Upload 2 files

api_scraper.py

@@ -855,6 +855,8 @@ class MLB_Scrape:
             height_list = [x['height'] if 'height' in x else None for x in player_data]
             age_list = [x['currentAge'] if 'currentAge' in x else None for x in player_data]
             birthDate_list = [x['birthDate'] if 'birthDate' in x else None for x in player_data]
+            pitchHand_list = [x['pitchHand']['code'] if 'pitchHand' in x else None for x in player_data]
+            batSide_list = [x['batSide']['code'] if 'batSide' in x else None for x in player_data]
     
             df = pl.DataFrame(data={
                 'player_id': id_list,
@@ -866,7 +868,9 @@ class MLB_Scrape:
                 'weight': weight_list,
                 'height': height_list,
                 'age': age_list,
-                'birthDate': birthDate_list
+                'birthDate': birthDate_list,
+                'pitchHand': pitchHand_list,
+                'batSide': batSide_list
             })
                 
         return df

app.py

@@ -1,153 +1,222 @@
-import polars as pl
-import numpy as np
-import joblib
-from shiny import App, reactive, render, ui
-import matplotlib.pyplot as plt
-import matplotlib.ticker as tkr
-import seaborn as sns
-import adjustText
-sns.set_style('whitegrid')
-
-
-import matplotlib
-cmap_sum = matplotlib.colors.LinearSegmentedColormap.from_list("", ['#FFFFFF','#FFB000','#FE6100'])
-
-xwoba_model = joblib.load('joblib_model/xwoba_model.joblib')
-
-x = np.arange(-30,90.5,.5)
-y = np.arange(0,120.5,0.1)
-
-xx, yy = np.meshgrid(x, y)
-
-df = pl.DataFrame({'launch_angle': xx.ravel(), 'launch_speed': yy.ravel()})
-
-df = df.with_columns(
-    pl.Series('xwoba', xwoba_model.predict_proba(df.select(['launch_angle','launch_speed'])) @ [0, 0.883, 1.244, 1.569, 2.004])
-)
-
-df = df.with_columns(
-    pl.Series('xslg', xwoba_model.predict_proba(df.select(['launch_angle','launch_speed'])) @ [0, 1, 2, 3, 4])
-)
-
-app_ui = ui.page_sidebar(
-    ui.sidebar(
-        ui.markdown("""
-        ### How to use this app
-        
-        1. Click anywhere on the plot to select a point, or manually enter coordinates
-        2. The selected point's coordinates will update automatically
-        3. The xwOBA value will be calculated based on these coordinates
-        """),
-        ui.hr(),
-        ui.input_numeric("x_select", "Launch Speed (mph)", value=110),
-        ui.input_numeric("y_select", "Launch Angle (°)", value=30),
-        ui.input_switch("flip_stat", "xwOBA", value=False),
-
-
-    ),
-    ui.output_plot("plot",width='900px',height='900px', click=True)
-)
-
-
-def server(input, output, session):
-    # Store the coordinates in reactive values
-    x_coord = reactive.value(110)
-    y_coord = reactive.value(30)
-    
-    @reactive.effect
-    @reactive.event(input.plot_click)
-    def _():
-        # Update reactive values when plot is clicked
-        click_data = input.plot_click()
-        if click_data is not None:
-            x_coord.set(click_data["x"])
-            y_coord.set(click_data["y"])
-            # Update the numeric inputs
-            ui.update_numeric("x_select", value=round(click_data["x"],1))
-            ui.update_numeric("y_select", value=round(click_data["y"],1))
-    
-    @reactive.effect
-    @reactive.event(input.x_select, input.y_select)
-    def _():
-        # Update reactive values when numeric inputs change
-        x_coord.set(round(input.x_select(),1))
-        y_coord.set(round(input.y_select(),1))
-
-
-    @render.plot
-    def plot():
-        switch = input.flip_stat()
-        fig, ax = plt.subplots(1, 1, figsize=(9, 9))
-
-
-        if switch:
-            h = ax.hexbin(df['launch_speed'], 
-                        df['launch_angle'],
-                        C=df['xwoba'], 
-                        gridsize=(40,25), 
-                        cmap=cmap_sum,
-                        vmin=0.0,
-                        vmax=2.0,)
-            bounds=[0.0,0.4,0.8,1.2,1.6,2.0]
-            fig.colorbar(h, ax=ax, label='xwOBA',format=tkr.FormatStrFormatter('%.3f'),shrink=0.5,
