Python在机器学习--决策树和集成学习

Python在机器学习–决策树和集成学习

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import scipy as sp
from matplotlib.font_manager import FontProperties
font=FontProperties(fname="E:\Fonts\方正粗黑宋简体.ttf",size=14)
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import matplotlib as mpl
import seaborn as sns
from sklearn import tree,metrics
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier

import pydotplus
import os
import graphviz
# from sklearn.externals.six import StringIO
# from sklearn.externals.six import StringIO
import io

from IPython.display import Image

'''读取训练集合测试集'''
def Read_data(path):
    data=pd.read_csv(path,engine='python')
    return data
def main1():
    path1 = os.path.join(os.getcwd(), "data", "Titanic_train.csv")
    path2 = os.path.join(os.getcwd(), "data", "Titanic_test.csv")
    paths = [path1, path2]
    datas = []
    for path in paths:
        datas.append(Read_data(path))

    train = datas[0]
    test = datas[1]
    data_pro=datas
    print("训练集的列缺失值得情况：\n",train.isnull().sum())
    print("测试集的列缺失值得情况：\n", test.isnull