pages/5_Structured_data.py

import streamlit as st
import pandas as pd

st.markdown(
    """
    <style>
    /* General page settings */
    body {
        background-color: #f0f0f5; /* Light gray background */
        color: #333333;  /* Dark text for good contrast */
        font-family: 'Arial', sans-serif; /* Clean, modern font */
    }

    /* Title and Header Styling */
    h1, h2, h3 {
        color: black;  
        font-weight: bold;
    }
    /* Style for subheaders */
     h3 {
        color: red;
        font-family: 'Roboto', sans-serif;
        font-weight: 500;
        margin-top: 20px;
    }
    .custom-subheader {
        color: #00FFFF;
        font-family: 'Roboto', sans-serif;
        font-weight: 600;
        margin-bottom: 15px;
    }
    /* Paragraph styling */
    p {
        font-family: 'Georgia', serif;
        line-height: 1.8;
        color: black;
        margin-bottom: 20px;
    }
    /* List styling with checkmark bullets */
    .icon-bullet {
        list-style-type: none;
        padding-left: 20px;
    }
    .icon-bullet li {
        font-family: 'Georgia', serif;
        font-size: 1.1em;
        margin-bottom: 10px;
        color: #FFFFF0;
    }
    .icon-bullet li::before {
        content: "◆";
        padding-right: 10px;
        color: #b3b3ff;
    }
    /* Sidebar styling */
    .sidebar .sidebar-content {
        background-color: #ffffff;
        border-radius: 10px;
        padding: 15px;
    }
    .sidebar h2 {
        color: #495057;
    }
    /* Custom button style */
    .streamlit-button {
        background-color: #00FFFF;
        color: #000000;
        font-weight: bold;
    }
    </style>
    """, unsafe_allow_html=True)

st.title("📂Handling Excel files📂")
st.markdown(''' - Excel is a widely used software application for organizing, 
                storing, and analyzing data in tabular format. 
            
- It is a spreadsheet tool that allows users to work with rows, columns, and cells to manage numerical or textual data. 
- Excel files are typically saved with extensions like .xls or .xlsx.''')

st.header('**How to Read These Files:**')
st.subheader('''**Using Python Libraries:**''')
st.code('''                
            import pandas as pd
            # Reading an Excel file
            df = pd.read_excel('file.xlsx')
            print(df.head())''')
st.header('**Issues in Excel:**')
st.markdown('''
1. **File Format Issues:**
- `.xls` and `.xlsx` are different formats.
2. **Corrupted Files:**
- Files may get corrupted during transfer or storage, making them unreadable.
3. **Encoding Issues:**
- Data with special characters or non-`UTF-8` encoding can cause errors.''')
st.write('**Solution:**')
st.code('''
    df = pd.read_excel('file.xlsx', encoding='utf-8')
        ''')
st.markdown('''
4. **Missing Values:**
- Cells with missing or `NaN values` may disrupt data processing.''')
st.write('**Solution:**')
st.code('''
    df.fillna(0, inplace=True)  
    df.dropna(inplace=True) 
        ''')
st.markdown('''
5. **Large File Size:**
- Handling very large Excel files can result in memory issues.''')
st.write('**Solution:**')
st.code('''
    chunks = pd.read_excel('large_file.xlsx', chunksize=10000)
    for chunk in chunks:
        print(chunk)
        ''')
st.markdown('''
6. **Multiple Sheets:**
- Huge files may have multiple sheets, making it harder to extract relevant data.''')
st.write('**Solution:**')
st.code('''
    df = pd.read_excel('file.xlsx', sheet_name=[0,1,2])
         ''')