CLAUDE: Add utility scripts for defense CSV column renaming
Added one-time utility scripts used to prepare 2005 defense CSV files for compatibility with retrosheet_data.py. Scripts: - rename_defense_columns.py: Renamed initial batch of defense columns - RF/9 → range_factor_per_nine - RF/G → range_factor_per_game - DP → DP_def, E → E_def, Ch → chances, Inn → Inn_def - CS% → caught_stealing_perc, PO → pickoffs - Name-additional → key_bbref - rename_additional_defense_columns.py: Second batch of column renames - Fld% → fielding_perc - Rtot → tz_runs_total, Rtot/yr → tz_runs_total_per_season - Rtz → tz_runs_field, Rdp → tz_runs_infield - undo_po_rename.py: Reverted PO → pickoffs for position players - Kept 'pickoffs' for defense_p.csv (pitchers) - Changed back to 'PO' for all other positions (c, 1b, 2b, etc.) - test_retrosheet_integration.py: Integration test for retrosheet_transformer - Validates batting and pitching stats loading - Tests date range filtering - Verifies player counts These scripts have already been executed and the defense files are properly formatted. Kept for historical reference and documentation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Cal Corum
parent
4e9e8d351d
commit
f9411c5e55
69
scripts/rename_additional_defense_columns.py
Normal file
69
scripts/rename_additional_defense_columns.py
Normal file
@ -0,0 +1,69 @@
|
||||
"""
|
||||
Script to rename additional defense CSV column headers.
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
import os
|
||||
|
||||
# Column mapping
|
||||
COLUMN_MAPPING = {
|
||||
'Fld%': 'fielding_perc',
|
||||
'Rtot': 'tz_runs_total',
|
||||
'Rtot/yr': 'tz_runs_total_per_season',
|
||||
'Rtz': 'tz_runs_field',
|
||||
'Rdp': 'tz_runs_infield'
|
||||
}
|
||||
|
||||
# Directory with defense files
|
||||
DATA_DIR = 'data-input/2005 Live Cardset/'
|
||||
|
||||
# All defense files
|
||||
DEFENSE_FILES = [
|
||||
'defense_c.csv',
|
||||
'defense_1b.csv',
|
||||
'defense_2b.csv',
|
||||
'defense_3b.csv',
|
||||
'defense_ss.csv',
|
||||
'defense_lf.csv',
|
||||
'defense_cf.csv',
|
||||
'defense_rf.csv',
|
||||
'defense_of.csv',
|
||||
'defense_p.csv'
|
||||
]
|
||||
|
||||
print("Renaming additional defense CSV columns...")
|
||||
print(f"Column mappings:")
|
||||
for old, new in COLUMN_MAPPING.items():
|
||||
print(f" {old} -> {new}")
|
||||
print()
|
||||
|
||||
for filename in DEFENSE_FILES:
|
||||
filepath = os.path.join(DATA_DIR, filename)
|
||||
|
||||
if not os.path.exists(filepath):
|
||||
print(f"⚠ Skipping {filename} (not found)")
|
||||
continue
|
||||
|
||||
# Read CSV
|
||||
df = pd.read_csv(filepath)
|
||||
|
||||
# Track which columns were renamed
|
||||
renamed = []
|
||||
for old_col, new_col in COLUMN_MAPPING.items():
|
||||
if old_col in df.columns:
|
||||
renamed.append(f"{old_col} -> {new_col}")
|
||||
|
||||
# Rename columns
|
||||
df = df.rename(columns=COLUMN_MAPPING)
|
||||
|
||||
# Save back
|
||||
df.to_csv(filepath, index=False)
|
||||
|
||||
if renamed:
|
||||
print(f"✓ {filename}: Renamed {len(renamed)} columns")
|
||||
for r in renamed:
|
||||
print(f" {r}")
|
||||
else:
|
||||
print(f" {filename}: No matching columns found")
|
||||
|
||||
print("\n✓ All defense files processed successfully!")
|
||||
71
scripts/rename_defense_columns.py
Normal file
71
scripts/rename_defense_columns.py
Normal file
@ -0,0 +1,71 @@
|
||||
"""
|
||||
Script to rename defense CSV column headers to match expected format.
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
import os
|
||||
|
||||
# Column mapping
|
||||
COLUMN_MAPPING = {
|
||||
'RF/9': 'range_factor_per_nine',
|
||||
'RF/G': 'range_factor_per_game',
|
||||
'DP': 'DP_def',
|
||||
'E': 'E_def',
|
||||
'Ch': 'chances',
|
||||
'Inn': 'Inn_def',
|
||||
'CS%': 'caught_stealing_perc',
|
||||
'PO': 'pickoffs',
|
||||
'Name-additional': 'key_bbref'
|
||||
}
|
||||
|
||||
# Directory with defense files
|
||||
DATA_DIR = 'data-input/2005 Live Cardset/'
|
||||
|
||||
# Defense files to process
|
||||
DEFENSE_FILES = [
|
||||
'defense_c.csv',
|
||||
'defense_1b.csv',
|
||||
'defense_2b.csv',
|
||||
'defense_3b.csv',
|
||||
'defense_ss.csv',
|
||||
'defense_lf.csv',
|
||||
'defense_cf.csv',
|
||||
'defense_rf.csv',
|
||||
'defense_of.csv',
|
||||
'defense_p.csv'
|
||||
]
|
||||
|
||||
print("Renaming defense CSV columns...")
