alueError: could not convert string to float: 'Technology' while optuna.create_study

Question

I have this code for making optimization with Optuna:

n_trials = 25
def objective(trial):
  params = {
      "n_estimators": trial.suggest_int("n_estimators", 100, 900),
      "max_depth": trial.suggest_int("max_depth", 5, 15),
      "min_samples_split": trial.suggest_int("min_samples_split", 2 ,6)
  }

  rfc = RandomForestClassifier(**params)
  rfc.fit(X_train_res, y_train_res)
  y_pred = rfc.predict(X_test)
  score = metrics.r2_score(y_test, y_pred)
  
  return score

study = optuna.create_study(study_name = "RandomForestRegressor", direction="maximize")
study.optimize(objective, n_trials)

print("Number of completed trials: {}".format(len(study.trials)))
print("Best trial:")
trial = study.best_trial

print("\tBest Score: {}".format(trial.value))

However it has resulted in this problem

---> 19 study.optimize(objective, n_trials)
     20 
     21 print("Number of completed trials: {}".format(len(study.trials)))

9 frames
/usr/local/lib/python3.7/dist-packages/pandas/core/series.py in __array__(self, dtype)
    855               dtype='datetime64[ns]')
    856         """
--> 857         return np.asarray(self._values, dtype)
    858 
    859     # ----------------------------------------------------------------------

ValueError: could not convert string to float: 'Technology

I have technology value in my y_train_res, here is how it looksenter image description here

Answer 1

Are you using sklearn.metrics.r2_score?

• https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html

I think r2_score doesn't accept an array of string, it must be one of number.

https://github.com/scikit-learn/scikit-learn/blob/baf828ca126bcb2c0ad813226963621cafe38adb/sklearn/metrics/_regression.py#L805-L808