pages/Automatic_Machine_learning_app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import os

# Streamlit Configuration
st.set_page_config(
    page_title="Cricket Performance Analytics",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Custom CSS for Styling
st.markdown("""
    <style>
    .main-title {
        color: #2E86C1;
        font-size: 36px;
        font-weight: bold;
        text-align: center;
        padding: 20px 0;
    }
    .section-header {
        color: #1A5276;
        font-size: 24px;
        padding: 10px 0;
    }
    .metric-card {
        background-color: #EAF2F8;
        padding: 15px;
        border-radius: 10px;
        text-align: center;
        box-shadow: 0 2px 5px rgba(0,0,0,0.1);
        margin: 5px;
    }
    .metric-card h3 {
        color: #1A5276;
        font-size: 18px;
        margin-bottom: 5px;
    }
    .metric-card p {
        color: #2E86C1;
        font-size: 24px;
        font-weight: bold;
        margin: 0;
    }
    </style>
""", unsafe_allow_html=True)

# Load Data
batting_path = "Teams_batting.csv"
bowling_path = "team_bowling.csv"

if not os.path.exists(batting_path) or not os.path.exists(bowling_path):
    st.error("CSV files not found. Please check file paths.")
    st.stop()

batting_df = pd.read_csv(batting_path)
bowling_df = pd.read_csv(bowling_path)

# Debugging: Print column names
st.write("Batting DataFrame Columns:", batting_df.columns.tolist())
st.write("Bowling DataFrame Columns:", bowling_df.columns.tolist())

# Correct column names
if "player_name" not in batting_df.columns:
    st.error("Column 'player_name' not found! Available columns: " + ", ".join(batting_df.columns))
    st.stop()

# Sidebar Team Selection
teams = sorted(set(batting_df['Country'].unique()).union(bowling_df['Country'].unique()))
selected_team = st.selectbox("Choose a Team", teams, format_func=lambda x: x.upper())

# Player Selection
batting_players = batting_df[batting_df['Country'] == selected_team]['player_name'].unique()
bowling_players = bowling_df[bowling_df['Country'] == selected_team]['player_name'].unique()
players = sorted(set(batting_players).union(bowling_players))

selected_player = st.selectbox("Choose a Player", players)

st.success("Code successfully executed!")
# Filter Player Data
player_batting = batting_df[(batting_df['player_name'] == selected_player) & 
                          (batting_df[team_column] == selected_team)]
player_bowling = bowling_df[(bowling_df['player_name'] == selected_player) & 
                          (bowling_df[team_column] == selected_team)]

# Main Dashboard
st.markdown(f'<div class="main-title">{selected_player}\'s Cricket Analytics</div>', unsafe_allow_html=True)

# Key Metrics Section
st.markdown('<div class="section-header">Key Performance Metrics</div>', unsafe_allow_html=True)
if not player_batting.empty:
    col1, col2, col3 = st.columns(3)
    with col1:
        total_runs = player_batting['runs'].sum()
        st.markdown(f'<div class="metric-card"><h3>Total Runs</h3><p>{total_runs}</p></div>', unsafe_allow_html=True)
    with col2:
        avg_sr = player_batting['sr'].mean().round(2)
        st.markdown(f'<div class="metric-card"><h3>Avg Strike Rate</h3><p>{avg_sr}</p></div>', unsafe_allow_html=True)
    with col3:
        matches = len(player_batting)
        st.markdown(f'<div class="metric-card"><h3>Matches</h3><p>{matches}</p></div>', unsafe_allow_html=True)
else:
    st.warning("No batting data available to display key metrics.")

# Visualization Section
tab1, tab2 = st.tabs(["Batting Analysis", "Bowling Analysis"])

with tab1:
    if not player_batting.empty:
        st.markdown('<div class="section-header">Batting Performance</div>', unsafe_allow_html=True)
        col1, col2 = st.columns(2)
        
        with col1:
            fig_runs = px.pie(player_batting, values='runs', names='format', 
                            title='Runs Distribution by Format',
                            color_discrete_sequence=px.colors.sequential.Blues)
            fig_runs.update_layout(title_x=0.5)
            st.plotly_chart(fig_runs, use_container_width=True)
        
        with col2:
            fig_sr = px.scatter(player_batting, x='format', y='sr', 
                              size='runs', color='format',
                              title='Strike Rate Analysis',
                              hover_data=['runs'])
            fig_sr.update_layout(title_x=0.5)
            st.plotly_chart(fig_sr, use_container_width=True)
    else:
        st.info("No batting statistics available for this player.")

with tab2:
    if not player_bowling.empty:
        st.markdown('<div class="section-header">Bowling Performance</div>', unsafe_allow_html=True)
        col3, col4 = st.columns(2)
        
        with col3:
            fig_wickets = px.bar(player_bowling, x='format', y='wickets',
                               color='format', 
                               title='Wickets by Format',
                               color_discrete_sequence=px.colors.sequential.Reds)
            fig_wickets.update_layout(title_x=0.5)
            st.plotly_chart(fig_wickets, use_container_width=True)
        
        with col4:
            fig_eco = px.area(player_bowling, x='format', y='eco',
                            title='Economy Rate Trend',
                            color_discrete_sequence=['#2ECC71'])
            fig_eco.update_layout(title_x=0.5)
            st.plotly_chart(fig_eco, use_container_width=True)
    else:
        st.info("No bowling statistics available for this player.")

# Raw Data Expander
with st.expander("View Raw Data"):
    if not player_batting.empty:
        st.write("### Batting Statistics")
        st.dataframe(player_batting.iloc[:, :17].style.set_properties(**{'background-color': '#F8F9F9'}))
    if not player_bowling.empty:
        st.write("### Bowling Statistics")
        st.dataframe(player_bowling.iloc[:, :15].style.set_properties(**{'background-color': '#F8F9F9'}))