版权声明：本套技术专栏是作者（秦凯新）平时工作的总结和升华，通过从真实商业环境抽取案例进行总结和分享，并给出商业应用的调优建议和集群环境容量规划等内容，请持续关注本套博客。QQ邮箱地址：1120746959@qq.com，如有任何技术交流，可随时联系。

1 基本数据探索

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
X = pd.read_csv('C:\\ML\\MLData\\iris.data')
X.columns = ['sepal_length_cm', 'sepal_width_cm', 'petal_length_cm', 'petal_width_cm', 'class']X.head()
X.sample(n=10)
复制代码

X.shape
(149, 5)X.dtypes
sepal_length_cm    float64
sepal_width_cm     float64
petal_length_cm    float64
petal_width_cm     float64
class               object
dtype: objectX.describe()
复制代码

• one-hot编码

    # 创建一个简单的原始数据testdata = pd.DataFrame({'age':[4,6,3,3],'pet':['cat','dog','dog','fish']})testdataage  pet0    4   cat1    6   dog2    3   dog3    3   fishpd.get_dummies(testdata,columns=['pet'])age  pet_cat pet_dog pet_fish0   4   1   0   01  6   0   1   02  3   0   1   03  3   0   0   1    testdata.pet.values.reshape(-1,1)array([['cat'],['dog'],['dog'],['fish']], dtype=object)from sklearn.preprocessing import OneHotEncoderOneHotEncoder().fit_transform(testdata.age.values.reshape(-1,1)).toarray()array([[0., 1., 0.],[0., 0., 1.],[1., 0., 0.],[1., 0., 0.]])
  复制代码

• 时间类型处理（DatetimeIndex）

    import pandas as pddata = pd.read_csv('kaggle_bike_competition_train.csv', header = 0, error_bad_lines=False)data.head()  #先看下数据的样子，打印前5行
  复制代码

    #下面我们只看datatime这个时间类型属性，#首先，我们可以将它切分成data = data.iloc[:,:1] #只看datatime这个属性temp = pd.DatetimeIndex(data['datetime'])data['date'] = temp.date  #日期  data['time'] = temp.time  #时间data['year'] = temp.year  #年data['month'] = temp.month #月data['day'] = temp.day #日data['hour'] = temp.hour #小时data['dayofweek'] = temp.dayofweek  #具体星期几data['dateDays'] = (data.date - data.date[0]) #生成一个时间长度特征  ['0days','0days',...,'1days',...]data['dateDays'] = data['dateDays'].astype('timedelta64[D]')  #转换成float型data
复制代码

2 数据可视化探索分析

• box 查看异常点

    X.plot(kind="box",subplots=True,layout=(1,4),figsize=(12,5))plt.show()
  复制代码

• hist区间图

    X.hist(figsize=(12,5),xlabelsize=1,ylabelsize=1)plt.show()
  复制代码

• 密度图

    X.plot(kind="density",subplots=True,layout=(1,4),figsize=(12,5))plt.show()
  复制代码

• 热力图关系图

    fig = plt.figure(figsize=(10,10))ax = fig.add_subplot(111)cax = ax.matshow(X.corr(),vmin=-1,vmax=1,interpolation="none")fig.colorbar(cax)ticks = np.arange(0,4,1)ax.set_xticks(ticks)ax.set_yticks(ticks)ax.set_xticklabels(col_name)ax.set_yticklabels(col_name)plt.show()
  复制代码

3 数据比例划分

    from sklearn.model_selection import KFoldfrom sklearn.model_selection import train_test_splitall_inputs = iris_data[['sepal_length_cm', 'sepal_width_cm','petal_length_cm', 'petal_width_cm']].valuesall_classes = iris_data['class'].values(training_inputs,testing_inputs,training_classes,testing_classes) = train_test_split(all_inputs, all_classes, train_size=0.75, random_state=1)
复制代码

4 多分类模型集中评估

    from sklearn.ensemble import AdaBoostClassifierfrom sklearn.ensemble import GradientBoostingClassifierfrom sklearn.ensemble import ExtraTreesClassifierfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.svm import SVCfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.linear_model import LogisticRegressionfrom sklearn.naive_bayes import GaussianNBfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysisfrom sklearn.model_selection import KFoldfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import cross_val_scoremodels = []models.append(("AB",AdaBoostClassifier()))models.append(("GBM",GradientBoostingClassifier()))models.append(("RF",RandomForestClassifier()))models.append(("ET",ExtraTreesClassifier()))models.append(("SVC",SVC()))models.append(("KNN",KNeighborsClassifier()))models.append(("LR",LogisticRegression()))models.append(("GNB",GaussianNB()))models.append(("LDA",LinearDiscriminantAnalysis()))names = []results = []for name,model in models:result = cross_val_score(model,training_inputs,training_classes,scoring="accuracy",cv=5)names.append(name)results.append(result)print("{}  Mean:{:.4f}(Std{:.4f})".format(name,result.mean(),result.std()))AB  Mean:0.9097(Std0.0290)GBM  Mean:0.9370(Std0.0361)RF  Mean:0.9461(Std0.0442)ET  Mean:0.9370(Std0.0361)SVC  Mean:0.9640(Std0.0340)KNN  Mean:0.9374(Std0.0454)LR  Mean:0.9379(Std0.0353)GNB  Mean:0.9556(Std0.0391)LDA  Mean:0.9735(Std0.0360)
复制代码

