Merge pull request #1635 from ranaroussi/hotfix/prices-events-merge

Fix merging 1d-prices with out-of-range divs/splits

tests/prices.py

@@ -223,6 +223,15 @@ class TestPriceHistory(unittest.TestCase):
                 print("{}-without-events missing these dates: {}".format(tkr, missing_from_df2))
                 raise
 
+        # Reproduce issue #1634 - 1d dividend out-of-range, should be prepended to prices
+        div_dt = _pd.Timestamp(2022, 7, 21).tz_localize("America/New_York")
+        df_dividends = _pd.DataFrame(data={"Dividends":[1.0]}, index=[div_dt])
+        df_prices = _pd.DataFrame(data={c:[1.0] for c in yf.const.price_colnames}|{'Volume':0}, index=[div_dt+_dt.timedelta(days=1)])
+        df_merged = yf.utils.safe_merge_dfs(df_prices, df_dividends, '1d')
+        self.assertEqual(df_merged.shape[0], 2)
+        self.assertTrue(df_merged[df_prices.columns].iloc[1:].equals(df_prices))
+        self.assertEqual(df_merged.index[0], div_dt)
+
     def test_intraDayWithEvents(self):
         tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
         test_run = False

yfinance/const.py

@@ -6,3 +6,5 @@ fundamentals_keys['financials'] = ["TaxEffectOfUnusualItems","TaxRateForCalcs","
 fundamentals_keys['balance-sheet'] = ["TreasurySharesNumber","PreferredSharesNumber","OrdinarySharesNumber","ShareIssued","NetDebt","TotalDebt","TangibleBookValue","InvestedCapital","WorkingCapital","NetTangibleAssets","CapitalLeaseObligations","CommonStockEquity","PreferredStockEquity","TotalCapitalization","TotalEquityGrossMinorityInterest","MinorityInterest","StockholdersEquity","OtherEquityInterest","GainsLossesNotAffectingRetainedEarnings","OtherEquityAdjustments","FixedAssetsRevaluationReserve","ForeignCurrencyTranslationAdjustments","MinimumPensionLiabilities","UnrealizedGainLoss","TreasuryStock","RetainedEarnings","AdditionalPaidInCapital","CapitalStock","OtherCapitalStock","CommonStock","PreferredStock","TotalPartnershipCapital","GeneralPartnershipCapital","LimitedPartnershipCapital","TotalLiabilitiesNetMinorityInterest","TotalNonCurrentLiabilitiesNetMinorityInterest","OtherNonCurrentLiabilities","LiabilitiesHeldforSaleNonCurrent","RestrictedCommonStock","PreferredSecuritiesOutsideStockEquity","DerivativeProductLiabilities","EmployeeBenefits","NonCurrentPensionAndOtherPostretirementBenefitPlans","NonCurrentAccruedExpenses","DuetoRelatedPartiesNonCurrent","TradeandOtherPayablesNonCurrent","NonCurrentDeferredLiabilities","NonCurrentDeferredRevenue","NonCurrentDeferredTaxesLiabilities","LongTermDebtAndCapitalLeaseObligation","LongTermCapitalLeaseObligation","LongTermDebt","LongTermProvisions","CurrentLiabilities","OtherCurrentLiabilities","CurrentDeferredLiabilities","CurrentDeferredRevenue","CurrentDeferredTaxesLiabilities","CurrentDebtAndCapitalLeaseObligation","CurrentCapitalLeaseObligation","CurrentDebt","OtherCurrentBorrowings","LineOfCredit","CommercialPaper","CurrentNotesPayable","PensionandOtherPostRetirementBenefitPlansCurrent","CurrentProvisions","PayablesAndAccruedExpenses","CurrentAccruedExpenses","InterestPayable","Payables","OtherPayable","DuetoRelatedPartiesCurrent","DividendsPayable","TotalTaxPayable","IncomeTaxPayable","AccountsPayable","TotalAssets","TotalNonCurrentAssets","OtherNonCurrentAssets","DefinedPensionBenefit","NonCurrentPrepaidAssets","NonCurrentDeferredAssets","NonCurrentDeferredTaxesAssets","DuefromRelatedPartiesNonCurrent","NonCurrentNoteReceivables","NonCurrentAccountsReceivable","FinancialAssets","InvestmentsAndAdvances","OtherInvestments","InvestmentinFinancialAssets","HeldToMaturitySecurities","AvailableForSaleSecurities","FinancialAssetsDesignatedasFairValueThroughProfitorLossTotal","TradingSecurities","LongTermEquityInvestment","InvestmentsinJointVenturesatCost","InvestmentsInOtherVenturesUnderEquityMethod","InvestmentsinAssociatesatCost","InvestmentsinSubsidiariesatCost","InvestmentProperties","GoodwillAndOtherIntangibleAssets","OtherIntangibleAssets","Goodwill","NetPPE","AccumulatedDepreciation","GrossPPE","Leases","ConstructionInProgress","OtherProperties","MachineryFurnitureEquipment","BuildingsAndImprovements","LandAndImprovements","Properties","CurrentAssets","OtherCurrentAssets","HedgingAssetsCurrent","AssetsHeldForSaleCurrent","CurrentDeferredAssets","CurrentDeferredTaxesAssets","RestrictedCash","PrepaidAssets","Inventory","InventoriesAdjustmentsAllowances","OtherInventories","FinishedGoods","WorkInProcess","RawMaterials","Receivables","ReceivablesAdjustmentsAllowances","OtherReceivables","DuefromRelatedPartiesCurrent","TaxesReceivable","AccruedInterestReceivable","NotesReceivable","LoansReceivable","AccountsReceivable","AllowanceForDoubtfulAccountsReceivable","GrossAccountsReceivable","CashCashEquivalentsAndShortTermInvestments","OtherShortTermInvestments","CashAndCashEquivalents","CashEquivalents","CashFinancial"]
 
