DataFrame append generates TypeError

Question

I am trying to write a function to write and read transaction details to/from a .h5 file. I want to effectively use one file to store some transaction details, and when necessary, derive the details. Here's my code:

import h5py
import numpy as np
import pandas as pd

from datetime import datetime
from os import listdir
from pandas import HDFStore


def maintainLedger(mode, tick, lastBuyy = 0, lastSell = 0, quan = 0, prof = 0):
    """THIS FUNCTION WRITES AND READS TRANSACTION DETAILS.
       mode = 0 - IF FILE EXITS, READ FILE
       mode = 1 - IF FILE EXITS, APPEND TO FILE"""

    # CHECK IF LEDGER FILE EXISTS, IF NOT CREATE A LEDGER FILE FOR THE FIRST TIME
    path = r'ledger'
    suff = r'h5'
    flie = listdir(path)
    flie = [item for item in flie if item.endswith(suff)]

    if len(flie) == 0:
        HDF5Data = HDFStore('ledger/ledger.h5')

        # GENERATE NEW VALUES OF DATE/TIME
        mi = int(datetime.now().minute)
        ho = int(datetime.now().hour)
        da = int(datetime.now().day)
        we = int(datetime.now().isocalendar()[1])
        mo = int(datetime.now().month)
        ye = int(datetime.now().year)

        newwData = np.array([mode, mi, ho, da, we, mo, ye, tick, lastBuyy, lastSell, quan, prof]).reshape(1, 12)
        newwData = pd.DataFrame(newwData, columns = ['mode', 'mi', 'ho', 'da', 'we', 'mo', 'ye', 'tick', 'laBu', 'laSe', 'quan', 'prof'])
        HDF5Data.put('data', newwData, format = 'table', data_columns = True)
        HDF5Data.close()

    elif len(flie) == 1:
        if mode == 0:
            # READ PREVIOUSLY SAVED DATA AS PANDAS DATAFRAME
            readData = pd.read_hdf('ledger/ledger.h5', mode = 'r')

            # DO SOMETHING...

        elif mode == 1:
            # GENERATE NEW VALUES OF DATE/TIME
            mi = int(datetime.now().minute)
            ho = int(datetime.now().hour)
            da = int(datetime.now().day)
            we = int(datetime.now().isocalendar()[1])
            mo = int(datetime.now().month)
            ye = int(datetime.now().year)

            # GATHER NEW DATA INTO NUMPY ARRAY AND CONVERT TO PANDAS DATAFRAME
            newwData = np.array([mode, mi, ho, da, we, mo, ye, tick, lastBuyy, lastSell, quan, prof]).reshape(1, 12)
            newwData = pd.DataFrame(newwData, columns = ['mode', 'mi', 'ho', 'da', 'we', 'mo', 'ye', 'tick', 'laBu', 'laSe', 'quan', 'prof'])

            # READ PREVIOUSLY SAVED DATA AS PANDAS DATAFRAME AND APPEND NEW DATA
            readData = pd.read_hdf('ledger/ledger.h5', mode = 'a')
            readData.append('data', newwData)

            tempData = pd.read_hdf('ledger/ledger.h5', mode = 'r')
            print(tempData)

        else:
            print('Please check input data for errors!')



if __name__ == '__main__':
    maintainLedger(1, "AAPL")

When I run the code, I am getting the following error:

TypeError: cannot concatenate object of type "<class 'str'>"; only pd.Series, pd.DataFrame, and pd.Panel (deprecated) objs are valid

I have tried looking for a solution, and a quick search led me to this, which didn't solve my problem. Is there something I am doing wrong? Any advice would be appreciated.

