import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer
import matplotlib.pyplot as plt
import seaborn as sns

from config import DATA_PROCESSED, FIGURES

# Load data
trained_distances = pd.read_csv(DATA_PROCESSED / 'trained_distances.csv')
untrained_distances = pd.read_csv(DATA_PROCESSED / 'untrained_distances.csv')

# Add group labels
trained_distances['group'] = 'trained'
untrained_distances['group'] = 'untrained'

# Combine data
combined_data = pd.concat([trained_distances, untrained_distances], ignore_index=True)
combined_data = combined_data.dropna(subset=['group'])

# Prepare features and target
features = ['distance', 'n_flies', 'area_fly1', 'area_fly2']
X = combined_data[features]
y = combined_data['group']

# Handle missing values in features
imputer = SimpleImputer(strategy='mean')
X_imputed = pd.DataFrame(imputer.fit_transform(X), columns=features)

# Split data
X_train, X_test, y_train, y_test = train_test_split(X_imputed, y, test_size=0.2, random_state=42)

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

print("=== MACHINE LEARNING CLASSIFICATION ===")
print(f"Training set size: {len(X_train)}")
print(f"Testing set size: {len(X_test)}")

# 1. Logistic Regression
print("\n1. Logistic Regression:")
lr_model = LogisticRegression(random_state=42)
lr_model.fit(X_train_scaled, y_train)
lr_predictions = lr_model.predict(X_test_scaled)
lr_accuracy = accuracy_score(y_test, lr_predictions)
print(f"Accuracy: {lr_accuracy:.4f}")
print("\nClassification Report:")
print(classification_report(y_test, lr_predictions))

# 2. Random Forest
print("\n2. Random Forest:")
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_train, y_train)
rf_predictions = rf_model.predict(X_test)
rf_accuracy = accuracy_score(y_test, rf_predictions)
print(f"Accuracy: {rf_accuracy:.4f}")
print("\nClassification Report:")
print(classification_report(y_test, rf_predictions))

# Feature importance
print("\nFeature Importance (Random Forest):")
feature_importance = pd.DataFrame({
    'feature': features,
    'importance': rf_model.feature_importances_
}).sort_values('importance', ascending=False)
print(feature_importance)

# Confusion matrix for the best model
best_model_name = "Random Forest" if rf_accuracy > lr_accuracy else "Logistic Regression"
best_predictions = rf_predictions if rf_accuracy > lr_accuracy else lr_predictions

plt.figure(figsize=(8, 6))
cm = confusion_matrix(y_test, best_predictions)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
            xticklabels=['Trained', 'Untrained'],
            yticklabels=['Trained', 'Untrained'])
plt.title(f'Confusion Matrix - {best_model_name}')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.tight_layout()
plt.savefig(FIGURES / 'confusion_matrix.png', dpi=300, bbox_inches='tight')
plt.show()

# Cross-validation scores
print("\n=== CROSS-VALIDATION SCORES ===")
lr_cv_scores = cross_val_score(LogisticRegression(random_state=42), X_train_scaled, y_train, cv=5)
rf_cv_scores = cross_val_score(RandomForestClassifier(n_estimators=100, random_state=42), X_train, y_train, cv=5)

print(f"Logistic Regression CV Score: {lr_cv_scores.mean():.4f} (+/- {lr_cv_scores.std() * 2:.4f})")
print(f"Random Forest CV Score: {rf_cv_scores.mean():.4f} (+/- {rf_cv_scores.std() * 2:.4f})")