Upload 27 files

app.py

@@ -1,284 +1,280 @@
-import polars as pl
-import numpy as np
-import pandas as pd
-import api_scraper
-scrape = api_scraper.MLB_Scrape()
-from functions import df_update
-from functions import pitch_summary_functions
-update = df_update.df_update()
-from stuff_model import feature_engineering as fe
-from stuff_model import stuff_apply
-import requests
-import joblib
-from matplotlib.gridspec import GridSpec
-from shiny import App, reactive, ui, render
-from shiny.ui import h2, tags
-import matplotlib.pyplot as plt
-import matplotlib.gridspec as gridspec
-import seaborn as sns
-from functions.pitch_summary_functions import *
-from shiny import App, reactive, ui, render
-from shiny.ui import h2, tags
-
-colour_palette = ['#FFB000','#648FFF','#785EF0',
-                  '#DC267F','#FE6100','#3D1EB2','#894D80','#16AA02','#B5592B','#A3C1ED']
-
-
-year_list = [2017,2018,2019,2020,2021,2022,2023,2024]
-
-
-
-level_dict =  {'1':'MLB',
-               '11':'AAA',
-               '12':'AA',
-               '13':'A+',
-               '14':'A',
-               '17':'AFL',
-               '22':'College',
-               '21':'Prospects',
-               '51':'International' }
-
-function_dict={
-    'velocity_kdes':'Velocity Distributions',
-    'break_plot':'Pitch Movement',
-    'tj_stuff_roling':'Rolling tjStuff+ by Pitch',
-    'tj_stuff_roling_game':'Rolling tjStuff+ by Game',
-    'location_plot_lhb':'Locations vs LHB',
-    'location_plot_rhb':'Locations vs RHB',
-}
-
-
-split_dict =  {'all':'All',
-               'left':'LHH',
-               'right':'RHH'}
-
-split_dict_hand =  {'all':['L','R'],
-               'left':['L'],
-               'right':['R']}
-
-from shiny import App, reactive, ui, render
-from shiny.ui import h2, tags
-
-# Define the UI layout for the app
-app_ui = ui.page_fluid(
-    ui.layout_sidebar(
-        ui.panel_sidebar(
-            # Row for selecting season and level
-            ui.row(
-                ui.column(6, ui.input_select('year_input', 'Select Season', year_list, selected=2024)),
-                ui.column(6, ui.input_select('level_input', 'Select Level', level_dict))
-            ),
-            # Row for the action button to get player list
-            ui.row(ui.input_action_button("player_button", "Get Player List", class_="btn-primary")),
-            # Row for selecting the player
-            ui.row(ui.column(12, ui.output_ui('player_select_ui', 'Select Player'))),
-            # Row for selecting the date range
-            ui.row(ui.column(12, ui.output_ui('date_id', 'Select Date'))),
-
-            # Rows for selecting plots and split options
-            ui.row(
-                ui.column(4, ui.input_select('plot_id_1', 'Plot Left', function_dict, multiple=False, selected='velocity_kdes')),
-                ui.column(4, ui.input_select('plot_id_2', 'Plot Middle', function_dict, multiple=False, selected='tj_stuff_roling')),
-                ui.column(4, ui.input_select('plot_id_3', 'Plot Right', function_dict, multiple=False, selected='break_plot'))
-            ),
-            ui.row(
-                ui.column(6, ui.input_select('split_id', 'Select Split', split_dict, multiple=False)),
-                ui.column(6, ui.input_numeric('rolling_window', 'Rolling Window (for tjStuff+ Plot)', min=1, value=50))
-            ),
-            
-            # Row for the action button to generate plot
-            ui.row(ui.input_action_button("generate_plot", "Generate Plot", class_="btn-primary")),
-        ),
-                
-        ui.panel_main(
-            ui.navset_tab(
-                # Tab for game summary plot
-                ui.nav("Pitching Summary",
-                       ui.output_text("status"),
-                       ui.output_plot('plot', width='2100px', height='2100px')
-                ),
-            )
-        )
-    )
-)
-
-
-def server(input, output, session):
-
-    @reactive.calc
-    @reactive.event(input.pitcher_id, input.date_id,input.split_id)
-    def cached_data():
-
-        year_input = int(input.year_input())
-        sport_id = int(input.level_input())
-        player_input = int(input.pitcher_id())
-        start_date = str(input.date_id()[0])
-        end_date = str(input.date_id()[1])
-        # Simulate an expensive data operation
-        game_list  = scrape.get_player_games_list(sport_id = sport_id,
-                                                season = year_input, 
-                                                player_id = player_input,
-                                                start_date = start_date,
-                                                end_date = end_date)
-
-        data_list = scrape.get_data(game_list_input = game_list[:])
-        df = (stuff_apply.stuff_apply(fe.feature_engineering(update.update(scrape.get_data_df(data_list = data_list).filter(
-                            (pl.col("pitcher_id") == player_input)&
-                            (pl.col("is_pitch") == True)&
-                            (pl.col('batter_hand').is_in(split_dict_hand[input.split_id()]))
