ML Model Training

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder

# Load and clean data
df = pd.read_csv('data.csv')
df = df.dropna()

# Encode categorical variables
le = LabelEncoder()
df['category'] = le.fit_transform(df['category'])

# Split data (70/15/15)
X = df.drop('target', axis=1)
y = df['target']
X_train, X_temp, y_train, y_temp = train_test_split(X, y, test_size=0.3)
X_val, X_test, y_val, y_test = train_test_split(X_temp, y_temp, test_size=0.5)

# Scale features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_val = scaler.transform(X_val)
X_test = scaler.transform(X_test)

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, accuracy_score

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

y_pred = model.predict(X_val)
print(classification_report(y_val, y_pred))

import torch
import torch.nn as nn

class Model(nn.Module):
    def __init__(self, input_dim):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(input_dim, 64),
            nn.ReLU(),
            nn.Dropout(0.3),
            nn.Linear(64, 32),
            nn.ReLU(),
            nn.Linear(32, 1),
            nn.Sigmoid()
        )

    def forward(self, x):
        return self.layers(x)

model = Model(X_train.shape[1])
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
criterion = nn.BCELoss()

for epoch in range(100):
    model.train()
    optimizer.zero_grad()
    output = model(X_train_tensor)
    loss = criterion(output, y_train_tensor)
    loss.backward()
    optimizer.step()

# ✅ Correct: Fit on train, transform train/val/test
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_val = scaler.transform(X_val)  # Only transform
X_test = scaler.transform(X_test)  # Only transform

# ❌ Wrong: Fitting on all data
X_all = scaler.fit_transform(X)  # Leaks test info!

from sklearn.utils.class_weight import compute_class_weight

# Compute class weights
class_weights = compute_class_weight('balanced', classes=np.unique(y_train), y=y_train)
model = RandomForestClassifier(class_weight='balanced')

# Or use SMOTE for oversampling minority class
from imblearn.over_sampling import SMOTE
smote = SMOTE()
X_resampled, y_resampled = smote.fit_resample(X_train, y_train)

# Dropout in PyTorch
nn.Dropout(0.3)

# L2 regularization in scikit-learn
RandomForestClassifier(max_depth=10, min_samples_split=20)

# Early stopping in Keras
from tensorflow.keras.callbacks import EarlyStopping
early_stop = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)
model.fit(X_train, y_train, validation_data=(X_val, y_val), callbacks=[early_stop])

import random
import numpy as np
import torch

random.seed(42)
np.random.seed(42)
torch.manual_seed(42)
if torch.cuda.is_available():
    torch.cuda.manual_seed_all(42)

from sklearn.model_selection import GridSearchCV

# ✅ Correct: Tune on train+val, evaluate on test
param_grid = {'n_estimators': [50, 100, 200], 'max_depth': [5, 10, 15]}
grid_search = GridSearchCV(RandomForestClassifier(), param_grid, cv=5)
grid_search.fit(X_train, y_train)  # Cross-validation on training set
best_model = grid_search.best_estimator_

# Final evaluation on held-out test set
final_score = best_model.score(X_test, y_test)