project / app.py
ArchiMathur's picture
Update app.py
87e08d6 verified
import gradio as gr
import pandas as pd
import numpy as np
import pickle
import sklearn
from datasets import load_dataset
import joblib
import requests
# Read the data
data = pd.read_csv("mldata.csv")
# Function to load model
def load_model():
with open('rfweights.pkl', 'rb') as pickleFile:
return pickle.load(pickleFile)
# Prepare categorical data
categorical_cols = data[[
'certifications',
'workshops',
'Interested subjects',
'interested career area ',
'Type of company want to settle in?',
'Interested Type of Books'
]].copy()
# Assign category codes
for i in categorical_cols:
data[i] = data[i].astype('category')
data[i] = data[i].cat.codes
# Create reference dictionaries for embeddings
def create_embedding_dict(column):
unique_names = list(categorical_cols[column].unique())
unique_codes = list(data[column].unique())
return dict(zip(unique_names, unique_codes))
certificates_references = create_embedding_dict('certifications')
workshop_references = create_embedding_dict('workshops')
subjects_interest_references = create_embedding_dict('Interested subjects')
career_interest_references = create_embedding_dict('interested career area ')
company_intends_references = create_embedding_dict('Type of company want to settle in?')
book_interest_references = create_embedding_dict('Interested Type of Books')
# Career-specific job data
CAREER_JOB_DATA = {
"Software Engineer": [
["Software Engineer", "Mindtree Ltd", "Bangalore, Karnataka", "₹5,50,000 - ₹11,00,000"],
["Software Developer", "Mphasis", "Pune, Maharashtra", "₹5,00,000 - ₹9,50,000"],
["Full Stack Developer", "Persistent Systems", "Hyderabad, Telangana", "₹6,00,000 - ₹12,00,000"],
["Backend Engineer", "Zensar Technologies", "Mumbai, Maharashtra", "₹5,80,000 - ₹10,50,000"],
["Junior Software Engineer", "Cyient", "Chennai, Tamil Nadu", "₹4,20,000 - ₹7,80,000"]
],
"Software Developer": [
["Software Developer", "LTI (L&T Infotech)", "Bangalore, Karnataka", "₹4,80,000 - ₹9,20,000"],
["Application Developer", "Hexaware Technologies", "Hyderabad, Telangana", "₹5,20,000 - ₹9,80,000"],
["Java Developer", "Birlasoft", "Pune, Maharashtra", "₹5,50,000 - ₹10,50,000"],
["Python Developer", "Sonata Software", "Noida, UP", "₹6,00,000 - ₹11,50,000"],
["Software Engineer Trainee", "Larsen & Toubro Technology", "Mumbai, Maharashtra", "₹3,80,000 - ₹6,50,000"]
],
"Web Developer": [
["Frontend Developer", "Nagarro", "Gurgaon, Haryana", "₹6,50,000 - ₹13,00,000"],
["Full Stack Web Developer", "Publicis Sapient", "Bangalore, Karnataka", "₹7,20,000 - ₹14,50,000"],
["React Developer", "ThoughtWorks", "Pune, Maharashtra", "₹8,00,000 - ₹16,00,000"],
["Web Developer", "Xoriant", "Mumbai, Maharashtra", "₹5,50,000 - ₹11,00,000"],
["UI Developer", "Synechron", "Bangalore, Karnataka", "₹6,80,000 - ₹13,50,000"]
],
"Mobile Applications Developer": [
["Android Developer", "Mindtree Ltd", "Bangalore, Karnataka", "₹7,50,000 - ₹15,00,000"],
["iOS Developer", "Cybage", "Pune, Maharashtra", "₹7,00,000 - ₹14,00,000"],
["Flutter Developer", "QuEST Global", "Bangalore, Karnataka", "₹6,50,000 - ₹13,00,000"],
["React Native Developer", "NIIT Technologies", "Noida, UP", "₹6,00,000 - ₹12,00,000"],
["Mobile App Developer", "iGate (Capgemini)", "Hyderabad, Telangana", "₹5,80,000 - ₹11,50,000"]
],
"Database Developer": [
["Database Developer", "Mastek", "Mumbai, Maharashtra", "₹6,50,000 - ₹13,00,000"],
