PYield 0.1.4__tar.gz → 0.1.6__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-0.1.4 → pyield-0.1.6}/PKG-INFO +1 -1
- {pyield-0.1.4 → pyield-0.1.6}/pyield/__about__.py +1 -1
- {pyield-0.1.4 → pyield-0.1.6}/pyield/di.py +48 -25
- {pyield-0.1.4 → pyield-0.1.6}/pyield/workday_calculator.py +17 -10
- {pyield-0.1.4 → pyield-0.1.6}/pyproject.toml +1 -1
- {pyield-0.1.4 → pyield-0.1.6}/LICENSE +0 -0
- {pyield-0.1.4 → pyield-0.1.6}/README.md +0 -0
- {pyield-0.1.4 → pyield-0.1.6}/pyield/__init__.py +0 -0
- {pyield-0.1.4 → pyield-0.1.6}/pyield/br_holidays.txt +0 -0
- {pyield-0.1.4 → pyield-0.1.6}/tests/__init__.py +0 -0
|
@@ -118,6 +118,8 @@ def get_raw_di_data(reference_date: pd.Timestamp) -> pd.DataFrame:
|
|
|
118
118
|
header=1,
|
|
119
119
|
thousands=".",
|
|
120
120
|
decimal=",",
|
|
121
|
+
# Avoid parsing "-" as a string. See column "AJUSTE CORRIG. (4)" in 02/01/2006.
|
|
122
|
+
na_values=["-"],
|
|
121
123
|
dtype_backend="numpy_nullable",
|
|
122
124
|
)[0]
|
|
123
125
|
# Remove rows with all NaN values
|
|
@@ -126,10 +128,9 @@ def get_raw_di_data(reference_date: pd.Timestamp) -> pd.DataFrame:
|
|
|
126
128
|
df = df.dropna(axis=1, how="all")
|
|
127
129
|
return df
|
|
128
130
|
|
|
129
|
-
except
|
|
130
|
-
# Emit a warning indicating the absence of data for the specific date
|
|
131
|
+
except Exception as e:
|
|
131
132
|
warnings.warn(
|
|
132
|
-
f"
|
|
133
|
+
f"A {type(e).__name__} occurred while reading the DI futures data for {reference_date.strftime("%d/%m/%Y")}. Is this a valid date? Returning an empty DataFrame."
|
|
133
134
|
)
|
|
134
135
|
return pd.DataFrame()
|
|
135
136
|
|
|
@@ -157,14 +158,14 @@ def process_di_data(df: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFr
|
|
|
157
158
|
"NÚM. NEGOC.": "number_of_trades",
|
|
158
159
|
"CONTR. NEGOC.": "trading_volume",
|
|
159
160
|
"VOL.": "financial_volume",
|
|
160
|
-
"AJUSTE ANTER. (3)": "
|
|
161
|
-
"AJUSTE CORRIG. (4)": "
|
|
161
|
+
"AJUSTE ANTER. (3)": "prev_settlement_rate",
|
|
162
|
+
"AJUSTE CORRIG. (4)": "adj_prev_settlement_rate",
|
|
162
163
|
"PREÇO ABERTU.": "opening_rate",
|
|
163
164
|
"PREÇO MÍN.": "min_rate",
|
|
164
165
|
"PREÇO MÁX.": "max_rate",
|
|
165
166
|
"PREÇO MÉD.": "avg_rate",
|
|
166
|
-
"ÚLT. PREÇO": "
|
|
167
|
-
"AJUSTE": "
|
|
167
|
+
"ÚLT. PREÇO": "closing_rate",
|
|
168
|
+
"AJUSTE": "settlement_rate",
|
|
168
169
|
"VAR. PTOS.": "point_variation",
|
|
169
170
|
"ÚLT.OF. COMPRA": "last_bid",
|
|
170
171
|
"ÚLT.OF. VENDA": "last_offer",
|
|
@@ -180,30 +181,53 @@ def process_di_data(df: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFr
|
|
|
180
181
|
df["maturity"] = df["contract_code"].apply(convert_contract_code)
|
|
181
182
|
|
|
182
183
|
df["bday"] = wd.count_business_days(reference_date, df["maturity"])
|
|
184
|
+
# Remove rows with bday <= 0
|
|
185
|
+
df = df[df["bday"] > 0]
|
|
186
|
+
|
|
187
|
+
# Columns where 0 means NaN
|
|
188
|
+
cols_with_nan = [
|
|
189
|
+
"prev_settlement_rate",
|
|
190
|
+
"adj_prev_settlement_rate",
|
|
191
|
+
"settlement_rate",
|
|
192
|
+
"opening_rate",
|
|
193
|
+
"min_rate",
|
|
194
|
+
"max_rate",
|
|
195
|
+
"avg_rate",
|
|
196
|
+
"closing_rate",
|
|
197
|
+
"last_bid",
|
|
198
|
+
"last_offer",
|
|
199
|
+
]
|
|
200
|
+
for col in cols_with_nan:
|
|
201
|
+
df[cols_with_nan] = df[cols_with_nan].replace(0, np.nan)
|
|
202
|
+
|
|
203
|
+
# Convert prices to rates in settlement columns
|
|
204
|
+
settlement_cols = [
|
|
205
|
+
"prev_settlement_rate",
|
|
206
|
+
"adj_prev_settlement_rate",
|
|
207
|
+
"settlement_rate",
|
|
208
|
+
]
|
|
209
|
+
for col in settlement_cols:
|
|
210
|
+
df[col] = (100_000 / df[col]) ** (252 / df["bday"]) - 1
|
|
211
|
+
# Convert to percentage and round to 3 decimal places
|
|
212
|
+
df[col] = (100 * df[col]).round(3)
|
|
183
213
|
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
df["settlement_rate"] = (100 * df["settlement_rate"]).round(3)
|
|
187
|
-
|
|
188
|
-
# Prior to 22/05/2006, prices were not converted to rates
|
|
189
|
-
rate_columns = [
|
|
214
|
+
# Prior to 01/01/2002, prices were not converted to rates
|
|
215
|
+
convert_cols = [
|
|
190
216
|
"opening_rate",
|
|
191
217
|
"min_rate",
|
|
192
218
|
"max_rate",
|
|
193
219
|
"avg_rate",
|
|
194
|
-
"
|
|
220
|
+
"closing_rate",
|
|
195
221
|
"last_bid",
|
|
196
222
|
"last_offer",
|
|
197
223
|
]
|
|
198
|
-
if reference_date < pd.Timestamp("
|
|
199
|
-
for col in
|
|
200
|
-
|
|
201
|
-
df[col] = df[col].astype(float)
|
|
202
|
-
df[col] = np.where(
|
|
203
|
-
df[col] == 0, 0, (100_000 / df[col]) ** (252 / df["bday"]) - 1
|
|
204
|
-
)
|
|
224
|
+
if reference_date < pd.Timestamp("2002-01-01"):
|
|
225
|
+
for col in convert_cols:
|
|
226
|
+
df[col] = (100_000 / df[col]) ** (252 / df["bday"]) - 1
|
|
205
227
|
# Convert to percentage and round to 3 decimal places
|
|
206
228
|
df[col] = (100 * df[col]).round(3)
|
|
229
|
+
# Invert low and high prices
|
|
230
|
+
df["min_rate"], df["max_rate"] = df["max_rate"], df["min_rate"]
|
|
207
231
|
|
|
208
232
|
# Order columns
|
|
209
233
|
df = df[
|
|
@@ -215,16 +239,15 @@ def process_di_data(df: pd.DataFrame, reference_date: pd.Timestamp) -> pd.DataFr
|
|
|
215
239
|
"number_of_trades",
|
|
216
240
|
"trading_volume",
|
|
217
241
|
"financial_volume",
|
|
218
|
-
"prev_settlement",
|
|
219
|
-
"adj_prev_settlement",
|
|
220
|
-
"settlement",
|
|
221
242
|
"opening_rate",
|
|
222
243
|
"min_rate",
|
|
223
244
|
"max_rate",
|
|
224
245
|
"avg_rate",
|
|
225
|
-
"
|
|
246
|
+
"closing_rate",
|
|
226
247
|
"last_bid",
|
|
227
248
|
"last_offer",
|
|
249
|
+
"prev_settlement_rate",
|
|
250
|
+
"adj_prev_settlement_rate",
|
|
228
251
|
"settlement_rate",
|
|
229
252
|
]
|
|
230
253
|
]
|
|
@@ -20,6 +20,17 @@ HOLIDAYS_NPA = df["date"].values.astype("datetime64[D]")
|
|
|
20
20
|
# HOLIDAYS_STR = df["date"].dt.strftime("%Y-%m-%d").to_list()
|
|
21
21
|
|
|
22
22
|
|
|
23
|
+
def convert_to_numpy_date(dates):
|
|
24
|
+
if isinstance(dates, pd.Timestamp):
|
|
25
|
+
return dates.to_numpy().astype("datetime64[D]")
|
|
26
|
+
else:
|
|
27
|
+
return dates.values.astype("datetime64[D]")
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
def adjust_to_next_business_day(dates):
|
|
31
|
+
return np.busday_offset(dates, 0, roll="forward", holidays=HOLIDAYS_NPA)
|
|
32
|
+
|
|
33
|
+
|
|
23
34
|
def count_business_days(
|
|
24
35
|
start_dates: pd.Series | pd.Timestamp,
|
|
25
36
|
end_dates: pd.Series | pd.Timestamp,
|
|
@@ -55,16 +66,12 @@ def count_business_days(
|
|
|
55
66
|
>>> bday_count(start_series, end_series)
|
|
56
67
|
array([22, 18])
|
|
57
68
|
"""
|
|
58
|
-
# Convert
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
else:
|
|
62
|
-
start_dates = start_dates.values.astype("datetime64[D]")
|
|
69
|
+
# Convert to numpy date format
|
|
70
|
+
start_dates = convert_to_numpy_date(start_dates)
|
|
71
|
+
end_dates = convert_to_numpy_date(end_dates)
|
|
63
72
|
|
|
64
|
-
#
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
else:
|
|
68
|
-
end_dates = end_dates.values.astype("datetime64[D]")
|
|
73
|
+
# Adjust start and end dates to the next business day if they fall on a holiday or weekend
|
|
74
|
+
start_dates = adjust_to_next_business_day(start_dates)
|
|
75
|
+
end_dates = adjust_to_next_business_day(end_dates)
|
|
69
76
|
|
|
70
77
|
return np.busday_count(start_dates, end_dates, holidays=HOLIDAYS_NPA)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|