Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -4,101 +4,7 @@ import seaborn as sns
 import matplotlib.pyplot as plt
 from io import StringIO
 
-# Page Title
-st.markdown("<h1 style='text-align:center; color:white;'>Data Cleaning and Processing</h1>", unsafe_allow_html=True)
 
-# Access dataset from session state
-df = st.session_state.get("dataset")
-
-# Exclude 'ProductID' from the dataset
-if df is not None:
-    df = df.drop(columns=['ProductID'], errors='ignore')  # Exclude 'ProductID' if it exists
-
-    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)
-
-    # Visualize Numeric Data (Histograms and Boxplots in subplots)
-    numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
-    if len(numeric_columns) > 0:
-        st.subheader("Histograms for Numeric Columns:")
-        # Create a multidimensional subplot (grid) for all histograms
-        num_plots = len(numeric_columns)
-        rows = (num_plots + 1) // 2  # To create a 2-column grid layout for histograms
-        fig, axs = plt.subplots(rows, 2, figsize=(12, 12))
-        axs = axs.flatten()  # Flatten the 2D array of axes to iterate over
-        
-        color_palettes_hist = ['Set1', 'Set2', 'Set3', 'Paired', 'Pastel1']  # Different color palettes for histograms
-        for i, col in enumerate(numeric_columns):
-            palette = sns.color_palette(color_palettes_hist[i % len(color_palettes_hist)])  # Ensure different palette for each plot
-            sns.histplot(df[col], bins=30, kde=True, color=palette[0], ax=axs[i])  # Apply the color palette
-            axs[i].set_title(f'Histogram of {col}')
-        st.pyplot(fig)
-        plt.clf()
-
-        st.subheader("Boxplots for Numeric Columns:")
-        # Create a multidimensional subplot (grid) for all boxplots
-        fig, axs = plt.subplots(rows, 2, figsize=(12, 12))
-        axs = axs.flatten()  # Flatten the 2D array of axes to iterate over
-        
-        color_palettes_box = ['coolwarm', 'Blues', 'viridis', 'cubehelix', 'crest']  # Different color palettes for boxplots
-        for i, col in enumerate(numeric_columns):
-            palette = sns.color_palette(color_palettes_box[i % len(color_palettes_box)])  # Ensure different palette for each plot
-            sns.boxplot(x=df[col], ax=axs[i], palette=palette)
-            axs[i].set_title(f'Boxplot of {col}')
-        st.pyplot(fig)
-        plt.clf()
-    else:
-        st.warning("No numeric columns available for visualization.")
-
-    # Visualize Categorical Data
-    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(df[selected_cat_col].value_counts())
-
-        plt.figure(figsize=(12, 6))
-        sns.countplot(x=selected_cat_col, data=df, palette='coolwarm')  # Unique palette for categorical data
-        plt.title(f'Bar Plot of {selected_cat_col}')
-        st.pyplot(plt)
-        plt.clf()
-    else:
-        st.warning("No categorical columns available for visualization.")
-
-    st.subheader("Cleaned Dataset:")
-    cleaned_data = df.drop_duplicates()
-    st.write(cleaned_data)
-
-    # Store cleaned data in session state for use in next page
-    st.session_state.cleaned_data = cleaned_data  # Store cleaned data in session state
-
-    # Convert cleaned data to CSV and provide a download button
-    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"
-    )
-
-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)
@@ -146,7 +52,103 @@ st.markdown(
     <div class="content-container">
         <div class="stMarkdown">
             <!-- Replace this with your app's content -->
-            <p>Insert your app's content here. All elements will be aligned to the center and limited to 70% width.</p>
+            <p>
+                # Page Title
+                st.markdown("<h1 style='text-align:center; color:white;'>Data Cleaning and Processing</h1>", unsafe_allow_html=True)
+                
+                # Access dataset from session state
+                df = st.session_state.get("dataset")
+                
+                # Exclude 'ProductID' from the dataset
+                if df is not None:
+                    df = df.drop(columns=['ProductID'], errors='ignore')  # Exclude 'ProductID' if it exists
+                
+                    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)
+                
+                    # Visualize Numeric Data (Histograms and Boxplots in subplots)
+                    numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
+                    if len(numeric_columns) > 0:
+                        st.subheader("Histograms for Numeric Columns:")
+                        # Create a multidimensional subplot (grid) for all histograms
+                        num_plots = len(numeric_columns)
+                        rows = (num_plots + 1) // 2  # To create a 2-column grid layout for histograms
+                        fig, axs = plt.subplots(rows, 2, figsize=(12, 12))
+                        axs = axs.flatten()  # Flatten the 2D array of axes to iterate over
+                        
+                        color_palettes_hist = ['Set1', 'Set2', 'Set3', 'Paired', 'Pastel1']  # Different color palettes for histograms
+                        for i, col in enumerate(numeric_columns):
+                            palette = sns.color_palette(color_palettes_hist[i % len(color_palettes_hist)])  # Ensure different palette for each plot
+                            sns.histplot(df[col], bins=30, kde=True, color=palette[0], ax=axs[i])  # Apply the color palette
+                            axs[i].set_title(f'Histogram of {col}')
+                        st.pyplot(fig)
+                        plt.clf()
+                
+                        st.subheader("Boxplots for Numeric Columns:")
+                        # Create a multidimensional subplot (grid) for all boxplots
+                        fig, axs = plt.subplots(rows, 2, figsize=(12, 12))
+                        axs = axs.flatten()  # Flatten the 2D array of axes to iterate over
+                        
+                        color_palettes_box = ['coolwarm', 'Blues', 'viridis', 'cubehelix', 'crest']  # Different color palettes for boxplots
+                        for i, col in enumerate(numeric_columns):
+                            palette = sns.color_palette(color_palettes_box[i % len(color_palettes_box)])  # Ensure different palette for each plot
+                            sns.boxplot(x=df[col], ax=axs[i], palette=palette)
+                            axs[i].set_title(f'Boxplot of {col}')
+                        st.pyplot(fig)
+                        plt.clf()
+                    else:
+                        st.warning("No numeric columns available for visualization.")
+                
+                    # Visualize Categorical Data
+                    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(df[selected_cat_col].value_counts())
+                
+                        plt.figure(figsize=(12, 6))
+                        sns.countplot(x=selected_cat_col, data=df, palette='coolwarm')  # Unique palette for categorical data
+                        plt.title(f'Bar Plot of {selected_cat_col}')
+                        st.pyplot(plt)
+                        plt.clf()
+                    else:
+                        st.warning("No categorical columns available for visualization.")
+                
+                    st.subheader("Cleaned Dataset:")
+                    cleaned_data = df.drop_duplicates()
+                    st.write(cleaned_data)
+                
+                    # Store cleaned data in session state for use in next page
+                    st.session_state.cleaned_data = cleaned_data  # Store cleaned data in session state
+                
+                    # Convert cleaned data to CSV and provide a download button
+                    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"
+                    )
+                
+                else:
+                    st.warning("No dataset found. Please upload a dataset on the Home page.")
+            </p>
         </div>
     </div>
     """,