["SQL Developer", "Virtusa", "Hyderabad, Telangana", "₹7,00,000 - ₹14,00,000"],
["Database Administrator", "Polaris Consulting", "Chennai, Tamil Nadu", "₹6,20,000 - ₹12,50,000"],
["Data Engineer", "Altimetrik", "Bangalore, Karnataka", "₹7,50,000 - ₹15,00,000"],
["Big Data Developer", "Sasken Technologies", "Bangalore, Karnataka", "₹7,80,000 - ₹15,50,000"]
],
"Network Security Engineer": [
["Security Engineer", "Quick Heal Technologies", "Pune, Maharashtra", "₹6,50,000 - ₹13,00,000"],
["Cybersecurity Analyst", "Paladion Networks", "Bangalore, Karnataka", "₹6,00,000 - ₹12,00,000"],
["Network Security Specialist", "K7 Computing", "Chennai, Tamil Nadu", "₹7,00,000 - ₹14,00,000"],
["Information Security Analyst", "SecureKloud", "Chennai, Tamil Nadu", "₹6,80,000 - ₹13,50,000"],
["Security Operations Analyst", "Sequretek", "Bangalore, Karnataka", "₹5,80,000 - ₹11,50,000"]
],
"UX Designer": [
["UX Designer", "Think Design", "Bangalore, Karnataka", "₹5,50,000 - ₹12,00,000"],
["UI/UX Designer", "F5 Studio", "Mumbai, Maharashtra", "₹5,00,000 - ₹11,00,000"],
["Product Designer", "Lollypop Design", "Bangalore, Karnataka", "₹6,00,000 - ₹13,00,000"],
["Visual Designer", "Designit (Wipro)", "Pune, Maharashtra", "₹5,80,000 - ₹12,50,000"],
["UX Researcher", "Happy Marketer", "Gurgaon, Haryana", "₹5,20,000 - ₹11,50,000"]
],
"Software Quality Assurance (QA)/ Testing": [
["QA Engineer", "Cigniti Technologies", "Hyderabad, Telangana", "₹4,20,000 - ₹8,50,000"],
["Software Tester", "TestingXperts", "Mumbai, Maharashtra", "₹3,80,000 - ₹7,80,000"],
["Automation Test Engineer", "Qualitest", "Pune, Maharashtra", "₹5,00,000 - ₹10,00,000"],
["QA Analyst", "QA InfoTech", "Noida, UP", "₹4,50,000 - ₹9,00,000"],
["Test Lead", "Maveric Systems", "Bangalore, Karnataka", "₹6,50,000 - ₹13,00,000"]
],
"Technical Support": [
["Technical Support Engineer", "Happiest Minds", "Bangalore, Karnataka", "₹3,20,000 - ₹6,50,000"],
["IT Support Specialist", "Rolta India", "Mumbai, Maharashtra", "₹2,80,000 - ₹5,80,000"],
["Desktop Support Engineer", "Fujitsu Consulting", "Pune, Maharashtra", "₹3,00,000 - ₹6,00,000"],
["Technical Support Associate", "iYogi Technical Services", "Gurgaon, Haryana", "₹3,50,000 - ₹7,00,000"],
["Help Desk Technician", "CSS Corp", "Chennai, Tamil Nadu", "₹2,80,000 - ₹5,50,000"]
],
"Systems Security Administrator": [
["System Administrator", "Kale Logistics", "Pune, Maharashtra", "₹4,50,000 - ₹9,00,000"],
["Linux Administrator", "Sify Technologies", "Chennai, Tamil Nadu", "₹5,50,000 - ₹11,00,000"],
["Windows System Admin", "Netmagic Solutions", "Mumbai, Maharashtra", "₹5,20,000 - ₹10,50,000"],
["Cloud Administrator", "CtrlS Datacenters", "Hyderabad, Telangana", "₹6,50,000 - ₹13,00,000"],
["DevOps Engineer", "Genpact", "Bangalore, Karnataka", "₹7,00,000 - ₹14,00,000"]
],
"Applications Developer": [
["Application Developer", "3i Infotech", "Mumbai, Maharashtra", "₹5,50,000 - ₹11,00,000"],
["Enterprise App Developer", "Ramco Systems", "Chennai, Tamil Nadu", "₹6,20,000 - ₹12,50,000"],
["Software Application Engineer", "Newgen Software", "Noida, UP", "₹6,50,000 - ₹13,00,000"],
["Business Application Developer", "Aurionpro Solutions", "Mumbai, Maharashtra", "₹5,80,000 - ₹11,50,000"],
["Custom App Developer", "Nucleus Software", "Noida, UP", "₹6,00,000 - ₹12,00,000"]
],
"CRM Technical Developer": [
["Salesforce Developer", "Tech Mahindra", "Pune, Maharashtra", "₹6,50,000 - ₹13,00,000"],
