Delete stuff_model

stuff_model/feature_engineering.py

@@ -1,118 +0,0 @@
-import polars as pl
-import numpy as np
-
-def feature_engineering(df: pl.DataFrame) -> pl.DataFrame:
-    # Extract the year from the game_date column
-    df = df.with_columns(
-        pl.col('game_date').str.slice(0, 4).alias('year')
-    )
-
-    df = df.with_columns([
-        
-        (-(pl.col('vy0')**2 - (2 * pl.col('ay') * (pl.col('y0') - 17/12)))**0.5).alias('vy_f'),
-        ])
-
-    df = df.with_columns([
-        ((pl.col('vy_f') - pl.col('vy0')) / pl.col('ay')).alias('t'),
-        ])
-
-    df = df.with_columns([
-        (pl.col('vz0') + (pl.col('az') * pl.col('t'))).alias('vz_f'),
-        (pl.col('vx0') + (pl.col('ax') * pl.col('t'))).alias('vx_f')
-        ])
-
-    df = df.with_columns([
-            (-np.arctan(pl.col('vz_f') / pl.col('vy_f')) * (180 / np.pi)).alias('vaa'),
-            (-np.arctan(pl.col('vx_f') / pl.col('vy_f')) * (180 / np.pi)).alias('haa')
-        ])
-
-    # Mirror horizontal break for left-handed pitchers
-    df = df.with_columns(
-        pl.when(pl.col('pitcher_hand') == 'L')
-        .then(-pl.col('ax'))
-        .otherwise(pl.col('ax'))
-        .alias('ax')
-    )
-
-    # Mirror horizontal break for left-handed pitchers
-    df = df.with_columns(
-        pl.when(pl.col('pitcher_hand') == 'L')
-        .then(-pl.col('hb'))
-        .otherwise(pl.col('hb'))
-        .alias('hb')
-    )
-
-    # Mirror horizontal release point for left-handed pitchers
-    df = df.with_columns(
-        pl.when(pl.col('pitcher_hand') == 'L')
-        .then(pl.col('x0'))
-        .otherwise(-pl.col('x0'))
-        .alias('x0')
-    )
-
-    # Define the pitch types to be considered
-    pitch_types = ['SI', 'FF', 'FC']
-
-    # Filter the DataFrame to include only the specified pitch types
-    df_filtered = df.filter(pl.col('pitch_type').is_in(pitch_types))
-
-    # Group by pitcher_id and year, then aggregate to calculate average speed and usage percentage
-    df_agg = df_filtered.group_by(['pitcher_id', 'year', 'pitch_type']).agg([
-        pl.col('start_speed').mean().alias('avg_fastball_speed'),
-        pl.col('az').mean().alias('avg_fastball_az'),
-        pl.col('ax').mean().alias('avg_fastball_ax'),
-        pl.len().alias('count')
-    ])
-
-    # Sort the aggregated data by count and average fastball speed
-    df_agg = df_agg.sort(['count', 'avg_fastball_speed'], descending=[True, True])
-    df_agg = df_agg.unique(subset=['pitcher_id', 'year'], keep='first')
-
-    # Join the aggregated data with the main DataFrame
-    df = df.join(df_agg, on=['pitcher_id', 'year'])
-
-    # If no fastball, use the fastest pitch for avg_fastball_speed
-    df = df.with_columns(
-        pl.when(pl.col('avg_fastball_speed').is_null())
-        .then(pl.col('start_speed').max().over('pitcher_id'))
-        .otherwise(pl.col('avg_fastball_speed'))
-        .alias('avg_fastball_speed')
-    )
-
-    # If no fastball, use the fastest pitch for avg_fastball_az
-    df = df.with_columns(
-        pl.when(pl.col('avg_fastball_az').is_null())
-        .then(pl.col('az').max().over('pitcher_id'))
-        .otherwise(pl.col('avg_fastball_az'))
-        .alias('avg_fastball_az')
-    )
-
-    # If no fastball, use the fastest pitch for avg_fastball_ax
-    df = df.with_columns(
-        pl.when(pl.col('avg_fastball_ax').is_null())
-        .then(pl.col('ax').max().over('ax'))
-        .otherwise(pl.col('avg_fastball_ax'))
-        .alias('avg_fastball_ax')
-    )
-
-    # Calculate pitch differentials
-    df = df.with_columns(
-        (pl.col('start_speed') - pl.col('avg_fastball_speed')).alias('speed_diff'),
-        (pl.col('az') - pl.col('avg_fastball_az')).alias('az_diff'),
-        (pl.col('ax') - pl.col('avg_fastball_ax')).abs().alias('ax_diff')
-    )
-
-    # Cast the year column to integer type
-    df = df.with_columns(
-        pl.col('year').cast(pl.Int64)
-    )
-
-
-    
-    df = df.with_columns([
-        pl.lit('All').alias('all')
-    ])
-
-
-    
-    return df

