def get_model(x, y, model_config):
if model_config["model"]["type"] == "regression":
regression_model = PolynomialRegressionModel(
model_config["model_name"],
model_config["model"]["polynomial_degree"])
regression_model.train(x, y)
return regression_model
elif model_config["model"]["type"] == "neural_net":
neural_net_model = NeuralNetModel(model_config["model_name"])
neural_net_model.train(x, y, model_config["model"])
return neural_net_model
return None
def get_model(x, y, model_config):
if model_config["model"]["type"] == "regression":
regression_model = PolynomialRegressionModel(
model_config["model_name"],
model_config["model"]["polynomial_degree"])
regression_model.train(x, y)
return regression_model
elif model_config["model"]["type"] == "neural_net":
neural_net_model = NeuralNetModel(model_config["model_name"])
neural_net_model.train(x, y,
model_config["model"]["hidden_layer_sizes"],
model_config["model"]["learning_rate"],
model_config["model"]["max_iter"])
return neural_net_model
return None
def make_predictions(data_raw, data_name, regression_model):
"""
makes predictions for NN and LR models
:param data_raw: input data not preprocessed
:param data_name: name of data
:param regression_model: initialized model for regression task
:return:
"""
# define column names in data. Usually would be a console input
key_columns = '(Opportunity_Name,Product)'
update_col = 'Upload_date'
created_col = 'Created'
opp_name_col = 'Opportunity_Name'
product_name_col = 'Product'
key_columns = key_columns[1:-1].split(',')
target = 'future stage' # target for the first part --> stage Won or Lost
target_second_part = 'time_diff_to_close' # target for the second part --> time till closing
# Models parameters
nn_activation_list = ['identity', 'logistic', 'tanh', 'relu']
nn_solver_list = ['lbfgs', 'sgd', 'adam']
nn_nodes_list = ['(2, 2, 2)', '(100, 100)', '(20, 16, 10, 4)', '(100, 80, 60, 40)']
lr_solver_list = ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga']
c_list = [x * .1 for x in range(1, 11)]
# preprocess data
X, y, index_train, index_test, second_part, y_proba_guessed, updates, data_won = preprocess(
data_raw, target, key_columns, update_col, created_col, opp_name_col, product_name_col)
# train model for periods prediction first, because the same model will be used each time
train_regression_model(regression_model, second_part, index_train, target_second_part)
X_train = X.loc[index_train]
X_test = X.loc[index_test]
y_train = y.loc[index_train]
y_test = y.loc[index_test]
y_guessed = [1 if x >= 0.5 else 0 for x in y_proba_guessed]
print('Guessed probabilities'.upper())
print(classification_report(y_test, y_guessed))
print('Confusion matrix'.upper())
print(confusion_matrix(y_test, y_guessed))
ns_auc = roc_auc_score(y_test, y_proba_guessed)
print('No Skill: ROC AUC=%.3f' % ns_auc)
best_auc, best_mae_weighted, best_mae_unweighted, best_model_auc, best_model_mae_weighted, best_model_mae_unweighted = initialize_metrics()
for nn_activation in nn_activation_list:
for nn_solver in nn_solver_list:
for nn_nodes in nn_nodes_list:
nn = NeuralNetModel(X_train, X_test, y_train, y_test, index_test,
index_train, second_part, target, update_col,
y_proba_guessed,
updates,
data_won, data_name, regression_model)
nn.define_model(solver=nn_solver, activation=nn_activation, n_nodes=nn_nodes)
auc, mae_guessed, mae_weighted, mae_unweighted, model = nn.fit_predict()
if auc > best_auc:
best_auc = auc
best_model_auc = model
if mae_weighted < best_mae_weighted:
best_mae_weighted = mae_weighted
best_model_mae_weighted = model
if mae_unweighted < best_mae_unweighted:
best_mae_unweighted = mae_unweighted
best_model_mae_unweighted = model
print(
'best nn model by AUC: '.upper() + best_model_auc.upper() + " with AUC {:.2f}".format(best_auc))
print(
'best guessed revenue MAE: '.upper() + '{:.2f}'.format(mae_guessed))
print(
'best nn model by predicted revenue MAE: '.upper() + best_model_mae_weighted.upper() +
" with MAE {:.2f}".format(best_mae_weighted))
print(
'best nn model by strictly predicted revenue MAE: '.upper() + best_model_mae_unweighted.upper() +
" with MAE {:.2f}".format(best_mae_unweighted))
best_auc, best_mae_weighted, best_mae_unweighted, best_model_auc, best_model_mae_weighted, best_model_mae_unweighted = initialize_metrics()
for lr_solver in lr_solver_list:
for c in c_list:
lr = LogRegModel(X_train, X_test, y_train, y_test, index_test,
index_train, second_part, target, update_col, y_proba_guessed,
updates, data_won, data_name, regression_model)
lr.define_model(solver=lr_solver, c=c)
auc, mae_guessed, mae_weighted, mae_unweighted, model = lr.fit_predict()
if auc > best_auc:
best_auc = auc
best_model_auc = model
if mae_weighted < best_mae_weighted:
best_mae_weighted = mae_weighted
best_model_mae_weighted = model
if mae_unweighted < best_mae_unweighted:
best_mae_unweighted = mae_unweighted
best_model_mae_unweighted = model
print(
'best lr model by AUC: '.upper() + best_model_auc.upper() + " with AUC {:.2f}".format(best_auc))
print(
'best guessed revenue MAE: '.upper() + '{:.2f}'.format(mae_guessed))
print(
'best lr model by predicted revenue MAE: '.upper() + best_model_mae_weighted.upper() +
" with MAE {:.2f}".format(best_mae_weighted))
print(
'best lr model by strictly predicted revenue MAE: '.upper() + best_model_mae_unweighted.upper() +
" with MAE {:.2f}".format(best_mae_unweighted))