PYield 0.26.5__tar.gz → 0.26.7__tar.gz

{pyield-0.26.5 → pyield-0.26.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PYield
-Version: 0.26.5
+Version: 0.26.7
 Summary: A Python library for analysis of fixed income instruments in Brazil
 Project-URL: Source, https://github.com/crdcj/PYield
 Author-email: Carlos Carvalho <cr.cj@outlook.com>

pyield-0.26.7/pyield/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.26.7"

pyield-0.26.7/pyield/ima.py

@@ -0,0 +1,156 @@
+import io
+import logging
+from typing import Literal
+
+import pandas as pd
+import requests
+
+ima_types = Literal[
+    "IRF-M 1",
+    "IRF-M 1+",
+    "IRF-M",
+    "IMA-B 5",
+    "IMA-B 5+",
+    "IMA-B",
+    "IMA-S",
+    "IMA-GERAL-EX-C",
+    "IMA-GERAL",
+]
+
+LAST_IMA_COL_MAPPING = {
+    # "2",
+    "Data de Referência": "Date",
+    "INDICE": "IMAType",
+    "Títulos": "BondType",
+    "Data de Vencimento": "Maturity",
+    "Código SELIC": "SelicCode",
+    "Código ISIN": "ISIN",
+    "Taxa Indicativa (% a.a.)": "IndicativeRate",
+    "PU (R$)": "Price",
+    # "PU de Juros (R$)": "InterestPrice",
+    "Quantidade (1.000 títulos)": "MarketQuantity",
+    "Quantidade Teórica (1.000 títulos)": "TheoreticalQuantity",
+    "Carteira a Mercado (R$ mil)": "MarketValue",
+    "Peso (%)": "Weight",
+    "Prazo (d.u.)": "BDToMat",
+    "Duration (d.u.)": "Duration",
+    # "Número de Operações *": "NumberOfOperations",
+    # "Quant. Negociada (1.000 títulos) *": "NegotiatedQuantity",
+    # "Valor Negociado (R$ mil) *": "NegotiatedValue",
+    "PMR": "PMR",  # Prazmo médio de repactuação
+    "Convexidade": "Convexity",
+}
+
+
+LAST_IMA_URL = "https://www.anbima.com.br/informacoes/ima/arqs/ima_completo.txt"
+
+
+def _fetch_last_ima() -> pd.DataFrame:
+    r = requests.get(LAST_IMA_URL)
+    r.raise_for_status()
+    r.encoding = "latin1"
+    text = r.text.split("2@COMPOSIÇÃO DE CARTEIRA")[1].strip()
+    string_io_buffer = io.StringIO(text)
+
+    df = pd.read_csv(
+        string_io_buffer,
+        sep="@",
+        decimal=",",
+        thousands=".",
+        dtype_backend="numpy_nullable",
+    )
+
+    return df
+
+
+def _process_last_ima(df: pd.DataFrame) -> pd.DataFrame:
+    df = df.rename(columns=LAST_IMA_COL_MAPPING)[LAST_IMA_COL_MAPPING.values()]
+    df["IndicativeRate"] = (df["IndicativeRate"] / 100).round(6)
+    df["Date"] = pd.to_datetime(df["Date"], format="%d/%m/%Y")
+    df["Maturity"] = pd.to_datetime(df["Maturity"], format="%d/%m/%Y")
+    df["MarketQuantity"] = (1000 * df["MarketQuantity"]).astype("Int64")
+    df["Price"] = df["Price"].round(6)
+    # Duration is in business days, convert to years
+    df["Duration"] /= 252
+    mduration = df["Duration"] / (1 + df["IndicativeRate"])
+    dv01 = 0.0001 * df["Price"] * mduration * df["MarketQuantity"]
+    # Since DV01 and MarketValue are total stock values, we round them to integers
