Update app.py

app.py

@@ -1,33 +1,105 @@
 import streamlit as st
 import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
 from datetime import date, timedelta
 import random
 
-# Functions for schedule generation and date assignment are as defined earlier
+# [All the scheduling functions and analytics functions here]
 
-def create_schedule(num_teams, num_conferences, num_inter_games):
-    """Create the entire schedule based on user inputs."""
-    full_schedule = []
+
+# Team Workload Analysis
+def team_workload_analysis(schedule_df):
+    """Generate a bar chart showing the number of matches each team has per week."""
+    schedule_df['Week'] = schedule_df['Date'].dt.isocalendar().week
+    team_counts = schedule_df.groupby(['Week', 'Team 1']).size().unstack().fillna(0)
+    
+    # Plot
+    team_counts.plot(kind='bar', stacked=True, figsize=(15, 7), cmap='Oranges')
+    plt.title('Team Workload Analysis')
+    plt.ylabel('Number of Matches')
+    plt.xlabel('Week Number')
+    plt.tight_layout()
+    plt.legend(title='Teams', bbox_to_anchor=(1.05, 1), loc='upper left')
+    plt.show()
+
+# Match Distribution
+def match_distribution(schedule_df):
+    """Generate a histogram showing match distribution across months."""
+    schedule_df['Month'] = schedule_df['Date'].dt.month_name()
+    month_order = ['November', 'December', 'January', 'February', 'March']
+    
+    # Plot
+    plt.figure(figsize=(10, 6))
+    sns.countplot(data=schedule_df, x='Month', order=month_order, palette='Oranges_r')
+    plt.title('Match Distribution Across Months')
+    plt.ylabel('Number of Matches')
+    plt.xlabel('Month')
+    plt.tight_layout()
+    plt.show()
+
+# Inter-Conference Match Analysis
+def inter_conference_analysis(schedule_df):
+    """Generate a heatmap showing inter-conference match frequencies."""
+    # Extract the conference from the team names
+    schedule_df['Conference 1'] = schedule_df['Team 1'].str[0]
+    schedule_df['Conference 2'] = schedule_df['Team 2'].str[0]
     
-    # Generate schedule for each conference
-    for i in range(num_conferences):
-        conference_name = chr(65 + i)  # 'A', 'B', 'C', 'D', ...
-        combined_schedule = combine_schedules(conference_name, num_teams, num_inter_games)
-        schedule_with_dates = assign_dates_to_matches_v2(combined_schedule)
-        
-        for match in schedule_with_dates:
-            full_schedule.append({
-                "Team 1": match[0],
-                "Team 2": match[1],
-                "Date": match[2]
-            })
+    # Filter out intra-conference matches
+    inter_conference_df = schedule_df[schedule_df['Conference 1'] != schedule_df['Conference 2']]
     
-    return pd.DataFrame(full_schedule)
+    # Create a crosstab for the heatmap
+    heatmap_data = pd.crosstab(inter_conference_df['Conference 1'], inter_conference_df['Conference 2'])
+    
+    # Ensure every conference combination has a value
+    all_conferences = schedule_df['Conference 1'].unique()
+    for conf in all_conferences:
+        if conf not in heatmap_data.columns:
+            heatmap_data[conf] = 0
+        if conf not in heatmap_data.index:
+            heatmap_data.loc[conf] = 0
+    
+    heatmap_data = heatmap_data.sort_index().sort_index(axis=1)
+    
+    # Plot
+    plt.figure(figsize=(8, 6))
+    sns.heatmap(heatmap_data, annot=True, cmap='Oranges', linewidths=.5, cbar_kws={'label': 'Number of Matches'})
+    plt.title('Inter-Conference Match Analysis')
+    plt.ylabel('Conference 1')
+    plt.xlabel('Conference 2')
+    plt.show()
+
+# Commissioner Analytics
+def commissioner_analytics(schedule_df, commissioners):
+    """Generate a bar chart showing matches overseen by each commissioner."""
+    # Assuming each commissioner oversees a specific conference
+    comm_dict = {f"Conference {chr(65+i)}": comm for i, comm in enumerate(commissioners)}
+    schedule_df['Commissioner'] = schedule_df['Conference 1'].map(comm_dict)
+    
+    # Count matches overseen by each commissioner
+    commissioner_counts = schedule_df['Commissioner'].value_counts()
+    
+    # Plot using matplotlib
+    plt.figure(figsize=(10, 6))
+    plt.bar(commissioner_counts.index, commissioner_counts.values, color='orange')
+    plt.title('Matches Overseen by Each Commissioner')
+    plt.ylabel('Number of Matches')
+    plt.xlabel('Commissioner')
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    plt.show()
+
+
 
