Update app.py

app.py

@@ -150,152 +150,304 @@ elif page == "📈 Player Career Info":
     st.plotly_chart(fig5)
 
 
-if page == "Player Comparision(🧍‍♂️ vs 🧍‍♂️)":
+# if page == "Player Comparision(🧍‍♂️ vs 🧍‍♂️)":
+#     st.title("🏏 Player Recognition & Performance Analysis")
+#     player_stats_df = pd.read_csv("final_cricket_dataset.csv")
+#     model = joblib.load("svc_face_classifier.pkl")
+#     label_encoder = joblib.load("label_encoder.pkl")
+#     face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
+    
+#     # Streamlit Page Setup   
+    
+#     # Image Preprocessing + Face Detection Function
+#     def detect_and_predict_face(image_file):
+#         image = Image.open(image_file).convert("RGB")
+#         img_np = np.array(image)
+#         gray = cv2.cvtColor(img_np, cv2.COLOR_RGB2GRAY)
+        
+#         faces = face_cascade.detectMultiScale(gray, 1.3, 5)
+#         if len(faces) == 0:
+#             return None, "No face detected!"
+    
+#         x, y, w, h = faces[0]
+#         face = gray[y:y+h, x:x+w]
+#         resized_face = cv2.resize(face, (64, 64))
+#         flattened = resized_face.flatten().reshape(1, -1)
+    
+#         pred_label = model.predict(flattened)[0]
+#         pred_name = label_encoder.inverse_transform([pred_label])[0]
+#         return pred_name, None
+    
+#     # Upload images
+#     col1, col2 = st.columns(2)
+#     with col1:
+#         img1 = st.file_uploader("Upload First Player Image", type=["jpg", "png", "jpeg"], key="img1")
+#     with col2:
+#         img2 = st.file_uploader("Upload Second Player Image", type=["jpg", "png", "jpeg"], key="img2")
+    
+#     if img1 and img2:
+#         p1_name, err1 = detect_and_predict_face(img1)
+#         p2_name, err2 = detect_and_predict_face(img2)
+    
+#         if err1:
+#             st.error(f"Image 1: {err1}")
+#         if err2:
+#             st.error(f"Image 2: {err2}")
+        
+#         if not err1 and not err2:
+#             st.success(f"✅ Player 1 Detected: {p1_name}")
+#             st.success(f"✅ Player 2 Detected: {p2_name}")
+    
+#             formats = ['Test', 'ODI', 'T20', 'IPL']
+#             df = player_stats_df
+#             players = [p1_name, p2_name]
+    
+#             if p1_name not in df['Label'].values or p2_name not in df['Label'].values:
+#                 st.error("One or both players not found in dataset.")
+#                 st.stop()
+    
+#             p1_data = df[df['Label'] == p1_name].iloc[0]
+#             p2_data = df[df['Label'] == p2_name].iloc[0]
+    
+#             st.markdown("## 📊 Comparative Stats")
+    
+#             # Batting Summary
+#             st.markdown("### 🏏 Batting Career Summary")
+#             batting_summary = []
+#             for fmt in formats:
+#                 batting_summary.append({
+#                     "Format": fmt,
+#                     p1_name: p1_data.get(f'batting_Runs_{fmt}', 0),
+#                     p2_name: p2_data.get(f'batting_Runs_{fmt}', 0)
+#                 })
+#             batting_df = pd.DataFrame(batting_summary)
+#             fig = px.bar(batting_df, x="Format", y=[p1_name, p2_name], barmode="group", title="Total Runs by Format")
+#             st.plotly_chart(fig, use_container_width=True)
+    
+#             # Bowling Summary
+#             st.markdown("### 🎯 Bowling Career Summary")
+#             bowling_summary = []
+#             for fmt in formats:
+#                 bowling_summary.append({
+#                     "Format": fmt,
+#                     p1_name: p1_data.get(f'bowling_{fmt}_Wickets', 0),
+#                     p2_name: p2_data.get(f'bowling_{fmt}_Wickets', 0)
+#                 })
+#             bowling_df = pd.DataFrame(bowling_summary)
+#             fig = px.bar(bowling_df, x="Format", y=[p1_name, p2_name], barmode="group", title="Total Wickets by Format")
+#             st.plotly_chart(fig, use_container_width=True)
+    
+#             # Strike Rate vs Runs
+#             st.markdown("### ⚡ Strike Rate vs Runs")
+#             data = {
+#                 "Format": formats,
+#                 f"{p1_name} Runs": [p1_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats],
