app.py

import json
import pandas as pd
import mysql.connector
import gradio as gr

# Define your data loading and processing functions
def load_data():
    data = json.load(open("all_job_skills.json"))
    job_skills = pd.DataFrame()
    for job in data.keys():
        temp = pd.DataFrame(data[job].keys(), columns=['skill'])
        temp['job'] = job
        job_skills = pd.concat([job_skills, temp])
    job_skills = job_skills[~job_skills['skill'].str.contains('opic')]
    job_skills['Weightage'] = 0
    return job_skills
def get_student_data(student_id):
    mydb = mysql.connector.connect(
        host="edwiselyproddb.crhg7zleeuhf.ap-south-1.rds.amazonaws.com",
        user="usermanage",
        password="7L6ZpWGgbbE9jiSv",
        database = "edwisely_college"
        )
    sql = mydb.cursor(buffered=True)
    query =f"""select sm.id, sm.name, ssqs.student_id, ssqs.avg_percentage_scored from subject_master sm
    join student_subject_questionnaire_stats ssqs on ssqs.subject_master_id = sm.id where ssqs.student_id = {student_id};"""
    sql.execute(query)
    df_student = pd.DataFrame(sql.fetchall(), columns = sql.column_names )
    sql.close()
    mydb.close()
    return df_student


def process_data(student_id):
    final_score_df = pd.read_excel('all_subject_2_final_score.xlsx')
    job_skills = load_data()
    df_student = get_student_data(student_id)
    for index, subject in df_student.iterrows():
        skills_df = final_score_df[final_score_df['subject']==subject['name']]
        skills_df['Weightage'] = skills_df['score'] * subject.avg_percentage_scored * 0.01  
        for index, row in skills_df.iterrows():
            job_skills.loc[job_skills['skill'] == row.skill, 'Weightage'] += row.Weightage
    result = job_skills.groupby('job')['Weightage'].sum().reset_index().sort_values('Weightage', ascending=False).iloc[:10, :]
    return result

# Define Gradio interface
iface = gr.Interface(
    fn=process_data,  # The function to be executed
    inputs=[
        "number"  # Student ID input
    ],
    outputs="dataframe"  # Display the result as a DataFrame
)

# Launch the Gradio interface
iface.launch(inline = False)