PYield 0.33.2__tar.gz → 0.34.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {pyield-0.33.2 → pyield-0.34.0}/PKG-INFO +1 -1
- pyield-0.34.0/pyield/__about__.py +1 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/__init__.py +4 -2
- pyield-0.34.0/pyield/bc/trades_intraday.py +219 -0
- pyield-0.33.2/pyield/bc/trade.py → pyield-0.34.0/pyield/bc/trades_monthly.py +19 -18
- {pyield-0.33.2 → pyield-0.34.0}/pyield/fwd.py +30 -13
- {pyield-0.33.2 → pyield-0.34.0}/pyield/interpolator.py +61 -20
- pyield-0.33.2/pyield/__about__.py +0 -1
- {pyield-0.33.2 → pyield-0.34.0}/.gitignore +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/LICENSE +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/README.md +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/ettj.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/ima.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/imaq.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/ipca.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/anbima/tpf.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/di_over.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/dif.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/futures/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/futures/common.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/futures/historical.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/futures/intraday.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/b3/futures/xml.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/auction.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/bcdata.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/ptax.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/repo.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bc/vna.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/bday.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/conftest.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/data_cache.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/date_converter.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/holidays/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/holidays/br_holidays_new.txt +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/holidays/br_holidays_old.txt +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/holidays/brholidays.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/ibge/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/ibge/ipca.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/py.typed +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/retry.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/__init__.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/lft.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/ltn.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/ntnb.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/ntnc.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/ntnf.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyield/tpf/tools.py +0 -0
- {pyield-0.33.2 → pyield-0.34.0}/pyproject.toml +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "0.34.0"
|
|
@@ -9,7 +9,8 @@ from pyield.bc.bcdata import (
|
|
|
9
9
|
)
|
|
10
10
|
from pyield.bc.ptax import ptax_series
|
|
11
11
|
from pyield.bc.repo import repos
|
|
12
|
-
from pyield.bc.
|
|
12
|
+
from pyield.bc.trades_intraday import fpd_intraday_trades
|
|
13
|
+
from pyield.bc.trades_monthly import fpd_monthly_trades
|
|
13
14
|
from pyield.bc.vna import vna_lft
|
|
14
15
|
|
|
15
16
|
__all__ = [
|
|
@@ -18,7 +19,8 @@ __all__ = [
|
|
|
18
19
|
"di_over_series",
|
|
19
20
|
"ptax_series",
|
|
20
21
|
"repos",
|
|
21
|
-
"
|
|
22
|
+
"fpd_monthly_trades",
|
|
23
|
+
"fpd_intraday_trades",
|
|
22
24
|
"selic_over",
|
|
23
25
|
"selic_over_series",
|
|
24
26
|
"selic_target",
|
|
@@ -0,0 +1,219 @@
|
|
|
1
|
+
import datetime as dt
|
|
2
|
+
import io
|
|
3
|
+
import logging
|
|
4
|
+
from pathlib import Path
|
|
5
|
+
from zoneinfo import ZoneInfo
|
|
6
|
+
|
|
7
|
+
import pandas as pd
|
|
8
|
+
import requests
|
|
9
|
+
|
|
10
|
+
from pyield import bday
|
|
11
|
+
|
|
12
|
+
BZ_TIMEZONE = ZoneInfo("America/Sao_Paulo")
|
|
13
|
+
REALTIME_START_TIME = dt.time(9, 0, 0)
|
|
14
|
+
REALTIME_END_TIME = dt.time(22, 0, 0)
|
|
15
|
+
|
|
16
|
+
logger = logging.getLogger(__name__)
|
|
17
|
+
test_file = Path(__file__).parent.parent.parent / "tests/data/negocios-registrados.csv"
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
def _fetch_csv_from_url() -> str:
|
|
21
|
+
FILE_URL = "https://www3.bcb.gov.br/novoselic/NegociosRegistradosDownload"
|
|
22
|
+
r = requests.get(FILE_URL, timeout=30) # API usually takes 10s to respond
|
|
23
|
+
r.raise_for_status()
|
|
24
|
+
r.encoding = "iso-8859-15"
|
|
25
|
+
return r.text
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
def _clean_csv(text: str) -> str:
|
|
29
|
+
"""Clean the CSV text data by removing unnecessary rows."""
