Upload pitch_summary_functions.py

pitch_summary_functions.py

@@ -230,6 +230,9 @@ def percentile(n):
 ### TJ STUFF+ DF CLEAN ###
 def df_clean(df):
     df_copy = df.copy()
+
+    df_copy = df_copy[(df_copy['spin_rate']>0)&(df_copy['extension']>0)]
+    
     df_copy.loc[df_copy['pitcher_hand'] == 'L','hb'] *= -1
     df_copy.loc[df_copy['pitcher_hand'] == 'L','x0'] *= -1
     df_copy.loc[df_copy['pitcher_hand'] == 'L','spin_direction'] = 360 - df_copy.loc[df_copy['pitcher_hand'] == 'L','spin_direction']
@@ -292,7 +295,7 @@ def df_clean(df):
     # df_copy['vaa'] = np.arctan(df_copy['z_diff'] / df_copy['release_pos_y']) * 360 / np.pi
     # df_copy['haa'] = np.arctan(-df_copy['x_diff'] / df_copy['release_pos_y']) * 360 / np.pi
 
-    df_copy = df_copy.dropna(subset=['pitch_type']).fillna(0)
+    df_copy = df_copy.dropna(subset=['pitch_type'])#.fillna(0)
     return df_copy
 
 ### PITCH COLOURS ###
@@ -726,7 +729,7 @@ def table_summary(df,
         plot_table = df_group[df_group['pitcher_id']==pitcher_id].sort_values(
             by=['pitches'],ascending=False)[['pitch_description','pitches','start_speed','ivb',
                     'hb', 'spin_rate','vaa', 'haa', 'vertical_release','horizontal_release',
-                    'extension','tj_stuff_plus','spin_direction_adj_clock','zone_percent','chase_percent','whiff_rate']]
+                    'extension','tj_stuff_plus','spin_direction_adj_clock','zone_percent','chase_percent','whiff_rate','xwobacon']]
 
         # if df['pitcher_hand'].values[0] == 'L':
         #     plot_table['hb'] = plot_table['hb']*-1
@@ -738,7 +741,7 @@ def table_summary(df,
 
         plot_table = plot_table[['pitch_description','pitches','pitch_percent','start_speed','ivb',
                     'hb', 'spin_rate','vaa', 'haa', 'vertical_release','horizontal_release', 
-                    'extension','spin_direction_adj_clock','tj_stuff_plus','zone_percent','chase_percent','whiff_rate']]
+                    'extension','spin_direction_adj_clock','tj_stuff_plus','zone_percent','chase_percent','whiff_rate','xwobacon']]
 
         plot_table_all = pd.DataFrame(data={'pitch_description': 'All',
         'pitches': plot_table['pitches'].sum(),
@@ -757,18 +760,21 @@ def table_summary(df,
         'zone_percent': df_group_all[df_group_all['pitcher_id']==pitcher_id]['zone_percent'].values[0],
         'chase_percent': df_group_all[df_group_all['pitcher_id']==pitcher_id]['chase_percent'].values[0],
         'whiff_rate': df_group_all[df_group_all['pitcher_id']==pitcher_id]['whiff_rate'].values[0],
+        'xwobacon': df_group_all[df_group_all['pitcher_id']==pitcher_id]['xwobacon'].values[0],
         
         
         },index=[0]
         )
-
+        print('LOOK HERE')
+        print(plot_table)
         plot_table = pd.concat([plot_table,plot_table_all]).fillna('—')
 
 
 
         plt.rcParams['font.family'] = 'Calibri'
+        
         table = ax.table(cellText=plot_table.values, colLabels=plot_table.columns, cellLoc='center',
-                        colWidths=[2.3,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1], bbox=[0.04, 0, 0.92, 0.8])
+                        colWidths=[2.3,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1], bbox=[0.04, 0, 0.92, 0.8])
 
         min_font_size = 14
         # Set table properties
@@ -777,7 +783,7 @@ def table_summary(df,
         table.set_fontsize(min_font_size)
         table.scale(1, 0.5)
 
