api.py

import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

class PlacementModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(PlacementModel, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.fc2 = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Load and preprocess data
df = pd.read_csv("Placement (2).csv")
df = df.drop(columns=["sl_no","stream","ssc_p","ssc_b","hsc_p","hsc_b","etest_p"])
df['internship'] = df['internship'].map({'Yes':1,'No':0})
df['status'] = df['status'].map({'Placed':1,'Not Placed':0})

X_fullstk = df.drop(['status','management','leadership','communication','sales'], axis=1)
y = df['status']

X_train_fullstk, X_test_fullstk, y_train, y_test = train_test_split(X_fullstk, y, test_size=0.20, random_state=42)

# Define model hyperparameters
input_size = X_fullstk.shape[1]
hidden_size = 128
output_size = 2
learning_rate = 0.01
epochs = 100

# Initialize model
model = PlacementModel(input_size, hidden_size, output_size)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# Train model
for epoch in range(epochs):
    inputs = torch.tensor(X_train_fullstk.values, dtype=torch.float32)
    labels = torch.tensor(y_train.values, dtype=torch.long)

    optimizer.zero_grad()

    outputs = model(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

    if epoch % 10 == 0:
        print(f'Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}')

# Evaluate model
with torch.no_grad():
    inputs = torch.tensor(X_test_fullstk.values, dtype=torch.float32)
    labels = torch.tensor(y_test.values, dtype=torch.long)

    outputs = model(inputs)
    _, predicted = torch.max(outputs.data, 1)
    accuracy = accuracy_score(labels, predicted)

    print(f'Test Accuracy: {accuracy:.4f}')

# Save model
torch.save(model.state_dict(), 'placement_model.pth')