pages/3.Simple EDA.py

import streamlit as st
import pandas as pd
import numpy as np
#import re
#import emoji

st.markdown("""
    <style>
    /* Set a soft background color */
    body {
        background-color: #eef2f7;
    }
    /* Style for main title */
    h1 {
        color: black;
        font-family: 'Roboto', sans-serif;
        font-weight: 700;
        text-align: center;
        margin-bottom: 25px;
    }
    /* Style for headers */
    h2 {
        color: black;
        font-family: 'Roboto', sans-serif;
        font-weight: 600;
        margin-top: 30px;
    }
    /* Style for subheaders */
    h3 {
        color: red;
        font-family: 'Roboto', sans-serif;
        font-weight: 500;
        margin-top: 20px;
    }
    .custom-subheader {
        color: black;
        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: black;
    }
    .icon-bullet li::before {
        content: "◆";
        padding-right: 10px;
        color: black;
    }
    /* 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.header(":red[📊 Simple EDA 💬]")

# Introduction to Simple EDA
st.markdown("<div class='section'>", unsafe_allow_html=True)
st.markdown("<h2 class='title'>🔍 Understanding Simple EDA</h2>", unsafe_allow_html=True)
st.markdown("<p class='subtitle'>Evaluating raw text data quality before processing</p>", unsafe_allow_html=True)

st.info("📌 **Simple EDA is a crucial step in the NLP lifecycle:**\n\n❁ Ensures raw data quality\n\n❁ Not dependent on problem statement\n\n❁ Helps in better data exploration")

st.markdown("</div>", unsafe_allow_html=True)

st.subheader(":violet[📃 Major Simple EDA Steps]")

st.markdown("❁ **Check Text Case** – Identify if text is in **lowercase, uppercase, or mixed case**.")
st.markdown("❁ **Detect HTML & URL Tags** – Analyze if text contains unwanted elements.")
st.markdown("❁ **Identify URLs** – Ensure URLs are either preserved or removed based on problem statement.")
st.markdown("❁ **Detect Mentions & Hashtags** – Find occurrences of `@mentions` or `#hashtags`.")
st.markdown("❁ **Identify Numeric Data** – Detect if text includes **digits or numerical data**.")
st.markdown("❁ **Analyze Punctuation Usage** – Check whether punctuation marks affect text clarity.")
st.markdown("❁ **Detect Emojis** – Ensure **emoji-based sentiments** are not lost.")
st.markdown("❁ **Analyze Date/Time Formats** – Identify the presence of date/time-related text.")

st.success("🚀 Performing **Simple EDA** ensures structured and high-quality text data, leading to better NLP model performance!")

st.code('''
import pandas as pd
import numpy as np
import re
import emoji
def simple_eda(data, column):
    lower_upper = data[column].apply(lambda x: True if (x.lower()) or (x.upper()) else False).sum()
    tags = data[column].apply(lambda x: True if re.search("<.*?>", x) else False).sum()
    urls = data[column].apply(lambda x: True if re.search("https://\\S+", x) else False).sum()
    mails = data[column].apply(lambda x: True if re.search("\\S+@\\S+", x) else False).sum()
    mentions = data[column].apply(lambda x: True if re.search("\\B[@#]\\S+", x) else False).sum()
    emojis = data[column].apply(lambda x: True if emoji.emoji_count(x) else False).sum()
    digit = data[column].apply(lambda x: True if re.search("\\d", x) else False).sum()
    punc = data[column].apply(lambda x: True if re.search('[!"#$%&\'()*+,-./:;<=>?@[\\\\]^_`{|}~]', x) else False).sum()
    dates = data[column].apply(lambda x: True if re.search(r"^[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}$", x) else False).sum()
    if lower_upper > 0:
        print("Text has a combination of cases.")
    if tags > 0:
        print("Text contains HTML tags.")
    if urls > 0:
        print("Text contains URLs.")
    if mails > 0:
        print("Text contains email addresses.")
    if mentions > 0:
        print("Text contains mentions or hashtags.")
    if emojis > 0:
        print("Text contains emojis.")
    if digit > 0:
        print("Text contains digits.")
    if punc > 0:
        print("Text contains punctuation marks.")
    if dates > 0:
        print("Text contains dates.")
''')

st.markdown('''
- By following this code, we will check the exploration of the data.
- It essentially gives the quality of the collected text data.
- After the simple EDA, we will perform pre-processing on text based on the problem statement after knowing the quality of the data.
''')