-                        ticks=bounds)
-            
-        else:
-            h = ax.hexbin(df['launch_speed'], 
-                        df['launch_angle'],
-                        C=df['xslg'], 
-                        gridsize=(40,25), 
-                        cmap=cmap_sum,
-                        vmin=0.0,
-                        vmax=4.0,)
-            bounds=[0.0,0.5,1,1.5,2,2.5,3,3.5,4]
-            fig.colorbar(h, ax=ax, label='xSLG',format=tkr.FormatStrFormatter('%.3f'),shrink=0.5,
-                        ticks=bounds)
-
-
-
-        ax.set_xlabel('Launch Speed')
-        ax.set_ylabel('Launch Angle')
-        if switch:
-            ax.set_title('Exit Velocity vs Launch Angle\nExpected Weighted On Base Average (xwOBA)\nBy: @TJStats, Data:MLB')
-        else:
-            ax.set_title('Exit Velocity vs Launch Angle\nExpected Total Bases (xSLG)\nBy: @TJStats, Data:MLB')
-            
-        ax.grid(False)
-        ax.axis('square')
-        ax.set_xlim(0, 120)
-        ax.set_ylim(-30, 90)
-
-        x_select = input.x_select()
-        y_select = input.y_select()
-
-
-        sns.scatterplot(x=[x_select],y=[y_select],color='#648FFF',s=50,ax=ax,edgecolor='k',zorder=100)
-
-        
-        if switch:
-            xwoba_value = (xwoba_model.predict_proba([[y_select,x_select]]) @ [0, 0.883, 1.244, 1.569, 2.004])[0]
-            texts = [ax.text(x_select+3, y_select+3, f'xwOBA: {xwoba_value:.3f}', color='black', fontsize=12, weight='bold',
-                            zorder=1000, bbox=dict(facecolor='white', alpha=0.5, edgecolor='black'))]
-    
-        else:
-            xwoba_value = (xwoba_model.predict_proba([[y_select,x_select]]) @ [0, 1, 2, 3, 4])[0]
-            texts = [ax.text(x_select+3, y_select+3, f'xSLG: {xwoba_value:.3f}', color='black', fontsize=12, weight='bold',
-                            zorder=1000, bbox=dict(facecolor='white', alpha=0.5, edgecolor='black'))]
-    
-
-
-
-        adjustText.adjust_text(texts,
-
-                                arrowprops=dict(arrowstyle='->', color='#DC267F'),avoid_self=True,
-                                min_arrow_len =5)
-        # xwoba_value = 
-
-        ax.axhline(y=y_select, color='k', linestyle='--',linewidth=1,alpha=0.5)
-        ax.axvline(x=x_select, color='k', linestyle='--',linewidth=1,alpha=0.5)
-
-        # ax.axis('square')
-
-
+import polars as pl
+import numpy as np
+import pandas as pd
+import api_scraper
+scrape = api_scraper.MLB_Scrape()
+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 shiny import App, reactive, ui, render
+from shiny.ui import h2, tags
+
+
+from shiny import App, ui, render
+
+
+# Import the MLB_Scrape class from the module
+from api_scraper import MLB_Scrape
+
+# Initialize the scraper
+scraper = MLB_Scrape()
+
+
+# Call the get_teams method
+teams = scraper.get_teams()
+print(teams)
+
+df_player = pl.concat([
+    scraper.get_players(sport_id=1,season=2025,game_type=['R']),
+    scraper.get_players(sport_id=11,season=2025,game_type=['R']),
+    scraper.get_players(sport_id=12,season=2025,game_type=['R']),
+    scraper.get_players(sport_id=13,season=2025,game_type=['R']),
+    scraper.get_players(sport_id=14,season=2025,game_type=['R']),
+    scraper.get_players(sport_id=22,season=2025,game_type=['R'])
+]).unique(subset=['player_id'])
+
+
+
+teams_mlb = teams.filter(pl.col("league_id").is_in([103,104])).sort("abbreviation")
+teams_dict = dict(zip(teams_mlb['team_id'],teams_mlb['abbreviation']))
+
+teams_name_dict = dict(zip(teams_mlb['team_id'],teams_mlb['franchise']))
+
+app_ui = ui.page_sidebar(
+    ui.sidebar(
+        ui.input_select(
+            "team_id",
+            "Select Team",
+            choices=teams_dict
+        ),
+        ui.input_switch("nri_only", "NRI Only"),
+        ui.div(
+            ui.div({"style": "font-size:1.2em;"}, ui.markdown("Legend")),
+            ui.div(
+                style="display: inline-block; width: 20px; height: 20px; background-color:  #b7e1cd; margin-right: 10px;"
+            ),
+            ui.span("NRI", style="vertical-align: top;"),
+            style="padding: 10px;"
