Upload stuff_model/feature_engineering.py with huggingface_hub

stuff_model/feature_engineering.py

@@ -7,6 +7,29 @@ def feature_engineering(df: pl.DataFrame) -> pl.DataFrame:
         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'),
@@ -69,7 +92,7 @@ def feature_engineering(df: pl.DataFrame) -> pl.DataFrame:
     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'])
+    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(
@@ -90,7 +113,7 @@ def feature_engineering(df: pl.DataFrame) -> pl.DataFrame:
     # 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'))
+        .then(pl.col('ax').max().over('pitcher_id'))
         .otherwise(pl.col('avg_fastball_ax'))
         .alias('avg_fastball_ax')
     )
@@ -113,27 +136,8 @@ def feature_engineering(df: pl.DataFrame) -> pl.DataFrame:
         pl.lit('All').alias('all')
     ])
 
-    # 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)
-            .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")
-    ])