|
|
30
|
+
rows = text.splitlines()
|
|
31
|
+
valid_rows = [row for row in rows if row.startswith("1;")]
|
|
32
|
+
return "\n".join(valid_rows)
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
def _convert_csv_to_df(text: str) -> pd.DataFrame:
|
|
36
|
+
return pd.read_csv(
|
|
37
|
+
io.StringIO(text),
|
|
38
|
+
sep=";",
|
|
39
|
+
decimal=",",
|
|
40
|
+
thousands=".",
|
|
41
|
+
dtype_backend="numpy_nullable",
|
|
42
|
+
header=None,
|
|
43
|
+
na_values="-",
|
|
44
|
+
)
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
def _process_df(df: pd.DataFrame) -> pd.DataFrame:
|
|
48
|
+
col_names_by_index = {
|
|
49
|
+
0: "RowType", # column indicating row type (filtered with "1")
|
|
50
|
+
1: "SelicCode", # código título
|
|
51
|
+
2: "MaturityDate", # data vencimento
|
|
52
|
+
3: "BondType", # sigla
|
|
53
|
+
4: "LastPrice", # pu último (mercado à vista)
|
|
54
|
+
5: "LastRate", # tx último (mercado à vista)
|
|
55
|
+
6: "MinPrice", # pu mínimo (mercado à vista)
|
|
56
|
+
7: "MinRate", # tx mínimo (mercado à vista)
|
|
57
|
+
8: "AvgPrice", # pu médio (mercado à vista)
|
|
58
|
+
9: "AvgRate", # tx médio (mercado à vista)
|
|
59
|
+
10: "MaxPrice", # pu máximo (mercado à vista)
|
|
60
|
+
11: "MaxRate", # tx máximo (mercado à vista)
|
|
61
|
+
12: "Trades", # totais liquidados operações (mercado à vista)
|
|
62
|
+
13: "BrokeredTrades", # corretagem liquidados operações (merc, à vista)
|
|
63
|
+
14: "Quantity", # títulos (mercado à vista)
|
|
64
|
+
15: "BrokeredQuantity", # corretagem títulos (mercado à vista)
|
|
65
|
+
16: "Volume", # financeiro (mercado à vista)
|
|
66
|
+
17: "ForwardLastPrice", # pu último (mercado a termo)
|
|
67
|
+
18: "ForwardLastRate", # tx último (mercado a termo)
|
|
68
|
+
19: "ForwardMinPrice", # pu mínimo (mercado a termo)
|
|
69
|
+
20: "ForwardMinRate", # tx mínimo (mercado a termo)
|
|
70
|
+
21: "ForwardAvgPrice", # pu médio (mercado a termo)
|
|
71
|
+
22: "ForwardAvgRate", # tx médio (mercado a termo)
|
|
72
|
+
23: "ForwardMaxPrice", # pu máximo (mercado a termo)
|
|
73
|
+
24: "ForwardMaxRate", # tx máximo (mercado a termo)
|
|
74
|
+
25: "ForwardTrades", # totais contratados operações (mercado a termo)
|
|
75
|
+
26: "ForwardBrokeredTrades", # corretagem contratados operações (merc. a termo)
|
|
76
|
+
27: "ForwardQuantity", # títulos (mercado a termo)
|
|
77
|
+
28: "ForwardBrokeredQuantity", # corretagem titulos (mercado a termo)
|
|
78
|
+
29: "ForwardVolume", # financeiro (mercado a termo)
|
|
79
|
+
}
|
|
80
|
+
df = df.rename(columns=col_names_by_index)
|
|
81
|
+
|
|
82
|
+
df["BondType"] = df["BondType"].str.strip()
|
|
83
|
+
df["MaturityDate"] = pd.to_datetime(df["MaturityDate"], format="%d-%m-%Y")
