def predict(data):
config = read_params(params_path)
model_dir_path = os.path.join(
"prediction_service", "model", "model.joblib")
model = joblib.load(model_dir_path)
prediction = model.predict(data)
return prediction[0]
def log_production_model(config_path):
config = read_params(config_path)
mlflow_config = config["mlflow_config"]
model_name = mlflow_config["registered_model_name"]
remote_server_uri = mlflow_config["remote_server_uri"]
mlflow.set_registry_uri(remote_server_uri)
runs = mlflow.search_runs(experiment_ids=1)
lowest = runs["metrics.mae"].sort_values(ascending=True)[0]
lowest_run_id = runs[runs["metrics.mae"] == lowest]["run_id"][0]
client = MlflowClient()
for mv in client.search_model_versions(f"name='{model_name}'"):
mv = dict(mv)
if mv["run_id"] == lowest_run_id:
current_version = mv["version"]
logged_model = mv["source"]
pprint(mv, indent=4)
client.transition_model_version_stage(name=model_name,
version=current_version,
stage="Production")
else:
current_version = mv["version"]
client.transition_model_version_stage(name=model_name,
version=current_version,
stage="Staging")
loaded_model = mlflow.pyfunc.load_model(logged_model)
model_path = config["webapp_model_dir"]
joblib.dump(loaded_model, model_path)
def train_and_evaluate(config_path):
config=get_data.read_params(config_path)
test_data_path = config["split_data"]["test_path"]
train_data_path = config["split_data"]["train_path"]
random_state = config["base"]["random_state"]
model_dir = config["model_dir"]
alpha = config["estimators"]["ElasticNet"]["params"]["alpha"]
l1_ratio = config["estimators"]["ElasticNet"]["params"]["l1_ratio"]
target = [config["base"]["target_col"]]
train=pd.read_csv(train_data_path,sep=",")
test=pd.read_csv(test_data_path,sep=",")
train_y=train[target]
test_y=test[target]
train_x= train.drop(target,axis=1)
test_x=test.drop(target,axis=1)
lr=ElasticNet(
alpha=alpha,
l1_ratio=l1_ratio,
random_state=random_state
)
lr.fit(train_x,train_y)
predicted_qualities=lr.predict(test_x)
(rmse,mae,r2)=eval_metrics(test_y,predicted_qualities)
print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
print(" RMSE: %s" % rmse)
print(" MAE: %s" % mae)
print(" R2: %s" % r2)
scores_file= config['reports']['scores']
params_file= config['reports']['params']
with open(scores_file,'w') as f:
scores = {
"rmse":rmse,
"mae":mae,
"r2":r2
}
json.dump(scores,f,indent=4)
with open(params_file,'w') as f:
params = {
"alpha":alpha,
"l1_ratio":l1_ratio
}
json.dump(params, f, indent=4)
os.makedirs(model_dir, exist_ok=True)
model_path = os.path.join(model_dir, "model.joblib")
joblib.dump(lr, model_path)
def split_and_saved_data(config_path):
config = get_data.read_params(config_path)
test_data_path = config['split_data']['test_path']
train_data_path = config['split_data']['train_path']
raw_data_path = config['load_data']['raw_dataset_csv']
split_ratio = config['split_data']['test_size']
random_state = config['base']['random_state']
df = pd.read_csv(raw_data_path, sep=",")
train, test = train_test_split(df,
test_size=split_ratio,
random_state=random_state)
train.to_csv(train_data_path, sep=",", index=False, encoding='utf-8')
test.to_csv(test_data_path, sep=',', index=False, encoding='utf-8')
def split_and_saved_data(config_path):
config = get_data.read_params(config_path)
test_data_path= config["split_data"]["test_path"]
train_data_path= config["split_data"]["train_path"]
raw_data_path= config["load_data"]["raw_dataset_csv"]
split_ratio= config["split_data"]["test_size"]
random_state= config["base"]["random_state"]
df=pd.read_csv(raw_data_path,sep=',',)
train,test=train_test_split(
df,
test_size=split_ratio,
random_state=random_state
)
train.to_csv(train_data_path,sep=',', index=False, encoding="utf-8")
test.to_csv(test_data_path,sep=',', index=False, encoding="utf-8")
def load_and_save(config_path):
config = get_data.read_params(config_path)
df = get_data.get_data(config_path)
new_cols = [col.replace(" ", "_") for col in df.columns]
raw_data_path = config['load_data']['raw_dataset_csv']
df.to_csv(raw_data_path, sep=',', index=False, header=new_cols)