购买ram以避免3050gbplus文件的分块

def txttohdf(path, contract): #create dataframes for trade and quote dftrade = pd.DataFrame(columns = ["datetime", "Price", "Volume"]) dfquote = pd.DataFrame(columns = ["datetime", "BidPrice", "BidSize","AskPrice", "AskSize"]) #create an hdf5 file with high compression and table so we can append hdf = pd.HDFStore(path + contract + '.h5', complevel=9, complib='blosc') hdf.put('trade', dftrade, format='table', data_columns=True) hdf.put('quote', dfquote, format='table', data_columns=True) #date1 = date(start).strftime('%Y%m%d') #date2 = date(end).strftime('%Y%m%d') #dd = [date1 + timedelta(days=x) for x in range((date2-date1).days + 1)] #walkthrough directories for subdir, dir, files in os.walk(path): for file in files: #check if contract has name #print(file) #create filename from directory and file filename = os.path.join(subdir, file) #read in csv if filename.endswith('.gz'): df = pd.read_csv(gzip.open(filename),header=0,iterator=True,chunksize = 10000, low_memory =False, names = ['RIC','Date','Time','GMTOffset','Type','ExCntrbID','LOC','Price','Volume','MarketVWAP','BuyerID','BidPrice','BidSize','NoBuyers','SellerID','AskPrice','AskSize','NoSellers','Qualifiers','SeqNo','ExchTime','BlockTrd','FloorTrd','PERatio','Yield','NewPrice','NewVol','NewSeqNo','BidYld','AskYld','ISMABidYld','ISMAAskYld','Duration','ModDurtn','BPV','AccInt','Convexity','BenchSpd','SwpSpd','AsstSwpSpd','SwapPoint','BasePrice','UpLimPrice','LoLimPrice','TheoPrice','StockPrice','ConvParity','Premium','BidImpVol','AskImpVol','ImpVol','PrimAct','SecAct','GenVal1','GenVal2','GenVal3','GenVal4','GenVal5','Crack','Top','FreightPr','1MnPft','3MnPft','PrYrPft','1YrPft','3YrPft','5YrPft','10YrPft','Repurch','Offer','Kest','CapGain','Actual','Prior','Revised','Forecast','FrcstHigh','FrcstLow','NoFrcts','TrdQteDate','QuoteTime','BidTic','TickDir','DivCode','AdjClose','PrcTTEFlag','IrgTTEFlag','PrcSubMktId','IrgSubMktId','FinStatus','DivExDate','DivPayDate','DivAmt','Open','High','Low','Last','OpenYld','HighYld','LowYld','ShortPrice','ShortVol','ShortTrdVol','ShortTurnnover','ShortWeighting','ShortLimit','AccVolume','Turnover','ImputedCls','ChangeType','OldValue','NewValue','Volatility','Strike','Premium','AucPrice','Auc Vol','MidPrice','FinEvalPrice','ProvEvalPrice','AdvancingIssues','DecliningIssues','UnchangedIssues','TotalIssues','AdvancingVolume','DecliningVolume','UnchangedVolume','TotalVolume','NewHighs','NewLows','TotalMoves','PercentageChange','AdvancingMoves','DecliningMoves','UnchangedMoves','StrongMarket','WeakMarket','ChangedMarket','MarketVolatility','OriginalDate','LoanAskVolume','LoanAskAmountTradingPrice','PercentageShortVolumeTradedVolume','PercentageShortPriceTradedPrice','ForecastNAV','PreviousDaysNAV','FinalNAV','30DayATMIVCall','60DayATMIVCall','90DayATMIVCall','30DayATMIVPut','60DayATMIVPut','90DayATMIVPut','BackgroundReference','DataSource','BidSpread','AskSpread','ContractPhysicalUnits','Miniumumquantity','NumberPhysicals','ClosingReferencePrice','ImbalanceQuantity','FarClearingPrice','NearClearingPrice','OptionAdjustedSpread','ZSpread','ConvexityPremium','ConvexityRatio','PercentageDailyReturn','InterpolatedCDSBasis','InterpolatedCDSSpread','ClosesttoMaturityCDSBasis','SettlementDate','EquityPrice','Parity','CreditSpread','Delta','InputVolatility','ImpliedVolatility','FairPrice','BondFloor','Edge','YTW','YTB','SimpleMargin','DiscountMargin','12MonthsEPS','UpperTradingLimit','LowerTradingLimit','AmountOutstanding','IssuePrice','GSpread','MiscValue','MiscValueDescription']) #parse date time this is quicker than doing it while we read it in for chunk in df: chunk['datetime'] = chunk.apply(lambda row: datetime.datetime.strptime(row['Date']+ ':' + row['Time'],'%d-%b-%Y:%H:%M:%S.