["CRM Developer", "HGS (Hinduja Global)", "Bangalore, Karnataka", "₹6,00,000 - ₹12,00,000"],
["Dynamics 365 Developer", "L&T Technology Services", "Vadodara, Gujarat", "₹6,80,000 - ₹13,50,000"],
["CRM Technical Consultant", "Firstsource Solutions", "Mumbai, Maharashtra", "₹6,20,000 - ₹12,50,000"],
["Salesforce Administrator", "WNS Global Services", "Pune, Maharashtra", "₹5,00,000 - ₹10,00,000"]
]
}
# Function to fetch job listings
def fetch_job_listings(job_title):
"""Fetch job listings - tries API first, then falls back to curated data"""
# Try API first
api_key = '714f5a2539msh798d996c3243876p19c71ajsnfcd7ce481cb9'
url = "https://jsearch.p.rapidapi.com/search"
querystring = {
"query": f"{job_title} in India",
"page": "1",
"num_pages": "1",
"date_posted": "all"
}
headers = {
"x-rapidapi-key": api_key,
"x-rapidapi-host": "jsearch.p.rapidapi.com"
}
try:
response = requests.get(url, headers=headers, params=querystring, timeout=10)
print(f"JSearch API Response Status: {response.status_code}")
if response.status_code == 200:
job_data = response.json()
if job_data.get('data') and len(job_data['data']) > 0:
job_listings = []
for job in job_data['data'][:5]:
salary = "Not specified"
if job.get('job_min_salary') and job.get('job_max_salary'):
min_sal = job.get('job_min_salary')
max_sal = job.get('job_max_salary')
currency = job.get('job_salary_currency', 'INR')
if currency == 'INR':
salary = f"₹{min_sal:,.0f} - ₹{max_sal:,.0f}"
else:
salary = f"{currency} {min_sal:,.0f} - {max_sal:,.0f}"
elif job.get('job_min_salary'):
min_sal = job.get('job_min_salary')
currency = job.get('job_salary_currency', 'INR')
salary = f"₹{min_sal:,.0f}+" if currency == 'INR' else f"{currency} {min_sal:,.0f}+"
location_parts = []
if job.get('job_city'):
location_parts.append(job.get('job_city'))
if job.get('job_state'):
location_parts.append(job.get('job_state'))
location = ', '.join(location_parts) if location_parts else job.get('job_country', 'India')
job_listings.append([
job.get('job_title', 'N/A'),
job.get('employer_name', 'N/A'),
location,
salary
])
print(f"Successfully fetched {len(job_listings)} real jobs from API")
return job_listings
except Exception as e:
print(f"API failed: {str(e)}, using curated data")
# Fallback to curated career-specific data
if job_title in CAREER_JOB_DATA:
print(f"Using curated data for {job_title}")
return CAREER_JOB_DATA[job_title]
# Generic fallback
return [
[f"{job_title} (Entry Level)", "Various IT Companies", "Bangalore, Karnataka", "₹4,00,000 - ₹8,00,000"],
[f"{job_title} (Mid Level)", "Various IT Companies", "Hyderabad, Telangana", "₹7,00,000 - ₹14,00,000"],
[f"{job_title} (Senior)", "Various IT Companies", "Pune, Maharashtra", "₹12,00,000 - ₹24,00,000"],
[f"{job_title} Intern", "Startups & IT Firms", "Mumbai, Maharashtra", "₹2,00,000 - ₹4,00,000"],
["💡 Job Search", "Check: Naukri, LinkedIn, Indeed", "India (Remote/Onsite)", "Apply to 10+ daily"]
]
# Prediction function (modified to return job suggestions)
def rfprediction(name, logical_thinking, hackathon_attend, coding_skills, public_speaking_skills,
self_learning, extra_course, certificate_code, worskhop_code, read_writing_skill, memory_capability,
subject_interest, career_interest, company_intend, senior_elder_advise, book_interest, introvert_extro,
team_player, management_technical, smart_hardworker):
try:
# Load the Random Forest model
rfmodel = load_model()
# Create DataFrame
df = pd.DataFrame({
"logical_thinking": [logical_thinking],
"hackathon_attend": [hackathon_attend],
"coding_skills": [coding_skills],
"public_speaking_skills": [public_speaking_skills],
"self_learning": [self_learning],
"extra_course": [extra_course],
"certificate": [certificate_code],
"workshop": [worskhop_code],
"read_writing_skills": [
(0 if "poor" in read_writing_skill else 1 if "medium" in read_writing_skill else 2)
],
"memory_capability": [
(0 if "poor" in memory_capability else 1 if "medium" in memory_capability else 2)
],
"subject_interest": [subject_interest],
"career_interest": [career_interest],
"company_intend": [company_intend],
"senior_elder_advise": [senior_elder_advise],
"book_interest": [book_interest],
"introvert_extro": [introvert_extro],
"team_player": [team_player],
"management_technical": [management_technical],
"smart_hardworker": [smart_hardworker]
})
# Replace string values with numeric representations - FIX for FutureWarning
replacement_dict = {
"certificate": certificates_references,
"workshop": workshop_references,
"subject_interest": subjects_interest_references,
"career_interest": career_interest_references,
"company_intend": company_intends_references,
"book_interest": book_interest_references
}
for col, mapping in replacement_dict.items():
if col in df.columns:
df[col] = df[col].map(mapping)
# Dummy encoding
userdata_list = df.values.tolist()
# Management-Technical dummy encoding
if df["management_technical"].values[0] == "Management":
userdata_list[0].extend([1, 0])
userdata_list[0].remove('Management')
elif df["management_technical"].values[0] == "Technical":
userdata_list[0].extend([0, 1])
userdata_list[0].remove('Technical')
else:
return {"Error": 1.0}, [["Error in Management-Technical encoding", "", "", ""]]
# Smart-Hard worker dummy encoding
if df["smart_hardworker"].values[0] == "smart worker":
userdata_list[0].extend([1, 0])
userdata_list[0].remove('smart worker')
elif df["smart_hardworker"].values[0] == "hard worker":
userdata_list[0].extend([0, 1])
userdata_list[0].remove('hard worker')
else:
return {"Error": 1.0}, [["Error in Smart-Hard worker encoding", "", "", ""]]
# Convert to numpy array for prediction
userdata_array = np.array(userdata_list)
# Prediction
prediction_result_all = rfmodel.predict_proba(userdata_array)
# Create result dictionary with probabilities
result_list = {
"Applications Developer": float(prediction_result_all[0][0]),
"CRM Technical Developer": float(prediction_result_all[0][1]),
"Database Developer": float(prediction_result_all[0][2]),
"Mobile Applications Developer": float(prediction_result_all[0][3]),
"Network Security Engineer": float(prediction_result_all[0][4]),
"Software Developer": float(prediction_result_all[0][5]),
"Software Engineer": float(prediction_result_all[0][6]),
"Software Quality Assurance (QA)/ Testing": float(prediction_result_all[0][7]),
"Systems Security Administrator": float(prediction_result_all[0][8]),
"Technical Support": float(prediction_result_all[0][9]),
"UX Designer": float(prediction_result_all[0][10]),
"Web Developer": float(prediction_result_all[0][11]),
}
# Find the top predicted career
top_career = max(result_list, key=result_list.get)
# Fetch job listings for the top predicted career
job_suggestions = fetch_job_listings(top_career)
return result_list, job_suggestions
except Exception as e:
error_msg = f"Error during prediction: {str(e)}"
return {"Error": 1.0}, [[error_msg, "", "", ""]]
