WillKoehrsen

# Replace all occurrences of Not Available with numpy not a number
data = data.replace({'Not Available': np.nan})

# Iterate through the columns
for col in list(data.columns):
    # Select columns that should be numeric
    if ('ft²' in col or 'kBtu' in col or 'Metric Tons CO2e' in col or 'kWh' in 
        col or 'therms' in col or 'gal' in col or 'Score' in col):
        # Convert the data type to float
        data[col] = data[col].astype(float)

WillKoehrsen

# Create a list of buildings with more than 100 measurements
types = data.dropna(subset=['score'])
types = types['Largest Property Use Type'].value_counts()
types = list(types[types.values > 100].index)

# Plot of distribution of scores for building categories
figsize(12, 10)

# Plot each building
for b_type in types:

WillKoehrsen

# Copy the original data
features = data.copy()

# Select the numeric columns
numeric_subset = data.select_dtypes('number')

# Create columns with log of numeric columns
for col in numeric_subset.columns:
    # Skip the Energy Star Score column
    if col == 'score':

WillKoehrsen

# Function to calculate mean absolute error
def mae(y_true, y_pred):
    return np.mean(abs(y_true - y_pred))

baseline_guess = np.median(y)

print('The baseline guess is a score of %0.2f' % baseline_guess)
print("Baseline Performance on the test set: MAE = %0.4f" % mae(y_test, baseline_guess))

WillKoehrsen

# Extract the columns to  plot
plot_data = features[['score', 'Site EUI (kBtu/ft²)', 
                      'Weather Normalized Source EUI (kBtu/ft²)', 
                      'log_Total GHG Emissions (Metric Tons CO2e)']]

# Replace the inf with nan
plot_data = plot_data.replace({np.inf: np.nan, -np.inf: np.nan})

# Rename columns 
plot_data = plot_data.rename(columns = {'Site EUI (kBtu/ft²)': 'Site EUI', 

WillKoehrsen

from sklearn.ensemble import GradientBoostingRegressor

# Create the model
gradient_boosted = GradientBoostingRegressor()

# Fit the model on the training data
gradient_boosted.fit(X, y)

# Make predictions on the test data
predictions = gradient_boosted.predict(X_test)

WillKoehrsen

# Loss function to be optimized
loss = ['ls', 'lad', 'huber']

# Number of trees used in the boosting process
n_estimators = [100, 500, 900, 1100, 1500]

# Maximum depth of each tree
max_depth = [2, 3, 5, 10, 15]

# Minimum number of samples per leaf

WillKoehrsen

from sklearn.ensemble import GradientBoostingRegressor

# Create the model with the best hyperparamters
model_reduced = GradientBoostingRegressor(loss='lad', max_depth=5, max_features=None,
                                  min_samples_leaf=6, min_samples_split=6, 
                                  n_estimators=800, random_state=42)

# Fit and test on the reduced set of features
model_reduced.fit(X_reduced, y)
model_reduced_pred = model_reduced.predict(X_test_reduced)

WillKoehrsen

import pandas as pd

# model is the trained model
importances = model.feature_importances_

# train_features is the dataframe of training features
feature_list = list(train_features.columns)

# Extract the feature importances into a dataframe
feature_results = pd.DataFrame({'feature': feature_list, 

WillKoehrsen

from sklearn import tree

# Extract a single tree (number 105)
single_tree = model.estimators_[105][0]

# Save the tree to a dot file
tree.export_graphviz(single_tree, out_file = 'images/tree.dot', 
                     feature_names = feature_list)