+    df["MarketDV01"] = dv01.round(0).astype("Int64")
+    df["MarketValue"] = (1000 * df["MarketValue"]).round(0).astype("Int64")
+    # LFT DV01 is zero
+    df["MarketDV01"] = df["MarketDV01"].where(df["BondType"] != "LFT", 0)
+    return df
+
+
+def _reorder_last_ima(df: pd.DataFrame) -> pd.DataFrame:
+    col_order = [
+        "Date",
+        "IMAType",
+        "BondType",
+        "Maturity",
+        "SelicCode",
+        "ISIN",
+        "Weight",
+        "IndicativeRate",
+        "Price",
+        "BDToMat",
+        "Duration",
+        "PMR",
+        "Convexity",
+        "TheoreticalQuantity",
+        "MarketDV01",
+        "MarketQuantity",
+        "MarketValue",
+    ]
+    return df[col_order].reset_index(drop=True)
+
+
+def ima(ima_type: ima_types | None = None) -> pd.DataFrame:
+    """
+    Fetch and process the last IMA market data available from ANBIMA.
+
+    This function processes the data into a structured DataFrame.
+    It handles conversion of date formats, renames columns to English, and converts
+    certain numeric columns to integer types. In the event of an error during data
+    fetching or processing, an empty DataFrame is returned.
+
+    Args:
+        ima_type (str, optional): Type of IMA index to filter the data. If None, all
+            IMA indexes are returned. Defaults to None.
+
+    Returns:
+        pd.DataFrame: A DataFrame containing the IMA data with the following columns:
+            - Date: Reference date of the data.
+            - Index: IMA index.
+            - BondType: Type of bond.
+            - Maturity: Bond maturity date.
+            - SelicCode: Code representing the SELIC rate.
+            - ISIN: International Securities Identification Number.
+            - Price: Bond price.
+            - Weight: Weight of the bond in the index.
+            - BDToMat: Business days to maturity.
+            - Duration: Duration of the bond in years.
+            - PMR: Average repurchase term.
+            - Convexity: Convexity of the bond.
+            - TheoreticalQuantity: Theoretical quantity.
+            - MarketDV01: Market DV01 in R$.
+            - MarketQuantity: Market quantity.
+            - MarketValue: Market value in R$.
+
+
+    Raises:
+        Exception: Logs error and returns an empty DataFrame if any error occurs during
+            fetching or processing.
+
+    """
+    try:
+        df = _fetch_last_ima()
+        df = _process_last_ima(df)
+        df = _reorder_last_ima(df)
+        if ima_type is not None:
+            df = df.query("IMAType == @ima_type").reset_index(drop=True)
+        df = df.sort_values(["IMAType", "BondType", "Maturity"]).reset_index(drop=True)
+        return df
+    except Exception as e:
+        logging.exception(f"Error fetching or processing the last IMA data: {e}")
+        return pd.DataFrame()

