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)

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 lime 

# Create a lime explainer object
explainer = lime.lime_tabular.LimeTabularExplainer(training_data = X, 
                                                   mode = 'regression',
                                                   training_labels = y,
                                                   feature_names = feature_list)


# Explanation for wrong prediction

WillKoehrsen

from sklearn.ensemble import GradientBoostingRegressor

# Create the model with the best hyperparamters
model = 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 features
model.fit(X, y)
model_pred = model.predict(X_test)

WillKoehrsen

from tpot import TPOTRegressor

# Create a tpot object with a specified parameters
tpot = TPOTRegressor(max_time_mins = 240, n_jobs = -1,
                     scoring = 'neg_mean_absolute_error', verbosity = 2,)

WillKoehrsen

# Import the optimizer class
from tpot import TPOTRegressor

# Create a tpot optimizer with parameters
tpot = TPOTRegressor(scoring = 'neg_mean_absolute_error', 
                     max_time_mins = 480, 
                     n_jobs = -1,
                     verbosity = 2,
                     cv = 5)

WillKoehrsen

# Preprocessing steps
imputer = Imputer(strategy="median")
imputer.fit(training_features)
training_features = imputer.transform(training_features)
testing_features = imputer.transform(testing_features)

# Final pipeline from TPOT
exported_pipeline = make_pipeline(
    StackingEstimator(estimator=LassoLarsCV(normalize=True)),
    GradientBoostingRegressor(alpha=0.95, learning_rate=0.1, loss="lad", 

WillKoehrsen

import pandas as pd

# Group loans by client id and calculate mean, max, min of loans
stats = loans.groupby('client_id')['loan_amount'].agg(['mean', 'max', 'min'])
stats.columns = ['mean_loan_amount', 'max_loan_amount', 'min_loan_amount']

# Merge with the clients dataframe
stats = clients.merge(stats, left_on = 'client_id', right_index=True, how = 'left')

stats.head(10)

WillKoehrsen

# Create an entity from the loans dataframe
# This dataframe already has an index and a time index
es = es.entity_from_dataframe(entity_id = 'loans', dataframe = loans, 
                              variable_types = {'repaid': ft.variable_types.Categorical},
                              index = 'loan_id', 
                              time_index = 'loan_start')