 fundamentals_keys['cash-flow'] = ["ForeignSales","DomesticSales","AdjustedGeographySegmentData","FreeCashFlow","RepurchaseOfCapitalStock","RepaymentOfDebt","IssuanceOfDebt","IssuanceOfCapitalStock","CapitalExpenditure","InterestPaidSupplementalData","IncomeTaxPaidSupplementalData","EndCashPosition","OtherCashAdjustmentOutsideChangeinCash","BeginningCashPosition","EffectOfExchangeRateChanges","ChangesInCash","OtherCashAdjustmentInsideChangeinCash","CashFlowFromDiscontinuedOperation","FinancingCashFlow","CashFromDiscontinuedFinancingActivities","CashFlowFromContinuingFinancingActivities","NetOtherFinancingCharges","InterestPaidCFF","ProceedsFromStockOptionExercised","CashDividendsPaid","PreferredStockDividendPaid","CommonStockDividendPaid","NetPreferredStockIssuance","PreferredStockPayments","PreferredStockIssuance","NetCommonStockIssuance","CommonStockPayments","CommonStockIssuance","NetIssuancePaymentsOfDebt","NetShortTermDebtIssuance","ShortTermDebtPayments","ShortTermDebtIssuance","NetLongTermDebtIssuance","LongTermDebtPayments","LongTermDebtIssuance","InvestingCashFlow","CashFromDiscontinuedInvestingActivities","CashFlowFromContinuingInvestingActivities","NetOtherInvestingChanges","InterestReceivedCFI","DividendsReceivedCFI","NetInvestmentPurchaseAndSale","SaleOfInvestment","PurchaseOfInvestment","NetInvestmentPropertiesPurchaseAndSale","SaleOfInvestmentProperties","PurchaseOfInvestmentProperties","NetBusinessPurchaseAndSale","SaleOfBusiness","PurchaseOfBusiness","NetIntangiblesPurchaseAndSale","SaleOfIntangibles","PurchaseOfIntangibles","NetPPEPurchaseAndSale","SaleOfPPE","PurchaseOfPPE","CapitalExpenditureReported","OperatingCashFlow","CashFromDiscontinuedOperatingActivities","CashFlowFromContinuingOperatingActivities","TaxesRefundPaid","InterestReceivedCFO","InterestPaidCFO","DividendReceivedCFO","DividendPaidCFO","ChangeInWorkingCapital","ChangeInOtherWorkingCapital","ChangeInOtherCurrentLiabilities","ChangeInOtherCurrentAssets","ChangeInPayablesAndAccruedExpense","ChangeInAccruedExpense","ChangeInInterestPayable","ChangeInPayable","ChangeInDividendPayable","ChangeInAccountPayable","ChangeInTaxPayable","ChangeInIncomeTaxPayable","ChangeInPrepaidAssets","ChangeInInventory","ChangeInReceivables","ChangesInAccountReceivables","OtherNonCashItems","ExcessTaxBenefitFromStockBasedCompensation","StockBasedCompensation","UnrealizedGainLossOnInvestmentSecurities","ProvisionandWriteOffofAssets","AssetImpairmentCharge","AmortizationOfSecurities","DeferredTax","DeferredIncomeTax","DepreciationAmortizationDepletion","Depletion","DepreciationAndAmortization","AmortizationCashFlow","AmortizationOfIntangibles","Depreciation","OperatingGainsLosses","PensionAndEmployeeBenefitExpense","EarningsLossesFromEquityInvestments","GainLossOnInvestmentSecurities","NetForeignCurrencyExchangeGainLoss","GainLossOnSaleOfPPE","GainLossOnSaleOfBusiness","NetIncomeFromContinuingOperations","CashFlowsfromusedinOperatingActivitiesDirect","TaxesRefundPaidDirect","InterestReceivedDirect","InterestPaidDirect","DividendsReceivedDirect","DividendsPaidDirect","ClassesofCashPayments","OtherCashPaymentsfromOperatingActivities","PaymentsonBehalfofEmployees","PaymentstoSuppliersforGoodsandServices","ClassesofCashReceiptsfromOperatingActivities","OtherCashReceiptsfromOperatingActivities","ReceiptsfromGovernmentGrants","ReceiptsfromCustomers"]
+
+price_colnames = ['Open', 'High', 'Low', 'Close', 'Adj Close']

yfinance/utils.py

@@ -21,6 +21,8 @@
 
 from __future__ import print_function
 
+from yfinance import const
+
 import datetime as _datetime
 import dateutil as _dateutil
 from typing import Dict, Union, List, Optional
@@ -689,21 +691,28 @@ def safe_merge_dfs(df_main, df_sub, interval):
 
     f_outOfRange = indices == -1
     if f_outOfRange.any() and not intraday:
-        # If dividend is occuring in next interval after last price row, 
-        # add a new row of NaNs
-        last_dt = df_main.index[-1]
-        next_interval_start_dt = last_dt + td
+        empty_row_data = {c:[_np.nan] for c in const.price_colnames}|{'Volume':[0]}
         if interval == '1d':
-            # Allow for weekends & holidays
-            next_interval_end_dt = last_dt+7*_pd.Timedelta(days=7)
-        else:
-            next_interval_end_dt = next_interval_start_dt + td
-        for i in _np.where(f_outOfRange)[0]:
-            dt = df_sub.index[i]
-            if dt >= next_interval_start_dt and dt < next_interval_end_dt:
-                new_dt = dt if interval == '1d' else next_interval_start_dt
+            # For 1d, add all out-of-range event dates
+            for i in _np.where(f_outOfRange)[0]:
+                dt = df_sub.index[i]
                 get_yf_logger().debug(f"Adding out-of-range {data_col} @ {dt.date()} in new prices row of NaNs")
-                df_main.loc[new_dt] = _np.nan
+                empty_row = _pd.DataFrame(data=empty_row_data, index=[dt])
+                df_main = _pd.concat([df_main, empty_row], sort=True)
+        else:
+            # Else, only add out-of-range event dates if occurring in interval 
+            # immediately after last pricfe row
+            last_dt = df_main.index[-1]
+            next_interval_start_dt = last_dt + td
+            next_interval_end_dt = next_interval_start_dt + td
+            for i in _np.where(f_outOfRange)[0]:
+                dt = df_sub.index[i]
+                if dt >= next_interval_start_dt and dt < next_interval_end_dt:
+                    new_dt = next_interval_start_dt
+                    get_yf_logger().debug(f"Adding out-of-range {data_col} @ {dt.date()} in new prices row of NaNs")
+                    empty_row = _pd.DataFrame(data=empty_row_data, index=[dt])
+                    df_main = _pd.concat([df_main, empty_row], sort=True)
+        df_main = df_main.sort_index()
 
         # Re-calculate indices
         indices = _np.searchsorted(_np.append(df_main.index, df_main.index[-1]+td), df_sub.index, side='right')
@@ -718,7 +727,7 @@ def safe_merge_dfs(df_main, df_sub, interval):
     f_outOfRange = indices == -1
     if f_outOfRange.any():
         if intraday or interval in ['1d', '1wk']:
-            raise Exception(f"The following '{data_col}' events are out-of-range, did not expect with interval {interval}: {df_sub.index}")
+            raise Exception(f"The following '{data_col}' events are out-of-range, did not expect with interval {interval}: {df_sub.index[f_outOfRange]}")
         get_yf_logger().debug(f'Discarding these {data_col} events:' + '\n' + str(df_sub[f_outOfRange]))
         df_sub = df_sub[~f_outOfRange].copy()
         indices = indices[~f_outOfRange]