这个流程主要是方便学习数据挖掘的IT人员快速了解数据挖掘的过程以及应该注意的要点
数据来源：Kaggle上有这样一个比赛：城市自行车共享系统使用状况。 https://www.kaggle.com/c/bike-sharing-demand可以下载 有一个博客对这个题目进行了专门的分析，见如下博客，题目分析以及特征的分析： https://blog.csdn.net/u013795429/article/details/52092659 数据的处理以及特征处理，见如下博客： https://blog.csdn.net/mlljava1111/article/details/53694055 https://blog.csdn.net/qiujiahao123/article/details/68927616
特征工程与相关算法的融合如下：
#coding=utf-8 import pandas as pd data = pd.read_csv("train.csv", header = 0,error_bad_lines=False) # print(data.head()) # 把datetime域切成 日期 和 时间 两部分。 temp = pd.DatetimeIndex(data['datetime']) data['date'] = temp.date data['time'] = temp.time # print(data.head()) #设定hour这个小时字段 data["hour"] = pd.to_datetime(data.time,format= '%H:%M:%S') data['hour'] = pd.Index(data["hour"]).hour #我们对时间类的特征处理，产出一个星期几的类别型变量 data["dayofweek"] = pd.DatetimeIndex(data.date).dayofweek #对时间类特征处理，产出一个时间长度变量 data['dateDays'] = (data.date - data.date[0]).astype('timedelta64[D]') #做一个小小的统计来看看真实的数据分布，我们统计一下一周各天的自行车租赁情况(分注册的人和没注册的人 byday = data.groupby(data["dayofweek"]) # 统计下没注册的用户租赁情况 byday['casual'].sum().reset_index() # 统计下注册的用户的租赁情况 # print(byday['casual'].sum().reset_index()) byday['registered'].sum().reset_index() #周末因为不同于平常，所以周末另外设置一列存储 data['Saturday'] = 0 data.Saturday[data["dayofweek"]==5]=1 data['Sunday'] = 0 data.Sunday[data["dayofweek"]==6]=1 # print(data.head()) # 从数据中，把原始的时间字段等踢掉 dataRel = data.drop(['datetime', 'count','date','time','dayofweek'], axis=1) # print(dataRel.head()) # 特征向量化 from sklearn.feature_extraction import DictVectorizer #将连续值的属性放入一个dict中 featureConCols = ['temp','atemp','humidity','windspeed','dateDays','hour'] dataFeatureCon = dataRel[featureConCols] # print(dataFeatureCon) #当数据中存在NaN缺失值时，我们可以用NA替代NaN dataFeatureCon = dataFeatureCon.fillna('NA') # 把离散值的属性放到一个dict中 X_dictCon = dataFeatureCon.T.to_dict().values() # print(X_dictCon) # print(dataFeatureCon) # 把离散值的属性放到另外一个dict中 featureCatCols = ['season','holiday','workingday','weather','Saturday', 'Sunday'] dataFeatureCat = dataRel[featureCatCols] # print(dataFeatureCat) dataFeatureCat = dataFeatureCat.fillna( 'NA' ) #in case I missed any X_dictCat = dataFeatureCat.T.to_dict().values() # print(X_dictCat) # print(dataFeatureCat.head()) # 向量化特征,即将上述的编成的特征与数字一一对应，进行组成数组 vec = DictVectorizer(sparse = False) X_vec_cat = vec.fit_transform(X_dictCat) # print(X_vec_cat) X_vec_con = vec.fit_transform(X_dictCon) # print(X_vec_con) # #标准化连续值特征 from sklearn import preprocessing #标准化连续值数据 scaler = preprocessing.StandardScaler().fit(X_vec_con) X_vec_con = scaler.transform(X_vec_con) # print(X_vec_con) #类别特征编码 #最常用的当然是one-hot编码咯，比如颜色 红、蓝、黄 会被编码为[1, 0, 0]，[0, 1, 0]，[0, 0, 1] from sklearn import preprocessing #one-hot编码 enc = preprocessing.OneHotEncoder() enc.fit(X_vec_cat) X_vec_cat = enc.transform(X_vec_cat).toarray() # print(X_vec_cat) # 把特征拼一起 # 把离散和连续的特征都组合在一起 import numpy as np X_vec = np.concatenate((X_vec_con,X_vec_cat),axis=1) # print(X_vec) #对结果值也处理一下 # 拿到结果的浮点数值 # 对Y向量化 Y_vec_reg = dataRel['registered'].values.astype(float) Y_vec_cas = dataRel['casual'].values.astype(float) # print(Y_vec_reg) # print(Y_vec_cas) Y = data['count'].values #print(Y) """模型训练，主要采用了4种模型进行训练， 1.岭回归、2.支持向量机、3.随机森林、 4.用网格搜索给随机森林找一组参数，然后在用随机森林预测 """ # 1.岭回归 from sklearn.model_selection import train_test_split # from sklearn.linear_model import Ridge from sklearn.linear_model import LinearRegression,Lasso,Ridge,ElasticNet print("\n1.