1、准备
# 首先 import 必要的模块
import pandas as pd
import numpy as np
from sklearn.model_selection import GridSearchCV
#竞赛的评价指标为logloss
from sklearn.metrics import log_loss
from matplotlib import pyplot
import seaborn as sns
%matplotlib inline
data = pd.read_csv('Otto_train.csv')
data.head()
data.info()
data.describe()
data.shape
#受机器性能所限取前两万条数据
data = data[:20000]
# Target 分布,看看各类样本分布是否均衡
sns.countplot(data.target)
pyplot.xlabel('target');
pyplot.ylabel('Number of occurrences');
2、数据标准化
# 将类别字符串变成数字
y_train = data.target
y_train = y_train.map(lambda s:s[6:])
y_train = y_train.map(lambda s:int(s)-1)
data = data.drop(['target','id'],axis=1)
X_train = np.array(data)
# 数据标准化
from sklearn.preprocessing import StandardScaler
# 初始化特征的标准化器
ss_X = StandardScaler()
# 分别对训练和测试数据的特征进行标准化处理
X_train = ss_X.fit_transform(X_train)
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import cross_val_score
lr= LogisticRegression()
# 交叉验证用于评估模型性能和进行参数调优(模型选择)
#分类任务中交叉验证缺省是采用StratifiedKFold
loss = cross_val_score(lr, X_train, y_train, cv=5, scoring='neg_log_loss')
print('logloss of each fold is: ',-loss)
print('cv logloss is:', -loss.mean())
3、调用GridSearchCV进行参数调优
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
#需要调优的参数
# 请尝试将L1正则和L2正则分开,并配合合适的优化求解算法(slover)
#tuned_parameters = {'penalty':['l1','l2'],
# 'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000]
# }
penaltys = ['l1','l2']
Cs = [0.001, 0.01, 0.1, 1, 10, 100, 1000]
tuned_parameters = dict(penalty = penaltys, C = Cs)
lr_penalty= LogisticRegression()
grid= GridSearchCV(lr_penalty, tuned_parameters,cv=5, scoring='neg_log_loss')
grid.fit(X_train,y_train)
grid.cv_results_
print(-grid.best_score_)
print(grid.best_params_)
# 绘制plot CV误差曲线
test_means = grid.cv_results_[ 'mean_test_score' ]
test_stds = grid.cv_results_[ 'std_test_score' ]
train_means = grid.cv_results_[ 'mean_train_score' ]
train_stds = grid.cv_results_[ 'std_train_score' ]
# plot results
n_Cs = len(Cs)
number_penaltys = len(penaltys)
test_scores = np.array(test_means).reshape(n_Cs,number_penaltys)
train_scores = np.array(train_means).reshape(n_Cs,number_penaltys)
test_stds = np.array(test_stds).reshape(n_Cs,number_penaltys)
train_stds = np.array(train_stds).reshape(n_Cs,number_penaltys)
x_axis = np.log10(Cs)
for i, value in enumerate(penaltys):
#pyplot.plot(log(Cs), test_scores[i], label= 'penalty:' + str(value))
pyplot.errorbar(x_axis, test_scores[:,i], yerr=test_stds[:,i] ,label = penaltys[i] +' Test')
pyplot.errorbar(x_axis, train_scores[:,i], yerr=train_stds[:,i] ,label = penaltys[i] +' Train')
pyplot.legend()
pyplot.xlabel( 'log(C)' )
pyplot.ylabel( 'neg-logloss' )
pyplot.savefig('LogisticGridSearchCV_C.png' )
pyplot.show()