pyield-0.26.5/pyield/__about__.py

@@ -1 +0,0 @@
-__version__ = "0.26.5"

pyield-0.26.5/pyield/ima.py

@@ -1,143 +0,0 @@
-import io
-import logging
-import re
-import warnings
-
-import pandas as pd
-import requests
-from bs4 import XMLParsedAsHTMLWarning
-
-from pyield import date_converter as dc
-from pyield.date_converter import DateScalar
-
-IMA_URL = "https://www.anbima.com.br/informacoes/ima/ima-quantidade-mercado.asp"
-COLUMN_MAPPING = {
-    "Data Referência": "Date",
-    "Título": "BondType",
-    "Data de Vencimento": "Maturity",
-    "Codigo Selic": "SelicCode",
-    "Código ISIN": "ISIN",
-    "PU (R$)": "Price",
-    "Quantidade em Mercado (1.000 Títulos)": "MarketQuantity",
-    "Valor de Mercado (R$ Mil)": "MarketValue",
-    "Variação da Quantidade (1.000 Títulos)": "QuantityVariation",
-    "Status do Titulo": "BondStatus",
-}
-
-
-def _fetch_url_tables(target_date: pd.Timestamp) -> pd.DataFrame:
-    # Warning supression for BeautifulSoup, as the text is valid HTML and not XML
-    warnings.filterwarnings("ignore", category=XMLParsedAsHTMLWarning)
-
-    target_date_str = target_date.strftime("%d/%m/%Y")
-    payload = {
-        "Tipo": "",
-        "DataRef": "",
-        "Pai": "ima",
-        "Dt_Ref_Ver": "20250117",
-        "Dt_Ref": f"{target_date_str}",
-    }
-
-    r = requests.post(IMA_URL, data=payload, timeout=10)
-    r.raise_for_status()
-    r.encoding = "iso-8859-1"
-    if "Não há dados disponíveis" in r.text:
-        logging.warning("No data found. Returning empty DataFrame.")
-        return pd.DataFrame()
-
-    string_io_buffer = io.StringIO(r.text)
-
-    dfs = pd.read_html(
-        string_io_buffer,
-        flavor="html5lib",
-        attrs={"width": "100%"},
-        header=0,
-        thousands=".",
-        decimal=",",
-        displayed_only=True,
-        dtype_backend="numpy_nullable",
-    )
-
-    df = (
-        pd.concat(dfs)
-        .query("`Data de Vencimento`.notnull()")
-        .query("Título!='Título'")
-        .drop_duplicates(subset="Código ISIN")
-        .reset_index(drop=True)
-    )
-
-    # Convert to CSV and then back to pandas to get automatic type conversion
-    csv_buffer = io.StringIO(df.to_csv(index=False))
-    df = pd.read_csv(csv_buffer, dtype_backend="numpy_nullable")
-
-    # Expressão regular para datas no formato dd/mm/ano
-    date_pattern = r"\b(\d{2}/\d{2}/\d{4})\b"
-
-    # Busca pela primeira data
-    match = re.search(date_pattern, r.text)
-
-    if match:
-        anbima_date_str = match.group(1)
-        anbima_date = pd.to_datetime(anbima_date_str, format="%d/%m/%Y")
-    else:
-        logging.warning("No date found. Returning empty DataFrame.")
-        return pd.DataFrame()
-
-    df["Data Referência"] = anbima_date
-
-    return df
-
-
-def _process_df(df: pd.DataFrame) -> pd.DataFrame:
-    df = df.rename(columns=COLUMN_MAPPING)[COLUMN_MAPPING.values()]
-    df["Maturity"] = pd.to_datetime(df["Maturity"], format="%d/%m/%Y")
-    # Converter a valores para inteiros
-    df["MarketQuantity"] = (1000 * df["MarketQuantity"]).astype("Int64")
-    df["MarketValue"] = (1000 * df["MarketValue"]).astype("Int64")
-    df["QuantityVariation"] = (1000 * df["QuantityVariation"]).astype("Int64")
-
-    return df
-
-
-def ima(date: DateScalar) -> pd.DataFrame:
-    """
-    Fetch and process IMA market data for a given date.
-
-    This function retrieves IMA market data for the specified date from ANBIMA,
-    processes the data into a structured DataFrame, and returns the resulting DataFrame.
-    It handles conversion of date formats, renames columns to English, and converts
-    certain numeric columns to integer types. In the event of an error during data
-    fetching or processing, an empty DataFrame is returned.
-
-    Args:
-        date (DateScalar): A date-like object representing the target date for fetching
-            the data.
-
-    Returns:
-        pd.DataFrame: A DataFrame containing the IMA data with the following columns:
-            - Date: Reference date of the data.
-            - BondType: Type of bond.
-            - Maturity: Bond maturity date.
-            - SelicCode: Code representing the SELIC rate.
-            - ISIN: International Securities Identification Number.
-            - Price: Bond price.
-            - MarketQuantity: Market quantity (in units of 1000 bonds).
-            - MarketValue: Market value (in units of 1000 reais).
-            - QuantityVariation: Variation in quantity (in units of 1000 bonds).
-            - BondStatus: Status of the bond.
-
-    Raises:
-        Exception: Logs error and returns an empty DataFrame if any error occurs during
-            fetching or processing.
-
-    """
-    try:
-        date = dc.convert_input_dates(date)
-        df = _fetch_url_tables(date)
-        df = _process_df(df)
-        return df
-    except Exception as e:
-        date_str = date.strftime("%d/%m/%Y")
-        logging.error(f"Error fetching IMA for {date_str}. Returning empty DataFrame.")
-        logging.error(f"Error message: {e}", exc_info=True)
-        return pd.DataFrame()