Skip to content

new #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sid-plt merged 2 commits into from
Sep 15, 2026
Merged

new #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d5dd59b
new
sid-plt Sep 15, 2026
78ff5e9
Merge branch 'main' into new
sid-plt Sep 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 ...ing_odds_lineup_20260904_111301_+0200.csv → archive/md exp pts/md2 exp pts.csv
View file
Open in desktop
File renamed without changes.
462 changes: 462 additions & 0 deletions archive/md exp pts/md3 exp pts.csv
View file
Open in desktop

Large diffs are not rendered by default.

23 changes: 16 additions & 7 deletions archive/notebooks/calculate_team_recent_form.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# 1. Imports\n",
"import json\n",
"from datetime import datetime, timezone\n",
Expand All @@ -39,7 +49,11 @@
" \"Required packages are missing. Install undetected-chromedriver, \"\n",
" \"selenium, beautifulsoup4, and pandas in this Jupyter kernel, \"\n",
" \"then restart the kernel.\"\n",
" ) from exc\n"
" ) from exc\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -63,7 +77,6 @@
" raise ValueError(\"Matchday must be a positive integer.\")\n",
"\n",
"# Edit these values if your local Chrome setup or preferred limits differ.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: HEADLESS.\n",
"HEADLESS = False\n",
"# Set workflow configuration value: PAGE_LOAD_TIMEOUT_SECONDS.\n",
Expand Down Expand Up @@ -211,11 +224,7 @@
"driver = None\n",
"# Handle expected failures with a clear, actionable message.\n",
"try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" use_subprocess=True,\n",
" )\n",
" driver = uc.Chrome(options=options, use_subprocess=True, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" driver.set_page_load_timeout(PAGE_LOAD_TIMEOUT_SECONDS)\n",
"except Exception as exc:\n",
" if driver is not None:\n",
Expand Down
22 changes: 16 additions & 6 deletions archive/notebooks/extract_sofascore_match_ids.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# Import the libraries required by this notebook step.\n",
"import json\n",
"from pathlib import Path\n",
Expand All @@ -49,14 +59,17 @@
"# Set workflow configuration value: OUTPUT_PATH_TEMPLATE.\n",
"OUTPUT_PATH_TEMPLATE = \"match_ids_{match_day}.json\"\n",
"# Set workflow configuration value: CHROME_MAJOR_VERSION.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: WAIT_TIMEOUT_SECONDS.\n",
"WAIT_TIMEOUT_SECONDS = 30\n",
"\n",
"\n",
"# Define Extraction Error to keep related behaviour explicit.\n",
"class ExtractionError(RuntimeError):\n",
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\""
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\"\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -78,10 +91,7 @@
" try:\n",
" # Handle expected failures with a clear, actionable message.\n",
" try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" )\n",
" driver = uc.Chrome(options=options, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" except Exception as exc:\n",
" raise ExtractionError(\n",
" f\"Could not start Chrome {CHROME_MAJOR_VERSION}: {exc}\"\n",
Expand Down
23 changes: 16 additions & 7 deletions ...ive/recovered_checkpoints/04_extract_team_recent_form_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# 1. Imports\n",
"import json\n",
"from datetime import datetime, timezone\n",
Expand All @@ -42,7 +52,11 @@
" \"Required packages are missing. Install undetected-chromedriver, \"\n",
" \"selenium, beautifulsoup4, and pandas in this Jupyter kernel, \"\n",
" \"then restart the kernel.\"\n",
" ) from exc\n"
" ) from exc\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -53,7 +67,6 @@
"outputs": [],
"source": [
"# 2. Parameters, Paths, and Snapshot Key\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: HEADLESS.\n",
"HEADLESS = False\n",
