Python_4.22_连接SPY数据，连接更多股票，简化函数，数据切片，绘制多股票的图形，图形标准化

连接SPY数据

导入pandas库

import pandas as pd

执行函数

• 默认join向左合并
• index_col设置dfSPY的索引为Date（原来默认是第一列添加的序号）
• parse_dates为真设置dateframe的索引为datetime的格式
• usecols选择只展示的列名，日期和调整收盘价
• na_values告诉read_csv，NAN不是一个数，而是字符串
• dropna()删除所有SPY值为NAN的行

def test_run():
    start_data='2010-01-22'
    end_data='2010-01-26'
    dates=pd.data_range(start_data,end_data)   
    
    df1=pd.DataFrame(index=dates)
    dfSPY=pd.read_csv("data/SPY.csv",index_col="Date",
                      parse_dates=True,
                      usecols=['Date','Adj Close'],
                      na_values=['nan'])

    df1=df1.join(dfSPY)
    df1=df1.dropna()
    print df1

最后删除空行也可以用How函数，参考
http://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.join.html

• how的参数：inner内连接，outer外连接，left左连接（默认），right右连接

df1=df1.join(dfSPY,how='inner')

连接更多股票

因为任何一支股票的调整收盘价都是Adj Close，列名重复造成clash（冲突），所以分别给列重命名

dfSPY=dfSPY.rename(columns={'Adj Close':'SPY'})
df1=df1.join(dfSPY,how='inner')

symbols=['GOOD','IBM','GLD']
for symbol in symbols:
    df_temp=pd.read_csv("data/{}.csv".format(symbol),index_col="Date",
                    parse_dates=True,usecols=['Date','Adj Close'],
                    na_values=['nan'])
    df_temp=df_temp.rename(columns={'Adj Close':symbol})
    df=df1.join(df_temp)
print df1

简化函数

import os
import pandas as pd
def symbol_to_path(symbol,base_dir="data"):
    return os.path.join(base_dir,"{}.csv".format(str(symbol)))

def get_data(symbols,dates):
    df=pd.DataFrame(index=dates)
    if 'SPY' not in symbols:
       symbols.insert(0,'SPY')

    for symbol in symbols:
    # TODO: Read and join data for each symbol
    df_temp=pd.read_csv(symbol_to_path(symbol),index_col="Date",
                    parse_dates=True,usecols=['Date','Adj Close'],
                    na_values=['nan'])
    df_temp=df_temp.rename(columns={'Adj Close':symbol})
    df=df.join(df_temp)
    if symbol =='SPY':
       df = df.dropna(subset=["SPY"])
    return df
    
def test_run():
    # Define a date range
    dates = pd.date_range('2010-01-22', '2010-01-26')

    # Choose stock symbols to read
    symbols = ['GOOG', 'IBM', 'GLD']
    
    # Get stock data
    df = get_data(symbols, dates)
    print df
    
if __name__ == "__main__":
    test_run()

数据切片

• sd 、ed第一纵行选择的的开始、结束的横行
• '__'里是第一横行选择的列名，不用连续

df2=df1[sd:ed,['GOOD','GLD']]

• 日期倒过来就会为空
• 没有ix也会打印相同结果，但是一般认为ix会让pythonic更加稳定，所以选择写

print df.ix['2010-01-01':'2010-01-31']
print df['GOOD']
print df['IBM','GLD']

print df.ix['2010-01-01':'2010-01-31',['IBM','GLD']]

绘制多股票的图形

在“简化函数”中加

import matplotlib.pypolt as plt

• ax 是坐标轴，标题通过参数传入

def plot_data(df,title="Stock prices"):
   ax = df.plot(title=title,fontsize=2)
   ax.set_xlabel("Date")
   ax.set_ylable("Price")
   plt.show()

绘制两个股票的图形

import os
import pandas as pd
import matplotlib.pyplot as plt

def plot_selected(df, columns, start_index, end_index):
    """Plot the desired columns over index values in the given range."""
    # TODO: Your code here!!!
    plot_data(df.ix[start_index:end_index,columns],title="Selected data")


def symbol_to_path(symbol, base_dir="data"):
    """Return CSV file path given ticker symbol."""
    return os.path.join(base_dir, "{}.csv".format(str(symbol)))


def get_data(symbols, dates):
    """Read stock data (adjusted close) for given symbols from CSV files."""
    df = pd.DataFrame(index=dates)
    if 'SPY' not in symbols:  # add SPY for reference, if absent
        symbols.insert(0, 'SPY')

    for symbol in symbols:
        df_temp = pd.read_csv(symbol_to_path(symbol), index_col='Date',
                parse_dates=True, usecols=['Date', 'Adj Close'], na_values=['nan'])
        df_temp = df_temp.rename(columns={'Adj Close': symbol})
        df = df.join(df_temp)
        if symbol == 'SPY':  # drop dates SPY did not trade
            df = df.dropna(subset=["SPY"])

    return df


def plot_data(df, title="Stock prices"):
    """Plot stock prices with a custom title and meaningful axis labels."""
    ax = df.plot(title=title, fontsize=12)
    ax.set_xlabel("Date")
    ax.set_ylabel("Price")
    plt.show()


def test_run():
    # Define a date range
    dates = pd.date_range('2010-01-01', '2010-12-31')

    # Choose stock symbols to read
    symbols = ['GOOG', 'IBM', 'GLD']  # SPY will be added in get_data()
    
    # Get stock data
    df = get_data(symbols, dates)

    # Slice and plot
    plot_selected(df, ['SPY', 'IBM'], '2010-03-01', '2010-04-01')

if __name__ == "__main__":
    test_run()

图形标准化

• 提取第一行，让所有数据都除以第一组数据，则所有数据都是从1开始

def normalize_data(df)
    return df/df.ix[0,:]