housing_data_inspection

import pandas as pd

df = pd.read_csv("/Users/wyatt/Downloads/Housing.csv")

print(f"Shape: {df.shape}")
columns = df.columns.tolist()
print(f"Columns ({len(columns)}):", columns if len(columns) <= 100 else columns[:100] + ["..."])

df.head()

print(f"Shape: {df.shape}")
columns = df.columns.tolist()
print(f"Columns ({len(columns)}):", columns if len(columns) <= 100 else columns[:100] + ["..."])

df.iloc[:5]

summary = pd.DataFrame({
    "dtype": df.dtypes.astype(str),
    "missing_values": df.isna().sum(),
    "unique_values": df.nunique()
})

display(summary)

from sklearn.model_selection import train_test_split
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
from sklearn.pipeline import Pipeline
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.linear_model import LinearRegression, Ridge
from sklearn.ensemble import RandomForestRegressor, ExtraTreesRegressor, GradientBoostingRegressor
from xgboost import XGBRegressor
import pandas as pd

X = df.drop(columns="price")
y = df["price"]

numeric_cols = X.select_dtypes(include="number").columns.tolist()
categorical_cols = X.select_dtypes(exclude="number").columns.tolist()

preprocessor = ColumnTransformer(
    transformers=[
        ("numeric", "passthrough", numeric_cols),
        ("categorical", OneHotEncoder(handle_unknown="ignore", sparse_output=False), categorical_cols),
    ]
)

models = {
    "XGBoost": XGBRegressor(
        n_estimators=500, learning_rate=0.03, max_depth=3,
        subsample=0.8, colsample_bytree=0.8, random_state=42, n_jobs=-1
    ),
    "Random Forest": RandomForestRegressor(n_estimators=500, random_state=42, n_jobs=-1),
    "Extra Trees": ExtraTreesRegressor(n_estimators=500, random_state=42, n_jobs=-1),
    "Gradient Boosting": GradientBoostingRegressor(random_state=42),
    "Ridge Regression": Ridge(alpha=10),
    "Linear Regression": LinearRegression(),
}

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.20, random_state=42
)

results = []
fitted_models = {}

for name, model in models.items():
    pipeline = Pipeline([
        ("preprocess", preprocessor),
        ("model", model),
    ])
    pipeline.fit(X_train, y_train)
    predictions = pipeline.predict(X_test)
    fitted_models[name] = pipeline

    results.append({
        "model": name,
        "MAE (USD)": round(mean_absolute_error(y_test, predictions), 2),
        "RMSE (USD)": round(mean_squared_error(y_test, predictions) ** 0.5, 2),
        "R²": round(r2_score(y_test, predictions), 4),
    })

results = pd.DataFrame(results).sort_values("RMSE (USD)").reset_index(drop=True)
results