5 流水线交叉验证

    from sklearn.pipeline import Pipelinefrom sklearn.preprocessing import StandardScalerpipeline = []pipeline.append(("ScalerET", Pipeline([("Scaler",StandardScaler()),("ET",ExtraTreesClassifier())])))pipeline.append(("ScalerGBM", Pipeline([("Scaler",StandardScaler()),("GBM",GradientBoostingClassifier())])))pipeline.append(("ScalerRF", Pipeline([("Scaler",StandardScaler()),("RF",RandomForestClassifier())])))names = []results = []for name,model in pipeline:kfold = KFold(n_splits=5,random_state=42)result = cross_val_score(model, training_inputs,training_classes, cv=kfold, scoring="accuracy")results.append(result)names.append(name)print("{}:  Error Mean:{:.4f} (Error Std:{:.4f})".format(name,result.mean(),result.std()))ScalerET:   Error Mean:0.9372 (Error Std:0.0358)
ScalerGBM:  Error Mean:0.9462 (Error Std:0.0332)
ScalerRF:   Error Mean:0.9553 (Error Std:0.0275)
复制代码

6 超参数网格交叉评估

    from sklearn.model_selection import GridSearchCVparam_grid = {"C":[0.1, 0.3, 0.5, 0.7, 0.9, 1.0, 1.3, 1.5, 1.7, 2.0],"kernel":['linear', 'poly', 'rbf', 'sigmoid']}model = SVC()kfold = KFold(n_splits=5, random_state=42)grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring="accuracy", cv=kfold)grid_result = grid.fit(training_inputs,training_classes)print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))means = grid_result.cv_results_['mean_test_score']stds = grid_result.cv_results_['std_test_score']params = grid_result.cv_results_['params']for mean, stdev, param in zip(means, stds, params):print("%f (%f) with: %r" % (mean, stdev, param))Best: 0.972973 using {'C': 0.9, 'kernel': 'linear'}0.954955 (0.027681) with: {'C': 0.1, 'kernel': 'linear'}0.927928 (0.021620) with: {'C': 0.1, 'kernel': 'poly'}0.945946 (0.016821) with: {'C': 0.1, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 0.1, 'kernel': 'sigmoid'}0.963964 (0.017933) with: {'C': 0.3, 'kernel': 'linear'}0.954955 (0.028629) with: {'C': 0.3, 'kernel': 'poly'}0.954955 (0.027681) with: {'C': 0.3, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 0.3, 'kernel': 'sigmoid'}0.963964 (0.017933) with: {'C': 0.5, 'kernel': 'linear'}0.954955 (0.028629) with: {'C': 0.5, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 0.5, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 0.5, 'kernel': 'sigmoid'}0.963964 (0.017933) with: {'C': 0.7, 'kernel': 'linear'}0.963964 (0.033773) with: {'C': 0.7, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 0.7, 'kernel': 'rbf'}0.342342 (0.045336) with: {'C': 0.7, 'kernel': 'sigmoid'}0.972973 (0.021914) with: {'C': 0.9, 'kernel': 'linear'}0.963964 (0.033773) with: {'C': 0.9, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 0.9, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 0.9, 'kernel': 'sigmoid'}0.972973 (0.021914) with: {'C': 1.0, 'kernel': 'linear'}0.963964 (0.033773) with: {'C': 1.0, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 1.0, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 1.0, 'kernel': 'sigmoid'}0.972973 (0.021914) with: {'C': 1.3, 'kernel': 'linear'}0.963964 (0.033773) with: {'C': 1.3, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 1.3, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 1.3, 'kernel': 'sigmoid'}0.972973 (0.021914) with: {'C': 1.5, 'kernel': 'linear'}0.963964 (0.033773) with: {'C': 1.5, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 1.5, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 1.5, 'kernel': 'sigmoid'}0.972973 (0.021914) with: {'C': 1.7, 'kernel': 'linear'}0.954955 (0.028629) with: {'C': 1.7, 'kernel': 'poly'}0.963964 (0.017933) with: {'C': 1.7, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 1.7, 'kernel': 'sigmoid'}0.963964 (0.017933) with: {'C': 2.0, 'kernel': 'linear'}0.954955 (0.028629) with: {'C': 2.0, 'kernel': 'poly'}0.954955 (0.027681) with: {'C': 2.0, 'kernel': 'rbf'}0.351351 (0.049646) with: {'C': 2.0, 'kernel': 'sigmoid'}
复制代码

总结

本文没有华丽的技术，在于整合多分类模型集中评估，流水线交叉验证以及超参数网格交叉评估多种场景。

版权声明：本套技术专栏是作者（秦凯新）平时工作的总结和升华，通过从真实商业环境抽取案例进行总结和分享，并给出商业应用的调优建议和集群环境容量规划等内容，请持续关注本套博客。QQ邮箱地址：1120746959@qq.com，如有任何技术交流，可随时联系。

秦凯新 于深圳