Step 4: Train Models

🤖 Step 4: Train Machine Learning Models

Train ML models using any Excel/CSV dataset. Select feature columns (inputs) and target columns (outputs) for prediction, then choose which algorithms to use.

Tip: Columns are pre-selected based on common patterns, but you can customize the selection for any dataset.

⏳ Training Models...

0%

🚫 Training Cancelled

The training process was cancelled.

✅ Training Complete!

Algorithms trained:

Rows in dataset:

Best model: (MAPE: %)

Model Performance Comparison

Rank	Model	MSE	RMSE	MAE	R²	MAPE (%)	Accuracy (%)

Download Trained Models

Models are saved as pickle files. You can download them for use in Step 5 (Predict).

❌ Error

📁 Use Previous Results

You have statistics file available from Step 3.

Or upload a new file below.

⏳ Loading Dataset...

Extracting column information from your file. This may take a moment for larger files.

Training Configuration

📁 Supported File Formats:

CSV (.csv) - Recommended for large datasets (memory-efficient, fastest loading)
CSV.zip (.csv.zip, .zip) - Compressed CSV for very large files
Excel (.xlsx) - Supported but uses more memory

📏 Maximum file size: 50 MB

💡 Tip: For files larger than 10 MB, use CSV format for better performance.

Training Data File

Upload CSV, CSV.zip, or Excel (.xlsx) file. Max 50 MB. CSV recommended for large datasets (faster loading, lower memory).

Select Algorithms

Choose which machine learning algorithms to train.

Linear Regression Ridge Regression Lasso Regression Random Forest Gradient Boosting Support Vector Regression K-Nearest Neighbors XGBoost

Test Set Size

Fraction of data to use for testing (0.1 to 0.5)

Random Seed

Random seed for reproducibility

Navigation

← Back to Step 3 Proceed to Step 5: Predict →

🔬 Cutting Plan Analyzer