gistfile1.txt

depth = 10
seed_range = range(0, 3000,288)
acc_vs_seed_result_rf = {"seed": [],\
        "train_acc": [],
        "valid_acc": [],
        "top_feature": [],
        "second_feature": [],
        "third_feature": []}

for seed in seed_range:
    model = H2ORandomForestEstimator(model_id="model", \
                                   sample_rate=0.7, \
                                   ntrees=200, \
                                   max_depth=depth, \
                                   seed=seed)
    model.train(x=x, y=y, training_frame=train)
    predict_valid = model.predict(valid[x])
    predict_train = model.predict(train[x])
    acc_vs_seed_result_rf["seed"].append(seed)
    acc_vs_seed_result_rf["valid_acc"].append((predict_valid["predict"] == valid["Survived"]).mean()[0])
    acc_vs_seed_result_rf["train_acc"].append((predict_train["predict"] == train["Survived"]).mean()[0])
    acc_vs_seed_result_rf["top_feature"].append(model.varimp()[0][0])
    acc_vs_seed_result_rf["second_feature"].append(model.varimp()[1][0])
    acc_vs_seed_result_rf["third_feature"].append(model.varimp()[2][0])
    
#Conevrting results to a DataFrame

acc_vs_seed_result_df_rf = pd.DataFrame(acc_vs_seed_result_rf)
cols = ["seed", "train_acc", "valid_acc", "top_feature", "second_feature", "third_feature"]
acc_vs_seed_result_df_rf = acc_vs_seed_result_df_rf[cols]
acc_vs_seed_result_df_rf