网站界面可以做版权吗网络推广营销方案免费

from sklearn.feature_selection import VarianceThreshold
data = .
var_thresh = VarianceThreshold(threshold=0.1)
transformed_data = var_thresh.fit_transform(data)

import pandas as pd
from sklearn.datasets import fetch_california_housing
data = fetch_california_housing()
X = data["data"]
col_names = data["feature_names"]
y = data["target"]
df = pd.DataFrame(X, columns=col_names)
df.loc[:, "MedInc_Sqrt"] = df.MedInc.apply(np.sqrt)
df.corr()

得出相关矩阵，如图 1 所⽰。 

from sklearn.feature_selection import chi2
from sklearn.feature_selection import f_classif
from sklearn.feature_selection import f_regression
from sklearn.feature_selection import mutual_info_classif
from sklearn.feature_selection import mutual_info_regression
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import SelectPercentileclass UnivariateFeatureSelction:def __init__(self, n_features, problem_type, scoring):if problem_type == "classification":valid_scoring = {"f_classif": f_classif,"chi2": chi2,"mutual_info_classif": mutual_info_classif}else:valid_scoring = {"f_regression": f_regression,"mutual_info_regression": mutual_info_regression}if scoring not in valid_scoring:raise Exception("Invalid scoring function")if isinstance(n_features, int):self.selection = SelectKBest(valid_scoring[scoring],k=n_features)elif isinstance(n_features, float):self.selection = SelectPercentile(valid_scoring[scoring],percentile=int(n_features * 100))else:raise Exception("Invalid type of feature")def fit(self, X, y):return self.selection.fit(X, y)def transform(self, X):return self.selection.transform(X)def fit_transform(self, X, y):return self.selection.fit_transform(X, y)

使⽤该类⾮常简单。

# Example usage:
ufs = UnivariateFeatureSelction(n_features=0.1,problem_type="regression",scoring="f_regression"
)
ufs.fit(X, y)
X_transformed = ufs.transform(X)

import pandas as pd
from sklearn import linear_model
from sklearn import metrics
from sklearn.datasets import make_classificationclass GreedyFeatureSelection:def evaluate_score(self, X, y):model = linear_model.LogisticRegression()model.fit(X, y)predictions = model.predict_proba(X)[:, 1]auc = metrics.roc_auc_score(y, predictions)return aucdef _feature_selection(self, X, y):good_features = []best_scores = []num_features = X.shape[1]while True:this_feature = Nonebest_score = 0for feature in range(num_features):if feature in good_features:continueselected_features = good_features + [feature]xtrain = X[:, selected_features]score = self.evaluate_score(xtrain, y)if score > best_score:this_feature = featurebest_score = scoreif this_feature is None:breakgood_features.append(this_feature)best_scores.append(best_score)if len(best_scores) > 1:if best_scores[-1] < best_scores[-2]:breakreturn best_scores[:-1], good_features[:-1]def __call__(self, X, y):scores, features = self._feature_selection(X, y)return X[:, features], scoresif __name__ == "__main__":X, y = make_classification(n_samples=1000, n_features=100)X_transformed, scores = GreedyFeatureSelection()(X, y)

import pandas as pd
from sklearn.feature_selection import RFE
from sklearn.linear_model import LinearRegression
from sklearn.datasets import fetch_california_housingdata = fetch_california_housing()
X = data["data"]
col_names = data["feature_names"]
y = data["target"]model = LinearRegression()
rfe = RFE(estimator=model,n_features_to_select=3
)
rfe.fit(X, y)
X_transformed = rfe.transform(X)

import pandas as pd
from sklearn.datasets import load_diabetes
from sklearn.ensemble import RandomForestRegressor
data = load_diabetes()
X = data["data"]
col_names = data["feature_names"]
y = data["target"]
model = RandomForestRegressor()
model.fit(X, y)

随机森林（或任何模型）的特征重要性可按如下⽅式绘制。

importances = model.feature_importances_
idxs = np.argsort(importances)
plt.title('Feature Importances')
plt.barh(range(len(idxs)), importances[idxs], align='center')
plt.yticks(range(len(idxs)), [col_names[i] for i in idxs])
plt.xlabel('Random Forest Feature Importance')
plt.show()

 结果如图 3 所⽰。

import pandas as pd
from sklearn.datasets import load_diabetes
from sklearn.ensemble import RandomForestRegressor
from sklearn.feature_selection import SelectFromModel
data = load_diabetes()
X = data["data"]
col_names = data["feature_names"]
y = data["target"]
model = RandomForestRegressor()
sfm = SelectFromModel(estimator=model)
X_transformed = sfm.fit_transform(X, y)
support = sfm.get_support()
print([x for x, y in zip(col_names, support) if y = True ])