岭回归") x_train,x_test,y_train,y_test = train_test_split(X_vec,Y,test_size=0.25,random_state=1) clf = LinearRegression() clf.fit(x_train, y_train) t=clf.predict(x_test) print(t) print("y_test:%s"%y_test) print("训练集准确率:{},测试集准确率:{}".format( clf.score(x_train, y_train), clf.score(x_test, y_test) )) # 2.支持向量机--为什么分类的SVM可以用来做回归 from sklearn.svm import SVR print("\n2.支持向量机") clf = SVR(kernel='rbf', C=10, gamma=0.001) clf.fit(x_train, y_train) t=clf.predict(x_test) print(t) print("y_test:%s"%y_test) print("训练集准确率:{},测试集准确率:{}".format( clf.score(x_train, y_train), clf.score(x_test, y_test) )) # 3.随机森林 print("\n3.随机森林") # from sklearn.ensemble import RandomForestClassifier from sklearn.ensemble import RandomForestRegressor clf = RandomForestRegressor(n_estimators=80) clf.fit(x_train, y_train) t=clf.predict(x_test) print(t) print("y_test:%s"%y_test) print("训练集准确率:{},测试集准确率:{}".format( clf.score(x_train, y_train), clf.score(x_test, y_test) )) # 4.用网格搜索给随机森林找一组参数，然后在用随机森林预测 print("\n4.用网格搜索给随机森林找一组参数，然后在用随机森林预测") from sklearn.model_selection import GridSearchCV params = {"n_estimators":[30,60,90]} scores = ['r2'] for score in scores: print(score) clf = GridSearchCV(RandomForestRegressor(),params,cv=5,scoring=score) clf.fit(x_train,y_train) print(clf.best_estimator_) clf = RandomForestRegressor(bootstrap=True,criterion='mse',max_depth=None, max_features = "auto",max_leaf_nodes = None, min_impurity_decrease=0.0,min_impurity_split=None, min_samples_leaf=1,min_samples_split=2, min_weight_fraction_leaf =0.0,n_estimators = 90,n_jobs = 1, oob_score=False,random_state = None,verbose=0,warm_start=False ) clf.fit(x_train, y_train) t=clf.predict(x_test) print(t) print("y_test:%s"%y_test) print("训练集准确率:{},测试集准确率:{}".format( clf.score(x_train, y_train), clf.score(x_test, y_test) ))结果：
SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy data.Saturday[data["dayofweek"]==5]=1 SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy data.Sunday[data["dayofweek"]==6]=1 [ 16 40 32 ..., 168 129 88] 1.岭回归 [ 174. 68. 392. ..., 114. -70. -26.] y_test:[308 14 539 ..., 24 14 8] 训练集准确率:0.39493964089432243,测试集准确率:0.4018670152885786 2.支持向量机 [ 161.9917164 64.73611511 258.07775507 ..., 106.7790444 -4.74826863 26.4338403 ] y_test:[308 14 539 ..., 24 14 8] 训练集准确率:0.27130138131106696,测试集准确率:0.26183605728175696 3.随机森林 [ 309.3 6.3375 570.5375 ..., 27.0625 10.125 14.2875] y_test:[308 14 539 ..., 24 14 8] 训练集准确率:0.9917779365294469,测试集准确率:0.9491408575667828 4.用网格搜索给随机森林找一组参数，然后在用随机森林预测 r2 RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=90, n_jobs=1, oob_score=False, random_state=None, verbose=0, warm_start=False) [ 304.53333333 7.82222222 565.82222222 ..., 27.72222222 10.93333333 13.9 ] y_test:[308 14 539 ..., 24 14 8] 训练集准确率:0.9918493230582454,测试集准确率:0.950078345686705算法参考： https://blog.csdn.net/shawroad88/article/details/87277407 https://blog.csdn.net/wong2016/article/details/87916292不一样的实现，可以看看 gridSearchCV（网格搜索）的参数、方法及示例： https://blog.csdn.net/weixin_41988628/article/details/83098130 数据挖掘一般流程及模型整理: https://mp.weixin.qq.com/s/mtU-58ZPW9ruOj7H16zpVQ https://blog.csdn.net/scheezer/article/details/82794757 参考： https://blog.csdn.net/mlljava1111/article/details/53694055 https://blog.csdn.net/qq_41185868/article/details/81711462 https://blog.csdn.net/shawroad88/article/details/87277407
