XGBoost Example

model.py

#!/usr/bin/env python
#!pip install sklearn xgboost
#!wget https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv

from numpy import loadtxt
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

import pprint

pp = pprint.PrettyPrinter(indent=4)

dataset = loadtxt('pima-indians-diabetes.data.csv', delimiter=",")

pp.pprint(dataset[0])

X = dataset[:,0:8]
Y = dataset[:,8]

print("X == ")
pp.pprint(X[0])

print("Y == ")
pp.pprint(Y[0])


seed = 7
test_size = 0.33
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=test_size, random_state=seed)


model = XGBClassifier()
model.fit(X_train, y_train)

pp.pprint(model)

print("Making predictions")

y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]

accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))