-
-                            )))).with_columns(
-                pl.col('pitch_type').count().over('pitch_type').alias('pitch_count')
-            ))
-        return df
-
-    @render.ui
-    @reactive.event(input.player_button, ignore_none=False)
-    def player_select_ui():
-        # Get the list of pitchers for the selected level and season
-        df_pitcher_info = scrape.get_players(sport_id=int(input.level_input()), season=int(input.year_input())).filter(
-            pl.col("position").is_in(['P','TWP'])).sort("name")
-        
-        # Create a dictionary of pitcher IDs and names
-        pitcher_dict = dict(zip(df_pitcher_info['player_id'], df_pitcher_info['name']))
-        
-        # Return a select input for choosing a pitcher
-        return ui.input_select("pitcher_id", "Select Pitcher", pitcher_dict, selectize=True)
-
-    @render.ui
-    @reactive.event(input.player_button, ignore_none=False)
-    def date_id():
-        # Create a date range input for selecting the date range within the selected year
-        return ui.input_date_range("date_id", "Select Date Range",
-                                   start=f"{int(input.year_input())}-01-01",
-                                   end=f"{int(input.year_input())}-12-31",
-                                   min=f"{int(input.year_input())}-01-01",
-                                    max=f"{int(input.year_input())}-12-31")
-    @output
-    @render.text
-    def status():
-        # Only show status when generating
-        if input.generate == 0:
-            return ""
-        return ""   
-    
-    @output
-    @render.plot
-    @reactive.event(input.generate_plot, ignore_none=False)   
-    def plot():     
-        # Show progress/loading notification
-        with ui.Progress(min=0, max=1) as p:
-            p.set(message="Generating plot", detail="This may take a while...")
-
-            
-            p.set(0.3, "Gathering data...")
-            year_input = int(input.year_input())
-            sport_id = int(input.level_input())
-            player_input = int(input.pitcher_id())
-            start_date = str(input.date_id()[0])
-            end_date = str(input.date_id()[1])
-
-            print(year_input, sport_id, player_input, start_date, end_date)
-
-            df = cached_data()
-            df = df.clone()
-
-            p.set(0.6, "Creating plot...")
-
-  
-            #plt.rcParams["figure.figsize"] = [10,10]
-            fig = plt.figure(figsize=(26,26))
-            plt.rcParams.update({'figure.autolayout': True})
-            fig.set_facecolor('white')
-            sns.set_theme(style="whitegrid", palette=colour_palette)
-            print('this is the one plot')
-
-            gs = gridspec.GridSpec(6, 8,
-                                height_ratios=[5,20,12,36,36,7],
-                                width_ratios=[4,18,18,18,18,18,18,4])
-
-
-            gs.update(hspace=0.2, wspace=0.5)
-
-            # Define the positions of each subplot in the grid
-            ax_headshot = fig.add_subplot(gs[1,1:3])
-            ax_bio = fig.add_subplot(gs[1,3:5])
-            ax_logo = fig.add_subplot(gs[1,5:7])
-
-            ax_season_table = fig.add_subplot(gs[2,1:7])
-
-            ax_plot_1 = fig.add_subplot(gs[3,1:3])
-            ax_plot_2 = fig.add_subplot(gs[3,3:5])
-            ax_plot_3 = fig.add_subplot(gs[3,5:7])
-
-            ax_table = fig.add_subplot(gs[4,1:7])
-
-            ax_footer = fig.add_subplot(gs[-1,1:7])
-            ax_header = fig.add_subplot(gs[0,1:7])
-            ax_left = fig.add_subplot(gs[:,0])
-            ax_right = fig.add_subplot(gs[:,-1])
-
-            # Hide axes for footer, header, left, and right
-            ax_footer.axis('off')
-            ax_header.axis('off')
-            ax_left.axis('off')
-            ax_right.axis('off')
-
-            sns.set_theme(style="whitegrid", palette=colour_palette)
-            fig.set_facecolor('white')
-
-            df_teams = scrape.get_teams()
-
-            player_headshot(player_input=player_input, ax=ax_headshot,sport_id=sport_id,season=year_input)
-            player_bio(pitcher_id=player_input, ax=ax_bio,sport_id=sport_id,year_input=year_input)
-            plot_logo(pitcher_id=player_input, ax=ax_logo, df_team=df_teams,df_players=scrape.get_players(sport_id,year_input))
-
-            stat_summary_table(df=df,
-                            ax=ax_season_table,
-                            player_input=player_input,
-                            split=input.split_id(),
-                            sport_id=sport_id)
-
-            # break_plot(df=df_plot,ax=ax2) 
-            for x,y,z in zip([input.plot_id_1(),input.plot_id_2(),input.plot_id_3()],[ax_plot_1,ax_plot_2,ax_plot_3],[1,3,5]):
-                if x == 'velocity_kdes':
-                            velocity_kdes(df,
-                            ax=y,
-                            gs=gs,
-                            gs_x=[3,4],
-                            gs_y=[z,z+2],
-                            fig=fig)
-                if x == 'tj_stuff_roling':