+        ),
+
+    ),
+    ui.card(
+        ui.div({"style": "font-size:2em;"}, ui.output_text("card_title")),
+
+        ui.output_table("team_stats")
+    )
+)
+
+def server(input, output, session):
+
+    @render.text
+    def card_title():
+        if input.nri_only():
+            return f"{teams_name_dict[int(input.team_id())]} — Spring Training Roster Non-Roster Invitees"
+        else:
+            return f"{teams_name_dict[int(input.team_id())]} — Spring Training Roster"
+
+    @render.table
+    def team_stats():
+        # Get the selected team's data
+        i = int(input.team_id())
+
+        url = f'https://statsapi.mlb.com/api/v1/teams/{i}/roster/40man?season=2025'
+        data = requests.get(url).json()
+        # Normalize the roster data
+        roster_df = pd.json_normalize(data['roster'])
+        roster_df['nri'] = False
+        roster_df['status.code'] = ''
+        roster_df = roster_df.fillna('')
+
+
+        url = f'https://statsapi.mlb.com/api/v1/teams/{i}/roster/nonRosterInvitees?season=2025'
+        data = requests.get(url).json()
+        # Normalize the roster data
+        nri_roster_df = pd.json_normalize(data['roster'])
+        nri_roster_df['nri'] = True
+        nri_roster_df['parentTeamId'] = i
+        nri_roster_df = nri_roster_df.fillna('')
+
+        df_output = pd.concat([roster_df,nri_roster_df]).sort_values(by=['position.code','status.code']).reset_index(drop=True)
+        if input.nri_only():
+            df_output = df_output[df_output['status.code'] == 'NRI']
+
+        
+        df_output = df_output.merge(df_player.to_pandas(),left_on='person.id',right_on='player_id',how='left')
+
+        conditions = [
+            (df_output['position.abbreviation'] == 'P') & (~df_output.duplicated(subset=['position.abbreviation'], keep='first')),
+            (df_output['position.abbreviation'] == 'C') & (~df_output.duplicated(subset=['position.abbreviation'], keep='first')),
+            (df_output['position.abbreviation'] == 'LF') & (~df_output.duplicated(subset=['position.abbreviation'], keep='first'))
+        ]
+
+        choices = ['Pitchers', 'Infielders', 'Outfielders']
+
+        df_output['position_group'] = np.select(conditions, choices, default='')
+
+
+
+        df_output['team'] = df_output['parentTeamId'].map(teams_dict)
+        df_output.loc[df_output['position.abbreviation'] == 'P', 'position.abbreviation'] = df_output['pitchHand'] + 'H' + df_output['position.abbreviation']
+        df_output['bat_throw'] = df_output['batSide'] + '/' + df_output['pitchHand']
+        df_output_small = df_output[['position_group','person.id', 'person.fullName',
+            'position.abbreviation','team', 'status.code', 'age','weight', 'height', 'bat_throw']]
+        df_output_small['age'] = df_output_small['age'].replace('', np.nan).astype(int)
+        df_output_small['weight'] = df_output_small['weight'].replace('', np.nan).astype(int)
+   
+        # # Insert blank rows with position group indicated
+        # blank_rows = []
+        # for idx, row in df_output_small.iterrows():
+        #     if row['position_group']:
+        #         blank_row = pd.Series([''] * len(df_output_small.columns), index=df_output_small.columns)
+        #         blank_row['position_group'] = row['position_group']
+        #         blank_rows.append((idx, blank_row))
+
+        # for idx, blank_row in reversed(blank_rows):
+        #     df_output_small = pd.concat([df_output_small.iloc[:idx], pd.DataFrame([blank_row]), df_output_small.iloc[idx:]]).reset_index(drop=True)
+        #     df_output_small.loc[(df_output_small['position_group'] != '') & (df_output_small['person.fullName'] != ''), 'position_group'] = ''
+
+        def highlight_nri(val):
+            color = 'yellow' if val else ''
+            return f'background-color: {color}'
+        # Function to alternate row colors
+        def highlight_alternate_rows(x):
+            return ['background-color: #ebebeb' if i % 2 == 0 else '' for i in range(len(x))]
+
+        #   
+
+
