Last active
March 15, 2022 14:29
-
-
Save jeanmidevacc/778e64e30c6209e9086854c622d3e8d6 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from time import time | |
from hyperopt import fmin, tpe, hp, anneal, Trials | |
import mlflow | |
from sklearn.metrics import mean_squared_error | |
import surprise | |
def evaluate_model(model, dfp_ratings_test): | |
dfp_evaluation = dfp_ratings_test.copy() | |
dfp_evaluation["rating_predicted"] = dfp_evaluation.apply(lambda row: compute_ranking(model, str(row["userid"]), str(row["contentid"])), axis=1) | |
return mean_squared_error(dfp_evaluation["rating"].tolist(), dfp_evaluation["rating_predicted"].tolist(), squared=False) | |
def mlflow_logging(rmse, training_time, evaluation_time, model_name, runid, type_training, params, log_model=log_model): | |
with mlflow.start_run(nested = True): | |
metrics = { | |
"rmse" : rmse, | |
"training_time": training_time, | |
"evaluation_time": evaluation_time | |
} | |
params["model"] = model_name | |
mlflow.set_tags({"model" : model_name, "runid" : runid, "type_training": type_training}) | |
mlflow.log_params(params) | |
mlflow.log_metrics(metrics) | |
def train_and_evaluate(params, model_name=model_name, trainset=trainset, data_train=data_train, dfp_ratings_test=dfp_ratings_test): | |
rmse = 100 | |
try: | |
tic_training = time() | |
params = { | |
"n_factors" : int(params["n_factors"]), | |
"n_epochs" : int(params["n_epochs"]), | |
"biased" : params["biased"], | |
"reg_pu" : params["reg_pu"], | |
'reg_qi' : params['reg_qi'] | |
} | |
model = surprise.prediction_algorithms.matrix_factorization.NMF(**params) | |
model = model.fit(trainset_surprise) | |
training_time = time() - tic_training | |
tic_evaluation = time() | |
rmse = evaluate_model(model, dfp_ratings_test) | |
evaluation_time = time() - tic_evaluation | |
mlflow_logging(rmse, training_time, evaluation_time, model_name, runid, type_training, params) | |
except Exception as e: | |
print(e) | |
return rmse | |
max_evals = 100 | |
model_name = "NMF" | |
space = { | |
"n_factors" : hp.randint('k', 1, 100), | |
"n_epochs" : hp.randint('n_epochs', 1, 100), | |
"biased" : hp.choice('biased', [True, False]), | |
"reg_pu" : hp.uniform('reg_u', 0.001, 100), | |
"reg_qi" : hp.uniform('reg_i', 0.001, 100) | |
} | |
trials = Trials() | |
best=fmin(fn=train_and_evaluate, # function to optimize | |
space=space, | |
algo=tpe.suggest, # optimization algorithm, hyperotp will select its parameters automatically | |
max_evals=max_evals, # maximum number of iterations | |
trials=trials) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment