python_ad_pca

#! /usr/bin/env python
#coding=utf-8
import pandas as pd
import numpy as np
from sklearn.decomposition import PCA
from collections import defaultdict
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
from matplotlib import pyplot as plt
#定义一个函数：1.前几个特征是数值，pandas把他们看成是字符串2.处理缺失值
def convert_number(x):
    try:
        return float(x)
    except ValueError:
        return np.nan
#