The analysis notebook

In [66]
import pandas as pd

In [67]
from sklearn.datasets import fetch_california_housing
import pandas as pd

# Fetch dataset
housing = fetch_california_housing(as_frame=True)

# Convert to DataFrame
df = housing.frame

# Save locally
df.to_csv("../data/california_housing.csv", index=False)

print(df.head())

MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude  \
0  8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88   
1  8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   
2  7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   
3  5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   
4  3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   

   Longitude  MedHouseVal  
0    -122.23        4.526  
1    -122.22        3.585  
2    -122.24        3.521  
3    -122.25        3.413  
4    -122.25        3.422

In [68]
df.head()

In [69]
df.shape

(20640, 9)

In [70]
df.columns

Index(['MedInc', 'HouseAge', 'AveRooms', 'AveBedrms', 'Population', 'AveOccup',
       'Latitude', 'Longitude', 'MedHouseVal'],
      dtype='str')

In [71]
df.info()

<class 'pandas.DataFrame'>
RangeIndex: 20640 entries, 0 to 20639
Data columns (total 9 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   MedInc       20640 non-null  float64
 1   HouseAge     20640 non-null  float64
 2   AveRooms     20640 non-null  float64
 3   AveBedrms    20640 non-null  float64
 4   Population   20640 non-null  float64
 5   AveOccup     20640 non-null  float64
 6   Latitude     20640 non-null  float64
 7   Longitude    20640 non-null  float64
 8   MedHouseVal  20640 non-null  float64
dtypes: float64(9)
memory usage: 1.4 MB

In [72]
df.describe()

In [73]
df.isnull().sum()

MedInc         0
HouseAge       0
AveRooms       0
AveBedrms      0
Population     0
AveOccup       0
Latitude       0
Longitude      0
MedHouseVal    0
dtype: int64

In [74]
df.dtypes

MedInc         float64
HouseAge       float64
AveRooms       float64
AveBedrms      float64
Population     float64
AveOccup       float64
Latitude       float64
Longitude      float64
MedHouseVal    float64
dtype: object

In [96]
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, mean_squared_error, root_mean_squared_error, r2_score
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.ensemble import HistGradientBoostingRegressor
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.ensemble import RandomForestRegressor

In [76]
X = df.drop("MedHouseVal", axis=1)
y = df["MedHouseVal"]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

In [77]
lr = LinearRegression()
lr.fit(X_train, y_train)

In [98]
y_pred = lr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.5332001304956557
Mean Squared Error: 0.5558915986952435
Root Mean Squared Error: 0.7455813830127758
R-squared: 0.5757877060324514

In [79]
rdg = Ridge(alpha=1.0)
rdg.fit(X_train, y_train)

In [80]
y_pred = rdg.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Squared Error: 0.5558034669932209
R-squared: 0.5758549611440127

In [81]
lss = Lasso(alpha=0.1)
lss.fit(X_train, y_train)

In [99]
y_pred = lss.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.5816074623949866
Mean Squared Error: 0.6135115198058131
Root Mean Squared Error: 0.7832697618354822
R-squared: 0.5318167610318159

In [83]
els = ElasticNet(alpha=0.1, l1_ratio=0.5)
els.fit(X_train, y_train)

In [100]
y_pred = els.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.5564907096828818
Mean Squared Error: 0.573099419802821
Root Mean Squared Error: 0.7570333016471739
R-squared: 0.5626560643897962

In [85]
dtr = DecisionTreeRegressor(random_state=42)
dtr.fit(X_train, y_train)

In [101]
y_pred = dtr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.4541711942829458
Mean Squared Error: 0.494255717630063
Root Mean Squared Error: 0.7030332265476953
R-squared: 0.622823312540521

In [87]
rfr = RandomForestRegressor(n_estimators=100, random_state=42)
rfr.fit(X_train, y_train)

In [102]
y_pred = rfr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.32773108008720936
Mean Squared Error: 0.25602182673365537
Root Mean Squared Error: 0.5059859946022769
R-squared: 0.8046244867176197

In [89]
gbr = GradientBoostingRegressor(n_estimators=100, random_state=42)
gbr.fit(X_train, y_train)

In [103]
y_pred = gbr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.37164256904255966
Mean Squared Error: 0.2939973248643864
Root Mean Squared Error: 0.5422152016168362
R-squared: 0.7756446042829697

In [91]
hgbr = HistGradientBoostingRegressor(max_iter=100, random_state=42)
hgbr.fit(X_train, y_train)

In [104]
y_pred = hgbr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Absolute Error: 0.3110552128758936
Mean Squared Error: 0.2165964110447516
Root Mean Squared Error: 0.4653991953632404
R-squared: 0.8347108310143663

In [93]
etr = ExtraTreesRegressor(n_estimators=100, random_state=42)
etr.fit(X_train, y_train)

In [94]
y_pred = etr.predict(X_test)

mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = root_mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)


print(f"Mean Absolute Error: {mae}")
print(f"Mean Squared Error: {mse}")
print(f"Root Mean Squared Error: {rmse}")
print(f"R-squared: {r2}")

Mean Squared Error: 0.25390365487798505
R-squared: 0.8062409071564614

In [107]
# Create a comparison table for all trained models
model_metrics = []

models = {
    "LinearRegression": lr,
    "Ridge": rdg,
    "Lasso": lss,
    "ElasticNet": els,
    "DecisionTreeRegressor": dtr,
    "RandomForestRegressor": rfr,
    "GradientBoostingRegressor": gbr,
    "HistGradientBoostingRegressor": hgbr,
    "ExtraTreesRegressor": etr
}

for model_name, model in models.items():
    y_pred = model.predict(X_test)
    mae = mean_absolute_error(y_test, y_pred)
    mse = mean_squared_error(y_test, y_pred)
    rmse = root_mean_squared_error(y_test, y_pred)
    r2 = r2_score(y_test, y_pred)

    model_metrics.append({
        "Model": model_name,
        "MAE": mae,
        "MSE": mse,
        "RMSE": rmse,
        "R2": r2
    })

comparison_table = pd.DataFrame(model_metrics).sort_values(by="R2", ascending=False).reset_index(drop=True)

for col in ["MAE", "MSE", "RMSE", "R2"]:
    comparison_table[col] = comparison_table[col].round(6)

# Optional: save the comparison table to CSV
comparison_table.to_csv("../data/model_comparison.csv", index=False)

comparison_table

In
import joblib

best_model = hgbr
joblib.dump(best_model, "../data/best_model.joblib")

print("Best model saved to ../data/best_model.joblib")