LightGBMError: The number of features in data (75) is not the same as it was in training data (74).

LightGBMError: The number of features in data (75) is not the same as it was in training data (74).
You can set predict_disable_shape_check=true to discard this error, but please be aware what you are doing.

モデルに渡すデータの特徴量数が異なる場合に表示されるエラー
predict_disable_shape_check=Trueを引数に渡すと、
エラー回避できるが誤った予測を得る可能性がある

pred = model.predict(df, predict_disable_shape_check=True)

そもそもカラム数が異なる場合、必要な処理が抜けているのかも

df_origin = df.drop('y', axis=1)
pred = model.predict(df_origin)

Reference

• predict_disable_shape_check