-        min_font_size = 18
+        min_font_size = 20
         # Set font size for values
         # Adjust the font size as needed
         for i in range(len(plot_table)+1):
@@ -797,7 +803,8 @@ def table_summary(df,
                     table.get_celld()[(i+1, 0)].set_text_props(color='#ffffff',fontweight='bold')
                     if table.get_celld()[(i+1, 0)].get_text().get_text() == 'Four-Seam Fastball':
                         table.get_celld()[(i+1, 0)].get_text().set_text('4-Seam')
-
+            print('LOOK HERE 3')
+            print(statcast_pitch_summary)
             select_df = statcast_pitch_summary[statcast_pitch_summary['pitch_description'] == plot_table['pitch_description'].values[i]]
 
             normalize = mcolors.Normalize(vmin=select_df['start_speed'].mean()-select_df.pitch_velocity_std.mean(), 
@@ -834,6 +841,14 @@ def table_summary(df,
             normalize = mcolors.Normalize(vmin=select_df['whiff_rate'].mean()*0.7, vmax=select_df['whiff_rate'].mean()*1.3)
             if table.get_celld()[(i+1,16)].get_text().get_text() != '—':
                 table.get_celld()[(i+1,16)].set_facecolor(get_color(float(table.get_celld()[(i+1, 16)].get_text().get_text().strip('%')),normalize,cmap_sum))  # Header cell color
+            print("LOOK HERE")
+            print(select_df)
+            cmap_sum = matplotlib.colors.LinearSegmentedColormap.from_list("", ['#FFB000','#FFFFFF','#648FFF',]) 
+            normalize = mcolors.Normalize(vmin=select_df['xwobacon'].mean()*0.7, vmax=select_df['xwobacon'].mean()*1.3)
+            if table.get_celld()[(i+1,17)].get_text().get_text() != '—':
+                table.get_celld()[(i+1,17)].set_facecolor(get_color(float(table.get_celld()[(i+1, 17)].get_text().get_text().strip('%')),normalize,cmap_sum))  # Header cell color
+
+
 
             table.get_celld()[(len(plot_table), 0)].set_text_props(color='#000000',fontweight='bold') 
             
@@ -856,6 +871,7 @@ def table_summary(df,
             '$\\bf{Zone\%}$',
             '$\\bf{Chase\%}$',
             '$\\bf{Whiff\%}$',
+            '$\\bf{xwOBA}$\n$\\bf{Contact}$',
             ]
 
             for i, col_name in enumerate(new_column_names):
@@ -878,6 +894,21 @@ def table_summary(df,
                #     print(fl)
                     table.get_celld()[(row_l,column_indices[0])].get_text().set_text('{:,.1f}'.format(float(table.get_celld()[(row_l,column_indices[0])].get_text().get_text().strip('%'))))
 
+        float_3_list = ['xwobacon']
+        for fl in float_3_list:
+            # Subset of column names
+            subset_columns = [fl]
+            
+            # Get the list of column indices
+            column_indices = [plot_table.columns.get_loc(col) for col in subset_columns]
+            
+           # # print(column_indices)
+            for row_l in range(1,len(plot_table)+1):
+           #     print(row_l)
+                if table.get_celld()[(row_l,column_indices[0])].get_text().get_text() != '—':
+               #     print()
+               #     print(fl)
+                    table.get_celld()[(row_l,column_indices[0])].get_text().set_text('{:,.3f}'.format(float(table.get_celld()[(row_l,column_indices[0])].get_text().get_text().strip('%'))))
 
 
         percent_list = ['pitch_percent','zone_percent','chase_percent','whiff_rate']
@@ -918,7 +949,10 @@ def table_summary(df,
 ### GROUED IVB CREATION ###
 def group_ivb_update(df,
                      agg_list=['pitcher_id','pitcher_name','pitcher_hand','pitch_type','pitch_description']):
-    
+
+
+        #df.loc[df['launch_speed']==0,'launch_speed'] = np.nan
+
         grouped_ivb = df.groupby(agg_list).agg(
         pitches = ('start_speed','count'),
         
@@ -941,6 +975,9 @@ def group_ivb_update(df,
         zone_contact = ('zone_contact','sum'),
         ozone_swing = ('ozone_swing','sum'),
         ozone_contact = ('ozone_contact','sum'),    
+        woba_pred = ('woba_pred','sum'),   
+        bip = ('launch_speed','count'),   
+        
         ).reset_index()
 
 
@@ -960,6 +997,9 @@ def group_ivb_update(df,
 
         grouped_ivb['swstr_rate'] = [grouped_ivb.whiffs[x]/grouped_ivb.pitches[x] if grouped_ivb.pitches[x] != 0 else np.nan for x in range(len(grouped_ivb))]
 
+
+        grouped_ivb['xwobacon'] = [grouped_ivb.woba_pred[x]/grouped_ivb.bip[x] if grouped_ivb.bip[x] != 0 else np.nan for x in range(len(grouped_ivb))]
+
         return grouped_ivb