when-developing-ml-models-use-ml-expertlisted

# ML Expert - Machine Learning Model Development ## Overview Specialized workflow for ML model development, training, and deployment. Supports various architectures (CNNs, RNNs, Transformers) with distributed training capabilities. ## When to Use - Developing new ML models - Training neural networks - Model optimization - Production deployment - Transfer learning - Fine-tuning existing models ## Phase 1: Data Preparation (10 min) ### Objective Clean, preprocess, and prepare training data ### Agent: ML-Developer **Step 1.1: Load and Analyze Data** ```python import pandas as pd import numpy as np from sklearn.model_selection import train_test_split # Load data data = pd.read_csv('dataset.csv') # Analyze analysis = { 'shape': data.shape, 'columns': data.columns.tolist(), 'dtypes': data.dtypes.to_dict(), 'missing': data.isnull().sum().to_dict(), 'stats': data.describe().to_dict() } # Store analysis await memory.store('ml-expert/data-analysis', analysis) ``` **Step 1.2: Data Cleaning** ```python # Handle missing values data = data.fillna(data.mean()) # Remove duplicates data = data.drop_duplicates() # Handle outliers from scipy import stats z_scores = np.abs(stats.zscore(data.select_dtypes(include=[np.number]))) data = data[(z_scores < 3).all(axis=1)] # Encode categorical variables from sklearn.preprocessing import LabelEncoder le = LabelEncoder() for col in data.select_dtypes(include=['object']).columns: data[col] = le.fit_transform(data[col