%f'), axis=1) #df = df[~df.comment.str.contains('ALIAS')] #drop uneeded columns inc date and time chunk = chunk.drop(['Date','Time','GMTOffset','ExCntrbID','LOC','MarketVWAP','BuyerID','NoBuyers','SellerID','NoSellers','Qualifiers','SeqNo','ExchTime','BlockTrd','FloorTrd','PERatio','Yield','NewPrice','NewVol','NewSeqNo','BidYld','AskYld','ISMABidYld','ISMAAskYld','Duration','ModDurtn','BPV','AccInt','Convexity','BenchSpd','SwpSpd','AsstSwpSpd','SwapPoint','BasePrice','UpLimPrice','LoLimPrice','TheoPrice','StockPrice','ConvParity','Premium','BidImpVol','AskImpVol','ImpVol','PrimAct','SecAct','GenVal1','GenVal2','GenVal3','GenVal4','GenVal5','Crack','Top','FreightPr','1MnPft','3MnPft','PrYrPft','1YrPft','3YrPft','5YrPft','10YrPft','Repurch','Offer','Kest','CapGain','Actual','Prior','Revised','Forecast','FrcstHigh','FrcstLow','NoFrcts','TrdQteDate','QuoteTime','BidTic','TickDir','DivCode','AdjClose','PrcTTEFlag','IrgTTEFlag','PrcSubMktId','IrgSubMktId','FinStatus','DivExDate','DivPayDate','DivAmt','Open','High','Low','Last','OpenYld','HighYld','LowYld','ShortPrice','ShortVol','ShortTrdVol','ShortTurnnover','ShortWeighting','ShortLimit','AccVolume','Turnover','ImputedCls','ChangeType','OldValue','NewValue','Volatility','Strike','Premium','AucPrice','Auc Vol','MidPrice','FinEvalPrice','ProvEvalPrice','AdvancingIssues','DecliningIssues','UnchangedIssues','TotalIssues','AdvancingVolume','DecliningVolume','UnchangedVolume','TotalVolume','NewHighs','NewLows','TotalMoves','PercentageChange','AdvancingMoves','DecliningMoves','UnchangedMoves','StrongMarket','WeakMarket','ChangedMarket','MarketVolatility','OriginalDate','LoanAskVolume','LoanAskAmountTradingPrice','PercentageShortVolumeTradedVolume','PercentageShortPriceTradedPrice','ForecastNAV','PreviousDaysNAV','FinalNAV','30DayATMIVCall','60DayATMIVCall','90DayATMIVCall','30DayATMIVPut','60DayATMIVPut','90DayATMIVPut','BackgroundReference','DataSource','BidSpread','AskSpread','ContractPhysicalUnits','Miniumumquantity','NumberPhysicals','ClosingReferencePrice','ImbalanceQuantity','FarClearingPrice','NearClearingPrice','OptionAdjustedSpread','ZSpread','ConvexityPremium','ConvexityRatio','PercentageDailyReturn','InterpolatedCDSBasis','InterpolatedCDSSpread','ClosesttoMaturityCDSBasis','SettlementDate','EquityPrice','Parity','CreditSpread','Delta','InputVolatility','ImpliedVolatility','FairPrice','BondFloor','Edge','YTW','YTB','SimpleMargin','DiscountMargin','12MonthsEPS','UpperTradingLimit','LowerTradingLimit','AmountOutstanding','IssuePrice','GSpread','MiscValue','MiscValueDescription'], axis=1) # convert to datetime explicitly and add nanoseconds to same time stamps chunk['datetime'] = pd.to_datetime(chunk.datetime) #nanoseconds = df.groupby(['datetime']).cumcount() #df['datetime'] += np.array(nanoseconds, dtype='m8[ns]') # drop empty prints and make sure all prices are valid dfRic = chunk[(chunk["RIC"] == contract)] if len(dfRic)>0: print(dfRic) if ~chunk.empty: dft = dfRic[(dfRic["Type"] == "Trade")] dft.dropna(subset = ["Volume"], inplace =True) dft = dft.drop(["RIC","Type","BidPrice", "BidSize", "AskPrice", "AskSize"], axis=1) dft = dft[(dft["Price"] > 0)] # clean up bid and ask dfq = dfRic[(dfRic["Type"] == "Quote")] dfq.dropna(how = 'all', subset = ["BidSize","AskSize"], inplace =True) dfq = dfq.drop(["RIC","Type","Price", "Volume"], axis=1) dfq = dfq[(dfq["BidSize"] > 0) | (dfq["AskSize"] > 0)] dfq = dfq.ffill() else: print("Empty") #add to hdf and close if loop finished hdf.append('trade', dft, format='table', data_columns=True) hdf.append('quote', dfq, format='table', data_columns=True) hdf.close()

1条回答

网友

1楼 · 发布于 2024-10-02 04:32:32

我认为你有很多东西可以优化：

首先，只读取您真正需要的列，而不是读取然后删除它们-使用usecols=list_of_needed_columns参数
增加你的chunksize-尝试不同的值-我会从10**5
不要使用chunk.apply(...)来转换日期时间-这是非常慢的pd.to\ U日期时间（列，格式=“…”）改为
在组合多个条件时，您可以更有效地过滤数据，而不是一步一步地进行：

相关问题更多 >

编程相关推荐

热门问题

热门文章