-                    tj_stuff_roling(df=df,
-                                window=int(input.rolling_window()),
-                                ax=y)
-                    
-                if x == 'tj_stuff_roling_game':
-                    tj_stuff_roling_game(df=df, 
-                                        window=int(input.rolling_window()),
-                                        ax=y)
-
-                if x == 'break_plot':
-                    break_plot(df = df,ax=y) 
-
-                if x == 'location_plot_lhb':
-                    location_plot(df = df,ax=y,hand='L')
-
-                if x == 'location_plot_rhb':
-                    location_plot(df = df,ax=y,hand='R')
-
-            summary_table(df=df,
-                        ax=ax_table)
-
-            plot_footer(ax_footer)   
-
-            fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
-
-
-    
-
-app = App(app_ui, server)
-
-            
-
+import polars as pl
+import numpy as np
+import pandas as pd
+import api_scraper
+scrape = api_scraper.MLB_Scrape()
+from functions import df_update
+from functions import pitch_summary_functions
+update = df_update.df_update()
+from stuff_model import feature_engineering as fe
+from stuff_model import stuff_apply
+import requests
+import joblib
+from matplotlib.gridspec import GridSpec
+from shiny import App, reactive, ui, render
+from shiny.ui import h2, tags
+import matplotlib.pyplot as plt
+import matplotlib.gridspec as gridspec
+import seaborn as sns
+from functions.pitch_summary_functions import *
+from shiny import App, reactive, ui, render
+from shiny.ui import h2, tags
+
+colour_palette = ['#FFB000','#648FFF','#785EF0',
+                  '#DC267F','#FE6100','#3D1EB2','#894D80','#16AA02','#B5592B','#A3C1ED']
+
+
+year_list = [2017,2018,2019,2020,2021,2022,2023,2024]
+
+
+
+level_dict =  {'1':'MLB',
+               '11':'AAA',
+               '12':'AA',
+               '13':'A+',
+               '14':'A',
+               '17':'AFL',
+               '22':'College',
+               '21':'Prospects',
+               '51':'International' }
+
+function_dict={
+    'velocity_kdes':'Velocity Distributions',
+    'break_plot':'Pitch Movement',
+    'tj_stuff_roling':'Rolling tjStuff+ by Pitch',
+    'tj_stuff_roling_game':'Rolling tjStuff+ by Game',
+    'location_plot_lhb':'Locations vs LHB',
+    'location_plot_rhb':'Locations vs RHB',
+}
+
+
+split_dict =  {'all':'All',
+               'left':'LHH',
+               'right':'RHH'}
+
+split_dict_hand =  {'all':['L','R'],
+               'left':['L'],
+               'right':['R']}
+
+from shiny import App, reactive, ui, render
+from shiny.ui import h2, tags
+
+# Define the UI layout for the app
+app_ui = ui.page_fluid(
+    ui.layout_sidebar(
+        ui.panel_sidebar(
+            # Row for selecting season and level
+            ui.row(
+                
+                ui.column(6, ui.input_date('date_input', 'Select Date')),
+                ui.column(6, ui.input_select('level_input', 'Select Level', level_dict))
+            ),
+            ui.row(ui.input_action_button("game_button", "Get Games", class_="btn-primary")),
+            ui.row(
+                 
+                ui.row(ui.column(12, ui.output_ui('game_select_ui', 'Select Game'))),
+                ui.row(ui.column(12, ui.output_ui('player_select_ui', 'Select Player'))),
+            ),
+
+            # Rows for selecting plots and split options
+            ui.row(
+                ui.column(4, ui.input_select('plot_id_1', 'Plot Left', function_dict, multiple=False, selected='velocity_kdes')),
+                ui.column(4, ui.input_select('plot_id_2', 'Plot Middle', function_dict, multiple=False, selected='tj_stuff_roling')),
+                ui.column(4, ui.input_select('plot_id_3', 'Plot Right', function_dict, multiple=False, selected='break_plot'))
+            ),
+            ui.row(
+                ui.column(6, ui.input_select('split_id', 'Select Split', split_dict, multiple=False)),
+                ui.column(6, ui.input_numeric('rolling_window', 'Rolling Window (for tjStuff+ Plot)', min=1, value=50))
+            ),
+            
+            # Row for the action button to generate plot
+            ui.row(ui.input_action_button("generate_plot", "Generate Plot", class_="btn-primary"))
+        ),
+                
+        ui.panel_main(
+            ui.navset_tab(
+                # Tab for game summary plot
+                ui.nav("Pitching Summary",
+                       ui.output_text("status"),
+                       ui.output_plot('plot', width='2100px', height='2100px')
+                ),
+            )
+        )
+    )
+)
+
+
+def server(input, output, session):
+
+    @render.ui
+    @reactive.event(input.game_button, ignore_none=False)   
+    def game_select_ui():
+        df = (scrape.get_schedule(year_input=[int(str(input.date_input())[:4])],
+                            sport_id=[int(input.level_input())],
+                            game_type=['S','R','P','E','A']).with_columns(pl.col('date').cast(pl.Utf8)).
