Kaggle - Exercise 5 - RandomForestRegressor

# ************************************************************************
# ************************************************************************
# 1. Decision Tree Regressor
# ************************************************************************
# ************************************************************************

# Code you have previously used to load data
import pandas as pd
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor


# Path of the file to read
iowa_file_path = '../input/home-data-for-ml-course/train.csv'
home_data = pd.read_csv(iowa_file_path)

y = home_data.SalePrice
features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']
X = home_data[features]

# Split into validation and training data
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=1)

# Specify and Fit the Model
iowa_model = DecisionTreeRegressor(random_state=1)
iowa_model.fit(train_X, train_y)

# Make validation predictions and calculate mean absolute error
val_predictions = iowa_model.predict(val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE when not specifying max_leaf_nodes: {:,.0f}".format(val_mae))

# Using best value for max_leaf_nodes
iowa_model = DecisionTreeRegressor(max_leaf_nodes=100, random_state=1)
iowa_model.fit(train_X, train_y)
val_predictions = iowa_model.predict(val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE for best value of max_leaf_nodes: {:,.0f}".format(val_mae))



# ************************************************************************
# ************************************************************************
# 2, Random Forest Regressor
# ************************************************************************
# ************************************************************************

from sklearn.ensemble import RandomForestRegressor

# Define the model. Set random_state to 1
rf_model = RandomForestRegressor(random_state=1)
rf_model.fit(train_X, train_y)
val_preds = rf_model.predict(val_X)
rf_val_mae = mean_absolute_error(val_y, val_preds)

print("Validation MAE for Random Forest: {:,.0f}".format(rf_val_mae))