"# Set workflow configuration value: PAGE_LOAD_TIMEOUT_SECONDS.\n",
Expand Down Expand Up @@ -174,11 +187,7 @@
"driver = None\n",
"# Handle expected failures with a clear, actionable message.\n",
"try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" use_subprocess=True,\n",
" )\n",
" driver = uc.Chrome(options=options, use_subprocess=True, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" driver.set_page_load_timeout(PAGE_LOAD_TIMEOUT_SECONDS)\n",
"except Exception as exc:\n",
" if driver is not None:\n",
Expand Down
19 changes: 16 additions & 3 deletions ...e/recovered_checkpoints/05_create_bundesliga_snapshot_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# Import the libraries required by this notebook step.\n",
"import difflib\n",
"import json\n",
Expand Down Expand Up @@ -93,7 +103,6 @@
" ) from exc\n",
"\n",
"# Set workflow configuration value: CHROME_MAJOR_VERSION.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: COMPETITION.\n",
"COMPETITION = \"Bundesliga\"\n",
"# Set workflow configuration value: SEASON.\n",
Expand Down Expand Up @@ -121,7 +130,11 @@
")\n",
"\n",
"# Set this to a Path only if the kernel does not start in the notebook directory.\n",
"NOTEBOOK_DIR_OVERRIDE = None\n"
"NOTEBOOK_DIR_OVERRIDE = None\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand Down Expand Up @@ -401,7 +414,7 @@
"try:\n",
" # Handle expected failures with a clear, actionable message.\n",
" try:\n",
" driver = uc.Chrome(version_main=150)\n",
" driver = uc.Chrome(browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" driver.set_page_load_timeout(PAGE_LOAD_TIMEOUT_SECONDS)\n",
" except Exception as exc:\n",
" raise RuntimeError(\n",
Expand Down
24 changes: 17 additions & 7 deletions ...checkpoints/08_extract_best_players_from_prev_matches_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,17 @@
"# Import the libraries required by this notebook step.\n",
"from __future__ import annotations\n",
"\n",
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"\n",
"import csv\n",
"import json\n",
"import math\n",
Expand Down Expand Up @@ -49,7 +60,6 @@
" ) from exc\n",
"\n",
"# Set workflow configuration value: CHROME_MAJOR_VERSION.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: HEADLESS.\n",
"HEADLESS = False\n",
"# Set workflow configuration value: PAGE_LOAD_TIMEOUT_SECONDS.\n",
Expand Down Expand Up @@ -85,7 +95,11 @@
" or isinstance(setting_value, bool)\n",
" or setting_value < 1\n",
" ):\n",
" raise ValueError(f\"{setting_name} must be a positive integer.\")\n"
" raise ValueError(f\"{setting_name} must be a positive integer.\")\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand Down Expand Up @@ -637,11 +651,7 @@
" driver = None\n",
" # Handle expected failures with a clear, actionable message.\n",
" try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=150,\n",
" use_subprocess=True,\n",
" )\n",
" driver = uc.Chrome(options=options, use_subprocess=True, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" driver.set_page_load_timeout(PAGE_LOAD_TIMEOUT_SECONDS)\n",
" print(\n",
" \"One reusable undetected Chrome session is ready \"\n",
Expand Down
22 changes: 16 additions & 6 deletions ...ive/recovered_checkpoints/extract_sofascore_match_ids_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# Import the libraries required by this notebook step.\n",
"import json\n",
"from pathlib import Path\n",
Expand All @@ -47,14 +57,17 @@
"# Set workflow configuration value: OUTPUT_PATH.\n",
"OUTPUT_PATH = Path(\"match_ids.json\")\n",
"# Set workflow configuration value: CHROME_MAJOR_VERSION.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: WAIT_TIMEOUT_SECONDS.\n",
"WAIT_TIMEOUT_SECONDS = 30\n",
"\n",
"\n",
"# Define Extraction Error to keep related behaviour explicit.\n",
"class ExtractionError(RuntimeError):\n",
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\""