+                            filter(pl.col('date') == str(input.date_input()))).with_columns(
+                                (pl.col('away')+' @ '+pl.col('home')).alias('matchup'))
+        game_dict = dict(zip(df['game_id'], df['matchup']))
+        
+        return ui.input_select("game_id", "Select Game", game_dict, selectize=True)
+    
+
+    @render.ui
+    @reactive.event(input.game_id)   
+    def player_select_ui():
+        try:
+            # Get the list of pitchers for the selected level and season
+            data_list = scrape.get_data(game_list_input = [int(input.game_id())])
+            df = (stuff_apply.stuff_apply(fe.feature_engineering(update.update(scrape.get_data_df(data_list = data_list).filter(
+                                (pl.col("is_pitch") == True)&
+                                (pl.col('batter_hand').is_in(split_dict_hand[input.split_id()]))
+
+                                )))).with_columns(
+                    pl.col('pitch_type').count().over('pitch_type').alias('pitch_count')
+                ).with_columns(
+                    (pl.col('pitcher_name')+' - '+pl.col('pitcher_team')).alias('pitcher_name'))
+                )
+            pitcher_dict = dict(zip(df['pitcher_id'], df['pitcher_name']))
+            return ui.input_select("pitcher_id", "Select Pitcher", pitcher_dict, selectize=True)
+        except Exception as e:
+            print(e)
+            return ui.output_text('pitcher_id',"No pitchers available for this game")
+
+    @output
+    @render.text
+    def status():
+        # Only show status when generating
+        if input.generate == 0:
+            return ""
+        return ""   
+    
+    @output
+    @render.plot
+    @reactive.event(input.generate_plot, ignore_none=False)   
+    def plot():     
+        # Show progress/loading notification
+        with ui.Progress(min=0, max=1) as p:
+            p.set(message="Generating plot", detail="This may take a while...")
+
+            
+            p.set(0.3, "Gathering data...")
+
+            data_list = scrape.get_data(game_list_input = [int(input.game_id())])
+            df = (stuff_apply.stuff_apply(fe.feature_engineering(update.update(scrape.get_data_df(data_list = data_list).filter(
+                                (pl.col("pitcher_id") == int(input.pitcher_id()))&
+                                (pl.col("is_pitch") == True)&
+                                (pl.col('batter_hand').is_in(split_dict_hand[input.split_id()]))
+
+                                )))).with_columns(
+                    pl.col('pitch_type').count().over('pitch_type').alias('pitch_count')
+                ))
+            df = df.clone()
+
+            p.set(0.6, "Creating plot...")
+
+  
+            #plt.rcParams["figure.figsize"] = [10,10]
+            fig = plt.figure(figsize=(26,26))
+            plt.rcParams.update({'figure.autolayout': True})
+            fig.set_facecolor('white')
+            sns.set_theme(style="whitegrid", palette=colour_palette)
+            print('this is the one plot')
+
+            gs = gridspec.GridSpec(6, 8,
+                                height_ratios=[5,20,12,36,36,7],
+                                width_ratios=[4,18,18,18,18,18,18,4])
+
+
+            gs.update(hspace=0.2, wspace=0.5)
+
+            # Define the positions of each subplot in the grid
+            ax_headshot = fig.add_subplot(gs[1,1:3])
+            ax_bio = fig.add_subplot(gs[1,3:5])
+            ax_logo = fig.add_subplot(gs[1,5:7])
+
+            ax_season_table = fig.add_subplot(gs[2,1:7])
+
+            ax_plot_1 = fig.add_subplot(gs[3,1:3])
+            ax_plot_2 = fig.add_subplot(gs[3,3:5])
+            ax_plot_3 = fig.add_subplot(gs[3,5:7])
+
+            ax_table = fig.add_subplot(gs[4,1:7])
+
+
+            ax_footer = fig.add_subplot(gs[-1,1:7])
+            ax_header = fig.add_subplot(gs[0,1:7])
+            ax_left = fig.add_subplot(gs[:,0])
+            ax_right = fig.add_subplot(gs[:,-1])
+
+            # Hide axes for footer, header, left, and right
+            ax_footer.axis('off')
+            ax_header.axis('off')
+            ax_left.axis('off')
+            ax_right.axis('off')
+
+            sns.set_theme(style="whitegrid", palette=colour_palette)
+            fig.set_facecolor('white')
+
+            df_teams = scrape.get_teams()
+
+            year_input = int(str(input.date_input())[:4])
+            sport_id = int(input.level_input())
+            player_input = int(input.pitcher_id())
+
+            player_headshot(player_input=player_input, ax=ax_headshot,sport_id=sport_id,season=year_input)
+            player_bio(pitcher_id=player_input, ax=ax_bio,sport_id=sport_id,year_input=year_input)