+#                 f"{p1_name} SR": [p1_data.get(f'batting_SR_{fmt}', 0) for fmt in formats],
+#                 f"{p2_name} Runs": [p2_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats],
+#                 f"{p2_name} SR": [p2_data.get(f'batting_SR_{fmt}', 0) for fmt in formats],
+#             }
+    
+#             fig = px.scatter(x=data[f"{p1_name} Runs"] + data[f"{p2_name} Runs"],
+#                              y=data[f"{p1_name} SR"] + data[f"{p2_name} SR"],
+#                              color=["Player 1"] * 4 + ["Player 2"] * 4,
+#                              text=formats * 2,
+#                              labels={"x": "Runs", "y": "Strike Rate"},
+#                              title="Runs vs Strike Rate Comparison")
+#             st.plotly_chart(fig, use_container_width=True)
+    
+#             # Milestones
+#             st.markdown("### 🏆 Milestone Comparison")
+#             milestone_df = pd.DataFrame({
+#                 "Format": formats * 2,
+#                 "Player": [p1_name] * 4 + [p2_name] * 4,
+#                 "50s": [p1_data.get(f"batting_50s_{fmt}", 0) for fmt in formats] +
+#                        [p2_data.get(f"batting_50s_{fmt}", 0) for fmt in formats],
+#                 "100s": [p1_data.get(f"batting_100s_{fmt}", 0) for fmt in formats] +
+#                         [p2_data.get(f"batting_100s_{fmt}", 0) for fmt in formats],
+#                 "200s": [p1_data.get(f"batting_200s_{fmt}", 0) for fmt in formats] +
+#                         [p2_data.get(f"batting_200s_{fmt}", 0) for fmt in formats]
+#             })
+    
+#             for stat in ['50s', '100s', '200s']:
+#                 fig = px.bar(milestone_df, x="Format", y=stat, color="Player", barmode="group",
+#                              title=f"{stat} Achievements Comparison")
+#                 st.plotly_chart(fig, use_container_width=True)
+    
+#             # Pie Chart - Matches Played
+#             st.markdown("### 🧩 Matches Played by Format")
+#             for i, data_player in enumerate([p1_data, p2_data]):
+#                 match_data = {
+#                     fmt: data_player.get(f"Matches_{fmt}", 0) for fmt in formats
+#                 }
+#                 fig = px.pie(values=list(match_data.values()), names=list(match_data.keys()), 
+#                              title=f"{players[i]} Matches Distribution")
+#                 st.plotly_chart(fig, use_container_width=True)
+    
+#             # Final Trend Overview
+#             st.markdown("### 📉 Trend Overview")
+#             fig, ax = plt.subplots(1, 2, figsize=(14, 5))
+#             sns.barplot(x=formats, y=[p1_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats], ax=ax[0], label=p1_name)
+#             sns.barplot(x=formats, y=[p2_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats], ax=ax[0], label=p2_name)
+#             ax[0].set_title("Batting Runs Trend")
+#             ax[0].legend()
+    
+#             sns.barplot(x=formats, y=[p1_data.get(f'bowling_{fmt}_Wickets', 0) for fmt in formats], ax=ax[1], label=p1_name)
+#             sns.barplot(x=formats, y=[p2_data.get(f'bowling_{fmt}_Wickets', 0) for fmt in formats], ax=ax[1], label=p2_name)
+#             ax[1].set_title("Bowling Wickets Trend")
+#             ax[1].legend()
+#             st.pyplot(fig)
+    
+elif page == "Player Comparision(🧍‍♂️ vs 🧍‍♂️)":
     st.title("🏏 Player Recognition & Performance Analysis")
     player_stats_df = pd.read_csv("final_cricket_dataset.csv")
     model = joblib.load("svc_face_classifier.pkl")
     label_encoder = joblib.load("label_encoder.pkl")
     face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
-    
-    # Streamlit Page Setup   
-    
-    # Image Preprocessing + Face Detection Function
+
     def detect_and_predict_face(image_file):
         image = Image.open(image_file).convert("RGB")
         img_np = np.array(image)
         gray = cv2.cvtColor(img_np, cv2.COLOR_RGB2GRAY)
-        
         faces = face_cascade.detectMultiScale(gray, 1.3, 5)
+
         if len(faces) == 0:
             return None, "No face detected!"
