Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -1,11 +1,7 @@
 import streamlit as st
 import pandas as pd
-import os
-from io import StringIO
-import sys
-import plotly.graph_objects as go
-import plotly.express as px
-from plotly.subplots import make_subplots
+import seaborn as sns
+import matplotlib.pyplot as plt
 from io import StringIO
 
 # Page Title
@@ -36,22 +32,20 @@ if df is not None:
     numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
     if len(numeric_columns) > 0:
         st.subheader("Histograms for Numeric Columns:")
-        fig = make_subplots(rows=len(numeric_columns), cols=1, subplot_titles=numeric_columns)
-        for i, col in enumerate(numeric_columns):
-            hist = px.histogram(df, x=col, nbins=30, title=f'Histogram of {col}')
-            fig.add_trace(hist.data[0], row=i + 1, col=1)
-
-        fig.update_layout(height=500 * len(numeric_columns), title_text="Histograms for Numeric Columns")
-        st.plotly_chart(fig)
+        for col in numeric_columns:
+            plt.figure(figsize=(10, 5))
+            sns.histplot(df[col], bins=30, kde=True)
+            plt.title(f'Histogram of {col}')
+            st.pyplot(plt)
+            plt.clf()
 
         st.subheader("Boxplots for Numeric Columns:")
-        fig = make_subplots(rows=len(numeric_columns), cols=1, subplot_titles=numeric_columns)
-        for i, col in enumerate(numeric_columns):
-            boxplot = px.box(df, y=col, title=f'Boxplot of {col}')
-            fig.add_trace(boxplot.data[0], row=i + 1, col=1)
-
-        fig.update_layout(height=500 * len(numeric_columns), title_text="Boxplots for Numeric Columns")
-        st.plotly_chart(fig)
+        for col in numeric_columns:
+            plt.figure(figsize=(10, 5))
+            sns.boxplot(x=df[col])
+            plt.title(f'Boxplot of {col}')
+            st.pyplot(plt)
+            plt.clf()
     else:
         st.warning("No numeric columns available for visualization.")
 
@@ -64,18 +58,14 @@ if df is not None:
         st.write(f"Value Counts for '{selected_cat_col}':")
         st.write(df[selected_cat_col].value_counts())
 
-        fig = px.bar(df, x=selected_cat_col, title=f'Bar Plot of {selected_cat_col}', color=selected_cat_col)
-        st.plotly_chart(fig)
+        plt.figure(figsize=(10, 5))
+        sns.countplot(x=selected_cat_col, data=df)
+        plt.title(f'Bar Plot of {selected_cat_col}')
+        st.pyplot(plt)
+        plt.clf()
     else:
         st.warning("No categorical columns available for visualization.")
 
-    # Correlation Matrix for Numeric Columns
-    if len(numeric_columns) > 1:
-        st.subheader("Correlation Matrix:")
-        corr_matrix = df[numeric_columns].corr()
-        fig = px.imshow(corr_matrix, title="Correlation Matrix", color_continuous_scale='coolwarm')
-        st.plotly_chart(fig)
-
     st.subheader("Cleaned Dataset:")
     cleaned_data = df.drop_duplicates()
     st.write(cleaned_data)
@@ -120,7 +110,7 @@ st.markdown(
         /* Styling the content to ensure text visibility */
         .stMarkdown {{
             color: white;  /* White text to ensure visibility */
-            font-size: 100px;  /* Adjust font size for better readability */
+            font-size: 30px;  /* Adjust font size for better readability */
         }}
     </style>
     """,