+            plot_logo(pitcher_id=player_input, ax=ax_logo, df_team=df_teams,df_players=scrape.get_players(sport_id,year_input))
+
+            # stat_summary_table(df=df,
+            #                 ax=ax_season_table,
+            #                 player_input=player_input,
+            #                 split=input.split_id(),
+            #                 sport_id=sport_id)
+
+            stat_daily_summary(df=df,
+                        data=data_list, 
+                        player_input=int(input.pitcher_id()), 
+                        sport_id=int(input.level_input()), 
+                        ax=ax_season_table)
+
+
+            # break_plot(df=df_plot,ax=ax2) 
+            for x,y,z in zip([input.plot_id_1(),input.plot_id_2(),input.plot_id_3()],[ax_plot_1,ax_plot_2,ax_plot_3],[1,3,5]):
+                if x == 'velocity_kdes':
+                            velocity_kdes(df,
+                            ax=y,
+                            gs=gs,
+                            gs_x=[3,4],
+                            gs_y=[z,z+2],
+                            fig=fig)
+                if x == 'tj_stuff_roling':
+                    tj_stuff_roling(df=df,
+                                window=int(input.rolling_window()),
+                                ax=y)
+                    
+                if x == 'tj_stuff_roling_game':
+                    tj_stuff_roling_game(df=df, 
+                                        window=int(input.rolling_window()),
+                                        ax=y)
+
+                if x == 'break_plot':
+                    break_plot(df = df,ax=y) 
+
+                if x == 'location_plot_lhb':
+                    location_plot(df = df,ax=y,hand='L')
+
+                if x == 'location_plot_rhb':
+                    location_plot(df = df,ax=y,hand='R')
+
+            summary_table(df=df,
+                        ax=ax_table)
+
+            plot_footer(ax_footer)   
+
+            fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
+
+
+            
+            
+
 app = App(app_ui, server)

app_streamlit.py

@@ -0,0 +1,253 @@
+import seaborn as sns
+import streamlit as st
+from st_aggrid import AgGrid, GridOptionsBuilder, GridUpdateMode
+import PitchPlotFunctions as ppf
+import requests
+import polars as pl
+from datetime import date
+import api_scraper
+
+
+
+# Display the app title and description
+st.markdown("""
+## MLB & AAA Pitch Plots App
+
+##### By: Thomas Nestico ([@TJStats](https://x.com/TJStats))
+##### Code: [GitHub Repo](https://github.com/tnestico/streamlit_pitch_plots)
+##### Data: [MLB](https://baseballsavant.mlb.com/)
+
+#### About
+This Streamlit app retrieves MLB and AAA Pitching Data for a selected pitcher from the MLB Stats API and is accessed using my [MLB Stats API Scraper](https://github.com/tnestico/mlb_scraper).
+
+The app outputs the pitcher's data into both a plot and table to illustrate and summarize the data. 
+It can also display data for games currently in progress.
+
+*More information about the data and plots is shown at the bottom of this page.*
+
+"""
+)
+
+# Initialize the plotter object from PitchPlotFunctions
+ploter = ppf.PitchPlotFunctions()
+# Initialize the scraper object
+scraper = api_scraper.MLB_Scrape()
+
+# Dictionary mapping league names to sport IDs
+sport_id_dict = {'MLB': 1, 'AAA': 11}
+
+# Create two columns for league and pitcher selection
+st.write("#### Plot")
+col_1, col_2 = st.columns(2)
+with col_1:
+    # Select league
+    selected_league = st.selectbox('##### Select League', list(sport_id_dict.keys()))
+    selected_sport_id = sport_id_dict[selected_league]
+
+with col_2:
+    # Get player data and filter for pitchers
+    df_player = scraper.get_players(sport_id=selected_sport_id)
+    df_player = df_player.filter(pl.col('position').str.contains('P'))
+    df_player = df_player.with_columns(
+        (pl.concat_str(["name", "player_id"], separator=" - ").alias("pitcher_name_id"))
+    )
+    
+    # Select specific columns and convert to dictionary
+    pitcher_name_id_dict = dict(df_player.select(['pitcher_name_id', 'player_id']).iter_rows())
+    
+    # Initialize session state for previous selection
+    if 'prev_pitcher_id' not in st.session_state:
+        st.session_state.prev_pitcher_id = None
+    
+    # Display a selectbox for pitcher selection
+    selected_pitcher = st.selectbox("##### Select Pitcher", list(pitcher_name_id_dict.keys()))
+    pitcher_id = pitcher_name_id_dict[selected_pitcher]
+
+# Clear cache if selection changes
+if pitcher_id != st.session_state.prev_pitcher_id:
+    st.cache_data.clear()
+    st.session_state.prev_pitcher_id = pitcher_id
+    st.session_state.cache_cleared = False
+    st.write('Cache cleared!')
