Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -3,8 +3,6 @@ import pandas as pd
 import os
 from io import StringIO
 import sys
-import streamlit as st
-import pandas as pd
 import plotly.graph_objects as go
 import plotly.express as px
 from plotly.subplots import make_subplots
@@ -35,12 +33,12 @@ if df is not None:
     st.write(df.shape)
 
     # Visualize Numeric Data
-    numeric_columns = data.select_dtypes(include=['float64', 'int64']).columns
+    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(data, x=col, nbins=30, title=f'Histogram of {col}')
+            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")
@@ -49,7 +47,7 @@ if df is not None:
         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(data, y=col, title=f'Boxplot of {col}')
+            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")
@@ -58,15 +56,15 @@ if df is not None:
         st.warning("No numeric columns available for visualization.")
 
     # Visualize Categorical Data
-    categorical_columns = data.select_dtypes(include=['object', 'category']).columns
+    categorical_columns = df.select_dtypes(include=['object', 'category']).columns
     if len(categorical_columns) > 0:
         st.subheader("Bar Plots for Categorical Columns:")
         selected_cat_col = st.selectbox("Select a Categorical Column", categorical_columns)
 
         st.write(f"Value Counts for '{selected_cat_col}':")
-        st.write(data[selected_cat_col].value_counts())
+        st.write(df[selected_cat_col].value_counts())
 
-        fig = px.bar(data, x=selected_cat_col, title=f'Bar Plot of {selected_cat_col}', color=selected_cat_col)
+        fig = px.bar(df, x=selected_cat_col, title=f'Bar Plot of {selected_cat_col}', color=selected_cat_col)
         st.plotly_chart(fig)
     else:
         st.warning("No categorical columns available for visualization.")
@@ -74,12 +72,12 @@ if df is not None:
     # Correlation Matrix for Numeric Columns
     if len(numeric_columns) > 1:
         st.subheader("Correlation Matrix:")
-        corr_matrix = data[numeric_columns].corr()
+        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 = data.drop_duplicates()
+    cleaned_data = df.drop_duplicates()
     st.write(cleaned_data)
 
     cleaned_csv = cleaned_data.to_csv(index=False).encode('utf-8')
@@ -121,10 +119,10 @@ st.markdown(
         }}
         /* Styling the content to ensure text visibility */
         .stMarkdown {{
-            color: black;  /* White text to ensure visibility */
-            font-size: 30px;  /* Adjust font size for better readability */
+            color: white;  /* White text to ensure visibility */
+            font-size: 100px;  /* Adjust font size for better readability */
         }}
     </style>
     """, 
     unsafe_allow_html=True
-)
+)