|
|
84
|
+
today = dt.datetime.now(BZ_TIMEZONE).date()
|
|
85
|
+
df["SettlementDate"] = pd.Timestamp(today)
|
|
86
|
+
|
|
87
|
+
# Remove percentage from rate columns
|
|
88
|
+
rate_cols = [col for col in df.columns if "Rate" in col]
|
|
89
|
+
for col in rate_cols:
|
|
90
|
+
df[col] = (df[col] / 100).round(6)
|
|
91
|
+
|
|
92
|
+
return df
|
|
93
|
+
|
|
94
|
+
|
|
95
|
+
def _reorder_columns(df: pd.DataFrame) -> pd.DataFrame:
|
|
96
|
+
reorder_columns = [
|
|
97
|
+
# "RowType",
|
|
98
|
+
"SettlementDate",
|
|
99
|
+
"BondType",
|
|
100
|
+
"SelicCode",
|
|
101
|
+
"MaturityDate",
|
|
102
|
+
"MinPrice",
|
|
103
|
+
"AvgPrice",
|
|
104
|
+
"MaxPrice",
|
|
105
|
+
"LastPrice",
|
|
106
|
+
"MinRate",
|
|
107
|
+
"AvgRate",
|
|
108
|
+
"MaxRate",
|
|
109
|
+
"LastRate",
|
|
110
|
+
"Trades",
|
|
111
|
+
"Quantity",
|
|
112
|
+
"Volume",
|
|
113
|
+
"BrokeredTrades",
|
|
114
|
+
"BrokeredQuantity",
|
|
115
|
+
"ForwardMinPrice",
|
|
116
|
+
"ForwardAvgPrice",
|
|
117
|
+
"ForwardLastPrice",
|
|
118
|
+
"ForwardMaxPrice",
|
|
119
|
+
"ForwardLastRate",
|
|
120
|
+
"ForwardMinRate",
|
|
121
|
+
"ForwardAvgRate",
|
|
122
|
+
"ForwardMaxRate",
|
|
123
|
+
"ForwardTrades",
|
|
124
|
+
"ForwardQuantity",
|
|
125
|
+
"ForwardVolume",
|
|
126
|
+
"ForwardBrokeredTrades",
|
|
127
|
+
"ForwardBrokeredQuantity",
|
|
128
|
+
]
|
|
129
|
+
|
|
130
|
+
column_order = [col for col in reorder_columns if col in df.columns]
|
|
131
|
+
return df[column_order].copy()
|
|
132
|
+
|
|
133
|
+
|
|
134
|
+
def is_selic_open() -> bool:
|
|
135
|
+
"""Verifica se o mercado está aberto no momento."""
|
|
136
|
+
now = dt.datetime.now(BZ_TIMEZONE)
|
|
137
|
+
today = now.date()
|
|
138
|
+
time = now.time()
|
|
139
|
+
is_last_bday = bday.is_business_day(today)
|
|
140
|
+
is_trading_time = REALTIME_START_TIME <= time <= REALTIME_END_TIME
|
|
141
|
+
|
|
142
|
+
return is_last_bday and is_trading_time
|
|
143
|
+
|
|
144
|
+
|
|
145
|
+
def fpd_intraday_trades() -> pd.DataFrame:
|
|
146
|
+
"""Fetches real-time secondary trading data for domestic Federal Public Debt (FPD)
|
|
147
|
+
from the Central Bank of Brazil (BCB).
|
|
148
|
+
|
|
149
|
+
This function checks if the SELIC market is currently open based on Brazil/Sao_Paulo
|
|
150
|
+
timezone business days and trading hours (defined by REALTIME_START_TIME and
|
|
151
|
+
REALTIME_END_TIME). If the market is closed, or if no data is available from the
|
|
152
|
+
source, or if an error occurs during fetching or processing, an empty DataFrame
|
|
153
|
+
is returned. Otherwise, it retrieves, cleans, and processes the intraday trade
|
|
154
|
+
data provided by BCB for Brazilian government bonds.
