Update app.py

app.py

@@ -54,12 +54,11 @@ if page == "Overview":
         - Simple, real-time capable models  
         """)
 
-# ----------- EDA Page ------------
 elif page == "EDA":
     st.header(" Exploratory Data Analysis")
     df = load_data("cleaned_sleep_data.csv")
 
-    # ---- Multi-select Filter Sleep/Wake ----
+    # ---- Filter by Sleep State ----
     st.markdown("### 🔎 Filter by Sleep State")
     state_options = st.multiselect("Select sleep states to display", ["Sleep", "Wake-Up"], default=["Sleep", "Wake-Up"])
 
@@ -68,42 +67,51 @@ elif page == "EDA":
         selected_values = [filter_map[opt] for opt in state_options]
         df = df[df["sleep"].isin(selected_values)]
 
-    # ---- Histograms ----
+    # ---- KDE Plots ----
     col1, col2 = st.columns(2)
     with col1:
-        st.subheader(" Anglez")
-        plot_histogram(df, "anglez", "#74b9ff")
-        st.markdown("- Distribution typical of rest posture")
+        st.subheader("KDE Plot: Anglez")
+        fig, ax = plt.subplots()
+        sns.kdeplot(data=df, x="anglez", hue="sleep", fill=True, palette="magma", ax=ax)
+        ax.set_title("Sleep vs Wake - Anglez Distribution")
+        st.pyplot(fig)
+        plt.close()
 
     with col2:
-        st.subheader(" ENMO")
-        plot_histogram(df, "enmo", "#81ecec")
-        st.markdown("- ENMO reflects movement intensity")
-
-    # ---- Pairplot ----
-    st.subheader(" Feature Relationships")
-    with st.spinner("Creating pairplot..."):
-        pairplot_fig = sns.pairplot(df, vars=['anglez', 'enmo'], hue='sleep', palette='coolwarm')
-        st.pyplot(pairplot_fig.fig, use_container_width=True)
+        st.subheader("KDE Plot: ENMO")
+        fig, ax = plt.subplots()
+        sns.kdeplot(data=df, x="enmo", hue="sleep", fill=True, palette="crest", ax=ax)
+        ax.set_title("Sleep vs Wake - ENMO Distribution")
+        st.pyplot(fig)
         plt.close()
 
-    # ---- Boxplots ----
-    st.subheader(" Boxplots")
+    # ---- Violin Plots ----
+    st.subheader("Violin Plots")
     fig, axs = plt.subplots(1, 2, figsize=(12, 5))
-    sns.boxplot(y=df["anglez"], ax=axs[0], color='#74b9ff')
-    axs[0].set_title("Boxplot: Anglez")
-    sns.boxplot(y=df["enmo"], ax=axs[1], color='#81ecec')
-    axs[1].set_title("Boxplot: ENMO")
-    st.pyplot(fig, use_container_width=True)
+    sns.violinplot(data=df, x="sleep", y="anglez", palette="Set2", ax=axs[0])
+    axs[0].set_title("Violin: Anglez")
+    sns.violinplot(data=df, x="sleep", y="enmo", palette="Set3", ax=axs[1])
+    axs[1].set_title("Violin: ENMO")
+    st.pyplot(fig)
     plt.close()
 
-    # ---- Correlation ----
-    st.subheader(" Correlation Heatmap")
+    # ---- Joint Plot ----
+    st.subheader("Joint Distribution Plot")
+    with st.spinner("Generating jointplot..."):
+        joint = sns.jointplot(data=df, x="anglez", y="enmo", hue="sleep", kind="kde", fill=True, palette="viridis")
+        st.pyplot(joint.fig)
+        plt.close()
+
+    # ---- Correlation Heatmap ----
+    st.subheader("Correlation Heatmap")
     fig, ax = plt.subplots()
-    sns.heatmap(df[["anglez", "enmo"]].corr(), annot=True, cmap="coolwarm", ax=ax)
-    st.pyplot(fig, use_container_width=True)
+    corr = df[["anglez", "enmo"]].corr()
+    sns.heatmap(corr, annot=True, fmt=".2f", cmap="coolwarm", square=True, linewidths=0.5, ax=ax)
+    ax.set_title("Feature Correlation")
+    st.pyplot(fig)
     plt.close()
 
+
 # ----------- Predict Page ------------
 elif page == "Predict":
     st.header(" Sleep Prediction")