fixed name of datasets in train and predict scripts (#2)

Signed-off-by: Akira Ura <ura.akira@jp.fujitsu.com>
sapientml · Sep 11, 2023 · 6fb4127 · 6fb4127
1 parent b7194e9
commit 6fb4127
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 21 deletions.
diff --git a/sapientml_loaddata/templates/loaddata_predict.py.jinja b/sapientml_loaddata/templates/loaddata_predict.py.jinja
@@ -5,19 +5,11 @@ import pandas as pd
 ignore_columns = {{ dataset.ignore_columns }}
 {% endif %}
 
-{% if dataset.test_data_path %}
-{% if dataset.test_data_path.endswith(".pkl") %}
-__test_dataset = pd.read_pickle("{{ dataset.test_data_path }}")
-{% else %}
-__test_dataset = pd.read_csv("{{ dataset.test_data_path }}", encoding="{{ dataset.csv_encoding }}", delimiter="{{ dataset.csv_delimiter }}")
-{% endif %}
-{% else %}{# It is assumed that test data has the same format as train data #}
 {% if dataset.training_data_path.endswith(".pkl") %}
 __test_dataset = pd.read_pickle("./test.pkl")
 {% else %}
 __test_dataset = pd.read_csv("./test.csv", encoding="{{ dataset.csv_encoding }}", delimiter="{{ dataset.csv_delimiter }}")
 {% endif %}
-{% endif %}
 __test_dataset_prediction_columns = __test_dataset
 {% if dataset.ignore_columns %}
 __test_dataset = __test_dataset.drop(ignore_columns, axis=1, errors="ignore")

diff --git a/sapientml_loaddata/templates/loaddata_train.py.jinja b/sapientml_loaddata/templates/loaddata_train.py.jinja
@@ -6,22 +6,11 @@ ignore_columns = {{ dataset.ignore_columns }}
 {% endif %}
 
 {% if dataset.training_data_path.endswith(".pkl") %}
-__train_dataset = pd.read_pickle("{{ dataset.training_data_path }}")
+__train_dataset = pd.read_pickle("./training.pkl")
 {% else %}
-__train_dataset = pd.read_csv("{{ dataset.training_data_path }}", encoding="{{ dataset.csv_encoding }}", delimiter="{{ dataset.csv_delimiter }}")
+__train_dataset = pd.read_csv("./training.csv", encoding="{{ dataset.csv_encoding }}", delimiter="{{ dataset.csv_delimiter }}")
 {% endif %}
 {% if dataset.ignore_columns %}
 __train_dataset = __train_dataset.drop(ignore_columns, axis=1, errors="ignore")
 {% endif %}
 
-{% if dataset.validation_data_path %}
-{% if dataset.validation_data_path.endswith(".pkl") %}
-__validation_dataset = pd.read_pickle("{{ dataset.validation_data_path }}")
-{% else %}
-__validation_dataset = pd.read_csv("{{ dataset.validation_data_path }}", encoding="{{ dataset.csv_encoding }}", delimiter="{{ dataset.csv_delimiter }}")
-{% endif %}
-{% if dataset.ignore_columns %}
-__validation_dataset = __validation_dataset.drop(ignore_columns, axis=1, errors="ignore")
-{% endif %}
-__train_dataset = pd.concat([__train_dataset, __validation_dataset]).reset_index(drop=True)
-{% endif %}{# if dataset.validation_data_path #}