Update pages/EDA.py

pages/EDA.py

@@ -1,5 +1,8 @@
 import streamlit as st
 import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
 
 st.markdown(
     "<h3 style='text-align: left; color: #555;'>Data Frame</h3>",
@@ -8,4 +11,53 @@ st.markdown(
 
 df = pd.read_csv("https://huggingface.co/spaces/varshitha22/Crop_Recommendation/resolve/main/Crop_Recommendation.csv")
 
-st.dataframe(df)  # Display the dataframe in Streamlit
+st.dataframe(df)  # Display the dataframe in Streamlit
+
+# Load dataset
+df = pd.read_csv("https://huggingface.co/spaces/varshitha22/Crop_Recommendation/resolve/main/Crop_Recommendation.csv")
+
+# Define numerical columns
+num_cols = ['Nitrogen', 'Phosphorus', 'Potassium', 'Temperature', 'Humidity', 'pH_Value', 'Rainfall']
+
+# Title
+st.markdown("<h2 style='text-align: center; color: #2E86C1;'>Outlier Detection and Handling</h2>", unsafe_allow_html=True)
+
+# --- Boxplot Visualization ---
+st.markdown("<h3 style='text-align: left; color: #D35400;'>Outlier Detection (Boxplots)</h3>", unsafe_allow_html=True)
+
+fig, ax = plt.subplots(2, 4, figsize=(12, 6))
+ax = ax.flatten()
+
+for i, col in enumerate(num_cols):
+    sns.boxplot(x=df[col], ax=ax[i], color="skyblue")
+    ax[i].set_title(col)
+
+plt.tight_layout()
+st.pyplot(fig)
+
+# --- Outlier Handling ---
+st.markdown("<h3 style='text-align: left; color: #28B463;'>Outlier Handling using IQR</h3>", unsafe_allow_html=True)
+
+outlier_counts = {}
+
+for col in num_cols:
+    Q1 = df[col].quantile(0.25)
+    Q3 = df[col].quantile(0.75)
+    IQR = Q3 - Q1
+
+    lower_bound = Q1 - 1.5 * IQR
+    upper_bound = Q3 + 1.5 * IQR
+
+    outliers = df[(df[col] < lower_bound) | (df[col] > upper_bound)]
+    outlier_counts[col] = len(outliers)
+
+    # Replace outliers with mean
+    df[col] = np.where((df[col] < lower_bound) | (df[col] > upper_bound), df[col].mean(), df[col])
+
+# Display Outlier Counts
+st.write("Number of Outliers Detected:")
+st.write(outlier_counts)
+
+# Display Cleaned Data
+st.markdown("<h3 style='text-align: left; color: #AF7AC5;'>Dataset After Handling Outliers</h3>", unsafe_allow_html=True)
+st.dataframe(df)