4.py

# -*- coding: utf-8 -*-
"""JOB-25 career_recommendation.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1kYu9jWQSTeXu31D_JHI37iWrbnDNfuCr

**CAREER RECOMMENDATION**

**The Objective is **

Load and Prepare data
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

import pandas as pd

df = pd.read_excel("New jobready_career_skill_dataset_1000_rows_v2.xlsx")

# Remove duplicates
df = df.drop_duplicates()

df

career_skills = df.groupby('Career').apply(
    lambda x: list(zip(
        x['Skill/Sub-skill'],
        x['Weight'],
        x['Threshold (0-100)'],
        x['Level Required']
    ))
).to_dict()

user_profile = {
    "skills": ["Python", "SQL", "Machine Learning", "Data Analysis"],
    "level": "Intermediate"
}

def match_career(user_profile, career_skills):
    scores = {}

    user_skills = set(user_profile["skills"])
    user_level = user_profile["level"]

    level_map = {
        "Beginner": 1,
        "Intermediate": 2,
        "Advanced": 3
    }

    for career, skills in career_skills.items():
        score = 0

        for skill, weight, threshold, level in skills:

            # Skill match
            if skill in user_skills:
                score += weight * 100   # boost score

            # Level match
            if level_map[user_level] >= level_map[level]:
                score += 5

            # Threshold influence
            score += (threshold / 100)

        scores[career] = score

    return sorted(scores.items(), key=lambda x: x[1], reverse=True)

recommendations = match_career(user_profile, career_skills)

for career, score in recommendations:
    print(career, score)