def karunru_analyze_columns(
input_df: XDataFrame) -> Tuple[List[str], List[str]]:
"""Classify columns to numerical or categorical.
Args:
input_df (XDataFrame) : Input data frame.
Returns:
Tuple[List[str], List[str]] : List of num cols and cat cols.
Example:
::
>>> import pandas as pd
>>> from xfeat.utils import analyze_columns
>>> df = pd.DataFrame({"col1": [1, 2], "col2": [2, 3], "col3": ["a", "b"]})
>>> analyze_columns(df)
(['col1', 'col2'], ['col3'])
"""
numerical_cols = []
categorical_cols = input_df.select_dtypes("category").columns.tolist()
for col in [
col for col in input_df.columns if col not in categorical_cols
]:
if pd.api.types.is_numeric_dtype(input_df[col]):
numerical_cols.append(col)
else:
categorical_cols.append(col)
return numerical_cols, categorical_cols
def predict(self, model: TabNetModel, features: XDataFrame) -> np.ndarray:
for col in features.select_dtypes(include="category").columns:
features[col] = features[col].cat.add_categories("Unknown")
features[col] = features[col].fillna("Unknown")
features[col] = features[col].cat.codes
numerical_cols = [
col
for col in features.columns
if col not in self.config["categorical_cols"]
]
for col in numerical_cols:
features[col] = features[col].fillna(features[col].mean())
if self.mode != "multiclass":
return model.predict(features.values).reshape(
-1,
)
else:
preds = model.predict_proba(features, ntree_limit=model.best_ntree_limit)
return preds @ np.arange(4) / 3