-    
+
         x, y, w, h = faces[0]
         face = gray[y:y+h, x:x+w]
-        resized_face = cv2.resize(face, (64, 64))
-        flattened = resized_face.flatten().reshape(1, -1)
-    
-        pred_label = model.predict(flattened)[0]
-        pred_name = label_encoder.inverse_transform([pred_label])[0]
-        return pred_name, None
-    
-    # Upload images
+        resized = cv2.resize(face, (64, 64))
+        flat = resized.flatten().reshape(1, -1)
+
+        pred = model.predict(flat)[0]
+        name = label_encoder.inverse_transform([pred])[0]
+        return name, None
+
     col1, col2 = st.columns(2)
-    with col1:
-        img1 = st.file_uploader("Upload First Player Image", type=["jpg", "png", "jpeg"], key="img1")
-    with col2:
-        img2 = st.file_uploader("Upload Second Player Image", type=["jpg", "png", "jpeg"], key="img2")
-    
+    img1 = col1.file_uploader("Upload First Player Image", type=["jpg", "jpeg", "png"], key="img1")
+    img2 = col2.file_uploader("Upload Second Player Image", type=["jpg", "jpeg", "png"], key="img2")
+
     if img1 and img2:
         p1_name, err1 = detect_and_predict_face(img1)
         p2_name, err2 = detect_and_predict_face(img2)
-    
-        if err1:
-            st.error(f"Image 1: {err1}")
-        if err2:
-            st.error(f"Image 2: {err2}")
-        
+
+        if err1: st.error(f"Image 1: {err1}")
+        if err2: st.error(f"Image 2: {err2}")
+
         if not err1 and not err2:
             st.success(f"✅ Player 1 Detected: {p1_name}")
             st.success(f"✅ Player 2 Detected: {p2_name}")
-    
-            formats = ['Test', 'ODI', 'T20', 'IPL']
-            df = player_stats_df
-            players = [p1_name, p2_name]
-    
+
+            df = player_stats_df.copy()
             if p1_name not in df['Label'].values or p2_name not in df['Label'].values:
                 st.error("One or both players not found in dataset.")
                 st.stop()
-    
+
             p1_data = df[df['Label'] == p1_name].iloc[0]
             p2_data = df[df['Label'] == p2_name].iloc[0]
-    
-            st.markdown("## 📊 Comparative Stats")
-    
-            # Batting Summary
-            st.markdown("### 🏏 Batting Career Summary")
-            batting_summary = []
-            for fmt in formats:
-                batting_summary.append({
-                    "Format": fmt,
-                    p1_name: p1_data.get(f'batting_Runs_{fmt}', 0),
-                    p2_name: p2_data.get(f'batting_Runs_{fmt}', 0)
-                })
-            batting_df = pd.DataFrame(batting_summary)
-            fig = px.bar(batting_df, x="Format", y=[p1_name, p2_name], barmode="group", title="Total Runs by Format")
-            st.plotly_chart(fig, use_container_width=True)
-    
-            # Bowling Summary
-            st.markdown("### 🎯 Bowling Career Summary")
-            bowling_summary = []
-            for fmt in formats:
-                bowling_summary.append({
-                    "Format": fmt,
-                    p1_name: p1_data.get(f'bowling_{fmt}_Wickets', 0),
-                    p2_name: p2_data.get(f'bowling_{fmt}_Wickets', 0)
+
+            st.write("### 📋 Player Data Preview")
+            st.write(p1_data)
+            st.write(p2_data)
+
+            formats = ['Test', 'ODI', 'T20', 'IPL']
+
+            def plot_bar(compare_col, title, y_label):
+                vals1 = [p1_data.get(f"{compare_col}_{fmt}", 0) for fmt in formats]
+                vals2 = [p2_data.get(f"{compare_col}_{fmt}", 0) for fmt in formats]
+                df_plot = pd.DataFrame({
+                    "Format": formats,
+                    p1_name: vals1,
+                    p2_name: vals2
                 })
