Create eda.py

src/eda.py

@@ -0,0 +1,65 @@
+# eda.py
+import streamlit as st
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.impute import SimpleImputer
+
+def run_eda():
+    st.header("📊 Exploratory Data Analysis")
+
+    df_raw = st.session_state.original_df
+    df = st.session_state.processed_df
+
+    c1, c2 = st.columns(2)
+    with c1:
+        st.subheader("Raw Data")
+        st.dataframe(df_raw.head(10))
+        st.write(df_raw.describe(include="all"))
+
+    with c2:
+        st.subheader("Processed Data")
+        st.dataframe(df.head(10))
+
+    st.subheader("🎯 Feature & Target Selection")
+
+    cols = df.columns.tolist()
+    target = st.selectbox("Target", cols)
+    features = st.multiselect("Features", [c for c in cols if c != target])
+
+    st.session_state.target_col = target
+    st.session_state.feature_cols = features
+
+    st.subheader("🧹 Cleaning")
+
+    if st.checkbox("Apply smart imputation"):
+        num = df.select_dtypes(include=np.number).columns
+        cat = df.select_dtypes(exclude=np.number).columns
+
+        if len(num):
+            df[num] = SimpleImputer(strategy="mean").fit_transform(df[num])
+        if len(cat):
+            df[cat] = SimpleImputer(strategy="most_frequent").fit_transform(df[cat])
+
+        st.session_state.processed_df = df
+        st.success("Imputation complete")
+        st.rerun()
+
+    st.subheader("📈 Visuals")
+
+    plot = st.selectbox(
+        "Plot type",
+        ["Correlation Heatmap", "Target Distribution"]
+    )
+
+    fig, ax = plt.subplots(figsize=(8,6))
+
+    if plot == "Correlation Heatmap":
+        sns.heatmap(df.select_dtypes(np.number).corr(), annot=True, ax=ax)
+
+    elif plot == "Target Distribution":
+        sns.histplot(df[target], kde=True, ax=ax)
+
+    st.pyplot(fig)
+    plt.close(fig)