tushare包使用案例

Tushare是一個免費、開源的python財經數據接口包。主要實現對股票等金融數據從數據采集、清洗加工 到 數據存儲的過程，能夠為金融分析人員提供快速、整潔、和多樣的便於分析的數據，為他們在數據獲取方面極大地減輕工作量，使他們更加專注於策略和模型的研究與實現上。考慮到Python pandas包在金融量化分析中體現出的優勢，Tushare返回的絕大部分的數據格式都是pandas DataFrame類型。

舉例使用

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tushare as ts

# 使用tushare 獲取每只股票的行情數據
df = ts.get_k_data('600519',start='2008-01-01')
print(type(df))
df.to_csv('600519.csv')
df = pd.read_csv('600519.csv',index_col='date',parse_dates=['date'])[['open','close','high','low']]
print(df)
# 輸出該股票所有收盤比開盤上漲3%以上的日期
print(df[(df['close']-df['open'])/df['open']>0.03].index)

# df.shift() 移動，正數向下移動，負數向上移動
# 輸出該股票所有開盤比前日收盤跌幅超過2%的日期
df[(df['open']-df['close'].shift(1))/df['close'].shift(1)<=-0.02].index

# 假如我從2008年1月1日開始，每月第一個交易日買入1手股票，每年最后一個交易日賣出所有股票，到今天為止，我的收益如何？

price_last = df['open'][-1]
df = df['2008-01':'2018-11'] #剔除首尾無用的數據

df_monthly = df.resample("MS" ).first() # 每月第一天
print("df_monthly 2008:")
print(df_monthly)
print("df_yearly:")
df_yearly = df.resample("A").last()[:-1]  # 每年最后一天
print(df_yearly)

cost_money=0
hold = 0
for year in range(2008,2018):
    cost_money += df_monthly[str(year)]['open'].sum() * 100
    hold += len(df_monthly[str(year)]['open'])*100
    cost_money -= df_yearly[str(year)]['open'][0] * hold
    hold = 0

print('cost_money: %s'%(0-cost_money))

# 求5日均線和30日均線

df = pd.read_csv('601318.csv',index_col='date',parse_dates=['date'])[['open','close','low','high']]
print(df.head())

df['ma5'] = np.NAN
df['ma30'] = np.NAN
#
# for i in range(4,len(df)):
#     df.loc[df.index[i],'ma5'] = df['close'][i-4:i+1].mean()
#
# for i in range(29,len(df)):
#     df.loc[df.index[i],'ma30'] = df['close'][i-29:i+1].mean()
#
# print(df.head(50))

df['ma5'] = df['close'].rolling(5).mean() # 窗口向下滾動5個
df['ma30'] = df['close'].rolling(30).mean() # 窗口向下滾動30個
print(df.head(50))

# 畫均線圖
df = df[:800]
df[['close','ma5','ma30']].plot()
plt.show()

# 金叉和死叉日期
golden_cross =[]
death_cross = []
for i in range(1,len(df)):
    if df['ma5'][i]>=df['ma30'][i] and df['ma5'][i-1]< df['ma30'][i-1]:
        golden_cross.append(df.index[i].to_pydatetime())
    if df['ma5'][i] <= df['ma30'][i] and df['ma5'][i - 1] > df['ma30'][i - 1]:
        death_cross.append(df.index[i])

print(golden_cross[:5])

sr1 = df['ma5'] < df['ma30']
sr2 = df['ma5'] >= df['ma30']
death_cross = df[sr1 & sr2.shift(1)].index
golden_cross = df[~(sr1 | sr2.shift(1))].index

print(death_cross)