ml.py

#!/usr/bin/env python3
  
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

url = "https://raw.githubusercontent.com/jadeyee/r2d3-part-1-data/master/part_1_data.csv"
df = pd.read_csv(url, header=2)
#print(df.describe())

# X = the data
X = df.iloc[:,1:].to_numpy()

# Y = the labels
Y = df.iloc[:,0].to_numpy()

# split the set
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.1)
print(X_train.shape, y_train.shape)
print(X_test.shape, y_test.shape)

from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
#clf = GaussianNB()
#clf = KNeighborsClassifier(n_neighbors=3)
clf = RandomForestClassifier(n_estimators=100, max_depth=2,random_state=0)

clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print(score)