app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
from streamlit.components.v1 import html
import nbformat
from nbconvert import HTMLExporter
from wordcloud import WordCloud

# Load the CSV data
file_path = 'category upwork jobs.csv'
jobs_df = pd.read_csv(file_path)

# Adjust column names as per the CSV
category_column = 'category'  # Replace with the actual column name for category
job_title_column = 'title'  # Replace with the actual column name for job title
description_column = 'description'
key_column = 'key'
date_column = 'Date'

# Sidebar menu
st.sidebar.title("Navigation")
option = st.sidebar.radio("Go to", ["Home", "Plots", "Notebook","Download Datasets"])
# Home Page: Display data with category filter
if option == "Home":
    st.title("Jobs Dashboard")

    # Filter Jobs by Category
    st.sidebar.header("Filter Jobs by Category")
    categories = jobs_df[category_column].unique()  # Extract unique categories
    selected_category = st.sidebar.selectbox("Choose a category:", categories)

    # Filter jobs based on the selected category
    filtered_jobs = jobs_df[jobs_df[category_column] == selected_category]

    # Display filtered jobs with additional columns
    st.write(f"Showing jobs in category: **{selected_category}**")
    st.dataframe(filtered_jobs[['title','key','description','date']])

    # Optional: Show a count of jobs in the selected category
    st.write(f"Total jobs in this category: {len(filtered_jobs)}")

# Plots Page: Display category distribution plot
elif option == "Plots":
    st.title("Job Visualization")

    # 1. Job Category Distribution Bar Plot
    st.subheader("Job Category Distribution")
    category_counts = jobs_df[category_column].value_counts()
    fig1, ax1 = plt.subplots()
    ax1.bar(category_counts.index, category_counts.values)
    ax1.set_xlabel("Job Category")
    ax1.set_ylabel("Number of Jobs")
    ax1.set_title("Distribution of Jobs Across Categories")
    plt.xticks(rotation=45, ha="right")
    st.pyplot(fig1)

    # 2. Pie Chart for Category Distribution
    st.subheader("Job Category Proportions")
    fig2, ax2 = plt.subplots(figsize=(10, 25))
    ax2.pie(category_counts, labels=category_counts.index, autopct='%1.1f%%', startangle=140)
    ax2.axis('equal')  # Equal aspect ratio ensures the pie chart is circular.
    st.pyplot(fig2)

    

    # 4. Top Job Titles Bar Plot
    st.subheader("Top Job Titles")
    top_job_titles = jobs_df[job_title_column].value_counts().head(10)
    fig4, ax4 = plt.subplots()
    ax4.bar(top_job_titles.index, top_job_titles.values)
    ax4.set_xlabel("Job Title")
    ax4.set_ylabel("Count")
    ax4.set_title("Top 10 Job Titles")
    plt.xticks(rotation=45, ha="right")
    st.pyplot(fig4)

    # 5. Word Cloud for Job Descriptions
    st.subheader("Word Cloud for Job Descriptions")
    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(' '.join(jobs_df[description_column].dropna()))
    fig5, ax5 = plt.subplots(figsize=(10, 5))
    ax5.imshow(wordcloud, interpolation='bilinear')
    ax5.axis('off')  # Turn off the axis
    st.pyplot(fig5)

elif option == "Notebook":
    st.title("Jupyter Notebook")

    # Load and convert the notebook to HTML
    notebook_path = 'upwork_dashboard.ipynb'  # Update with the actual path to your notebook
    with open(notebook_path) as f:
        notebook_content = nbformat.read(f, as_version=4)

    # Create a new markdown cell with the link to the Google Colab notebook
    colab_link = "[Open in Google Colab](https://colab.research.google.com/drive/1qoTldQ-Kr6DgePRNYgdlQqqHq5JQax0h?usp=sharing)"
    new_cell = nbformat.v4.new_markdown_cell(colab_link)

    # Insert the new cell at the top of the notebook
    notebook_content.cells.insert(0, new_cell)

    # Export the notebook to HTML
    html_exporter = HTMLExporter()
    html_exporter.exclude_input = False  # Include code cells in the notebook display
    notebook_html, _ = html_exporter.from_notebook_node(notebook_content)

    # Display the notebook HTML in Streamlit
    html(notebook_html, height=800, scrolling=True)
    # Notebook Page: Render the Jupyter Notebook
elif option == "Download Datasets":
    st.title("Download Datasets")
    d=pd.read_csv("category upwork jobs.csv")
    d1=pd.read_csv("jobs.csv")
    # Download links for the datasets
    st.markdown("Click the links below to download the datasets:")
    
    # Link for category upwork jobs dataset
    with open("category upwork jobs.csv", 'rb') as f:
        st.download_button(
            label="Download Category Upwork Jobs Dataset",
            data=f,
            file_name='category_upwork_jobs.csv',
            mime='text/csv'
        )
    st.dataframe(d)
    # Link for the original dataset
    with open("jobs.csv", 'rb') as f:
        st.download_button(
            label="Download Original Dataset",
            data=f,
            file_name='origina scraped data.csv',
            mime='text/csv'
        )
        st.dataframe(d1)