-            bowling_df = pd.DataFrame(bowling_summary)
-            fig = px.bar(bowling_df, x="Format", y=[p1_name, p2_name], barmode="group", title="Total Wickets by Format")
-            st.plotly_chart(fig, use_container_width=True)
-    
-            # Strike Rate vs Runs
-            st.markdown("### ⚡ Strike Rate vs Runs")
-            data = {
-                "Format": formats,
-                f"{p1_name} Runs": [p1_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats],
-                f"{p1_name} SR": [p1_data.get(f'batting_SR_{fmt}', 0) for fmt in formats],
-                f"{p2_name} Runs": [p2_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats],
-                f"{p2_name} SR": [p2_data.get(f'batting_SR_{fmt}', 0) for fmt in formats],
-            }
-    
-            fig = px.scatter(x=data[f"{p1_name} Runs"] + data[f"{p2_name} Runs"],
-                             y=data[f"{p1_name} SR"] + data[f"{p2_name} SR"],
-                             color=["Player 1"] * 4 + ["Player 2"] * 4,
-                             text=formats * 2,
-                             labels={"x": "Runs", "y": "Strike Rate"},
-                             title="Runs vs Strike Rate Comparison")
-            st.plotly_chart(fig, use_container_width=True)
-    
-            # Milestones
-            st.markdown("### 🏆 Milestone Comparison")
-            milestone_df = pd.DataFrame({
-                "Format": formats * 2,
-                "Player": [p1_name] * 4 + [p2_name] * 4,
-                "50s": [p1_data.get(f"batting_50s_{fmt}", 0) for fmt in formats] +
-                       [p2_data.get(f"batting_50s_{fmt}", 0) for fmt in formats],
-                "100s": [p1_data.get(f"batting_100s_{fmt}", 0) for fmt in formats] +
-                        [p2_data.get(f"batting_100s_{fmt}", 0) for fmt in formats],
-                "200s": [p1_data.get(f"batting_200s_{fmt}", 0) for fmt in formats] +
-                        [p2_data.get(f"batting_200s_{fmt}", 0) for fmt in formats]
-            })
-    
-            for stat in ['50s', '100s', '200s']:
-                fig = px.bar(milestone_df, x="Format", y=stat, color="Player", barmode="group",
+                if df_plot[[p1_name, p2_name]].sum().sum() == 0:
+                    st.warning(f"No data to plot for {title}.")
+                    return
+                try:
+                    fig = px.bar(df_plot, x="Format", y=[p1_name, p2_name], barmode="group", title=title)
+                    st.plotly_chart(fig, use_container_width=True)
+                except Exception as e:
+                    st.error(f"Could not render {title}: {e}")
+
+            st.markdown("## 📊 Comparative Stats")
+            st.subheader("🛡️ Batting – Total Runs by Format")
+            plot_bar("batting_Runs", "Total Runs by Format", "Runs")
+            st.subheader("🎯 Bowling – Total Wickets by Format")
+            plot_bar("bowling_Wickets", "Total Wickets by Format", "Wickets")
+
+            st.subheader("⚡ Runs vs Strike Rate Scatter")
+
+            data_pts = []
+            for player, pdata in [(p1_name, p1_data), (p2_name, p2_data)]:
+                runs = [pdata.get(f"batting_Runs_{fmt}", 0) for fmt in formats]
+                sr = [pdata.get(f"batting_SR_{fmt}", 0) for fmt in formats]
+                for fmt, r, s in zip(formats, runs, sr):
+                    data_pts.append({
+                        "Player": player,
+                        "Format": fmt,
+                        "Runs": r,
+                        "Strike Rate": s
+                    })
+            scatter_df = pd.DataFrame(data_pts)
+            if scatter_df[['Runs', 'Strike Rate']].sum().sum() == 0:
+                st.warning("Not enough data for scatter plot.")
