Update pages/Data Collection.py

pages/Data Collection.py

@@ -412,43 +412,55 @@ if st.session_state.current_page == "explore_excel":
     for chunk in pd.read_excel('large_file.xlsx', chunksize=chunk_size):
         print(chunk.head())
     """, language="python")
-
+    
     # 5. Sheet Name Selection
-    st.write("#### 5. Sheet Name Selection")
+    st.markdown("""
+    <h4 style="color: #5b2c6f;">5. Sheet Name Selection</h4>
+    """, unsafe_allow_html=True)
     st.write("Excel files may have multiple sheets, and reading the wrong one can lead to incorrect analysis.")
     st.code("""
+    # Specify the sheet name explicitly
     data = pd.read_excel('file.xlsx', sheet_name='Sheet1')
     print(data.head())
     """, language="python")
     
     # 6. Data Type Conversion
-    st.write("#### 6. Data Type Conversion")
+    st.markdown("""
+    <h4 style="color: #5b2c6f;">6. Data Type Conversion</h4>
+    """, unsafe_allow_html=True)
     st.write("Excel files may have columns with inconsistent or incorrect data types.")
     st.code("""
+    # Convert columns to appropriate data types
     data = pd.read_excel('file.xlsx')
-    data['column_name'] = data['column_name'].astype(int)
+    data['column_name'] = data['column_name'].astype(int)  # Replace 'column_name' with your column
     print(data.dtypes)
     """, language="python")
-
-    # 7. Merged Cells
-    st.write("#### 7. Merged Cells")
-    st.write("Merged cells in Excel can lead to missing or misaligned data.")
+    
+    # 7. Hidden Characters or Whitespace
+    st.markdown("""
+    <h4 style="color: #5b2c6f;">7. Hidden Characters or Whitespace</h4>
+    """, unsafe_allow_html=True)
+    st.write("Whitespace or hidden characters in the data can cause parsing issues.")
     st.code("""
-    data = pd.read_excel('file.xlsx', merge_cells=False)
+    # Remove leading/trailing whitespaces
+    data = pd.read_excel('file.xlsx')
+    data.columns = data.columns.str.strip()  # Remove whitespace from column names
+    data['column_name'] = data['column_name'].str.strip()  # Clean specific column
     print(data.head())
     """, language="python")
-
     
-    # 8. Date Parsing
-    st.write("#### 8. Date Parsing")
-    st.write("Dates in Excel files may not be interpreted correctly.")
+    # 8. Merged Cells
+    st.markdown("""
+    <h4 style="color: #5b2c6f;">8. Merged Cells</h4>
+    """, unsafe_allow_html=True)
+    st.write("Merged cells in Excel can lead to missing or misaligned data.")
     st.code("""
-    data = pd.read_excel('file.xlsx', parse_dates=['date_column'])
-    print(data.dtypes)
+    # Handle merged cells by filling forward
+    data = pd.read_excel('file.xlsx', merge_cells=False)  # Disable merging
+    print(data.head())
     """, language="python")
 
-    # Back Button
-    col1 = st.columns(1)
+    col1 = st.columns(1)[0]  # Access the first (and only) column from the list of columns
     with col1:
         if st.button("⬅️ Back to Previous Page"):
             navigate_to("main")