README.md

---
pipeline_tag: tabular-classification
tags:
- sklearn
language:
- ko
library_name: sklearn
---

# label_encoder_map
```python
label_encoder_map = {
    "의약품제형": LabelEncoder(),
    "색상앞": LabelEncoder(),
    "색상뒤": LabelEncoder(),
    "분할선앞": LabelEncoder(),
    "분할선뒤": LabelEncoder(),
    "제형코드명": LabelEncoder(),
}

ds = ds.add_column('의약품제형_encoded', label_encoder_map['의약품제형'].fit_transform(ds.to_pandas()['의약품제형']))
ds = ds.add_column('색상앞_encoded', label_encoder_map['색상앞'].fit_transform(ds.to_pandas()['색상앞']))
ds = ds.add_column('색상뒤_encoded', label_encoder_map['색상뒤'].fit_transform(ds.to_pandas()['색상뒤']))
ds = ds.add_column('분할선앞_encoded', label_encoder_map['분할선앞'].fit_transform(ds.to_pandas()['분할선앞']))
ds = ds.add_column('분할선뒤_encoded', label_encoder_map['분할선뒤'].fit_transform(ds.to_pandas()['분할선뒤']))
ds = ds.add_column('제형코드명_encoded', label_encoder_map['제형코드명'].fit_transform(ds.to_pandas()['제형코드명']))
```

```python
knn = KNeighborsClassifier(n_neighbors=5, metric='cosine')
knn.fit(ds.select_columns(
    ['의약품제형_encoded', '색상앞_encoded', '색상뒤_encoded', '분할선앞_encoded', '분할선뒤_encoded', '제형코드명_encoded']).to_pandas(), ds.select_columns("품목명").to_pandas())
```

[Full code](https://gist.github.com/brainer3220/4176af5b013c9cd1dd419626f1a7b0d9)

# Condensed-Co-Graph-And-Size-Graph
```python
from datasets import load_dataset, disable_caching, Value
import numpy as np
from sklearn.preprocessing import LabelEncoder

co_graph_edges = load_dataset('brainer/pill_identification_graph', 'co-graph-edges')['train']
co_graph_nodes = load_dataset('brainer/pill_identification_graph', 'co-graph-nodes')['train']
size_graph_edges = load_dataset('brainer/pill_identification_graph', 'size-graph-edges')['train']
size_graph_nodes = load_dataset('brainer/pill_identification_graph', 'size-graph-nodes')['train']
pill_ingredients_edges = load_dataset('brainer/pill_identification_graph', 'merge-hira-pill_identification-edges')['train']
pill_ingredients_nodes = load_dataset('brainer/pill_identification_graph', 'merge-hira-pill_identification-nodes')['train']
co_graph_nodes, co_graph_edges, size_graph_nodes, size_graph_edges, pill_ingredients_nodes, pill_ingredients_edges
pill_identification_data = load_dataset('brainer/pill_identification_data', 'default')



drug_name_encoder = LabelEncoder()
gnl_nm_encoder = LabelEncoder()


item_serial_number = pill_identification_data.cast_column('품목일련번호', Value(dtype='string'))['train']['품목일련번호']

drug_name_encoder.fit(list(set(np.asarray(size_graph_nodes['id'] + size_graph_edges['target'] + pill_ingredients_edges['target'] + item_serial_number))))

gnl_nm_encoder.fit(list(set(np.asarray(co_graph_nodes['id'] + pill_ingredients_nodes['id']))))
```