|
|
155
|
+
|
|
156
|
+
Returns:
|
|
157
|
+
pd.DataFrame: A DataFrame containing the latest intraday trades for FPD
|
|
158
|
+
securities. Returns an empty DataFrame if the market is closed, no data
|
|
159
|
+
is found, or an error occurs. The DataFrame includes the following columns:
|
|
160
|
+
|
|
161
|
+
* `SettlementDate`: The reference date for the spot market
|
|
162
|
+
trading activity reported in this dataset (the current
|
|
163
|
+
business day). Forward trades listed have future settlement dates
|
|
164
|
+
not specified here.
|
|
165
|
+
* `BondType`: Abbreviation/ticker for the bond type (e.g., LFT,
|
|
166
|
+
LTN, NTN-B).
|
|
167
|
+
* `SelicCode`: The unique SELIC code identifying the specific bond issue.
|
|
168
|
+
* `MaturityDate`: The maturity date of the bond.
|
|
169
|
+
|
|
170
|
+
**Spot Market Data:**
|
|
171
|
+
* `MinPrice`: Minimum traded price.
|
|
172
|
+
* `AvgPrice`: Average traded price.
|
|
173
|
+
* `MaxPrice`: Maximum traded price.
|
|
174
|
+
* `LastPrice`: Last traded price.
|
|
175
|
+
* `MinRate`: Minimum traded yield/rate (as a decimal, e.g., 0.11 for 11%).
|
|
176
|
+
* `AvgRate`: Average traded yield/rate (as a decimal).
|
|
177
|
+
* `MaxRate`: Maximum traded yield/rate (as a decimal).
|
|
178
|
+
* `LastRate`: Last traded yield/rate (as a decimal).
|
|
179
|
+
* `Trades`: Total number of trades settled.
|
|
180
|
+
* `Quantity`: Total number of bonds traded (quantity).
|
|
181
|
+
* `Volume`: Total financial volume traded (in BRL).
|
|
182
|
+
* `BrokeredTrades`: Number of brokered trades settled.
|
|
183
|
+
* `BrokeredQuantity`: Quantity of bonds traded via brokers.
|
|
184
|
+
|
|
185
|
+
**Forward Market Data:**
|
|
186
|
+
* `ForwardMinPrice`: Minimum traded price.
|
|
187
|
+
* `ForwardAvgPrice`: Average traded price.
|
|
188
|
+
* `ForwardMaxPrice`: Maximum traded price.
|
|
189
|
+
* `ForwardLastPrice`: Last traded price.
|
|
190
|
+
* `ForwardMinRate`: Minimum traded yield/rate (decimal).
|
|
191
|
+
* `ForwardAvgRate`: Average traded yield/rate (decimal).
|
|
192
|
+
* `ForwardMaxRate`: Maximum traded yield/rate (decimal).
|
|
193
|
+
* `ForwardLastRate`: Last traded yield/rate (decimal).
|
|
194
|
+
* `ForwardTrades`: Total number of trades contracted.
|
|
195
|
+
* `ForwardQuantity`: Total number of bonds traded (quantity).
|
|
196
|
+
* `ForwardVolume`: Total financial volume traded (in BRL).
|
|
197
|
+
* `ForwardBrokeredTrades`: Number of brokered trades contracted.
|
|
198
|
+
* `ForwardBrokeredQuantity`: Quantity of bonds traded via brokers.
|
|
199
|
+
"""
|
|
200
|
+
if not is_selic_open():
|
|
201
|
+
logger.info("Market is closed. Returning empty DataFrame.")
|
|
202
|
+
return pd.DataFrame()
|
|
203
|
+
|
|
204
|
+
try:
|
|
205
|
+
raw_text = _fetch_csv_from_url()
|
|
206
|
+
# raw_text = test_file.read_text(encoding="iso-8859-15")
|
|
207
|
+
cleaned_text = _clean_csv(raw_text)
|
|
208
|
+
if not cleaned_text:
|
|
209
|
+
logger.warning("No data found in the FPD intraday trades.")
|
|
210
|
+
return pd.DataFrame()
|
|
211
|
+
df = _convert_csv_to_df(cleaned_text)
|
|
212
|
+
df = _process_df(df)
|
|
213
|
+
df = _reorder_columns(df)
|
|
214
|
+
volume = df["Volume"].sum() / 10**9
|
|
215
|
+
logger.info(f"Fetched {volume:,.1f} billion BRL in FPD intraday trades.")
