Question

这看起来是一个非常有用的代码示例，用于查找数据集的最佳/最差性能。唯一的问题是，我很难启动并运行“ statsmodels.api”。

此行：

import statsmodels.api as sm

引发此错误：

ImportError: cannot import name 'factorial' from 'scipy.misc'

我用Google搜索了一个解决方案，发现了一些基本的想法可以尝试，但实际上没有任何工作对我有用，所以我被困住了。

完整代码示例如下所示。

# https://towardsdatascience.com/feature-selection-with-pandas-e3690ad8504b

#importing libraries
from sklearn.datasets import load_boston
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
# %matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.feature_selection import RFE
from sklearn.linear_model import RidgeCV, LassoCV, Ridge, Lasso
#Loading the dataset
x = load_boston()
df = pd.DataFrame(x.data, columns = x.feature_names)
df["MEDV"] = x.target
X = df.drop("MEDV",1)   #Feature Matrix
y = df["MEDV"]          #Target Variable
df.head()


#Using Pearson Correlation
plt.figure(figsize=(12,10))
cor = df.corr()
sns.heatmap(cor, annot=True, cmap=plt.cm.Reds)
plt.show()


#Correlation with output variable
cor_target = abs(cor["MEDV"])
#Selecting highly correlated features
relevant_features = cor_target[cor_target>0.5]
relevant_features


print(df[["LSTAT","PTRATIO"]].corr())
print(df[["RM","LSTAT"]].corr())


#Adding constant column of ones, mandatory for sm.OLS model
X_1 = sm.add_constant(X)
#Fitting sm.OLS model
model = sm.OLS(y,X_1).fit()
model.pvalues


#Backward Elimination
cols = list(X.columns)
pmax = 1
while (len(cols)>0):
    p= []
    X_1 = X[cols]
    X_1 = sm.add_constant(X_1)
    model = sm.OLS(y,X_1).fit()
    p = pd.Series(model.pvalues.values[1:],index = cols)      
    pmax = max(p)
    feature_with_p_max = p.idxmax()
    if(pmax>0.05):
        cols.remove(feature_with_p_max)
    else:
        break
selected_features_BE = cols
print(selected_features_BE)


model = LinearRegression()
#Initializing RFE model
rfe = RFE(model, 7)
#Transforming data using RFE
X_rfe = rfe.fit_transform(X,y)  
#Fitting the data to model
model.fit(X_rfe,y)
print(rfe.support_)
print(rfe.ranking_)


#no of features
nof_list=np.arange(1,13)            
high_score=0
#Variable to store the optimum features
nof=0           
score_list = []
for n in range(len(nof_list)):
    X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.3, random_state = 0)
    model = LinearRegression()
    rfe = RFE(model,nof_list[n])
    X_train_rfe = rfe.fit_transform(X_train,y_train)
    X_test_rfe = rfe.transform(X_test)
    model.fit(X_train_rfe,y_train)
    score = model.score(X_test_rfe,y_test)
    score_list.append(score)
    if(score>high_score):
        high_score = score
        nof = nof_list[n]
print("Optimum number of features: %d" %nof)
print("Score with %d features: %f" % (nof, high_score))


cols = list(X.columns)
model = LinearRegression()
#Initializing RFE model
rfe = RFE(model, 10)             
#Transforming data using RFE
X_rfe = rfe.fit_transform(X,y)  
#Fitting the data to model
model.fit(X_rfe,y)              
temp = pd.Series(rfe.support_,index = cols)
selected_features_rfe = temp[temp==True].index
print(selected_features_rfe)


reg = LassoCV()
reg.fit(X, y)
print("Best alpha using built-in LassoCV: %f" % reg.alpha_)
print("Best score using built-in LassoCV: %f" %reg.score(X,y))
coef = pd.Series(reg.coef_, index = X.columns)


print("Lasso picked " + str(sum(coef != 0)) + " variables and eliminated the other " +  str(sum(coef == 0)) + " variables")


imp_coef = coef.sort_values()
import matplotlib
matplotlib.rcParams['figure.figsize'] = (8.0, 10.0)
imp_coef.plot(kind = "barh")
plt.title("Feature importance using Lasso Model")

这里的任何人以前都遇到过这个问题，实际上已经使它起作用了吗？如果是这样，请分享您的解决方案。 TIA。

特征选择或特征工程：存在的问题

0 个答案: