PYield 0.8.1__tar.gz → 0.8.2__tar.gz

{pyield-0.8.1 → pyield-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PYield
-Version: 0.8.1
+Version: 0.8.2
 Summary: A Python library for analysis of fixed income instruments in Brazil
 Keywords: fixed-income, brazil, finance, analysis, bonds
 Author-Email: Carlos Carvalho <cr.cj@outlook.com>

pyield-0.8.2/pyield/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.8.2"

{pyield-0.8.1 → pyield-0.8.2}/pyield/futures/historical.py

@@ -119,7 +119,7 @@ def fetch_raw_df(asset_code: str, trade_date: pd.Timestamp) -> pd.DataFrame:
     url_date = trade_date.strftime("%d/%m/%Y")
     # url example: https://www2.bmf.com.br/pages/portal/bmfbovespa/boletim1/SistemaPregao_excel1.asp?Data=05/10/2023&Mercadoria=DI1
     url = f"https://www2.bmf.com.br/pages/portal/bmfbovespa/boletim1/SistemaPregao_excel1.asp?Data={url_date}&Mercadoria={asset_code}&XLS=false"
-    r = requests.get(url)
+    r = requests.get(url, timeout=10)
 
     text = r.text
     if "VENCTO" not in text:

{pyield-0.8.1 → pyield-0.8.2}/pyield/futures/intraday.py

@@ -1,10 +1,20 @@
+from io import StringIO
+
 import pandas as pd
 import requests
 
 from .. import bday
 
 
-def _fetch_raw_df(future_code: str) -> pd.DataFrame:
+# Função para salvar DataFrame em CSV e ler com read_csv
+def convert_with_read_csv(df):
+    buffer = StringIO()
+    df.to_csv(buffer, index=False)
+    buffer.seek(0)  # Reposiciona o cursor no início do buffer
+    return pd.read_csv(buffer, dtype_backend="numpy_nullable")
+
+
+def _fetch_b3_df(future_code: str) -> pd.DataFrame:
     """
     Fetch the latest data for a given future code from B3 derivatives quotation API.
 
@@ -34,34 +44,8 @@ def _fetch_raw_df(future_code: str) -> pd.DataFrame:
     # Normalize JSON response into a flat table
     df = pd.json_normalize(r.json()["Scty"])
 
-    # Clean and reformat the DataFrame columns
-    df.columns = (df.columns
-        .str.replace("SctyQtn.", "")
-        .str.replace("asset.AsstSummry.", "")
-    )  # fmt: skip
-    df.drop(columns=["desc", "asset.code", "mkt.cd"], inplace=True)
-
-    # Convert maturity codes to datetime and drop rows with missing values
-    df["mtrtyCode"] = pd.to_datetime(df["mtrtyCode"], errors="coerce")
-    df.dropna(subset=["mtrtyCode"], inplace=True)
-
-    # Sort the DataFrame by maturity code and reset the index
-    df.sort_values("mtrtyCode", inplace=True, ignore_index=True)
-
-    # Get currante date
-    today = pd.Timestamp.now().normalize()
-    df["TradeDate"] = today
-
-    # Get current date and time
-    now = pd.Timestamp.now().round("s")
-    # Subtract 15 minutes from the current time to account for API delay
-    trade_ts = now - pd.Timedelta(minutes=15)
-    df["TradeTime"] = trade_ts
-
     # Convert DataFrame to use nullable data types for better type consistency
-    df = df.convert_dtypes(dtype_backend="numpy_nullable")
-
-    return df
+    return convert_with_read_csv(df)
 
 
 def _rename_columns(df: pd.DataFrame) -> pd.DataFrame:
@@ -101,6 +85,32 @@ def _rename_columns(df: pd.DataFrame) -> pd.DataFrame:
 def _process_df(raw_df: pd.DataFrame) -> pd.DataFrame:
     df = raw_df.copy()
 
+    # Clean and reformat the DataFrame columns
+    df.columns = (df.columns
+        .str.replace("SctyQtn.", "")
+        .str.replace("asset.AsstSummry.", "")
+    )  # fmt: skip
+    df.drop(columns=["desc", "asset.code", "mkt.cd"], inplace=True)
+
+    df = _rename_columns(df)
+
+    # Convert maturity codes to datetime and drop rows with missing values
+    df["ExpirationDate"] = pd.to_datetime(df["ExpirationDate"], errors="coerce")
+    df.dropna(subset=["ExpirationDate"], inplace=True)
+
+    # Sort the DataFrame by maturity code and reset the index
+    df.sort_values("ExpirationDate", inplace=True, ignore_index=True)
+
+    # Get currante date
+    today = pd.Timestamp.now().normalize()
+    df["TradeDate"] = today
+
+    # Get current date and time
+    now = pd.Timestamp.now().round("s")
+    # Subtract 15 minutes from the current time to account for API delay
+    trade_ts = now - pd.Timedelta(minutes=15)
+    df["TradeTime"] = trade_ts
+
     df["BDaysToExp"] = bday.count_bdays(df["TradeDate"], df["ExpirationDate"])
 
     df["DaysToExp"] = (df["ExpirationDate"] - df["TradeDate"]).dt.days
@@ -156,10 +166,9 @@ def fetch_intraday_df(future_code: str) -> pd.DataFrame:
     Returns:
         pd.DataFrame: A Pandas pd.DataFrame containing the latest DI futures data.
     """
-    raw_df = _fetch_raw_df(future_code)
+    raw_df = _fetch_b3_df(future_code)
     if raw_df.empty:
         return raw_df
-    df = _rename_columns(raw_df)
-    df = _process_df(df)
+    df = _process_df(raw_df)
     df = _select_and_reorder_columns(df)
     return df

{pyield-0.8.1 → pyield-0.8.2}/pyield/futures/xml.py

@@ -43,7 +43,7 @@ def _get_file_from_url(trade_date: pd.Timestamp, source_type: str) -> io.BytesIO
     else:
         raise ValueError("Invalid source type. Must be either 'PR' or 'SPR'.")
 
-    response = requests.get(url)
+    response = requests.get(url, timeout=10)
 
     # File will be considered invalid if it is too small
     if response.status_code != 200 or len(response.content) < 1024:
@@ -74,9 +74,15 @@ def _extract_xml_from_zip(zip_file: io.BytesIO) -> io.BytesIO:
 
 def _extract_data_from_xml(xml_file: io.BytesIO, asset_code: str) -> list[dict]:
     parser = etree.XMLParser(
-        ns_clean=True, remove_blank_text=True, remove_comments=True, recover=True
+        ns_clean=True,
+        remove_blank_text=True,
+        remove_comments=True,
+        recover=True,
+        resolve_entities=False,
+        no_network=True,
+        load_dtd=False,  # Disable DTD loading
     )
-    tree = etree.parse(xml_file, parser)
+    tree = etree.parse(xml_file, parser=parser)
 
     # XPath para encontrar elementos cujo texto começa com código do ativo: DI1, FRC...
     namespaces = {"ns": "urn:bvmf.217.01.xsd"}

{pyield-0.8.1 → pyield-0.8.2}/pyield/ntnb.py

@@ -302,7 +302,7 @@ def _get_nir_df(reference_date: pd.Timestamp) -> pd.DataFrame:
     """
     df = da.fetch_asset(asset_code="DI1", reference_date=reference_date)
     if "CurrentRate" in df.columns:
-        df = df.rename(columns={"CurrentRate": "NIR"})
+        df = df.rename(columns={"CurrentRate": "NSR_DI"})
         keep_cols = [
             "TradeDate",
             "TradeTime",
@@ -311,15 +311,21 @@ def _get_nir_df(reference_date: pd.Timestamp) -> pd.DataFrame:
             "BDaysToExp",
             "CurrentAskRate",
             "CurrentBidRate",
-            "NIR",
+            "NSR_DI",
         ]
     elif "SettlementRate" in df.columns:
-        df = df.rename(columns={"SettlementRate": "NIR"})
-        keep_cols = ["TradeDate", "TickerSymbol", "ExpirationDate", "BDaysToExp", "NIR"]
+        df = df.rename(columns={"SettlementRate": "NSR_DI"})
+        keep_cols = [
+            "TradeDate",
+            "TickerSymbol",
+            "ExpirationDate",
+            "BDaysToExp",
+            "NSR_DI",
+        ]
     else:
         raise ValueError("NIR data not found in the DataFrame.")
 
-    df = df[keep_cols].dropna(subset=["NIR"])
+    df = df[keep_cols].dropna(subset=["NSR_DI"])
 
     # Add DI spreads for prefixed bonds (LTN) and adjust NIR
     today = pd.Timestamp.today().normalize()
@@ -334,7 +340,7 @@ def _get_nir_df(reference_date: pd.Timestamp) -> pd.DataFrame:
     df_pre.drop(columns=["BondType"], inplace=True)
 
     df = pd.merge_asof(df, df_pre, left_on="ExpirationDate", right_on="MaturityDate")
-    df["NIRAdj"] = df["NIR"] + df["DISpread"]
+    df["NSR_PRE"] = df["NSR_DI"] + df["DISpread"]
 
     return df
 
@@ -346,46 +352,57 @@ def breakeven_inflation(
     ytm_rates: pd.Series,
 ) -> pd.DataFrame:
     """
-    Calculate the Breakeven Inflation (BEI) for NTN-B bonds based on nominal and real
+    Calculate the Breakeven Inflation (INF) for NTN-B bonds based on nominal and real
     interest rates.
 
     Args:
-        reference_date (str | pd.Timestamp): The reference date for fetching data and
-            calculations.
-        settlement_date (str | pd.Timestamp): The settlement date for the bonds.
-        maturity_dates (pd.Series): Series of maturity dates for the bonds.
-        ytm_rates (pd.Series): Series of Yield to Maturity (YTM) rates corresponding to
-            the maturity dates.
+        reference_date (str or pd.Timestamp): The reference date for fetching data and
+            performing calculations.
+        settlement_date (str or pd.Timestamp): The settlement date for the bonds.
+        maturity_dates (pd.Series): A series of maturity dates for the bonds.
+        ytm_rates (pd.Series): A series of Yield to Maturity (YTM) rates corresponding
+            to the maturity dates.
 
     Returns:
-        pd.DataFrame: DataFrame containing the maturity dates, real interest rates
-            (RIR), nominal interest rates (NIR) and breakeven inflation rates (BEI).
+        pd.DataFrame: DataFrame containing the maturity dates, business days to maturity
+            (BDays), Yield to Maturity (YTM), real spot rates (RSR), nominal spot rates
+            (NSR_DI and NSR_PRE), and breakeven inflation rates (INF_DI and INF_PRE).
     """
     # Normalize input dates
     reference_date = dv.normalize_date(reference_date)
     settlement_date = dv.normalize_date(settlement_date)
 
-    # Fetch Nominal Interest Rate (NIR) data
+    # Fetch Nominal Spot Rate (NSR) data
     df_nir = _get_nir_df(reference_date)
     known_bdays = df_nir["BDaysToExp"].to_list()
-    known_rates = df_nir["NIR"].to_list()
+    known_rates = df_nir["NSR_DI"].to_list()
 
-    # Calculate Real Interest Rate (RIR)
+    # Calculate Real Spot Rate (RSR)
     df_rir = spot_rates(settlement_date, maturity_dates, ytm_rates)
-    df_rir = df_rir.rename(columns={"SpotRate": "RIR"})
+    df_rir = df_rir.rename(columns={"SpotRate": "RSR"})
     df_rir["BDays"] = bday.count_bdays(reference_date, df_rir["MaturityDate"])
-    df_rir["NIR"] = df_rir["BDays"].apply(
+    df_rir["NSR_DI"] = df_rir["BDays"].apply(
         lambda x: ip.find_and_interpolate_flat_forward(x, known_bdays, known_rates)
     )
 
-    # Calculate Breakeven Inflation (BEI)
-    df_rir["BEI"] = ((df_rir["NIR"] + 1) / (df_rir["RIR"] + 1)) - 1
+    # Calculate Breakeven Inflation (INF)
+    df_rir["INF_DI"] = ((df_rir["NSR_DI"] + 1) / (df_rir["RSR"] + 1)) - 1
 
     # Adjust BEI for DI spread in prefixed bonds
-    known_rates = df_nir["NIRAdj"].to_list()
-    df_rir["NIRAdj"] = df_rir["BDays"].apply(
+    known_rates = df_nir["NSR_PRE"].to_list()
+    df_rir["NSR_PRE"] = df_rir["BDays"].apply(
         lambda x: ip.find_and_interpolate_flat_forward(x, known_bdays, known_rates)
     )
-    df_rir["BEIAdj"] = ((df_rir["NIRAdj"] + 1) / (df_rir["RIR"] + 1)) - 1
-
-    return df_rir.drop(columns=["BDays", "NIR", "NIRAdj"])
+    df_rir["INF_PRE"] = ((df_rir["NSR_PRE"] + 1) / (df_rir["RSR"] + 1)) - 1
+
+    order_cols = [
+        "MaturityDate",
+        "BDays",
+        "YTM",
+        "RSR",
+        "NSR_DI",
+        "NSR_PRE",
+        "INF_DI",
+        "INF_PRE",
+    ]
+    return df_rir[order_cols].copy()

{pyield-0.8.1 → pyield-0.8.2}/pyield/projections.py

@@ -54,7 +54,7 @@ def fetch_current_month_ipca_projection() -> IndicatorProjection:
     """
     # Define the URL and get the data
     url = "https://www.anbima.com.br/informacoes/indicadores/arqs/indicadores.xls"
-    response = requests.get(url)
+    response = requests.get(url, timeout=10)
     excel_data = io.BytesIO(response.content)
 
     # Load the workbook and select the first sheet

{pyield-0.8.1 → pyield-0.8.2}/pyproject.toml

@@ -32,7 +32,7 @@ dependencies = [
     "requests>=2.31.0",
 ]
 dynamic = []
-version = "0.8.1"
+version = "0.8.2"
 
 [project.license]
 file = "LICENSE"

pyield-0.8.1/pyield/__about__.py

@@ -1 +0,0 @@
-__version__ = "0.8.1"