Upload folder using huggingface_hub

stuff_model/feature_engineering.py

@@ -1,144 +1,144 @@
-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')
-    )
-
-    # Calculate mound_to_release as 60.5 - extension
-    df = df.with_columns([
-        (60.5 - df["extension"]).alias("release_pos_y")
-    ])
-    
-    # Calculate delta time (Δt)
-    delta_t = (df["release_pos_y"] - df["y0"]) / df["vy0"]
-    # print((df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2))
-    # Corrected back-calculation of release_pos_x and release_pos_z
-
-    
-    df = df.with_columns(
-            pl.when(pl.col('pitcher_hand')== 'R')
-            .then((df["x0"] + df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2)*-1)
-            .otherwise(df["x0"] + df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2)
-            .alias('release_pos_x')
-        )
-
-    df = df.with_columns([
-        (df["z0"] + df["vz0"] * delta_t + 0.5 * df["az"] * delta_t ** 2).alias("release_pos_z")
-    ])
-
-
-    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'],how='left')
-
-    # 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('pitcher_id'))
-        .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')
-    ])
-
-
-
-
-
-    
+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')
+    )
+
+    # Calculate mound_to_release as 60.5 - extension
+    df = df.with_columns([
+        (60.5 - df["extension"]).alias("release_pos_y")
+    ])
+    
+    # Calculate delta time (Δt)
+    delta_t = (df["release_pos_y"] - df["y0"]) / df["vy0"]
+    # print((df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2))
+    # Corrected back-calculation of release_pos_x and release_pos_z
+
+    
+    df = df.with_columns(
+            pl.when(pl.col('pitcher_hand')== 'R')
+            .then((df["x0"] + df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2)*-1)
+            .otherwise(df["x0"] + df["vx0"] * delta_t + 0.5 * df["ax"] * delta_t ** 2)
+            .alias('release_pos_x')
+        )
+
+    df = df.with_columns([
+        (df["z0"] + df["vz0"] * delta_t + 0.5 * df["az"] * delta_t ** 2).alias("release_pos_z")
+    ])
+
+
+    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','FA']
+
+    # 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'],how='left')
+
+    # 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('pitcher_id'))
+        .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/stuff_apply.py

@@ -1,7 +1,7 @@
 import polars as pl
 import joblib
 
-model = joblib.load('stuff_model/lgbm_model_2020_2023.joblib')
+model = joblib.load('stuff_model/stuff_model.joblib')
 # Read the values from the text file
 with open('stuff_model/target_stats.txt', 'r') as file:
     lines = file.readlines()

stuff_model/stuff_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b14dc2756695cfa67a340dfa77616894b3ec0715c61ad73ded704fc24386e8
+size 3109736

stuff_model/target_stats.txt

@@ -1,2 +1,2 @@
-0.0034732498406374636
-0.006846752748626548
+0.0036819646648982335
+0.006743548730130907

stuff_model/tj_stuff_plus_pitch.csv

@@ -1,16 +1,18 @@
-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
+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
+FA,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
+EP,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