Evaluating classification algorithms on a multi-class single feature problem

fizzBuzz.py

import pandas as pd

from sklearn.linear_model import LogisticRegression
from sklearn import svm
from sklearn.ensemble import RandomForestClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split

df = pd.DataFrame(columns=['Number','Class'])

for i in range(122):
    flag3 = False
    flag5 = False
    
    if i%3 == 0:
        flag3 = True
    if i%5 == 0:
        flag5 = True
    
    if flag3 and flag5:
        df.loc[i] = [str(i)] + ['fizzbuzz']
    elif flag3:
        df.loc[i] = [str(i)] + ['fizz']
    elif flag5:
        df.loc[i] = [str(i)] + ['buzz']
    else:
        df.loc[i] = [str(i)] + ['blank']

X = df[['Number']]
y = df.Class

X_tr, X_test, y_tr, y_test = train_test_split(X, y, random_state = 0)

LR = LogisticRegression(random_state=0, solver='lbfgs', 
                        multi_class='multinomial').fit(X_tr, y_tr)
LR.predict(X_test)
print(round(LR.score(X_test,y_test), 4))

SVM = svm.SVC(decision_function_shape="ovo").fit(X_tr, y_tr)
SVM.predict(X_test)
print(round(SVM.score(X_test, y_test), 4))

RF = RandomForestClassifier(n_estimators=1000, max_depth=10, 
                            random_state=0).fit(X_tr, y_tr)
RF.predict(X_test)
print(round(RF.score(X_test, y_test), 4))

NN = MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=(150, 10), 
                   random_state=1).fit(X_tr, y_tr)
NN.predict(X_test)
print(round(NN.score(X_test, y_test), 4))