import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt

data = pd.read_csv("iris.csv")
data = np.array(data)     # 变成array形式
np.random.shuffle(data)
percent = 0.5


def train_test_splits(data, percent):
    train_size = int(data.shape[0]*percent)
    return data[:train_size], data[train_size:]


train, test = train_test_splits(data, percent)
x_train = train[:, 0:train.shape[1] - 1]
y_train = train[:, train.shape[1]-1]
x_test = test[:, 0:test.shape[1] - 1]
y_test = test[:, test.shape[1]-1]
# 利用随机森林进行训练
forest = DecisionTreeClassifier()
forest.fit(x_train, y_train)

#
num = y_test.shape[0]
score = forest.score(x_test, y_test)
result = forest.predict(x_test)
print(y_test, result)
plt.figure()
# 只取前一百条可视化，因为数据太多了
plt.plot(np.arange(num), y_test, "go-", label="True value")
plt.plot(np.arange(num), result, "ro-", label="Predict value")
plt.title(f"RandomForest---score:{score}")
# plt.legend(loc="best")
plt.show()