+
+# Initialize session state for cache status
+if 'cache_cleared' not in st.session_state:
+    st.session_state.cache_cleared = False
+
+# Dictionary for batter hand selection
+batter_hand_picker = {
+    'All': ['L', 'R'],
+    'LHH': ['L'],
+    'RHH': ['R']
+}
+
+# Define date range for the season
+min_date = date(2024, 3, 20)
+max_date = date(2024, 11, 30)
+
+# Create columns for input widgets
+st.write("##### Filters")
+col1, col2, col3 = st.columns(3)
+with col1:
+    # Selectbox for batter handedness
+    batter_hand_select = st.selectbox('Batter Handedness:', list(batter_hand_picker.keys()))
+    batter_hand = batter_hand_picker[batter_hand_select]
+with col2:
+    # Date input for start date
+    start_date = st.date_input('Start Date:', 
+                  value=min_date, 
+                  min_value=min_date, 
+                  max_value=max_date, 
+                  format="YYYY-MM-DD")
+with col3:
+    # Date input for end date
+    end_date = st.date_input('End Date:', 
+                  value="default_value_today", 
+                  min_value=min_date, 
+                  max_value=max_date, 
+                  format="YYYY-MM-DD")
+
+# Dictionary for plot type selection
+plot_picker_dict = {
+    'Short Form Movement': 'short_form_movement',
+    'Long Form Movement': 'long_form_movement',
+    'Release Points': 'release_point'
+}
+
+# Selectbox for plot type
+plot_picker_select = st.selectbox('Select Plot Type:', list(plot_picker_dict.keys()))
+plot_picker = plot_picker_dict[plot_picker_select]
+
+# Extract season from start date
+season = str(start_date)[0:4]
+
+# Get list of games for the selected player and date range
+player_games = scraper.get_player_games_list(player_id=pitcher_id, season=season,
+                                             start_date=str(start_date), end_date=str(end_date),
+                                             sport_id=selected_sport_id,
+                                             game_type = ['R','P'])
+
+# Function to fetch data and cache it
+@st.cache_data
+def fetch_data():
+    data = scraper.get_data(game_list_input=player_games)
+    df = scraper.get_data_df(data_list=data)
+    return df
+
+# Fetch data and manage cache status
+if not st.session_state.cache_cleared:
+    df_original = fetch_data()
+    st.session_state.cache_cleared = True
+else:
+    df_original = fetch_data()
+
+# Button to generate plot
+if st.button('Generate Plot'):
+    try:
+        # Convert dataframe to polars and filter based on inputs
+        df = ploter.df_to_polars(df_original=df_original,
+                                 pitcher_id=pitcher_id,
+                                 start_date=str(start_date),
+                                 end_date=str(end_date),
+                                 batter_hand=batter_hand)
+        print(df)
+        if len(df) == 0:
+            st.write('Please select different parameters.')
+        else:
+            # Generate the final plot
+            ploter.final_plot(
+                df=df,
+                pitcher_id=pitcher_id,
+                plot_picker=plot_picker,
+                sport_id=selected_sport_id)
+            
+            # Use a container to control the width of the AgGrid display
+            with st.container():
+                # Group the data by pitch type
+                grouped_df = (
+                    df.group_by(['pitcher_id', 'pitch_description'])
+                    .agg([
+                        pl.col('is_pitch').drop_nans().count().alias('pitches'),
+                        pl.col('start_speed').drop_nans().mean().round(1).alias('start_speed'),
+                        pl.col('vb').drop_nans().mean().round(1).alias('vb'),
+                        pl.col('ivb').drop_nans().mean().round(1).alias('ivb'),
+                        pl.col('hb').drop_nans().mean().round(1).alias('hb'),
+                        pl.col('spin_rate').drop_nans().mean().round(0).alias('spin_rate'),
+                        pl.col('x0').drop_nans().mean().round(1).alias('x0'),
+                        pl.col('z0').drop_nans().mean().round(1).alias('z0'),
+                    ])
+                    .with_columns(
+                        (pl.col('pitches') / pl.col('pitches').sum().over('pitcher_id') * 100).round(3).alias('proportion')
+                    )).sort('proportion', descending=True).select(["pitch_description", "pitches", "proportion", "start_speed", "vb", "ivb", "hb",
+                                                                   "spin_rate", "x0", "z0"])
+
+                st.write("#### Pitching Data")
+                column_config_dict = {
+                    'pitcher_id': 'Pitcher ID',
+                    'pitch_description': 'Pitch Type',
+                    'pitches': 'Pitches',
+                    'start_speed': 'Velocity',
+                    'vb': 'VB',
+                    'ivb': 'iVB',
+                    'hb': 'HB',
+                    'spin_rate': 'Spin Rate',
+                    'proportion': st.column_config.NumberColumn("Pitch%", format="%.1f%%"),
+                    'x0': 'hRel',
+                    'z0': 'vRel',
+                }
+
+                st.markdown(f"""##### {selected_pitcher.split('-')[0]} {selected_league} Pitch Data""")
+                st.dataframe(grouped_df,
+                             hide_index=True,
+                             column_config=column_config_dict,
+                             width=1500)
+
+                # Configure the AgGrid options
+                # gb = GridOptionsBuilder.from_dataframe(grouped_df)
+                # # Set display names for columns
+                # for col, display_name in zip(grouped_df.columns, grouped_df.columns):
+                #     gb.configure_column(col, headerName=display_name)
+
+                # grid_options = gb.build()
+
+                # # Display the dataframe using AgGrid
+                # grid_response = AgGrid(
+                #     grouped_df,
+                #     gridOptions=grid_options,
+                #     height=300,
+                #     allow_unsafe_jscode=True,
+                # )
+
+    except IndexError:
+        st.write('Please select different parameters.')