+            else:
+                fig = px.scatter(scatter_df, x="Runs", y="Strike Rate",
+                                 color="Player", text="Format",
+                                 title="Runs vs Strike Rate Comparison",
+                                 labels={"Runs": "Runs", "Strike Rate": "Strike Rate"})
+                fig.update_traces(textposition='top center')
+                st.plotly_chart(fig, use_container_width=True)
+
+            st.subheader("🏆 Milestone Comparison")
+            milestone_data = []
+            for player, pdata in [(p1_name, p1_data), (p2_name, p2_data)]:
+                for fmt in formats:
+                    milestone_data.append({
+                        "Player": player,
+                        "Format": fmt,
+                        "50s": pdata.get(f"batting_50s_{fmt}", 0),
+                        "100s": pdata.get(f"batting_100s_{fmt}", 0),
+                        "200s": pdata.get(f"batting_200s_{fmt}", 0)
+                    })
+            ms_df = pd.DataFrame(milestone_data)
+            for stat in ["50s", "100s", "200s"]:
+                fig = px.bar(ms_df, x="Format", y=stat,
+                             color="Player", barmode="group",
                              title=f"{stat} Achievements Comparison")
                 st.plotly_chart(fig, use_container_width=True)
-    
-            # Pie Chart - Matches Played
-            st.markdown("### 🧩 Matches Played by Format")
-            for i, data_player in enumerate([p1_data, p2_data]):
-                match_data = {
-                    fmt: data_player.get(f"Matches_{fmt}", 0) for fmt in formats
-                }
-                fig = px.pie(values=list(match_data.values()), names=list(match_data.keys()), 
-                             title=f"{players[i]} Matches Distribution")
+
+            st.subheader("🧩 Matches Distribution by Format")
+            for player, pdata in [(p1_name, p1_data), (p2_name, p2_data)]:
+                match_counts = [pdata.get(f"Matches_{fmt}", 0) for fmt in formats]
+                if sum(match_counts) == 0:
+                    st.warning(f"No match data for {player}.")
+                    continue
+                fig = px.pie(values=match_counts, names=formats,
+                             title=f"{player} – Matches Distribution")
                 st.plotly_chart(fig, use_container_width=True)
-    
-            # Final Trend Overview
-            st.markdown("### 📉 Trend Overview")
-            fig, ax = plt.subplots(1, 2, figsize=(14, 5))
-            sns.barplot(x=formats, y=[p1_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats], ax=ax[0], label=p1_name)
-            sns.barplot(x=formats, y=[p2_data.get(f'batting_Runs_{fmt}', 0) for fmt in formats], ax=ax[0], label=p2_name)
-            ax[0].set_title("Batting Runs Trend")
-            ax[0].legend()
-    
-            sns.barplot(x=formats, y=[p1_data.get(f'bowling_{fmt}_Wickets', 0) for fmt in formats], ax=ax[1], label=p1_name)
-            sns.barplot(x=formats, y=[p2_data.get(f'bowling_{fmt}_Wickets', 0) for fmt in formats], ax=ax[1], label=p2_name)
-            ax[1].set_title("Bowling Wickets Trend")
-            ax[1].legend()
+
+            st.subheader("📉 Final Trends Overview")
+            fig, axes = plt.subplots(1, 2, figsize=(14, 5))
+            sns.set_theme(style="whitegrid")
+
+            sns.barplot(x=formats,
+                        y=[p1_data.get(f"batting_Runs_{fmt}", 0) for fmt in formats],
+                        ax=axes[0], label=p1_name, color="b", alpha=0.6)
+            sns.barplot(x=formats,
+                        y=[p2_data.get(f"batting_Runs_{fmt}", 0) for fmt in formats],
+                        ax=axes[0], label=p2_name, color="r", alpha=0.6)
+            axes[0].set_title("Batting Runs Trend")
+            axes[0].legend()
+
+            sns.barplot(x=formats,
+                        y=[p1_data.get(f"bowling_Test_Wickets", 0) for fmt in formats],
+                        ax=axes[1], label=p1_name, color="b", alpha=0.6)
+            sns.barplot(x=formats,
+                        y=[p2_data.get(f"bowling_Test_Wickets", 0) for fmt in formats],
+                        ax=axes[1], label=p2_name, color="r", alpha=0.6)
+            axes[1].set_title("Bowling Wickets Trend")
+            axes[1].legend()
+
             st.pyplot(fig)
-    
-    
+