},
cv=5)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end - start)
helpers.log_fit_time('CENSUS_KNN', end - start)
# Plot the learning curve vs train size after finding the best model
helpers.plot_learning_curve_vs_train_size(
best_model,
df,
feature_cols,
'income_num',
output_location=
'census_output/knn_%s_best_model_num_samples_learning_curve.png' %
weighting,
)
# Predict income with the trained best model
y_pred = best_model.predict(x_test)
cv=5
)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end-start)
helpers.log_fit_time('CENSUS_SVM', end-start)
# Predict income with the trained best model
y_pred = best_model.predict(x_test)
helpers.produce_model_performance_summary(
best_model,
x_test,
y_test,
y_pred,
output_location='census_output/svm_summary.txt',
cv=kfold,
scoring='accuracy',
grid_search=grid_search
)
'n_estimators':
[10, 20, 30, 40, 50, 60, 70, 80, 90, 100],
},
cv=3)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end - start)
helpers.log_fit_time('WINE_BOOST', end - start)
# Predict quality with the trained best model
y_pred = best_model.predict(x_test)
helpers.produce_model_performance_summary(
best_model,
x_test,
y_test,
y_pred,
output_location='wine_output/boost_summary.txt',
cv=3,
scoring='accuracy')
cv=5
)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end-start)
helpers.log_fit_time('CENSUS_BOOST', end-start)
# Predict income with the trained best model
y_pred = best_model.predict(x_test)
helpers.produce_model_performance_summary(
best_model,
x_test,
y_test,
y_pred,
grid_search=grid_search,
output_location='census_output/boost_summary.txt',
cv=kfold,
scoring='accuracy'
)
param_grid={
'max_iter': range(50, 650, 50),
},
cv=3)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end - start)
helpers.log_fit_time('WINE_SVM', end - start)
# Predict quality with the trained best model
y_pred = best_model.predict(x_test)
helpers.produce_model_performance_summary(
best_model,
x_test,
y_test,
y_pred,
output_location='wine_output/SVM_summary.txt',
cv=3,
scoring='accuracy')
'n_neighbors':
[5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100],
},
cv=3)
grid_search.fit(x_train, y_train)
print(grid_search.best_score_)
print(grid_search.best_params_)
# train the best model
best_model = grid_search.best_estimator_
# Time fitting best model
start = timeit.default_timer()
best_model.fit(x_train, y_train)
end = timeit.default_timer()
print('Time to fit:', end - start)
helpers.log_fit_time('WINE_KNN', end - start)
# Predict quality with the trained best model
y_pred = best_model.predict(x_test)
helpers.produce_model_performance_summary(
best_model,
x_test,
y_test,
y_pred,
output_location='wine_output/knn_%s_summary.txt' % weighting,
cv=3,
scoring='accuracy')