|
|
216
|
+
return df
|
|
217
|
+
except Exception:
|
|
218
|
+
logger.exception("Error fetching data from BCB. Returning empty DataFrame.")
|
|
219
|
+
return pd.DataFrame()
|
|
@@ -15,10 +15,10 @@ COLUMN_MAPPING = {
|
|
|
15
15
|
"CODIGO": "SelicCode",
|
|
16
16
|
"CODIGO ISIN": "ISIN",
|
|
17
17
|
"EMISSAO": "IssueDate",
|
|
18
|
-
"VENCIMENTO": "
|
|
19
|
-
"NUM DE OPER": "
|
|
20
|
-
"QUANT NEGOCIADA": "
|
|
21
|
-
"VALOR NEGOCIADO": "
|
|
18
|
+
"VENCIMENTO": "MaturityDate",
|
|
19
|
+
"NUM DE OPER": "Trades",
|
|
20
|
+
"QUANT NEGOCIADA": "Quantity",
|
|
21
|
+
"VALOR NEGOCIADO": "Volume",
|
|
22
22
|
"PU MIN": "MinPrice",
|
|
23
23
|
"PU MED": "AvgPrice",
|
|
24
24
|
"PU MAX": "MaxPrice",
|
|
@@ -27,8 +27,8 @@ COLUMN_MAPPING = {
|
|
|
27
27
|
"TAXA MIN": "MinRate",
|
|
28
28
|
"TAXA MED": "AvgRate",
|
|
29
29
|
"TAXA MAX": "MaxRate",
|
|
30
|
-
"NUM OPER COM CORRETAGEM": "
|
|
31
|
-
"QUANT NEG COM CORRETAGEM": "
|
|
30
|
+
"NUM OPER COM CORRETAGEM": "BrokerageTrades",
|
|
31
|
+
"QUANT NEG COM CORRETAGEM": "BrokerageQuantity",
|
|
32
32
|
}
|
|
33
33
|
|
|
34
34
|
|
|
@@ -63,9 +63,11 @@ def _fetch_data_from_url(file_url: str) -> pd.DataFrame:
|
|
|
63
63
|
return df
|
|
64
64
|
|
|
65
65
|
|
|
66
|
-
def
|
|
67
|
-
|
|
68
|
-
|
|
66
|
+
def fpd_monthly_trades(
|
|
67
|
+
target_date: DateScalar, all_operations: bool = True
|
|
68
|
+
) -> pd.DataFrame:
|
|
69
|
+
"""Fetches monthly secondary trading data for the domestic 'Federal Public Debt'
|
|
70
|
+
(FPD) registered in the Brazilian Central Bank (BCB) Selic system.
|
|
69
71
|
|
|
70
72
|
Downloads the monthly bond trading data from the Brazilian Central Bank (BCB)
|
|
71
73
|
website for the month corresponding to the provided date. The data is downloaded
|
|
@@ -90,30 +92,29 @@ def tpf_trades(target_date: DateScalar, all_operations: bool = True) -> pd.DataF
|
|
|
90
92
|
- SelicCode: Unique code in the SELIC system
|
|
91
93
|
- ISIN: International Securities Identification Number
|
|
92
94
|
- IssueDate: Date when the security was issued
|
|
93
|
-
-
|
|
94
|
-
-
|
|
95
|
-
-
|
|
96
|
-
-
|
|
95
|
+
- MaturityDate: Security's maturity date
|
|
96
|
+
- Trades: Number of trades executed
|
|
97
|
+
- Quantity: Quantity traded
|
|
98
|
+
- Volume: Total value traded
|
|
97
99
|
- AvgPrice: Average price
|
|
98
100
|
- AvgRate: Average rate
|
|
99
101
|
And additional trading metrics like min/max prices and rates.
|
|
100
102
|
|
|
101
103
|
Examples:
|
|
102
104
|
>>> from pyield import bc
|
|
103
|
-
>>> df = bc.
