2020-01-10

皮爾遜相關(guān)系數(shù)

image.png

衡量線性相關(guān)性，檢查數(shù)據(jù)集里目標(biāo)和數(shù)值特征之間皮爾遜相關(guān)系數(shù)的絕對(duì)值。根據(jù)這個(gè)準(zhǔn)則保留前n個(gè)特征。def cor_selector(X, y,num_feats):

cor_list = []

feature_name = X.columns.tolist()

# calculate the correlation with y for each feature

for i in X.columns.tolist():

cor = np.corrcoef(X[i], y)[0, 1]

cor_list.append(cor)

# replace NaN with 0

cor_list = [0 if np.isnan(i) else i for i in cor_list]

# feature name

cor_feature = X.iloc[:,np.argsort(np.abs(cor_list))

[-num_feats:]].columns.tolist()

# feature selection? 0 for not select, 1 for select

cor_support = [True if i in cor_feature else False for i in

feature_name]

return cor_support, cor_feature

cor_support, cor_feature = cor_selector(X, y,num_feats)

print(str(len(cor_feature)), 'selected features')from sklearn.feature_selection import SelectKBest

from scipy.stats import pearsonr

from sklearn.datasets import load_iris

iris=load_iris()

#選擇K個(gè)最好的特征，返回選擇特征后的數(shù)據(jù)

#第一個(gè)參數(shù)為計(jì)算評(píng)估特征是否好的函數(shù)，該函數(shù)輸入特征矩陣和目標(biāo)向量，輸出二元組(評(píng)分，P值)的數(shù)組，數(shù)組第i項(xiàng)為第i個(gè)特征的評(píng)分和P值。在此定義為計(jì)算相關(guān)系數(shù)

#參數(shù)k為選擇的特征個(gè)數(shù)

# 定義函數(shù)

def multivariate_pearsonr(X, y):

scores, pvalues = [], []

for ret in map(lambda x:pearsonr(x, y), X.T):

scores.append(abs(ret[0]))

pvalues.append(ret[1])

return (np.array(scores), np.array(pvalues))

transformer = SelectKBest(score_func=multivariate_pearsonr, k=2)

Xt_pearson = transformer.fit_transform(iris.data, iris.target)

print(Xt_pearson)

卡方分布

只能用于二分類(lèi)

計(jì)算目標(biāo)與數(shù)值變量之間的卡方度量分布，只選取卡方值最大的變量。

image.png

假設(shè)自變量有N種取值，因變量有M種取值，考慮自變量等于i且因變量等于j的樣本頻數(shù)的觀察值與期望的差距，構(gòu)建統(tǒng)計(jì)量：

image.pngfrom sklearn.feature_selection import SelectKBestfrom

sklearn.feature_selection import chi2

#選擇K個(gè)最好的特征，返回選擇特征后的數(shù)據(jù)

SelectKBest(chi2, k=2).fit_transform(iris.data, iris.target)from sklearn.feature_selection import SelectKBest

from sklearn.feature_selection import chi2

from sklearn.preprocessing import MinMaxScaler

X_norm = MinMaxScaler().fit_transform(X)

chi_selector = SelectKBest(chi2, k=num_feats)

chi_selector.fit(X_norm, y)

chi_support = chi_selector.get_support()

chi_feature = X.loc[:,chi_support].columns.tolist()

print(str(len(chi_feature)), 'selected features')

遞歸特征消除

通過(guò)特征的重要性，遞歸的去掉不重要的from sklearn.feature_selection import RFE

from sklearn.linear_model import LogisticRegression

rfe_selector = RFE(estimator=LogisticRegression(),

n_features_to_select=num_feats, step=10, verbose=5)

rfe_selector.fit(X_norm, y)

rfe_support = rfe_selector.get_support()

rfe_feature = X.loc[:,rfe_support].columns.tolist()

print(str(len(rfe_feature)), 'selected features')from sklearn.feature_selection import RFE

from sklearn.linear_model import LogisticRegression

#遞歸特征消除法，返回特征選擇后的數(shù)據(jù)

#參數(shù)estimator為基模型

#參數(shù)n_features_to_select為選擇的特征個(gè)數(shù)

RFE(estimator=LogisticRegression(), n_features_to_select=2).fit_transform(iris.data,iris.target)

套索：SelectFromModel

Lasso和RF都有自己的特征選擇方法。Lasso正則化器強(qiáng)制許多特征權(quán)重為零from sklearn.feature_selection import Select

FromModelfrom sklearn.linear_model import LogisticRegression

embeded_lr_selector = SelectFromModel(LogisticRegression(penalty="l1"),

max_features=num_feats)

embeded_lr_selector.fit(X_norm, y)

embeded_lr_support = embeded_lr_selector.get_support()

embeded_lr_feature = X.loc[:,embeded_lr_support].columns.tolist()

print(str(len(embeded_lr_feature)), 'selected features')

基于樹(shù)形結(jié)構(gòu)：SelectFromModel

使用隨機(jī)森林，根據(jù)特征的重要性來(lái)選擇特征, 使用每個(gè)決策樹(shù)中的節(jié)點(diǎn)雜質(zhì)來(lái)計(jì)算特征的重要性。隨機(jī)森林中，最終的特征重要性是所有決策樹(shù)特征重要性的平均值。from sklearn.feature_selection import SelectFromModel

from sklearn.ensemble import RandomForestClassifier

embeded_rf_selector =

SelectFromModel(RandomForestClassifier(n_estimators=100),

max_features=num_feats)

embeded_rf_selector.fit(X, y)e

mbeded_rf_support = embeded_rf_selector.get_support()

embeded_rf_feature = X.loc[:,embeded_rf_support].columns.tolist()

print(str(len(embeded_rf_feature)), 'selected features')

結(jié)合GBDT模型from sklearn.feature_selection import SelectFromModel

from sklearn.ensemble import GradientBoostingClassifier

#GBDT作為基模型的特征選擇

SelectFromModel(GradientBoostingClassifier()).fit_transform(iris.data, iris.target)

可以使用 LightGBM或者XGBoost 對(duì)象，只要它有feature_importances_屬性from sklearn.feature_selection import SelectFromModel

from lightgbm import LGBMClassifier

gbc=LGBMClassifier(n_estimators=500, learning_rate=0.05,

num_leaves=32, colsample_bytree=0.2,

reg_alpha=3, reg_lambda=1, min_split_gain=0.01,

min_child_weight=40)

embeded_lgb_selector = SelectFromModel(lgbc, max_features=num_feats)

embeded_lgb_selector.fit(X, y)

embeded_lgb_support = embeded_lgb_selector.get_support()

embeded_lgb_feature = X.loc[:,embeded_lgb_support].columns.tolist()

print(str(len(embeded_lgb_feature)), 'selected features'

總結(jié)

全部使用# put all selection together

feature_selection_df = pd.DataFrame({'Feature':feature_name,

'Pearson':cor_support, 'Chi-2':chi_support, 'RFE':rfe_support,

'Logistics':embeded_lr_support,

'Random Forest':embeded_rf_support,

'LightGBM':embeded_lgb_support})

# count the selected times for each feature

feature_selection_df['Total'] = np.sum(feature_selection_df, axis=1)

# display the top 100

feature_selection_df =

feature_selection_df.sort_values(['Total','Feature'] , ascending=False)

feature_selection_df.index = range(1, len(feature_selection_df)+1)

feature_selection_df.head(num_feats)

functionComputeSMA(data,window_size)

https://www.jianshu.com/p/ddcc51dfc578

總結(jié)

以上是生活随笔為你收集整理的python 特征选择卡方_特征选择的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。