dataframe向新序列列追加数据

Question

我有一个熊猫DataFrame结构，我想向其中添加另一个列，但我不能使用append、add或insert来完成此操作。

我正在尝试使用Panda的内置函数复制投资组合数据，因为如果我请求的周期低于~1.5年，此脚本不会给我提供正确的数据，而如果我想要，即使是两天的数据也必须获得。下面是我要重写的脚本：

import QSTK.qstkutil.qsdateutil as du
import QSTK.qstkutil.tsutil as tsu
import QSTK.qstkutil.DataAccess as da

import datetime as dt
import matplotlib.pyplot as plt
import pandas as pd

ls_symbols = ["AAPL", "GLD", "GOOG", "$SPX", "XOM"]
dt_start = dt.datetime(2006, 1, 1)
dt_end = dt.datetime(2010, 12, 31)
dt_timeofday = dt.timedelta(hours=16)
ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt_timeofday)

c_dataobj = da.DataAccess('Yahoo')
ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
ldf_data = c_dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)
**d_data = dict(zip(ls_keys, ldf_data))**

d_data = dict(zip(ls_keys, ldf_data))是我想要复制的，因为它不会获取我想要的数据，但我需要找到一种方法来将新列附加到我的字典中。下面是我的脚本：

from pandas.io.data import DataReader, DataFrame
import QSTK.qstkutil.qsdateutil as du
import QSTK.qstkutil.DataAccess as da

import datetime as dt

def get_historical_data(symbol, source, date_from, date_to):
    global data_validator
    symbol_data = {}

    ls_keys = ['Open', 'High', 'Low', 'Close', 'Volume', 'Adj Close']

    for key in ls_keys:
        symbol_data[key] = DataFrame({})

    dataframe_open = DataFrame({})

    for item in symbol:
        print 'Fetching data for:', item
        current_data = DataReader(str(item), source, date_from, date_to)
        dataframe_open = {item : current_data['Open']}
        if len(symbol_data['Open'].columns) == 0:
            symbol_data['Open'] = DataFrame(dataframe_open)
        else:
            **#i want to add the new column here but can't seem to do this.**
            #symbol_data['Open'].loc[:item] = DataFrame(dataframe_open)
            pass
    return symbol_data

附注:出于测试目的，我使用以下参数调用函数：

test = get_historical_data(['SPY', 'DIA'], 'yahoo', datetime(2015,1,1), datetime(2015,1,31))

Answer 1

下面的方法有帮助吗？还没有测试过，但原则上应该可以工作...只需将数据放入长度相等的数组中，并从中构造数据帧。

def get_historical_data(symbols=[], source=None, date_from=None, date_to=None):
    global data_validator
    symbol_data = {}

    ls_keys = ['Open', 'High', 'Low', 'Close', 'Volume', 'Adj Close']
    data = []
    for item in ls_keys:
        data.append(DataReader(str(item), source, date_from, date_to)
    symbol_dataframe=DataFrame(data=data, columns=ls_keys)
    #symbol_dataframe = DataFrame()
    #for key in ls_keys:
    #    symbol_data[key] = DataFrame({})

    #dataframe_open = DataFrame({})

    #for item in symbols:
    '''    print 'Fetching data for:', item
        current_data = DataReader(str(item), source, date_from, date_to)
        dataframe_open = {item : current_data['Open']}
        #print(dataframe_open)
        if len(symbol_data['Open'].columns) == 0:
            symbol_data['Open'] = DataFrame(dataframe_open)
        else:
            #i want to add the new column here but can't seem to do this.**
            symbol_data['Open'] = DataFrame(dataframe_open)
            symbol_data.head()
    '''
    return symbol_dataframe