|
|
105
|
+
>>> df = bc.fpd_monthly_trades("07-01-2025") # Returns all trades for Jan/2025
|
|
104
106
|
|
|
105
107
|
Notes:
|
|
106
108
|
Transactions are considered off-group when the transferring counterparty's
|
|
107
109
|
conglomerate is different from the receiving counterparty's conglomerate,
|
|
108
110
|
or when at least one of the counterparties does not belong to a conglomerate.
|
|
109
111
|
In the case of funds, the conglomerate considered is that of the administrator.
|
|
110
|
-
|
|
111
112
|
"""
|
|
112
113
|
filename = _build_filename(target_date, all_operations)
|
|
113
|
-
logger.info(f"Fetching
|
|
114
|
+
logger.info(f"Fetching FPD trades for {target_date} from BCB")
|
|
114
115
|
url = f"{BASE_URL}/{filename}"
|
|
115
116
|
df = _fetch_data_from_url(url)
|
|
116
117
|
df = df.rename(columns=COLUMN_MAPPING)
|
|
117
|
-
#
|
|
118
|
-
df["
|
|
118
|
+
# Volume are empty in the original BCB file, so we calculate it
|
|
119
|
+
df["Volume"] = (df["Quantity"] * df["AvgPrice"]).round(2)
|
|
119
120
|
return df
|
|
@@ -69,8 +69,19 @@ def forwards(
|
|
|
69
69
|
2 0.090284
|
|
70
70
|
dtype: Float64
|
|
71
71
|
|
|
72
|
+
>>> # Exemplo com agrupamento (a última está isolada em outro grupo)
|
|
73
|
+
>>> groupby_dates = pd.Series([1, 1, 2])
|
|
74
|
+
>>> yd.forwards(bdays, rates, groupby_dates)
|
|
75
|
+
0 0.05
|
|
76
|
+
1 0.070095
|
|
77
|
+
2 0.07
|
|
78
|
+
dtype: Float64
|
|
79
|
+
|
|
72
80
|
Note:
|
|
73
|
-
A função
|
|
81
|
+
- A função ordena os dados de entrada primeiro por `groupby_dates`,
|
|
82
|
+
se for fornecido, e depois por `bdays` para garantir a ordem cronológica
|
|
83
|
+
correta no cálculo das taxas a termo.
|
|
84
|
+
- Os resultados são retornados na mesma ordem dos dados de entrada.
|
|
74
85
|
""" # noqa: E501
|
|
75
86
|
bdays = bdays.astype("Int64")
|
|
76
87
|
rates = rates.astype("Float64")
|
|
@@ -79,9 +90,12 @@ def forwards(
|
|
|
79
90
|
if not bdays.index.equals(rates.index):
|
|
80
91
|
raise ValueError("The indexes of bdays and rates must be the same.")
|
|
81
92
|
|
|
93
|
+
# Store original index
|
|
94
|
+
original_index = bdays.index
|
|
95
|
+
|
|
82
96
|
# Create a DataFrame to work with the given series
|
|
83
|
-
df = pd.DataFrame({"
|
|
84
|
-
df["
|
|
97
|
+
df = pd.DataFrame({"du_k": bdays, "rate_k": rates})
|
|
98
|
+
df["time_k"] = df["du_k"] / 252
|
|
85
99
|
|
|
86
100
|
if isinstance(groupby_dates, pd.Series):
|
|
87
101
|
if not groupby_dates.index.equals(bdays.index):
|
|
@@ -91,27 +105,30 @@ def forwards(
|
|
|
91
105
|
df["groupby_date"] = 0 # Dummy value to group the DataFrame
|
|
92
106
|
|
|
93
107
|
# Sort by the groupby_dates and t2 columns to ensure proper chronological order
|
|
94
|
-
df.sort_values(by=["groupby_date", "
|
|
108
|
+
df = df.sort_values(by=["groupby_date", "time_k"])
|
|
95
109
|
|
|
96
110
|
# Calculate the next zero rate and business day for each group
|
|
97
|
-
df["
|
|
98
|
-
df["
|
|
111
|
+
df["rate_j"] = df.groupby("groupby_date")["rate_k"].shift(1)
|
|
112
|
+
df["time_j"] = df.groupby("groupby_date")["time_k"].shift(1)
|
|
99
113
|
|
|
100
114
|
# Calculate the formula components
|
|
101
115
|
# fₖ = fⱼ→ₖ = ((1 + rₖ)^tₖ / (1 + rⱼ)^tⱼ) ^ (1/(tₖ - tⱼ)) - 1
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
df["fwd"] = (
|
|
116
|
+
factor_k = (1 + df["rate_k"]) ** df["time_k"] # (1 + rₖ)^tₖ
|
|
117
|
+
factor_j = (1 + df["rate_j"]) ** df["time_j"] # (1 + rⱼ)^tⱼ
|
|
118
|
+
factor_t = 1 / (df["time_k"] - df["time_j"]) # 1/(tₖ - tⱼ)
|
|
119
|
+
df["fwd"] = (factor_k / factor_j) ** factor_t - 1
|
|
106
120
|
|
|
107
121
|
# Identifify the first index of each group of dates
|
|
108
122
|
first_indices = df.groupby("groupby_date").head(1).index
|
|
109
123
|
# Set the first forward rate of each group to the zero rate
|
|
110
|
-
df.loc[first_indices, "fwd"] = df.loc[first_indices, "
|
|
124
|
+
df.loc[first_indices, "fwd"] = df.loc[first_indices, "rate_k"]
|
|
125
|
+
|
|
126
|
+
# Reindex the result to match the original input order
|
|
127
|
+
result_fwd = df["fwd"].reindex(original_index)
|
|
111
128
|
|
|
112
129
|
# Return the forward rates as a Series with no name
|
|
113
|
-
|
|
114
|
-
return
|
|
130
|
+
result_fwd.name = None
|
|
131
|
+
return result_fwd
|
|
115
132
|
|
|
116
133
|
|
|
117
134
|
def forward(
|
|
@@ -32,13 +32,13 @@ class Interpolator:
|
|
|
32
32
|
>>> known_rates = [0.045, 0.05, 0.055]
|
|
33
33
|
|
|
34
34
|
Linear interpolation example:
|
|
35
|
-
>>>
|
|
36
|
-
>>>
|
|
35
|
+
>>> linear = Interpolator("linear", known_bdays, known_rates)
|
|
36
|
+
>>> linear(45)
|
|
37
37
|
0.0475
|
|
38
38
|
|
|
39
39
|
Flat forward interpolation example:
|
|
40
|
-
>>>
|
|
41
|
-
>>>
|
|
40
|
+
>>> fforward = Interpolator("flat_forward", known_bdays, known_rates)
|
|
41
|
+
>>> fforward(45)
|
|
42
42
|
0.04833068080970859
|
|
43
43
|
"""
|
|
44
44
|
|
|
@@ -61,18 +61,60 @@ class Interpolator:
|
|
|
61
61
|
self._known_rates = tuple(df["rate"])
|
|
62
62
|
self._extrapolate = bool(extrapolate)
|
|
63
63
|
|
|
64
|
-
def
|
|
65
|
-
"""
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
64
|
+
def flat_forward(self, bday: int, k: int) -> float:
|
|
65
|
+
r"""
|
|
66
|
+
Performs the interest rate interpolation using the flat forward method.
|
|
67
|
+
|
|
68
|
+
This method calculates the interpolated interest rate for a given
|
|
69
|
+
number of business days (`bday`) using the flat forward methodology,
|
|
70
|
+
based on two known points: the current point (`k`) and the previous point (`j`).
|
|
71
|
+
|
|
72
|
+
Assuming interest rates are in decimal form, the interpolated rate
|
|
73
|
+
is calculated. Time is measured in years based on a 252-business-day year.
|
|
74
|
+
|
|
75
|
+
The interpolated rate is given by the formula:
|
|
76
|
+
|
|
77
|
+
$$
|
|
78
|
+
\left(f_j*\left(\frac{f_k}{f_j}\right)^{f_t}\right)^{\frac{1}{time}}-1
|
|
79
|
+
$$
|
|
80
|
+
|
|
81
|
+
Where the factors used in the formula are defined as:
|
|
82
|
+
|
|
83
|
+
* `fⱼ = (1 + rateⱼ)^timeⱼ` is the compounding factor at point `j`.
|
|
84
|
+
* `fₖ = (1 + rateₖ)^timeₖ` is the compounding factor at point `k`.
|
|
85
|
+
* `fₜ = (time - timeⱼ)/(timeₖ - timeⱼ)` is the time factor.
|
|
86
|
+
|
|
87
|
+
And the variables are defined as:
|
|
88
|
+
|
|
89
|
+
* `time = bday/252` is the time in years for the interpolated point. `bday` is
|
|
90
|
+
the number of business days for the interpolated point (input to this method).
|
|
91
|
+
* `k` is the index of the current known point.
|
|
92
|
+
* `timeₖ = bdayₖ/252` is the time in years of point `k`.
|
|
93
|
+
* `rateₖ` is the interest rate (decimal) at point `k`.
|
|
94
|
+
* `j` is the index of the previous known point (`k - 1`).
|
|
95
|
+
* `timeⱼ = bdayⱼ/252` is the time in years of point `j`.
|
|
96
|
+
* `rateⱼ` is the interest rate (decimal) at point `j`.
|
|
97
|
+
|
|
98
|
+
Args:
|
|
99
|
+
bday (int): Number of bus. days for which the rate is to be interpolated.
|
|
100
|
+
k (int): The index in the known_bdays and known_rates arrays such that
|
|
101
|
+
known_bdays[k-1] < bday < known_bdays[k]. This `k` corresponds
|
|
102
|
+
to the index of the next known point after `bday`.
|
|
103
|
+
|
|
104
|
+
Returns:
|
|
105
|
+
float: The interpolated interest rate in decimal form.
|
|
106
|
+
"""
|
|
107
|
+
rate_j = self._known_rates[k - 1]
|
|
108
|
+
time_j = self._known_bdays[k - 1] / 252
|
|
109
|
+
rate_k = self._known_rates[k]
|
|
110
|
+
time_k = self._known_bdays[k] / 252
|
|
111
|
+
time = bday / 252
|
|
70
112
|
|
|
71
113
|
# Perform flat forward interpolation
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
return (
|
|
114
|
+
f_j = (1 + rate_j) ** time_j
|
|
115
|
+
f_k = (1 + rate_k) ** time_k
|
|
116
|
+
f_t = (time - time_j) / (time_k - time_j)
|
|
117
|
+
return (f_j * (f_k / f_j) ** f_t) ** (1 / time) - 1
|
|
76
118
|
|
|
77
119
|
def interpolate(self, bday: int) -> float:
|
|
78
120
|
"""
|
|
@@ -104,15 +146,15 @@ class Interpolator:
|
|
|
104
146
|
if method == "linear":
|
|
105
147
|
return float(np.interp(bday, known_bdays, known_rates))
|
|
106
148
|
|
|
107
|
-
# Find
|
|
108
|
-
|
|
149
|
+
# Find k such that known_bdays[k-1] < bday < known_bdays[k]
|
|
150
|
+
k = bisect.bisect_left(known_bdays, bday)
|
|
109
151
|
|
|
110
152
|
# Check if the interpolation point is known
|
|
111
|
-
if
|
|
112
|
-
return float(known_rates[
|
|
153
|
+
if k < len(known_bdays) and known_bdays[k] == bday:
|
|
154
|
+
return float(known_rates[k])
|
|
113
155
|
|
|
114
156
|
# Perform flat forward interpolation
|
|
115
|
-
return float(self.
|
|
157
|
+
return float(self.flat_forward(bday, k))
|
|
116
158
|
|
|
117
159
|
def __call__(self, bday: int) -> float:
|
|
118
160
|
"""
|
|
@@ -130,7 +172,6 @@ class Interpolator:
|
|
|
130
172
|
|
|
131
173
|
def __repr__(self) -> str:
|
|
132
174
|
"""Textual representation, used in terminal or scripts."""
|
|
133
|
-
|
|
134
175
|
return repr(self._df)
|
|
135
176
|
|
|
136
177
|
def __len__(self) -> int:
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "0.33.02"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|