def train_model(config_path: Text, base_config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
base_config = yaml.load(open(base_config_path), Loader=yaml.FullLoader)
estimator_name = config['estimator_name']
param_grid = config['estimators'][estimator_name]['param_grid']
cv = config['cv']
class_weight = config['class_weight']
target_column = base_config['featurize']['target_column']
train_df = get_dataset(base_config['split_train_test']['train_csv'],
base_config['featurize']['dataset_sep'])
valid_df = get_dataset(base_config['split_train_test']['valid_csv'],
base_config['featurize']['dataset_sep'])
sampler = base_config['split_train_test']['sampler']
sampler_rate = base_config['split_train_test']['sampler_rate']
'''
Your code is here !!!
'''
print(model.best_score_)
model_name = base_config['base']['model']['model_name']
models_folder = base_config['base']['model']['models_folder']
joblib.dump(model, os.path.join(models_folder, model_name))
def train_model(config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
estimator_name = config['train']['estimator_name']
param_grid = config['train']['estimators'][estimator_name]['param_grid']
cv = config['train']['cv']
target_column = config['featurize']['target_column']
train_df = get_dataset(config['split_train_test']['train_csv'])
model = train(
df=train_df,
target_column=target_column,
estimator_name=estimator_name,
param_grid=param_grid,
cv=cv
)
print(model.best_score_)
model_name = config['base']['model']['model_name']
models_folder = config['base']['model']['models_folder']
joblib.dump(
model,
os.path.join(models_folder, model_name)
)
def evaluate_model(config_path: Text, base_config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
base_config = yaml.load(open(base_config_path), Loader=yaml.FullLoader)
target_column = base_config['featurize']['target_column']
test_df = get_dataset(base_config['split_train_test']['test_csv'],
base_config['featurize']['dataset_sep'])
model_name = base_config['base']['model']['model_name']
models_folder = base_config['base']['model']['models_folder']
model = joblib.load(os.path.join(models_folder, model_name))
'''
Your code is here !!!
'''
test_report = {
'f1_score': f1,
'precision': precision,
'recall': recall,
'accuracy': accuracy
}
#print(test_report)
filepath = os.path.join(
base_config['base']['experiments']['experiments_folder'],
config['metrics_file'])
json.dump(obj=test_report, fp=open(filepath, 'w'), indent=2)
'''
Your code is here !!!
'''
experiment.log_confusion_matrix(matrix=cm.tolist())
experiment.log_metrics(test_report)
experiment.log_dataset_hash(test_df)
def featurize(config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
dataset = get_dataset(config['dataset_csv'], config['dataset_sep'])
featured_dataset = extract_features(dataset, config['features_columns_range'], config['target_column'])
filpath = config['featured_dataset_csv']
featured_dataset.to_csv(filpath, index=False, sep = config['dataset_sep'])
def featurize(config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
dataset = get_dataset(config['dataset_csv'])
featured_dataset = extract_features(dataset)
filpath = config['featured_dataset_csv']
featured_dataset.to_csv(filpath, index=False)
def data_load(config_path: Text) -> None:
"""Load raw data.
Args:
config_path {Text}: path to config
"""
config = load_config(config_path)
dataset = get_dataset()
dataset.to_csv(config.data_load.dataset_csv, index=False)
print(f'Data saved to: {config.data_load.dataset_csv}')
def split_dataset(config_path: Text, base_config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
base_config = yaml.load(open(base_config_path), Loader=yaml.FullLoader)
dataset = get_dataset(base_config['featurize']['featured_dataset_csv'],
base_config['featurize']['dataset_sep'])
random_state = base_config['base']['random_state']
base_dataset = get_dataset(base_config['featurize']['dataset_csv'],
base_config['featurize']['dataset_sep'])
base_dataset = base_dataset[base_config['featurize']
['features_columns_range']]
var_numeric = base_dataset.select_dtypes([np.number]).columns
test_size = config['test_size']
valid_size = config['valid_size']
train_csv_path = config['train_csv']
test_csv_path = config['test_csv']
valid_csv_path = config['valid_csv']
'''
Your code is here !!!
'''
train_dataset.to_csv(train_csv_path,
sep=base_config['featurize']['dataset_sep'],
encoding='utf-8',
index=False)
test_dataset.to_csv(test_csv_path,
sep=base_config['featurize']['dataset_sep'],
encoding='utf-8',
index=False)
valid_dataset.to_csv(valid_csv_path,
sep=base_config['featurize']['dataset_sep'],
encoding='utf-8',
index=False)
def evaluate_model(config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
estimator_name = config['train']['estimator_name']
target_column = config['featurize']['target_column']
test_df = get_dataset(config['split_train_test']['test_csv'])
model_name = config['base']['model']['model_name']
models_folder = config['base']['model']['models_folder']
model = joblib.load(os.path.join(models_folder, model_name))
f1, cm = evaluate(df=test_df, target_column=target_column, clf=model)
test_report = {'f1_score': f1, 'confusion_matrix': cm.tolist()}
print(test_report)
filepath = os.path.join(
config['base']['experiments']['experiments_folder'],
config['evaluate']['metrics_file'])
json.dump(obj=test_report, fp=open(filepath, 'w'), indent=2)
# Logging into mlflow
client = MlflowClient()
experiments = client.list_experiments(
) # returns a list of mlflow.entities.Experiment
mlflow.set_experiment(estimator_name)
print(experiments)
with mlflow.start_run() as run:
print(run)
print(run.info)
print(run.info.run_uuid)
param_grid = config['train']['estimators'][estimator_name][
'param_grid']
log_param(key='estimator', value=estimator_name)
log_param(key='cv', value=config['train']['cv'])
for param, value in param_grid.items():
log_param(key=param, value=value)
log_metric(key='f1_score', value=f1)
log_artifact(local_path='models/model.joblib')
log_artifact(local_path='src/features/features.py')
log_artifact(local_path='src/train/train.py')
log_artifact(local_path='src/pipelines/train.py')
def split_dataset(config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
dataset = get_dataset(config['featurize']['featured_dataset_csv'])
target_column = config['featurize']['target_column']
random_state = config['base']['random_state']
test_size = config['split_train_test']['test_size']
train_csv_path = config['split_train_test']['train_csv']
test_csv_path = config['split_train_test']['test_csv']
dataset = transform_targets_to_numerics(dataset,
target_column=target_column)
train_dataset, test_dataset = split_dataset_in_train_test(
dataset, test_size=test_size, random_state=random_state)
train_dataset.to_csv(train_csv_path, index=False)
test_dataset.to_csv(test_csv_path, index=False)
def evaluate_model(config_path: Text, base_config_path: Text):
config = yaml.load(open(config_path), Loader=yaml.FullLoader)
base_config = yaml.load(open(base_config_path), Loader=yaml.FullLoader)
target_column = base_config['featurize']['target_column']
test_df = get_dataset(base_config['split_train_test']['test_csv'])
model_name = base_config['base']['model']['model_name']
models_folder = base_config['base']['model']['models_folder']
model = joblib.load(os.path.join(models_folder, model_name))
f1, cm = evaluate(df=test_df,
target_column=target_column,
clf=model)
test_report = {
'f1_score': f1,
'confusion_matrix': cm.tolist()
}
print(test_report)
filepath = os.path.join(base_config['base']['experiments']['experiments_folder'],
config['metrics_file'])
json.dump(obj=test_report, fp=open(filepath, 'w'), indent=2)