ai_prediction.py

# -*- coding: utf-8 -*-
"""AI Prediction

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1q3pA4LqpvgGDOq-QSzb8ZYFWvrsvwPKo
"""

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

from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics import accuracy_score, classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline
from scipy.sparse import hstack
import re

import os
os.listdir("/content")

df = pd.read_csv("/content/AI-Based Hiring Prediction System (1).csv")
df.head()

df.head()

df.tail()

df.sample(5)

df.shape

df.columns

df.info()

df["Recruiter Decision"].value_counts()

df.describe()

df = df.drop(["Resume_ID", "Name"], axis=1)

df["Recruiter Decision"] = df["Recruiter Decision"].map({"Hire":1, "Reject":0})

df.isnull().sum()

df.fillna("", inplace=True)

df["combined_text"] = df["Skills"] + " " + df["Certifications"] + " " + df["Job Role"]

def clean_text(text):
    text = text.lower()
    text = re.sub(r"[^a-zA-Z ]", "", text)
    text = re.sub(r"\s+", " ", text)
    return text

df["combined_text"] = df["combined_text"].apply(clean_text)

tfidf = TfidfVectorizer(max_features=3000)
text_features = tfidf.fit_transform(df["combined_text"])

le = LabelEncoder()
df["Education"] = le.fit_transform(df["Education"])

y = df["Recruiter Decision"]

X_numeric = df[[
    "Experience (Years)",
    "Salary Expectation ($)",
    "Projects Count",
    "Education"
]]

X_train_num, X_test_num, y_train, y_test = train_test_split(
    X_numeric, y, test_size=0.2, random_state=42
)

X_train_text, X_test_text = train_test_split(
    text_features, test_size=0.2, random_state=42
)

scaler = StandardScaler()
X_train_num = scaler.fit_transform(X_train_num)
X_test_num = scaler.transform(X_test_num)

X_train = hstack([X_train_text, X_train_num])
X_test = hstack([X_test_text, X_test_num])

models = {
    "Logistic Regression": LogisticRegression(),
    "Random Forest": RandomForestClassifier(),
    "SVM": SVC(probability=True),
    "KNN": KNeighborsClassifier()
}

results = {}

for name, model in models.items():
    model.fit(X_train, y_train)
    preds = model.predict(X_test)
    acc = accuracy_score(y_test, preds)
    results[name] = acc

    print(name)
    print("Accuracy:", acc)
    print(classification_report(y_test, preds))

pd.DataFrame(results.items(), columns=["Model", "Accuracy"])

pipe = Pipeline([
    ("tfidf", TfidfVectorizer()),
    ("clf", LogisticRegression())
])

params = {"clf__C": [0.1, 1, 10]}

grid = GridSearchCV(pipe, params, cv=5)
grid.fit(df["combined_text"], y)

grid.best_params_

def predict_hiring(skills, experience, education, certs, projects, salary):

    text = clean_text(skills + " " + certs)
    text_vec = tfidf.transform([text])

    edu_encoded = le.transform([education])[0]

    num_data = scaler.transform([[experience, salary, projects, edu_encoded]])

    final_input = hstack([text_vec, num_data])

    model = models["Random Forest"]
    prob = model.predict_proba(final_input)[0][1]
    pred = model.predict(final_input)[0]

    return ("Hire" if pred==1 else "Reject", prob)

predict_hiring(
    skills="Python SQL Machine Learning",
    experience=3,
    education="M.Tech",
    certs="AWS Data Science",
    projects=5,
    salary=60000
)

le.classes_