Python學(xué)習(xí)筆記之pandas索引列、過濾、分組、求和功能示例

from bs4 import BeautifulSoup
import os
import csv
# 使用 BeautifulSoup 解析html內(nèi)容
def getFundDetailData(html):
  soup = BeautifulSoup(html,"html.parser")
  rows = soup.find("table").tbody.find_all("tr")
  result = []
  for row in rows:
    tds=row.find_all('td')
    result.append({"fcode": '519961'
            ,"fdate": tds[0].get_text()
           , "NAV": tds[1].get_text()
           , "ACCNAV": tds[2].get_text()
           , "DGR": tds[3].get_text()
           , "pstate":tds[4].get_text()
           , "rstate": tds[5].get_text()
           }
         )
  return result
# 把解析之后的數(shù)據(jù)寫入到csv文件
def writeToCSV():
  data_dir = "../htmls/details"
  all_path = os.listdir(data_dir)
  all_result = []
  for path in all_path:
    if os.path.isfile(os.path.join(data_dir,path)):
      with open(os.path.join(data_dir,path),"rb") as f:
        content = f.read().decode("utf-8")
        f.close()
        all_result = all_result + getFundDetailData(content)
  with open("../csv/519961.csv","w",encoding="utf-8",newline="") as f:
    writer = csv.writer(f)
    writer.writerow(['fcode', 'fdate', 'NAV', "ACCNAV", 'DGR', 'pstate', "rstate"])
    for r in all_result:
      writer.writerow([r["fcode"], r["fdate"], r["NAV"], r["ACCNAV"], r["DGR"], r["pstate"], r["rstate"]])
    f.close()

# 執(zhí)行
writeToCSV()

# coding: utf-8
import pandas
if __name__ == "__main__" :
  # 讀取csv文件 創(chuàng)建pandas對(duì)象
  pd = pandas.read_csv("./csv/519961.csv", dtype={"fcode":pandas.np.str_}, index_col="fdate") # 把 fdate 這列設(shè)置為 索引列
  # 根據(jù)索引列 倒序
  print(pd.sort_index(ascending=False))

# 讀取csv文件 創(chuàng)建pandas對(duì)象
pd = pandas.read_csv("./csv/519961.csv", dtype={"fcode":pandas.np.str_}, index_col="fdate") # 把 fdate 這列設(shè)置為 索引列
pd.index = pandas.to_datetime(pd.index)
print(pd["2017-11-29 "]) # 2017-11-29 519961 1.189  1.189 -1.00% 限制大額申購  開放贖回

# 讀取csv文件 創(chuàng)建pandas對(duì)象
pd = pandas.read_csv("./csv/519961.csv", dtype={"fcode":pandas.np.str_}, index_col="fdate", parse_dates=["fdate"]) # 指明fdate是日期類型
print(pd["2017-11-29 "]) # 2017-11-29 519961 1.189  1.189 -1.00% 限制大額申購  開放贖回

print(pd.index) # 打印 索引

DatetimeIndex(['2015-08-13', '2015-08-12', '2015-08-11', '2015-08-10',
        '2015-08-07', '2015-08-06', '2015-08-05', '2015-08-04',
        '2015-08-03', '2015-07-31',
        ...
        '2015-07-02', '2015-07-01', '2015-06-30', '2015-06-29',
        '2015-06-26', '2015-06-25', '2015-06-24', '2015-06-23',
        '2015-06-19', '2015-06-18'],
       dtype='datetime64[ns]', name='fdate', length=603, freq=None)

# 取出 2017年7月的 全部數(shù)據(jù)
print(pd["2017-07"])
# 取出 2017年7月到9月的 數(shù)據(jù)
print(pd["2017-07":"2017-09"])
# 到2015-07的數(shù)據(jù)
print(pd[:"2015-07"])
# 取出截至到2015-07的數(shù)據(jù)
# 然后 倒序
print(pd[:"2015-7"].sort_index(ascending=False))

result = pd[pd["DGR"].notnull()] # DGR一定要有值
# 過濾掉DGR值里的%號(hào),最后取出小于0的值（負(fù)數(shù)就表示增長率下跌了 ）
result = result[result['DGR'].str.strip("%").astype(pandas.np.float)<0]
# 按照月份 統(tǒng)計(jì)DGR跌的次數(shù)
result = result.groupby(lambda d:d.strftime("%Y-%m")).size()
# 對(duì)DGR跌的次數(shù) 倒序,然后取出前面第一個(gè)
result = result.sort_values(ascending=False).head(1)
print(result) # 2016-04  12 意思就是2016年4月份 是該基金DGR下跌次數(shù)最多的月份