def __init__(self, pathToData):
self.dataFilePath = pathToData
self.algoname = 'Boosting'
self.datasetName = 'Abalone'
self.baseEstimater = dtr()
self.classifier = abr(base_estimator=self.baseEstimater)
self.cv = 5
def get_regression_model(algo, poly_Order=2, **kwargs):
# for key in kwargs: print(key) sys.exit()
print_mod_info = False
### Regression models
### https://stackoverflow.com/questions/12860841/python-import-in-if
if algo == 'XGR':
mod = xgr(**kwargs)
elif algo == 'RFR':
mod = rfr(**kwargs)
elif algo == 'ABR':
mod = abr(**kwargs)
elif algo == 'P1R':
mod = LinearRegression(**kwargs)
elif algo == 'P2R':
mod = make_pipeline(PolynomialFeatures(poly_Order), Ridge(**kwargs))
elif algo == 'ANN':
mod = MLPRegressor(**kwargs)
elif algo == 'ELN':
mod = ElasticNet(**kwargs) # add parameters later
elif algo == 'E2R':
mod = make_pipeline(PolynomialFeatures(poly_Order),
ElasticNet(**kwargs))
elif algo == 'PLS':
mod = PLSRegression(**kwargs)
else:
print('Algorithm has not yet been added to the menu.')
sys.exit()
return mod
def regression(self, metric="root_mean_squared_error", folds=10, alphas=[], graph=False):
size = 1.3 * self.report_width // 10
models = {}
models["Linear regressor"] = lr()
models["Lasso regressor"] = lassor()
models["Lasso CV regressor"] = lassocvr()
models["Ridge regressor"] = rr(alpha=0, normalize=True)
models["Ridge CV regressor"] = rcvr(alphas = alphas)
models["K nearest neighbors regressor K2u"] = knnr(n_neighbors=2, weights='uniform')
models["K nearest neighbors regressor K2d"] = knnr(n_neighbors=2, weights='distance')
models["K nearest neighbors regressor K5"] = knnr(n_neighbors=5)
models["K nearest neighbors regressor K10"] = knnr(n_neighbors=10)
models["SGD regressor"] = sgdr(max_iter=10000, warm_start=True)
models["Decision tree regressor"] = dtr()
models["Decision tree regressor D3"] = dtr(max_depth=3)
models["Random forest regressor"] = rfr()
models["Ada boost regressor"] = abr()
models["Gradient boost regressor"] = gbr()
models["Support vector regressor"] = svr()
self.models = models
print('\n')
print(self.report_width * '*', '\n*')
print('* REGRESSION RESULTS - BEFORE PARAMETERS BOOSTING \n*')
#kf = StratifiedKFold(n_splits=folds, shuffle=True)
kf = KFold(n_splits=folds)
results = []
names = []
for model_name in models:
cv_scores = -1 * cross_val_score(models[model_name], self.Xt_train, self.yt_train.values.ravel(), cv=kf, scoring=metric)
results.append(cv_scores)
names.append(model_name)
print(self.report_width * '*', '')
report = pd.DataFrame({'Regressor': names, 'Score': results})
report['Score (avg)'] = report.Score.apply(lambda x: x.mean())
report['Score (std)'] = report.Score.apply(lambda x: x.std())
report['Score (VC)'] = 100 * report['Score (std)'] / report['Score (avg)']
report.sort_values(by='Score (avg)', inplace=True)
report.drop('Score', axis=1, inplace=True)
display(report)
print('\n')
if graph:
fig, ax = plt.subplots(figsize=(size, 0.5 * size))
plt.title('Regressor Comparison')
#ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.xticks(rotation=45)
plt.subplots_adjust(hspace=0.0)
plt.show()
return None
def get_regression_model(algo, settings, print_mod_info=False):
### Regression models
### https://stackoverflow.com/questions/12860841/python-import-in-if
if algo == 'XGR':
mod = xgr(n_estimators=settings[0], max_depth=settings[1])
if print_mod_info: print('XGBoost:', mod)
elif algo == 'RFR':
mod = rfr(n_estimators=settings[0])
if print_mod_info: print('Random Forest:', mod)