stuff_model/lgbm_model_2020_2023.joblib

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:41001a1acf6ce7dbe247f1b8b7e68a1bb1b112f39d080b7e95a83479e56cb7c1
-size 3092328

stuff_model/stuff_apply.py

@@ -1,57 +0,0 @@
-import polars as pl
-import joblib
-
-model = joblib.load('stuff_model/lgbm_model_2020_2023.joblib')
-# Read the values from the text file
-with open('stuff_model/target_stats.txt', 'r') as file:
-    lines = file.readlines()
-    target_mean = float(lines[0].strip())
-    target_std = float(lines[1].strip())
-    
-# Define the features to be used for training
-features = ['start_speed',
-            'spin_rate',
-            'extension',
-            'az',
-            'ax',
-            'x0',
-            'z0',
-            'speed_diff',
-            'az_diff',
-            'ax_diff']
-
-
-def stuff_apply(df:pl.DataFrame) -> pl.DataFrame:
-    # Filter the dataframe to include only the rows for the year 2024 and drop rows with null values in the specified features and target column
-    # df_test = df.drop_nulls(subset=features)
-    df_test = df.clone()
-
-    # Predict the target values for the 2024 data using the trained model
-    df_test = df_test.with_columns(
-        pl.Series(name="target", values=model.predict(df_test[features].to_numpy()))
-    )
-    # Standardize the target column to create a z-score
-    df_test = df_test.with_columns(
-        ((pl.col('target') - target_mean) / target_std).alias('target_zscore')
-    )
-
-    # Convert the z-score to tj_stuff_plus
-    df_test = df_test.with_columns(
-        (100 - (pl.col('target_zscore') * 10)).alias('tj_stuff_plus')
-    )
-
-    df_pitch_types = pl.read_csv('stuff_model/tj_stuff_plus_pitch.csv')
-
-    # Join the pitch type statistics with the main DataFrame based on pitch_type
-    df_pitch_all = df_test.join(df_pitch_types, left_on='pitch_type', right_on='pitch_type')
-
-    # Normalize pitch_grade values to a range between -0.5 and 0.5 based on the percentiles
-    df_pitch_all = df_pitch_all.with_columns(
-        ((pl.col('tj_stuff_plus') - pl.col('mean')) / pl.col('std')).alias('pitch_grade')
-    )
-
-    # Scale the pitch_grade values to a range between 20 and 80
-    df_pitch_all = df_pitch_all.with_columns(
-        (pl.col('pitch_grade') * 10 + 50).clip(20, 80)
-    )
-    return df_pitch_all

stuff_model/target_stats.txt

@@ -1,2 +0,0 @@
-0.0034732498406374636
-0.006846752748626548

stuff_model/tj_stuff_plus_pitch.csv

@@ -1,16 +0,0 @@
-pitch_type,mean,std,median,min,max,percentile_1,percentile_99
-ST,106.44784631565936,5.593943599731136,106.24878922952112,91.18894850636659,125.29541262167034,91.69322149368426,125.25688309207108
-SV,103.73183202363764,3.001226780758946,103.50047554089315,93.3173875900245,111.34757479687066,93.32953434698274,111.33689503153641
-SL,103.49296290610897,5.265572779780409,103.19144262214559,88.84957017284297,121.88798777026031,89.76670287371176,121.36013955239422
-KC,101.8993919341341,4.271694896723436,100.79211889194949,93.69754063161618,119.4933202093256,93.75149298057133,119.38166236091195
-All,99.9275100894791,5.01699442232884,99.65265124489378,84.73033633038408,116.94934527087541,86.65905811630736,116.7610246502804
-CU,99.88832068607897,4.615228571103906,99.08993373693156,89.84495168337246,119.90089262632986,90.20429983334718,117.89567125997061
-FC,98.83449547008738,5.811964883678063,98.54483029899575,83.20928731685326,119.78700324933075,83.34007602984008,118.21186533190846
-FS,98.25541635267653,6.898952096824192,98.46204303842217,72.25450024197754,114.88400714657823,73.39595959354874,114.78967217449389
-FO,98.15224613640243,1.081819065809178,99.94816563615653,94.0023252668585,100.50624750619224,94.0142169475971,100.50513134245217
-FF,97.29024735737988,6.078459125845886,97.09670890504734,81.2230917971995,118.10419744965911,81.32311771953398,117.7938724746093
-SC,97.27958020025409,1.2452898498180456,97.27958020025409,93.536223938276,101.02293646223218,93.54371065079995,101.01544974970822
-CH,96.35866365133434,6.178939251378385,95.80884625564597,81.28802319264824,121.14136334013493,82.02275793969746,119.09639344796777
-SI,95.14161603816645,4.9734372581529955,95.11657827702109,82.5850956341191,112.99618112461533,82.8856383780296,112.72626192694757
-CS,93.97853627048322,0.0,93.97853627048322,93.97853627048322,93.97853627048322,93.97853627048322,93.97853627048322
-KN,93.41890096234394,0.0,93.41890096234394,93.41890096234394,93.41890096234394,93.41890096234394,93.41890096234394