tushare package Use Cases

Tushare is a free, open-source python Finance data interface package. The main achievement of stocks and other financial data from data acquisition , cleansing processing  to the  data storage process can provide rapid financial analysts, clean, and a variety of easy data analysis for data in terms of their access to greatly reduce the workload, the they are more focused on the study and implementation of strategies and models. Considering the Python pandas package reflects the quantitative analysis of the financial advantage, Tushare return of most of the data formats are pandas DataFrame type.

For example use

Import numpy AS NP
 Import PANDAS AS PD
 Import matplotlib.pyplot AS PLT
 Import tushare AS TS 

# used tushare obtain each stock market data 
DF = ts.get_k_data ( ' 600,519 ' , 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)
 # outputs the stock closed than opened up to all of 3% or date 
Print (DF [(DF [ ' Close ' ] -df [ ' Open ' ]) / DF [ ' Open ' ]> 0.03 ] .index) 

# df.shift () moves downward moving positive, negative moved upwardly 
# outputs the opened more than 2% of all the stock than the day before closing down date 
df [(df [ ' Open ' ] -df [ ' Close ' ] .shift (. 1)) / DF [ ' Close ' ].shift(1)<=-0.02] .index 

# If I from January 1, 2008 start, first trading day of each month to buy a hand stock, sell all the stock last trading day of each year, to date, how my earnings? 

price_last = DF [ ' Open ' ] [-. 1 ] 
DF = DF [ ' 2008-01 ' : ' 2018-11 ' ] # remove unnecessary data inclusive 

df_monthly = df.resample ( " the MS " ) .first () # per The first day of May 
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)) 

# request and the 5-day moving average 30 

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'] [. 4-I: 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 () # window scroll down 5 
DF [ ' MA30 ' ] = DF [ ' Close ' ] .rolling (30) .mean () # window scroll down 30 
Print (DF.head(50))

# Videos FIG average 
DF DF = [: 800 ] 
DF [[ ' Close ' , ' MA5 ' , ' MA30 ' .]] Plot () 
plt.show () 

# MACD Sicha and date 
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)