+        df_output_small.columns = ['Group','Player ID', 'Name', 'Pos','Team', 'Status','Age','Weight', 'Height', 'B/T']
+
+
+
+        style_df = (df_output_small.style.set_precision(1)
+                  .set_properties(**{'border': '3 px'}, overwrite=False)
+                  .set_table_styles([{
+                      'selector': 'caption',
+                      'props': [
+                      ('color', ''),
+                      ('fontname', 'Century Gothic'),
+                      ('font-size', '16px'),
+                      ('font-style', 'italic'),
+                      ('font-weight', ''),
+                      ('text-align', 'centre'),
+                      ]
+                  }, {
+                      'selector': 'th',
+                      'props': [('font-size', '16px'), ('text-align', 'center'), ('Height', 'px'), ('color', 'black'), ('border', '1px black solid !important')]
+                  }, {
+                      'selector': 'td',
+                      'props': [('text-align', 'center'), ('font-size', '16px'), ('color', 'black')]
+                  }], overwrite=False)
+                  .set_properties(**{'background-color': 'White', 'index': 'White', 'min-width': '72px'}, overwrite=False)
+                  .set_table_styles([{'selector': 'th:first-child', 'props': [('background-color', 'white')]}], overwrite=False)
+                  .set_table_styles([{'selector': 'tr:first-child', 'props': [('background-color', 'white')]}], overwrite=False)
+                  .set_table_styles([{'selector': 'tr', 'props': [('line-height', '20px')]}], overwrite=False)
+                  .set_properties(**{'Height': '8px'}, **{'text-align': 'center'}, overwrite=False)
+                  .hide_index()
+                  .set_properties(**{'border': '1px black solid'})
+                  .set_table_styles([{'selector': 'thead th:nth-child(1)', 'props': [('min-width', '150px')]}], overwrite=False)
+                  .set_table_styles([{'selector': 'thead th:nth-child(2)', 'props': [('min-width', '150px')]}], overwrite=False)
+                  .set_table_styles([{'selector': 'thead th:nth-child(3)', 'props': [('min-width', '250px')]}], overwrite=False)
+                  .set_table_styles([{'selector': 'thead th', 'props': [('height', '30px')]}], overwrite=False)
+                  .apply(highlight_alternate_rows, axis=0, subset=df_output_small.columns[1:])
+                  .applymap(lambda x: 'background-color: #bdbdbd' if x != '' else '', subset=['Group'])
+                  .applymap(lambda x: 'background-color: #bdbdbd' if x else '', subset=['Group'])
+                #   .apply(lambda x: ['background-color: #bdbdbd' if x['Group'] != '' else '' for _ in x], axis=1)
+                  .set_properties(
+                    **{'background-color':'#bdbdbd'},  # Apply only right border
+                    subset=df_output_small.columns[0]  # Only affects column 1
+                        )
+                  .set_properties(
+                            **{'border-top': 'none', 'border-bottom': 'none'}, 
+                            subset=df_output_small.columns[0]  # Apply only to column 1
+                    )
+          
+                #   .format({'Age': '{:.0f}', 'Weight': '{:.0f}'})
+        )
+        def highlight_nri(s):
+            return ['background-color: #b7e1cd' if s.name != 'Status' and s['Status'] == 'NRI' else '' for _ in s]
+
+        # style_df = style_df.style.apply(highlight_nri, axis=1, subset=style_df.columns[1:])
+                
+        if not input.nri_only():
+            style_df = style_df.apply(highlight_nri, axis=1, subset=df_output_small.columns[1:])
+
+        def add_top_border(s):
+            return ['border-top: 3px solid black' if s['Group'] != '' else '' for _ in s]
+
+        styled_df = style_df.apply(add_top_border, axis=1)
+        
+        def add_bottom_border(s):
+            return ['border-bottom: 3px solid black' if s.name == len(df_output_small) - 1 else '' for _ in s]
+
+        styled_df = style_df.apply(add_bottom_border, axis=1)
+
+
+        return style_df
 app = App(app_ui, server)