growth':value_list[21],
                'Total Cash':value_list[22],
                'Total Cash Per Share':value_list[23],
                'Total Debt':value_list[24],
                'Current Ratio':value_list[25],
                'Book Value Per Share':value_list[26],
                'Cash Flow':value_list[27],
                'Beta':value_list[28],
                'Held by Insiders':value_list[29],
                'Held by Institutions':value_list[30],
                'Shares Short (as of':value_list[31],
                'Short Ratio':value_list[32],
                'Short % of Float':value_list[33],
                'Shares Short (prior ':value_list[34],
                'Status':status
              },
              ignore_index=True)
        except Exception as e:
          pass

  df.to_csv("key_stats_acc_perf_WITH_NA.csv")

Key_Stats()

▌最后

虽然分c君_BingWong只是作为一名搬运工，连码农都称不上。 但制作代码中的注释、翻译和搬运都花了很多时间，请各位大侠高抬贵手，在转载时请注明出处。