+
+# Display column and plot descriptions
+st.markdown("""
+#### Column Descriptions
+
+- **`Pitch Type`**: Describes the type of pitch thrown (e.g., 4-Seam Fastball, Curveball, Slider).
+- **`Pitches`**: The total number of pitches thrown by the pitcher.
+- **`Pitch%`**: Proportion of pitch thrown.
+- **`Velocity`**: The initial velocity of the pitch as it leaves the pitcher's hand, measured in miles per hour (mph).
+- **`VB`**: Vertical Break (VB), representing the amount movement of a pitch due to spin and gravity, measured in inches (in).
+- **`iVB`**: Induced Vertical Break (iVB), representing the amount movement of a pitch strictly due to the spin imparted on the ball, measured in inches (in).
+- **`HB`**: Horizontal Break (HB), indicating the amount of horizontal movement of a pitch, measured in inches (in).
+- **`Spin Rate`**: The rate of spin of the pitch as it is released, measured in revolutions per minute (rpm).
+- **`hRel`**: The horizontal release point of the pitch, measured in feet from the center of the pitcher's mound (ft).
+- **`vRel`**: The vertical release point of the pitch, measured in feet above the ground (ft).
+
+#### Plot Descriptions
+
+- **`Short Form Movement`**: Illustrates the movement of the pitch due to spin, where (0,0) indicates a pitch with perfect gyro-spin (e.g. Like a Football).
+- **`Long Form Movement`**: Illustrates the movement of the pitch due to spin and gravity.
+- **`Release Points`**: Illustrates a pitchers release points from the catcher's perspective.
+
+#### Acknowledgements
+
+Big thanks to [Michael Rosen](https://twitter.com/bymichaelrosen) and [Jeremy Maschino](https://twitter.com/pitchprofiler) for inspiration for this project
+
+Check Out Michael's [Pitch Plotting App](https://pitchplotgenerator.streamlit.app/)
+
+Check Out Jeremy's Website [Pitch Profiler](http://www.mlbpitchprofiler.com/)
+"""
+)

functions/pitch_summary_functions.py

@@ -866,7 +866,7 @@ def plot_logo(pitcher_id: str, ax: plt.Axes, df_team: pl.DataFrame, df_players:
 
         # Turn off the axis
         ax.axis('off')
-    except KeyError:
+    except (KeyError,IndexError) as e:
         ax.axis('off')
         return
 
@@ -1121,3 +1121,149 @@ def stat_summary_table(df: pl.DataFrame,
     # Add title to the plot
     ax.text(0.5, 0.9, title, va='bottom', ha='center', fontsize=36, fontstyle='italic')
     ax.axis('off')
+
+
+
+def stat_daily_summary(df: pl.DataFrame,
+                        data: list, 
+                        player_input: int, 
+                        sport_id: int, 
+                        ax: plt.Axes):
+ 
+        
+        pk_list = []
+        pitcher_id_list = []
+        summary_list = []
+        ip_list = []
+        pa_list = []
+        er_list = []
+        hit_list = []
+        k_list = []
+        bb_list = []
+        hbp_list = []
+        strikes_list = []
+        hr_list = []
+        test_list = []
+        game_pk_list = []
+        pitches_list = []
+
+
+        # 'inningsPitched','battersFaced','earnedRuns','hits','strikeOuts','baseOnBalls','hitByPitch'
+
+        for y in range(0,len(data)):
+                
+            pk_list.append([data[y]['gameData']['game']['pk'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            pk_list.append([data[y]['gameData']['game']['pk'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            pitcher_id_list.append([x for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            pitcher_id_list.append([x for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+
+            ip_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['inningsPitched'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            ip_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['inningsPitched'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            pa_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['battersFaced'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            pa_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['battersFaced'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            er_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['earnedRuns'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            er_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['earnedRuns'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            hit_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['hits'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            hit_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['hits'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            k_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['strikeOuts'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            k_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['strikeOuts'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            bb_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['baseOnBalls'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            bb_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['baseOnBalls'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            hbp_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['hitByPitch'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            hbp_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['hitByPitch'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            strikes_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['strikes'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            strikes_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['strikes'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            pitches_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['pitchesThrown'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+            pitches_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['pitchesThrown'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+                        