elif algo == 'ABR':
mod = abr(n_estimators=settings[0])
if print_mod_info: print('AdaBoost:', mod)
elif algo == 'P1R':
mod = LinearRegression()
if print_mod_info: print('Linear:', mod)
elif algo == 'P2R':
mod = make_pipeline(PolynomialFeatures(settings[0]), Ridge())
if print_mod_info: print('Poly 2:', mod)
elif algo == 'ANN':
mod = MLPRegressor(
solver='lbfgs',
hidden_layer_sizes=(settings[0], settings[1]), # (137,73),
tol=settings[2])
if print_mod_info: print('Neural Net Regression:', mod)
elif algo == 'ELN':
mod = ElasticNet(alpha=settings[0],
l1_ratio=settings[1]) # add parameters later
if print_mod_info: print('Elastic Net Regression:', mod)
elif algo == 'E2R':
mod = make_pipeline(
PolynomialFeatures(settings[0]),
ElasticNet(alpha=settings[1], l1_ratio=settings[2]))
if print_mod_info: print('Poly 2:', mod)
elif algo == 'PLS':
mod = PLSRegression(n_components=settings[0])
if print_mod_info: print('Partial Least Squares Regression:', mod)
else:
print('Algorithm not setup yet.')
sys.exit()
return mod
def regression(self, metric, folds=10, alphas=[], printt=True, graph=False):
size = self.graph_width
# significant model setup differences should be list as different models
models = {}
models["Linear regressor"] = lr()
models["Lasso regressor"] = lassor()
models["Lasso CV regressor"] = lassocvr()
models["Ridge regressor"] = rr(alpha=0, normalize=True)
models["Ridge CV regressor"] = rcvr(alphas = alphas)
models["Elastic net regressor"] = enr()
models["K nearest neighbors regressor K2u"] = knnr(n_neighbors=2, weights='uniform')
models["K nearest neighbors regressor K2d"] = knnr(n_neighbors=2, weights='distance')
models["K nearest neighbors regressor K5"] = knnr(n_neighbors=5)
models["K nearest neighbors regressor K10"] = knnr(n_neighbors=10)
models["SGD regressor"] = sgdr(max_iter=10000, warm_start=True)
models["Decision tree regressor"] = dtr()
models["Decision tree regressor D3"] = dtr(max_depth=3)
models["Random forest regressor"] = rfr()
models["Ada boost regressor"] = abr()
models["Gradient boost regressor"] = gbr()
models["Support vector regressor RBF"] = svr()
models["Support vector regressor Linear"] = svr('linear')
models["Support vector regressor Poly"] = svr(kernel='poly')
self.models = models
kf = KFold(n_splits=folds, shuffle=True)
results = []
names = []
et = []
for model_name in models:
start = time.time()
cv_scores = -1 * cross_val_score(models[model_name], self.Xt_train, self.yt_train, cv=kf, scoring=metric)
results.append(cv_scores)
names.append(model_name)
et.append((time.time() - start))
report = pd.DataFrame({'Model': names, 'Score': results, 'Elapsed Time': et})
report['Score (avg)'] = report.Score.apply(lambda x: np.sqrt(x).mean())
report['Score (std)'] = report.Score.apply(lambda x: np.sqrt(x).std())
report['Score (VC)'] = 100 * report['Score (std)'] / report['Score (avg)']
report.sort_values(by='Score (avg)', inplace=True)
report.drop('Score', axis=1, inplace=True)
report.reset_index(inplace=True, drop=True)
self.report_performance = report
if printt:
print('\n')
print(self.report_width * '*', '\n*')
print('* REGRESSION RESULTS - BEFORE PARAMETERS BOOSTING \n*')
print(self.report_width * '*', '')
print(report)
print('\n')
if graph:
fig, ax = plt.subplots(figsize=(size, 0.5 * size))
plt.title('Regressor Comparison')
#ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.xticks(rotation=45)
plt.subplots_adjust(hspace=0.0, bottom=0.25)
self.graphs_model.append(fig)
plt.show()
return None