# Compute the correlation coefficient
correlation = data["ad_spend"].corr(data["weekly_sales"])
print(f"Correlation coefficient: {correlation:.3f}")

# Or we can see the full correlation matrix
print("\nFull correlation matrix:")
data.corr()

from sklearn.linear_model import LinearRegression

# Prepare the data
X = data[["ad_spend"]]  # Feature matrix (note the double brackets)
y = data["weekly_sales"]  # Target variable

# Fit the model
model = LinearRegression()
model.fit(X, y)

# Extract the results
intercept = model.intercept_
slope = model.coef_[0]

print(f"Intercept (β₀): ${intercept:.0f}")
print(f"Slope (β₁): ${slope:.2f}")

# Make predictions for different scenarios
scenarios = pd.DataFrame({
    'ad_spend': [1500, 2500, 3000]
})

predictions = model.predict(scenarios)

print("Business Predictions:")
for spend, pred in zip(scenarios['ad_spend'], predictions):
    print(f"Spend ${spend:,} → Predicted Sales: ${pred:,.0f}")
    
# Manual calculation to verify
print(f"\nManual check for $1,500:")
manual_pred = 1.68 * 1500 + 3552
print(f"1.68 × 1500 + 3552 = ${manual_pred:.0f}")

from sklearn.metrics import r2_score, root_mean_squared_error

# Predictions from the model we fit on all 20 weeks
fitted_sales = model.predict(X)

r2 = r2_score(y, fitted_sales)
rmse = root_mean_squared_error(y, fitted_sales)

print(f"R²:   {r2:.2f}")
print(f"RMSE: ${rmse:,.0f}")

from sklearn.model_selection import train_test_split

# Hold out 30% of the weeks as a test set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=11
)

print(f"Training weeks: {len(X_train)}")
print(f"Test weeks:     {len(X_test)}")

# Learn ONLY from the training weeks
model = LinearRegression()
model.fit(X_train, y_train)

# Score the model on both sets
train_preds = model.predict(X_train)
test_preds = model.predict(X_test)

print(f"Training → R²: {r2_score(y_train, train_preds):.2f} | RMSE: ${root_mean_squared_error(y_train, train_preds):,.0f}")
print(f"Test     → R²: {r2_score(y_test, test_preds):.2f} | RMSE: ${root_mean_squared_error(y_test, test_preds):,.0f}")

for seed in [1, 3, 5, 11, 21]:
    X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.3, random_state=seed)
    seed_model = LinearRegression().fit(X_tr, y_tr)
    test_rmse = root_mean_squared_error(y_te, seed_model.predict(X_te))
    print(f"random_state={seed:>2} → Test RMSE: ${test_rmse:,.0f}")

# Step 1: Import a dataset
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score, root_mean_squared_error

# Load the classic Advertising dataset
advertising = pd.read_csv("../data/Advertising.csv")
print("Dataset shape:", advertising.shape)
advertising.head()

# Step 2: Split data into features (X) and target (y), then train/test
X = advertising[['TV', 'radio', 'newspaper']]  # Multiple predictors
y = advertising['sales']  # Target variable

# Split into train/test sets
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

print(f"Training set: {len(X_train)} samples")
print(f"Test set: {len(X_test)} samples")

# Step 3: Train our regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Look at our model coefficients
print("Model coefficients:")
for feature, coef in zip(X.columns, model.coef_):
    print(f"  {feature}: {coef:.3f}")
print(f"Intercept: {model.intercept_:.3f}")

# Step 4: Evaluate model performance
train_predictions = model.predict(X_train)
test_predictions = model.predict(X_test)

# Calculate metrics
train_r2 = r2_score(y_train, train_predictions)
test_r2 = r2_score(y_test, test_predictions)
train_rmse = root_mean_squared_error(y_train, train_predictions)
test_rmse = root_mean_squared_error(y_test, test_predictions)

print("Performance Summary:")
print(f"Training R²: {train_r2:.3f} | Training RMSE: {train_rmse:.2f}")
print(f"Test R²: {test_r2:.3f} | Test RMSE: {test_rmse:.2f}")