Please, when you ask about an error, show where it occurs! Some readers are magicians and can guess where, but most of us need some help. — hpaulj, Oct 22 '18 at 01:39
I don't see a `concatenate` call, but see a `readData.append` that looks like it might use that. Looking up its docs, I see: `DataFrame.append(other, ...`, where `other` is supposed to be a dataframe or series. You give a string, 'data', instead. — hpaulj, Oct 22 '18 at 01:44
If my guess is right, then your subject line is wrong. It isn't a `HDFStore append` but a `Dataframe append` that's raising the error. — hpaulj, Oct 22 '18 at 01:48
@hpaulj I think it's the way I am appending the data is the issue. I have found the solution the the issue. See below for updated code. — troymyname00, Oct 22 '18 at 02:04
@hpaulj You're correct about the DataFrame append step raising the error. — troymyname00, Oct 22 '18 at 02:07

score 1 · Accepted Answer · answered Oct 22 '18 at 02:05

import h5py
import numpy as np
import pandas as pd

from datetime import datetime
from os import listdir
from pandas import HDFStore


def maintainLedger(mode, tick = 'QUERY', lastBuyy = 0, lastSell = 0, quan = 0, prof = 0):
    """THIS FUNCTION WRITES AND READS TRANSACTION DETAILS.
       mode = 0 - IF FILE EXITS, READ FILE
       mode = 1 - IF FILE EXITS, APPEND TO FILE"""

    # CHECK IF LEDGER FILE EXISTS, IF NOT CREATE A LEDGER FILE FOR THE FIRST TIME
    path = r'ledger'
    suff = r'h5'
    flie = listdir(path)
    flie = [item for item in flie if item.endswith(suff)]

    if len(flie) == 0:
        # GENERATE NEW VALUES OF DATE/TIME
        mi = int(datetime.now().minute)
        ho = int(datetime.now().hour)
        da = int(datetime.now().day)
        we = int(datetime.now().isocalendar()[1])
        mo = int(datetime.now().month)
        ye = int(datetime.now().year)

        # GATHER NEW DATA INTO NUMPY ARRAY AND CONVERT TO PANDAS DATAFRAME
        newwData = np.array([mode, mi, ho, da, we, mo, ye, tick, lastBuyy, lastSell, quan, prof]).reshape(1, 12)
        newwData = pd.DataFrame(newwData, columns = ['mode', 'mi', 'ho', 'da', 'we', 'mo', 'ye', 'tick', 'laBu', 'laSe', 'quan', 'prof'])

        # SAVE ALL DATA INTO .H5 FORMAT
        HDF5Data = HDFStore('ledger/ledger.h5')
        HDF5Data.put('data', newwData, format = 'table', data_columns = True)
        HDF5Data.close()

    elif len(flie) == 1:
        if mode == 0:
            """THIS OPTION ENABLES CODE TO READ DATA."""

            # READ PREVIOUSLY SAVED DATA AS PANDAS DATAFRAME
            readData = pd.read_hdf('ledger/ledger.h5', mode = 'r')

            # DO SOMETHING...
            print(readData)

        elif mode == 1:
            """THIS OPTION ENABLES CODE TO APPEND DATA."""

            # GENERATE NEW VALUES OF DATE/TIME
            mi = int(datetime.now().minute)
            ho = int(datetime.now().hour)
            da = int(datetime.now().day)
            we = int(datetime.now().isocalendar()[1])
            mo = int(datetime.now().month)
            ye = int(datetime.now().year)

            # GATHER NEW DATA INTO NUMPY ARRAY AND CONVERT TO PANDAS DATAFRAME
            newwData = np.array([mode, mi, ho, da, we, mo, ye, tick, lastBuyy, lastSell, quan, prof]).reshape(1, 12)
            newwData = pd.DataFrame(newwData, columns = ['mode', 'mi', 'ho', 'da', 'we', 'mo', 'ye', 'tick', 'laBu', 'laSe', 'quan', 'prof'])

            # READ PREVIOUSLY SAVED DATA AS PANDAS DATAFRAME AND APPEND NEW DATA
            readData = pd.read_hdf('ledger/ledger.h5', mode = 'r')
            readData = readData.append(newwData)

            # SAVE ALL DATA INTO .H5 FORMAT
            HDF5Data = HDFStore('ledger/ledger.h5')
            HDF5Data.put('data', readData, format = 'table', data_columns = True)
            HDF5Data.close()

        else:
            print('Please check input data for errors!')



if __name__ == '__main__':
    maintainLedger(1, 'MSFT')

DataFrame append generates TypeError

1 Answers1