|
||||
print(f"Column mappings:")
|
||||
for old, new in COLUMN_MAPPING.items():
|
||||
print(f" {old} -> {new}")
|
||||
print()
|
||||
|
||||
for filename in DEFENSE_FILES:
|
||||
filepath = os.path.join(DATA_DIR, filename)
|
||||
|
||||
if not os.path.exists(filepath):
|
||||
print(f"⚠ Skipping {filename} (not found)")
|
||||
continue
|
||||
|
||||
# Read CSV
|
||||
df = pd.read_csv(filepath)
|
||||
|
||||
# Track which columns were renamed
|
||||
renamed = []
|
||||
for old_col, new_col in COLUMN_MAPPING.items():
|
||||
if old_col in df.columns:
|
||||
renamed.append(f"{old_col} -> {new_col}")
|
||||
|
||||
# Rename columns
|
||||
df = df.rename(columns=COLUMN_MAPPING)
|
||||
|
||||
# Save back
|
||||
df.to_csv(filepath, index=False)
|
||||
|
||||
print(f"✓ {filename}: Renamed {len(renamed)} columns")
|
||||
if renamed:
|
||||
for r in renamed:
|
||||
print(f" {r}")
|
||||
|
||||
print("\n✓ All defense files processed successfully!")
|
||||
56
scripts/test_retrosheet_integration.py
Normal file
56
scripts/test_retrosheet_integration.py
Normal file
@ -0,0 +1,56 @@
|
||||
"""
|
||||
Test script to verify retrosheet_data.py works with the new transformer.
|
||||
"""
|
||||
|
||||
import sys
|
||||
import logging
|
||||
from retrosheet_data import get_base_batting_df, get_base_pitching_df, RETRO_FILE_PATH, EVENTS_FILENAME
|
||||
|
||||
# Set up logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Testing Retrosheet Data Integration")
|
||||
print(f"{'='*60}\n")
|
||||
|
||||
file_path = f'{RETRO_FILE_PATH}{EVENTS_FILENAME}'
|
||||
print(f"Loading from: {file_path}")
|
||||
|
||||
# Test date range (full 2005 season)
|
||||
start_date = 20050403 # Opening Day 2005
|
||||
end_date = 20051003 # End of 2005 regular season
|
||||
|
||||
print(f"\nTest 1: Loading Batting Data")
|
||||
print(f"Date range: {start_date} to {end_date}")
|
||||
|
||||
try:
|
||||
all_plays_batting, batting_stats = get_base_batting_df(file_path, start_date, end_date)
|
||||
print(f"✓ Success!")
|
||||
print(f" - Total plays loaded: {len(all_plays_batting)}")
|
||||
print(f" - Qualified batters: {len(batting_stats)}")
|
||||
print(f"\nSample batting stats:")
|
||||
print(batting_stats.head(3))
|
||||
except Exception as e:
|
||||
print(f"✗ Failed: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
print(f"\n{'-'*60}\n")
|
||||
print(f"Test 2: Loading Pitching Data")
|
||||
|
||||
try:
|
||||
all_plays_pitching, pitching_stats = get_base_pitching_df(file_path, start_date, end_date)
|
||||
print(f"✓ Success!")
|
||||
print(f" - Total plays loaded: {len(all_plays_pitching)}")
|
||||
print(f" - Qualified pitchers: {len(pitching_stats)}")
|
||||
print(f"\nSample pitching stats:")
|
||||
print(pitching_stats.head(3))
|
||||
except Exception as e:
|
||||
print(f"✗ Failed: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"All tests passed! ✓")
|
||||
print(f"{'='*60}\n")
|
||||
48
scripts/undo_po_rename.py
Normal file
48
scripts/undo_po_rename.py
Normal file
@ -0,0 +1,48 @@
|
||||
"""
|
||||
Script to undo PO -> pickoffs rename for position player defense files.
|
||||
Keeps the rename for defense_p.csv (pitchers).
|
||||
"""
|
||||
|
||||
import pandas as pd
|
||||
import os
|
||||
|
||||
# Directory with defense files
|
||||
DATA_DIR = 'data-input/2005 Live Cardset/'
|
||||
|
||||
# Position player defense files (NOT pitchers)
|
||||
POSITION_DEFENSE_FILES = [
|
||||
'defense_c.csv',
|
||||
'defense_1b.csv',
|
||||
'defense_2b.csv',
|
||||
'defense_3b.csv',
|
||||
'defense_ss.csv',
|
||||
'defense_lf.csv',
|
||||
'defense_cf.csv',
|
||||
'defense_rf.csv',
|
||||
'defense_of.csv'
|
||||
]
|
||||
|
||||
print("Undoing PO -> pickoffs rename for position player defense files...")
|
||||
print("(Keeping pickoffs for defense_p.csv)")
|
||||
print()
|
||||
|
||||
for filename in POSITION_DEFENSE_FILES:
|
||||
filepath = os.path.join(DATA_DIR, filename)
|
||||
|
||||
if not os.path.exists(filepath):
|
||||
print(f"⚠ Skipping {filename} (not found)")
|
||||
continue
|
||||
|
||||
# Read CSV
|
||||
df = pd.read_csv(filepath)
|
||||
|
||||
# Rename pickoffs back to PO if it exists
|
||||
if 'pickoffs' in df.columns:
|
||||
df = df.rename(columns={'pickoffs': 'PO'})
|
||||
df.to_csv(filepath, index=False)
|
||||
print(f"✓ {filename}: Renamed pickoffs -> PO")
|
||||
else:
|
||||
print(f"⚠ {filename}: Column 'pickoffs' not found")
|
||||
|
||||
print("\n✓ Position player defense files updated!")
|
||||
print(" defense_p.csv still has 'pickoffs' column")
|
||||
Loading…
Reference in New Issue
Block a user