 # Streamlit App
 
 st.title("Basketball Game Schedule Generator")
 
+# Initialize session state for schedule_df
+if 'schedule_df' not in st.session_state:
+    st.session_state.schedule_df = None
+
 # Configuration UI
 st.header("Configuration")
 
@@ -43,16 +115,45 @@ if add_commissioner:
 
 # Schedule Generation
 if st.button("Generate Schedule"):
-    global schedule_df
-    schedule_df = create_schedule(num_teams, num_conferences, num_inter_games)
+    st.session_state.schedule_df = create_schedule(num_teams, num_conferences, num_inter_games)
 
 # Schedule Viewing
 st.header("View Schedule")
 conference_selector = st.selectbox("Select conference to view schedule:", options=["All"] + [f"Conference {chr(65+i)}" for i in range(num_conferences)])
-if conference_selector == "All":
-    st.dataframe(schedule_df)
-else:
-    filtered_schedule = schedule_df[(schedule_df["Team 1"].str.startswith(conference_selector)) | (schedule_df["Team 2"].str.startswith(conference_selector))]
-    st.dataframe(filtered_schedule)
+if st.session_state.schedule_df is not None:
+    if conference_selector == "All":
+        st.dataframe(st.session_state.schedule_df)
+    else:
+        filtered_schedule = st.session_state.schedule_df[(st.session_state.schedule_df["Team 1"].str.startswith(conference_selector)) | (st.session_state.schedule_df["Team 2"].str.startswith(conference_selector))]
+        st.dataframe(filtered_schedule)
+
+# Analytics & Comparisons
+st.header("Analytics & Comparisons")
+analytics_option = st.selectbox("Choose an analysis type:", ["Team Workload Analysis", "Match Distribution", "Inter-Conference Match Analysis", "Commissioner Analytics"])
+historical_data = generate_mock_historical_data(num_teams, num_conferences, num_inter_games, date(2022, 11, 6), date(2023, 3, 1))
+
+if analytics_option == "Team Workload Analysis":
+    st.subheader("Historical Data")
+    st.pyplot(team_workload_analysis(historical_data))
+    st.subheader("Current Data")
+    st.pyplot(team_workload_analysis(st.session_state.schedule_df))
+
+elif analytics_option == "Match Distribution":
+    st.subheader("Historical Data")
+    st.pyplot(match_distribution(historical_data))
+    st.subheader("Current Data")
+    st.pyplot(match_distribution(st.session_state.schedule_df))
+
+elif analytics_option == "Inter-Conference Match Analysis":
+    st.subheader("Historical Data")
+    st.pyplot(inter_conference_analysis(historical_data))
+    st.subheader("Current Data")
+    st.pyplot(inter_conference_analysis(st.session_state.schedule_df))
+
+elif analytics_option == "Commissioner Analytics":
+    st.subheader("Historical Data")
+    st.pyplot(commissioner_analytics(historical_data, commissioners))
+    st.subheader("Current Data")
+    st.pyplot(commissioner_analytics(st.session_state.schedule_df, commissioners))
 
 # Export functionality can be added later