+            
+            hr_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['homeRuns'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            hr_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['homeRuns'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+            
+            summary_list.append([data[y]['liveData']['boxscore']['teams']['away']['players']['ID'+str(x)]['stats']['pitching']['summary'] for x in data[y]['liveData']['boxscore']['teams']['away']['pitchers']])
+            summary_list.append([data[y]['liveData']['boxscore']['teams']['home']['players']['ID'+str(x)]['stats']['pitching']['summary'] for x in data[y]['liveData']['boxscore']['teams']['home']['pitchers']])
+
+            test_list.append([x for x in data[y]['liveData']['plays']['allPlays']])
+            game_pk_list.append([data[y]['gameData']['game']['pk'] for x in data[y]['liveData']['plays']['allPlays']])
+
+        flat_list_pk = [item for sublist in pk_list for item in sublist]
+        flat_list_pitcher_id = [item for sublist in pitcher_id_list for item in sublist]
+        flat_list_summary = [item for sublist in summary_list for item in sublist]
+        flat_list_hits = [item for sublist in hit_list for item in sublist]
+        flat_list_k = [item for sublist in k_list for item in sublist]
+        flat_list_bb = [item for sublist in bb_list for item in sublist]
+        flat_list_pa = [item for sublist in pa_list for item in sublist]
+        flat_list_ip = [item for sublist in ip_list for item in sublist]
+        flat_list_hbp= [item for sublist in hbp_list for item in sublist]
+        flat_list_strikes = [item for sublist in strikes_list for item in sublist]
+        flat_list_hr= [item for sublist in hr_list for item in sublist]
+        flat_list_er= [item for sublist in er_list for item in sublist]
+        flat_list_pitches= [item for sublist in pitches_list for item in sublist]
+
+
+
+        pitcher_summary_df = pl.DataFrame(data={'game_id':flat_list_pk,
+                                                'pitcher_id':flat_list_pitcher_id,
+                                                'summary':flat_list_summary,
+                                                'hits':flat_list_hits,
+                                                'k':flat_list_k,
+                                                'bb':flat_list_bb,
+                                                'pa':flat_list_pa,
+                                                'hbp':flat_list_hbp,
+                                                'strikes':flat_list_strikes,
+                                                'hr':flat_list_hr,
+                                                'ip':flat_list_ip,
+                                                'er':flat_list_er,
+                                                'pitches':flat_list_pitches})
+
+
+
+        # Add additional calculated columns
+        pitcher_summary_df = pitcher_summary_df.filter(pl.col('pitcher_id')==player_input).with_columns(
+            pl.lit(df['is_whiff'].sum()).alias('whiffs'),
+            ((pl.col('strikes'))/(pl.col('pitches'))*100).round(1).cast(pl.Utf8).str.concat('%').alias('strikePercentage')
+        )
+
+        # Determine columns and title based on game count and sport ID
+        
+        pitcher_stats_call_df_small = pitcher_summary_df.select(['ip', 
+                                                                    'pa', 
+                                                                    'er', 
+                                                                    'hits', 
+                                                                    'k', 
+                                                                    'bb', 
+                                                                    'hbp', 
+                                                                    'hr', 
+                                                                    'strikePercentage', 
+                                                                    'whiffs'])
+        
+        new_column_names = ['$\\bf{IP}$', '$\\bf{PA}$', '$\\bf{ER}$', '$\\bf{H}$', '$\\bf{K}$', '$\\bf{BB}$', '$\\bf{HBP}$', '$\\bf{HR}$', '$\\bf{Strike\%}$', '$\\bf{Whiffs}$']
+        title = f'{df["game_date"][0]} vs {df["batter_team"][0]}'
+
+        table_fg = ax.table(cellText=pitcher_stats_call_df_small.to_numpy(), colLabels=pitcher_stats_call_df_small.columns, cellLoc='center',
+                        bbox=[0.0, 0.1, 1, 0.7])
+        
+        min_font_size = 20
+        table_fg.set_fontsize(min_font_size)
+
+
+        new_column_names = ['$\\bf{IP}$','$\\bf{PA}$','$\\bf{ER}$','$\\bf{H}$','$\\bf{K}$','$\\bf{BB}$','$\\bf{HBP}$','$\\bf{HR}$','$\\bf{Strike\%}$','$\\bf{Whiffs}$']
+        # #new_column_names = ['Pitch Name', 'Pitch%', 'Velocity', 'Spin Rate','Exit Velocity', 'Whiff%', 'CSW%']
+        for i, col_name in enumerate(new_column_names):
+            table_fg.get_celld()[(0, i)].get_text().set_text(col_name)
+
+        ax.axis('off')
+
+        # Add title to the plot
+        ax.text(0.5, 0.9, title, va='bottom', ha='center', fontsize=36, fontstyle='italic')
+        ax.axis('off')

requirements.txt

@@ -1,14 +1,12 @@
-joblib==1.3.2
-lightgbm
-matplotlib==3.5.1
-numpy==1.23.5
-pandas==1.5.2
-polars==1.12.0
-Requests==2.31.0
-scipy==1.11.1
-seaborn==0.11.1
-scikit-learn==1.0.1
-shiny==0.6.1
-Jinja2==3.1.4
-tqdm==4.62.3
-
+joblib==1.4.2
+matplotlib==3.5.1
+numpy==1.22.1
+pandas==2.0.3
+Pillow==11.0.0
+polars==1.12.0
+pytz==2022.7.1
+Requests==2.32.3
+seaborn==0.11.1
+shiny==0.7.1
+streamlit==1.37.1
+tqdm==4.62.3