ML in Geofisika

# Complete pipeline example
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix

# 1. Load data
df = pd.read_csv('F3_seismic_facies.csv')

# 2. Prepare features and target
features = ['amplitude', 'envelope', 'inst_freq', 'inst_phase', 'sweetness']
X = df[features]
y = df['facies']

# 3. Split data
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# 4. Scale features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# 5. Train model
model = RandomForestClassifier(
    n_estimators=200,
    max_depth=25,
    min_samples_split=5,
    class_weight='balanced',
    random_state=42,
    n_jobs=-1
)
model.fit(X_train_scaled, y_train)

# 6. Evaluate
y_pred = model.predict(X_test_scaled)
print(classification_report(y_test, y_pred))
print(f"Accuracy: {model.score(X_test_scaled, y_test):.3f}")

# 7. Feature importance
for feat, imp in zip(features, model.feature_importances_):
    print(f"{feat}: {imp:.3f}")

from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.linear_model import Ridge
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error
import numpy as np

# Compare multiple models
models = {
    'Ridge': Ridge(alpha=1.0),
    'Random Forest': RandomForestRegressor(n_estimators=100, random_state=42),
    'Gradient Boosting': GradientBoostingRegressor(n_estimators=100, random_state=42)
}

results = []
for name, model in models.items():
    model.fit(X_train_scaled, y_train)
    y_pred = model.predict(X_test_scaled)
    
    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)
    rmse = np.sqrt(mean_squared_error(y_test, y_pred))
    
    results.append({
        'Model': name,
        'R²': r2,
        'MAE': mae,
        'RMSE': rmse
    })
    
# Display results
results_df = pd.DataFrame(results)
print(results_df)