def run_training():
"""Train the model."""
# read training data
data = load_dataset(config.TRAINING_DATA_FILE)
print("------------")
# select only the customer conversations
data = data[data["message_source"] == "customer"][["message","case_type"]]
# divide train and test
sss = StratifiedShuffleSplit(n_splits=5, test_size=0.2, random_state=config.SEED)
X = data.drop(config.TARGET, axis=1)
y = data[config.TARGET].apply(lambda x: 0 if x=="cancel_order" else 1)
for train_index, test_index in sss.split(X, y):
X_train, X_test = X.iloc[train_index], X.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
X_train = X_train[config.FEATURES]
X_test = X_test[config.FEATURES]
print(X_train.iloc[0])
pipeline.full_pipe.fit(X_train, y_train)
save_pipeline(pipeline_to_persist=pipeline.full_pipe)
def run_training() -> None:
data = load_data(filename=config.DATA_FILE)
X_train, X_test, y_train, y_test = train_test_split(data[config.FEATURES],
data[config.TARGET],
test_size=0.4,
random_state=42)
y_train = encode_target(y_train)
status_pipeline.fit(X_train, y_train)
save_pipeline(pipeline_to_persist=status_pipeline)
def run_training() -> None:
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# divide train and test
X_train, X_test, y_train, y_test = train_test_split(
data.drop(config.TARGET, axis=1),
data[config.TARGET],
test_size=0.2,
random_state=config.RANDOM_SEED) # we are setting the seed here
# fit pipeline
pipeline.titanic_pipe.fit(X_train, y_train)
_logger.info(f"saving model version: {_version}")
# save pipeline
save_pipeline(pipeline_to_persist=pipeline.titanic_pipe)
def run_training():
"""Train the model."""
# read training data
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
# divide train and test
X_train, X_test, y_train, y_test = train_test_split(
data.drop(config.TARGET, axis=1),
data[config.TARGET],
test_size=0.2,
random_state=0) # we are setting the seed here
pipeline.titanic_pipe.fit(X_train, y_train)
joblib.dump(pipeline.titanic_pipe, config.PIPELINE_NAME)
_logger.info(f"saving model version: {_version}")
save_pipeline(pipeline_to_persist=pipeline.titanic_pipe)
def run_training() -> None:
data = load_dataset(file_name=config.TRAINING_DATA_FILE)
X_train, X_test, y_train, y_test = train_test_split(data[config.FEATURES],
data[config.TARGET],
test_size=0.1,
random_state=0)
X_train[config.DISCRETE_SET1_FEATURES + config.DISCRETE_SET2_FEATURES +
config.DISCRETE_SET3_FEATURES] = X_train[
config.DISCRETE_SET1_FEATURES + config.DISCRETE_SET2_FEATURES +
config.DISCRETE_SET3_FEATURES].astype(str)
X_test[config.DISCRETE_SET1_FEATURES + config.DISCRETE_SET2_FEATURES +
config.DISCRETE_SET3_FEATURES] = X_test[
config.DISCRETE_SET1_FEATURES + config.DISCRETE_SET2_FEATURES +
config.DISCRETE_SET3_FEATURES].astype(str)
pipeline.rf_pipe.fit(X_train[config.FEATURES], y_train)
_logger.info(f"saving model version: {_version}")
save_pipeline(pipeline_to_persist=pipeline.rf_pipe)