Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -1,17 +1,40 @@
 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
+import os
 from io import StringIO
+import sys
 
 # Page Title
-st.markdown("<h1 style='text-align:center; color:white;'>Data Cleaning and Preprocessing</h1>", unsafe_allow_html=True)
+st.markdown("<h1 style='text-align:center; color:#008080;'>Data Cleaning and Processing</h1>", unsafe_allow_html=True)
 
-# Define the URL of the background image (use your own image URL)
-background_image_url = "https://cdn-uploads.huggingface.co/production/uploads/67441c51a784a9d15cb12871/clljdAv7f_LGL8dH5vCZQ.jpeg"
+# Access dataset from session state
+df = st.session_state.get("dataset")
+
+if df is not None:
+    st.subheader("Dataset Preview:")
+    st.write(df.head())
+
+    st.subheader("Info of the Dataset:")
+    # Redirect the output of df.info() to a string buffer
+    buffer = StringIO()
+    df.info(buf=buffer)
+    
+    # Display the content in Streamlit
+    st.write(buffer.getvalue())
+
+    st.subheader("Dataset Description:")
+    st.write(df.describe())
+
+    st.subheader("Shape of the Dataset:")
+    st.write(df.shape)
+else:
+    st.warning("No dataset found. Please upload a dataset on the Home page.")
 
+
+# Define the URL of the background image (use your own image URL)
 # Apply custom CSS for the background image and overlay
+background_image_url = "https://cdn-uploads.huggingface.co/production/uploads/675fab3a2d0851e23d23cad3/FlisTFfpU7flDCWj_KttH.jpeg"
+
 st.markdown(
     f"""
     <style>
@@ -33,84 +56,12 @@ st.markdown(
             background: rgba(0, 0, 0, 0.4);  /* Adjust transparency here (0.4 for 40% transparency) */
             z-index: -1;
         }}
+        /* Styling the content to ensure text visibility */
+        .stMarkdown {{
+            color: black;  /* White text to ensure visibility */
+            font-size: 30px;  /* Adjust font size for better readability */
+        }}
     </style>
     """, 
     unsafe_allow_html=True
-)
-
-# Check if the dataset is already in session state
-data = st.session_state.get("df")
-
-if data is not None:
-    st.subheader("Dataset Preview:")
-    st.write(data.head())
-
-    st.subheader("Dataset Overview:")
-    st.write(data.describe())
-
-    st.subheader("Missing Values:")
-    st.write(data.isnull().sum())
-
-    st.subheader("Duplicate Rows:")
-    st.write(f"Number of duplicate rows: {data.duplicated().sum()}")
-
-    # Visualize Numeric Data
-    numeric_columns = data.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}')
-            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)
-
-        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}')
-            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)
-    else:
-        st.warning("No numeric columns available for visualization.")
-
-    # Visualize Categorical Data
-    categorical_columns = data.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())
-
-        fig = px.bar(data, 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.")
-
-    # Correlation Matrix for Numeric Columns
-    if len(numeric_columns) > 1:
-        st.subheader("Correlation Matrix:")
-        corr_matrix = data[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()
-    st.write(cleaned_data)
-
-    cleaned_csv = cleaned_data.to_csv(index=False).encode('utf-8')
-    st.download_button(
-        label="Download Cleaned Dataset",
-        data=cleaned_csv,
-        file_name="cleaned_dataset.csv",
-        mime="text/csv"
-    )
-
-    st.session_state['df'] = cleaned_data
-
-else:
-    st.warning("No dataset found. Please upload a dataset on the Home page.")
+)