Ayushijain09

1. Mutual Information
2. Chi Square
3. ANOVA
4. