datamule 0.422__cp39-cp39-win_amd64.whl → 0.424__cp39-cp39-win_amd64.whl
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.
- datamule/parser/sgml_parsing/sgml_parser_cy.c +1812 -888
- datamule/parser/sgml_parsing/sgml_parser_cy.cp39-win_amd64.pyd +0 -0
- datamule/portfolio.py +14 -4
- {datamule-0.422.dist-info → datamule-0.424.dist-info}/METADATA +2 -2
- {datamule-0.422.dist-info → datamule-0.424.dist-info}/RECORD +7 -8
- datamule/parser/document_parsing/generalized_xml_parser.py +0 -0
- {datamule-0.422.dist-info → datamule-0.424.dist-info}/WHEEL +0 -0
- {datamule-0.422.dist-info → datamule-0.424.dist-info}/top_level.txt +0 -0
Binary file
|
datamule/portfolio.py
CHANGED
@@ -4,13 +4,23 @@ from concurrent.futures import ProcessPoolExecutor
|
|
4
4
|
from .submission import Submission
|
5
5
|
|
6
6
|
class Portfolio:
|
7
|
-
|
7
|
+
@classmethod
|
8
|
+
def create(cls, path):
|
9
|
+
# This method handles the process pool lifecycle
|
10
|
+
with ProcessPoolExecutor() as executor:
|
11
|
+
portfolio = cls(path, executor)
|
12
|
+
return portfolio
|
13
|
+
|
14
|
+
def __init__(self, path, executor=None):
|
8
15
|
self.path = Path(path)
|
9
16
|
folders = [f for f in self.path.iterdir() if f.is_dir()]
|
10
17
|
print(f"Loading {len(folders)} submissions")
|
11
|
-
|
12
|
-
|
13
|
-
#
|
18
|
+
|
19
|
+
if executor is None:
|
20
|
+
# Fall back to sequential loading if no executor
|
21
|
+
self.submissions = [Submission(f) for f in tqdm(folders, desc="Loading submissions")]
|
22
|
+
else:
|
23
|
+
# Use provided executor for parallel loading
|
14
24
|
self.submissions = list(tqdm(
|
15
25
|
executor.map(Submission, folders),
|
16
26
|
total=len(folders),
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: datamule
|
3
|
-
Version: 0.
|
3
|
+
Version: 0.424
|
4
4
|
Summary: Making it easier to use SEC filings.
|
5
5
|
Home-page: https://github.com/john-friedman/datamule-python
|
6
6
|
Author: John Friedman
|
@@ -24,8 +24,8 @@ Requires-Dist: pandas; extra == "dataset-builder"
|
|
24
24
|
Requires-Dist: google-generativeai; extra == "dataset-builder"
|
25
25
|
Requires-Dist: psutil; extra == "dataset-builder"
|
26
26
|
Provides-Extra: all
|
27
|
-
Requires-Dist: flask; extra == "all"
|
28
27
|
Requires-Dist: openai; extra == "all"
|
29
28
|
Requires-Dist: google-generativeai; extra == "all"
|
29
|
+
Requires-Dist: flask; extra == "all"
|
30
30
|
Requires-Dist: pandas; extra == "all"
|
31
31
|
Requires-Dist: psutil; extra == "all"
|
@@ -3,7 +3,7 @@ datamule/document.py,sha256=6xEaI-32AQiBxX3gZcX4Qr49bgvcvLviFAwUGpTwtr0,5273
|
|
3
3
|
datamule/helper.py,sha256=8HOjB3Y7svw_zjEY-AY5JKOJ-LrBiuQMPyok3MH6CCg,4716
|
4
4
|
datamule/monitor.py,sha256=WVds1HGV_ojYgWmo0b4Dsiv9mzZ85HHnCucH-7XoUw8,9350
|
5
5
|
datamule/packageupdater.py,sha256=qVabK4YwSd62OjIvNY59hcQNgZCi4R2PRgCenq7THgE,9790
|
6
|
-
datamule/portfolio.py,sha256=
|
6
|
+
datamule/portfolio.py,sha256=OOlu_05S88uwg5Me_EpY3C7BQ93Yq9eE0_tMY_Gqyrw,1117
|
7
7
|
datamule/submission.py,sha256=sB6tidsAdaqP5VIQEFPq6PjLTgmD-crgdNviaOpiqlU,2558
|
8
8
|
datamule/data/company_former_names.csv,sha256=zTBWdV12_JE3aROFOMrFNTHLPW_M4TDruxtl15-XfA0,714528
|
9
9
|
datamule/data/company_metadata.csv,sha256=X7uSIwConqC0sz-moIhXIISg6FI7GLGSlvAfDDf8Sd0,3078648
|
@@ -38,7 +38,6 @@ datamule/parser/document_parsing/basic_13g_parser.py,sha256=H9_MuOgkYVTIGwhj9w_W
|
|
38
38
|
datamule/parser/document_parsing/basic_8k_parser.py,sha256=fzf8q9LOpBMHGWw-sfqUq3pyFZBlw47nLJBQWPhtGGg,2549
|
39
39
|
datamule/parser/document_parsing/form_d_parser.py,sha256=NTAfC8W3i2y7aIofXoLlAbY-4F6QVELYfIPIrVErjVY,2105
|
40
40
|
datamule/parser/document_parsing/generalized_item_parser.py,sha256=M2bmYivSXe0POyBtDlPMykyyCgG8n1egRpJuZtZTR_g,2694
|
41
|
-
datamule/parser/document_parsing/generalized_xml_parser.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
42
41
|
datamule/parser/document_parsing/helper.py,sha256=wEhqx70CQ0SyEfmOfSCcNsf2TNTtomZvTbmoOhwG3kk,2607
|
43
42
|
datamule/parser/document_parsing/information_table_parser_13fhr.py,sha256=vCIEqxOoBf1lnOKTJAifnPEXihtSPZcwRFW8yWhEZLc,1808
|
44
43
|
datamule/parser/document_parsing/insider_trading_parser.py,sha256=IrH5a3qikPjC1GFoYzapfYW_CArbK0FkbJLbWSfsYNQ,7264
|
@@ -46,9 +45,9 @@ datamule/parser/document_parsing/mappings.py,sha256=dq6EjaxxDHjH-sg62adRwJOf1v73
|
|
46
45
|
datamule/parser/document_parsing/n_port_p_parser.py,sha256=T6GliMm-TETPsFM-hDKt1BkMnSenvDeThj50RsIip50,2293
|
47
46
|
datamule/parser/document_parsing/sec_parser.py,sha256=YewOdOsi0P25teQuxS5DNEND9ZCyxE2ewK1DoP9mPto,2788
|
48
47
|
datamule/parser/document_parsing/sgml_parser.py,sha256=ASpe1SzgPj4qk0VOmmuMiEQeatjcwZzsuO3MvsYCHhc,3410
|
49
|
-
datamule/parser/sgml_parsing/sgml_parser_cy.c,sha256=
|
50
|
-
datamule/parser/sgml_parsing/sgml_parser_cy.cp39-win_amd64.pyd,sha256=
|
51
|
-
datamule-0.
|
52
|
-
datamule-0.
|
53
|
-
datamule-0.
|
54
|
-
datamule-0.
|
48
|
+
datamule/parser/sgml_parsing/sgml_parser_cy.c,sha256=66QwBAmhxkKdhCgCjOkg29umbIgQoK4T5_mmMy3NkkM,841089
|
49
|
+
datamule/parser/sgml_parsing/sgml_parser_cy.cp39-win_amd64.pyd,sha256=RodMP8SF6eKFm_f1DyA80FXOj0izjpb38Va66EN06H0,133120
|
50
|
+
datamule-0.424.dist-info/METADATA,sha256=Zmztc3truLfyxzAms6KFRDEtSLzh2qh2S3nKBwaIRnI,1037
|
51
|
+
datamule-0.424.dist-info/WHEEL,sha256=EfPXSsrLwp9clrn29v9vbmPfEm-IfFzseSJd0ZtI9XA,99
|
52
|
+
datamule-0.424.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
|
53
|
+
datamule-0.424.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|