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\"\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -76,10 +89,7 @@
" try:\n",
" # Handle expected failures with a clear, actionable message.\n",
" try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" )\n",
" driver = uc.Chrome(options=options, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" except Exception as exc:\n",
" raise ExtractionError(\n",
" f\"Could not start Chrome {CHROME_MAJOR_VERSION}: {exc}\"\n",
Expand Down
22 changes: 16 additions & 6 deletions ...ered_checkpoints/extract_sofascore_match_ids_team_ids_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# Import the libraries required by this notebook step.\n",
"import json\n",
"from pathlib import Path\n",
Expand All @@ -46,14 +56,17 @@
"# Set workflow configuration value: OUTPUT_PATH_TEMPLATE.\n",
"OUTPUT_PATH_TEMPLATE = \"match_ids_{match_day}.json\"\n",
"# Set workflow configuration value: CHROME_MAJOR_VERSION.\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: WAIT_TIMEOUT_SECONDS.\n",
"WAIT_TIMEOUT_SECONDS = 30\n",
"\n",
"\n",
"# Define Extraction Error to keep related behaviour explicit.\n",
"class ExtractionError(RuntimeError):\n",
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\""
" \"\"\"Raised when match data cannot be retrieved or validated.\"\"\"\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -74,10 +87,7 @@
" try:\n",
" # Handle expected failures with a clear, actionable message.\n",
" try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" )\n",
" driver = uc.Chrome(options=options, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" except Exception as exc:\n",
" raise ExtractionError(\n",
" f\"Could not start Chrome {CHROME_MAJOR_VERSION}: {exc}\"\n",
Expand Down
23 changes: 16 additions & 7 deletions archive/recovered_checkpoints/extract_sofascore_odds_recovered_checkpoint_20260810.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,16 @@
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"_chrome_start = Path(globals().get(\"__vsc_ipynb_file__\", Path.cwd())).resolve()\n",
"for _chrome_root in (_chrome_start, *_chrome_start.parents):\n",
" if (_chrome_root / \"chrome_runtime.py\").is_file():\n",
" sys.path.insert(0, str(_chrome_root))\n",
" break\n",
"else:\n",
" raise FileNotFoundError(\"Start Jupyter from the Kickbase project directory.\")\n",
"\n",
"# Imports\n",
"import json\n",
"from fractions import Fraction\n",
Expand All @@ -34,7 +44,11 @@
" raise ImportError(\n",
" \"Browser dependencies are missing. Install them in this Jupyter kernel with \"\n",
" \"'%pip install undetected-chromedriver selenium', then restart the kernel.\"\n",
" ) from exc"
" ) from exc\n",
"\n",
"from chrome_runtime import detect_chrome_major_version\n",
"CHROME_EXECUTABLE_PATH = uc.find_chrome_executable()\n",
"CHROME_MAJOR_VERSION = detect_chrome_major_version(CHROME_EXECUTABLE_PATH)\n"
]
},
{
Expand All @@ -47,7 +61,6 @@
"matchday = 1 # Change this value to process another Bundesliga matchday.\n",
"\n",
"# Notebook constants\n",
"CHROME_MAJOR_VERSION = 150\n",
"# Set workflow configuration value: PAGE_LOAD_TIMEOUT_SECONDS.\n",
"PAGE_LOAD_TIMEOUT_SECONDS = 30\n",
"# Set workflow configuration value: WAIT_TIMEOUT_SECONDS.\n",
Expand Down Expand Up @@ -215,11 +228,7 @@
"driver = None\n",
"# Handle expected failures with a clear, actionable message.\n",
"try:\n",
" driver = uc.Chrome(\n",
" options=options,\n",
" version_main=CHROME_MAJOR_VERSION,\n",
" use_subprocess=True,\n",
" )\n",
" driver = uc.Chrome(options=options, use_subprocess=True, browser_executable_path=CHROME_EXECUTABLE_PATH, version_main=CHROME_MAJOR_VERSION)\n",
" driver.set_page_load_timeout(PAGE_LOAD_TIMEOUT_SECONDS)\n",
" driver.execute_cdp_cmd(\"Network.enable\", {})\n",
"except Exception as exc:\n",
Expand Down
Loading
Loading