diff --git a/.gitignore b/.gitignore index ede56e028618bac635db31390c39f97ad9c44813..0c6f380c18eedcea231d0fa63c7d84bf5938fc7e 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,3 @@ -./gen_train_data/input -./gen_train_data/output -./EDA/input \ No newline at end of file +gen_train_data/input/ +gen_train_data/output/ +EDA/input/ \ No newline at end of file diff --git a/gen_train_data/gen_train_data.ipynb b/gen_train_data/gen_train_data.ipynb index 5688ba2bcfa0058d5198cf131e8774218b4d1ae0..d5181185fffa51e90b121eec8e16a1dc8803f10b 100644 --- a/gen_train_data/gen_train_data.ipynb +++ b/gen_train_data/gen_train_data.ipynb @@ -36,8 +36,8 @@ "outputs": [], "source": [ "# Load clean datasets\n", - "df_pre = pd.read_csv('./data/input/pre_dataset.csv')\n", - "df_post = pd.read_csv('./data/input/post_dataset.csv')" + "df_pre = pd.read_csv('./input/pre_dataset.csv')\n", + "df_post = pd.read_csv('./input/post_dataset.csv')" ] }, { @@ -95,10 +95,10 @@ "outputs": [], "source": [ "# Save test data\n", - "np.save('./data/output/pre/X_test_pre.npy', X_test_pre)\n", - "np.save('./data/output/pre/y_test_pre.npy', y_test_pre)\n", - "np.save('./data/output/post/X_test_post.npy', X_test_post)\n", - "np.save('./data/output/post/y_test_post.npy', y_test_post)" + "np.save('./output/pre/X_test_pre.npy', X_test_pre)\n", + "np.save('./output/pre/y_test_pre.npy', y_test_pre)\n", + "np.save('./output/post/X_test_post.npy', X_test_post)\n", + "np.save('./output/post/y_test_post.npy', y_test_post)" ] }, { @@ -108,10 +108,10 @@ "outputs": [], "source": [ "# Save ORIGINAL training data\n", - "np.save('./data/output/pre/X_train_pre.npy', X_train_pre)\n", - "np.save('./data/output/pre/y_train_pre.npy', y_train_pre)\n", - "np.save('./data/output/post/X_train_post.npy', X_train_post)\n", - "np.save('./data/output/post/y_train_post.npy', y_train_post)" + "np.save('./output/pre/X_train_pre.npy', X_train_pre)\n", + "np.save('./output/pre/y_train_pre.npy', y_train_pre)\n", + "np.save('./output/post/X_train_post.npy', X_train_post)\n", + "np.save('./output/post/y_train_post.npy', y_train_post)" ] }, { @@ -133,10 +133,10 @@ "outputs": [], "source": [ "# Save oversampled training data\n", - "np.save('./data/output/pre/X_train_over_pre.npy', X_train_over_pre)\n", - "np.save('./data/output/pre/y_train_over_pre.npy', y_train_over_pre)\n", - "np.save('./data/output/post/X_train_over_post.npy', X_train_over_post)\n", - "np.save('./data/output/post/y_train_over_post.npy', y_train_over_post)" + "np.save('./output/pre/X_train_over_pre.npy', X_train_over_pre)\n", + "np.save('./output/pre/y_train_over_pre.npy', y_train_over_pre)\n", + "np.save('./output/post/X_train_over_post.npy', X_train_over_post)\n", + "np.save('./output/post/y_train_over_post.npy', y_train_over_post)" ] }, { @@ -158,10 +158,10 @@ "outputs": [], "source": [ "# Save undersampled training data\n", - "np.save('./data/output/pre/X_train_under_pre.npy', X_train_under_pre)\n", - "np.save('./data/output/pre/y_train_under_pre.npy', y_train_under_pre)\n", - "np.save('./data/output/post/X_train_under_post.npy', X_train_under_post)\n", - "np.save('./data/output/post/y_train_under_post.npy', y_train_under_post)" + "np.save('./output/pre/X_train_under_pre.npy', X_train_under_pre)\n", + "np.save('./output/pre/y_train_under_pre.npy', y_train_under_pre)\n", + "np.save('./output/post/X_train_under_post.npy', X_train_under_post)\n", + "np.save('./output/post/y_train_under_post.npy', y_train_under_post)" ] }, { @@ -171,7 +171,7 @@ "outputs": [], "source": [ "# Save features\n", - "np.save('./data/output/attributes.npy', feat)" + "np.save('./output/attributes.npy', feat)" ] } ],