# Lists for dropdown menus
cert_list = ["app development", "distro making", "full stack", "hadoop", "information security", "machine learning", "python", "r programming", "shell programming"]
workshop_list = ["cloud computing", "data science", "database security", "game development", "hacking", "system designing", "testing", "web technologies"]
skill = ["excellent", "medium", "poor"]
subject_list = ["cloud computing", "Computer Architecture", "data engineering", "hacking", "IOT", "Management", "networks", "parallel computing", "programming", "Software Engineering"]
career_list = ["Business process analyst", "cloud computing", "developer", "security", "system developer", "testing"]
company_list = ["BPA", "Cloud Services", "Finance", "Product based", "product development", "SAaS services", "Sales and Marketing", "Service Based", "Testing and Maintainance Services", "Web Services"]
book_list = ["Action and Adventure", "Anthology", "Art", "Autobiographies", "Biographies", "Childrens", "Comics","Cookbooks","Diaries","Dictionaries","Drama","Encyclopedias","Fantasy","Guide","Health","History","Horror","Journals","Math","Mystery","Poetry","Prayer books","Religion-Spirituality","Romance","Satire","Science","Science fiction","Self help","Series","Travel","Trilogy"]
Choice_list = ["Management", "Technical"]
worker_list = ["hard worker", "smart worker"]
# Create Gradio interface
def create_output_component():
return [
gr.Label(label="Career Probabilities"),
gr.Dataframe(
headers=["Job Title", "Company", "Location", "Salary"],
label="Job Suggestions"
)
]
demo = gr.Interface(
fn=rfprediction,
inputs=[
gr.Textbox(placeholder="What is your name?", label="Name"),
gr.Slider(minimum=1, maximum=9, value=3, step=1, label="Are you a logical thinking person?", info="Scale: 1 - 9"),
gr.Slider(minimum=0, maximum=6, value=0, step=1, label="Do you attend any Hackathons?", info="Scale: 0 - 6 | 0 - if not attended any"),
gr.Slider(minimum=1, maximum=9, value=5, step=1, label="How do you rate your coding skills?", info="Scale: 1 - 9"),
gr.Slider(minimum=1, maximum=9, value=3, step=1, label="How do you rate your public speaking skills/confidency?", info="Scale: 1 - 9"),
gr.Radio(["Yes", "No"], type="index", label="Are you a self-learning person? *"),
gr.Radio(["Yes", "No"], type="index", label="Do you take extra courses in uni (other than IT)? *"),
gr.Dropdown(cert_list, label="Select a certificate you took!"),
gr.Dropdown(workshop_list, label="Select a workshop you attended!"),
gr.Dropdown(skill, label="Select your read and writing skill"),
gr.Dropdown(skill, label="Is your memory capability good?"),
gr.Dropdown(subject_list, label="What subject you are interested in?"),
gr.Dropdown(career_list, label="Which IT-Career do you have interests in?"),
gr.Dropdown(company_list, label="Do you have any interested company that you intend to settle in?"),
gr.Radio(["Yes", "No"], type="index", label="Do you ever seek any advices from senior or elders? *"),
gr.Dropdown(book_list, label="Select your interested genre of book!"),
gr.Radio(["Yes", "No"], type="index", label="Are you an Introvert?| No - extrovert *"),
gr.Radio(["Yes", "No"], type="index", label="Ever worked in a team? *"),
gr.Dropdown(Choice_list, label="Which area do you prefer: Management or Technical?"),
gr.Dropdown(worker_list, label="Are you a Smart worker or Hard worker?")
],
outputs=create_output_component(),
title="AI-Enhanced Career Guidance System"
)
# Main execution
if __name__ == "__main__":
demo.launch(share=False)