Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -3,11 +3,15 @@ import pandas as pd
 import plotly.graph_objects as go
 import plotly.express as px
 from plotly.subplots import make_subplots
+from io import StringIO
 
-# Background Image URL
+# Page Title
+st.markdown("<h1 style='text-align:center; color:#008080;'>Exploratory Data Analysis (EDA) App</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"
 
-# Apply background image using CSS
+# Apply custom CSS for the background image and overlay
 st.markdown(
     f"""
     <style>
@@ -17,79 +21,66 @@ st.markdown(
             background-position: center;
             height: 100vh;
         }}
+        
+        /* Semi-transparent overlay */
+        .stApp::before {{
+            content: "";
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            background: rgba(0, 0, 0, 0.4);  /* Adjust transparency here (0.4 for 40% transparency) */
+            z-index: -1;
+        }}
     </style>
-    """,
+    """, 
     unsafe_allow_html=True
 )
 
-# Page Title
-st.title("Exploratory Data Analysis (EDA) App")
-
-st.markdown("""
-### Perform EDA and Clean Data
-This app provides basic insights into the dataset, highlights missing values, 
-and visualizes numeric and categorical columns.
----
-""")
-
 # Check if the dataset is already in session state
-if 'df' in st.session_state:
-    data = st.session_state['df']
-    st.success("Dataset loaded from previous session!")
+data = st.session_state.get("df")
 
-    # Show Data Preview
-    st.write("### Preview of Dataset")
-    st.dataframe(data.head())
+if data is not None:
+    st.subheader("Dataset Preview:")
+    st.write(data.head())
 
-    # Overview Section
-    st.write("### Dataset Overview")
+    st.subheader("Dataset Overview:")
     st.write(data.describe())
 
-    # Missing Values
-    st.write("### Missing Values")
+    st.subheader("Missing Values:")
     st.write(data.isnull().sum())
 
-    # Duplicate Rows
-    st.write("### Duplicate Rows")
+    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.write("### Histograms for Numeric Columns")
-        
-        # Create subplots for histograms
+        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.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.write("### Boxplots for Numeric Columns")
-
-        # Create subplots for boxplots
+        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.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.write("No numeric columns available for visualization.")
+        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.write("### Bar Plots for Categorical Columns")
+        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}':")
@@ -98,45 +89,19 @@ if 'df' in st.session_state:
         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.write("No categorical columns available for visualization.")
+        st.warning("No categorical columns available for visualization.")
 
     # Correlation Matrix for Numeric Columns
     if len(numeric_columns) > 1:
-        st.write("### Correlation Matrix")
+        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)
 
-    # Check the columns before renaming
-    st.write("### Dataset Columns:")
-    st.write(data.columns)
-
-    # Renaming columns if they exist
-    if 'ProductCategory' in data.columns and 'ProductBrand' in data.columns and 'ProductPrice' in data.columns:
-        data = data.rename(columns={'ProductCategory': 'Category', 'ProductBrand': 'Brand', 'ProductPrice': 'Price'})
-        st.success("Columns renamed successfully!")
-    else:
-        st.warning("Columns 'ProductCategory', 'ProductBrand', or 'ProductPrice' not found in the dataset.")
-
-    # Now check if 'Category' exists and plot
-    if 'Category' in data.columns:
-        st.write("### Bar Plot for Category")
-        fig = px.bar(data, x='Category', title='Bar Plot of Category', color='Category')
-        st.plotly_chart(fig)
-    else:
-        st.warning("'Category' column not found for plotting.")
-
-    # Binning of age column
-    bins = [0, 18, 35, 50, 65, 100]
-    labels = ['Child', 'Young Adult', 'Adult', 'Middle Aged', 'Senior']
-    data['age_bins'] = pd.cut(data['CustomerAge'], bins=bins, labels=labels, right=False)
-
-    # Data Cleaning Section
-    st.write("### Cleaned Dataset")
+    st.subheader("Cleaned Dataset:")
     cleaned_data = data.drop_duplicates()
-    st.dataframe(cleaned_data)
+    st.write(cleaned_data)
 
-    # Save cleaned data to CSV and provide download option
     cleaned_csv = cleaned_data.to_csv(index=False).encode('utf-8')
     st.download_button(
         label="Download Cleaned Dataset",
@@ -145,8 +110,7 @@ if 'df' in st.session_state:
         mime="text/csv"
     )
 
-    # Store the cleaned dataframe in session state for use in other pages
     st.session_state['df'] = cleaned_data
 
 else:
-    st.info("No dataset found in session. Please upload a CSV file on the previous page.")
+    st.warning("No dataset found. Please upload a dataset on the Home page.")