Python机器学习 集成算法实例

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
%matplotlib inline

SEED = 222
np.random.seed(SEED)

df = pd.read_csv('input.csv')
#切分训练集和测试集
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score

def get_train_test(test_size = 0.95):
    y = 1 * (df.cand_pty_affiliation == "REP")
    X = df.drop(["cand_pty_affiliation"], axis = 1)
    X = pd.get_dummies(X, sparse = True)
    #对样本的特征进行独热编码“one-hot encoding”
    X.drop(X.columns[X.std() == 0], axis = 1, inplace = True)
    #去掉标准差=0 即该特征所有样本都一样的列
    return train_test_split(X,y,test_size = test_size, random_state = SEED)

xtrain, xtest, ytrain, ytest = get_train_test()

print("\nExample data:")
df.head()

 

cand_pty_affiliation：我们要预测的指标，共和党或者民主党
entity_tp：个人还是组织
classification:领域
rpt_tp：贡献的大小
cycle：捐赠在哪年
transaction_amt：捐献金额

df.cand_pty_affiliation.value_counts(normalize = True).plot(
    kind  = "bar", title = "Share of No. donations")
plt.show()
#这里看一下原始数据正例和负例的比例，这里对应的是民主党和共和党 

 

import pydotplus
#导入结构化图形绘制工具
from IPython.display import Image
#导入图片显示的库，能够打开图片文件在jupyter中进行显示
from sklearn.metrics import roc_auc_score
from sklearn.tree import DecisionTreeClassifier, export_graphviz
#导入决策树模型和绘制决策树.dot文件的库

def print_graph(clf, feature_names):
    "打印决策树"
    graph &#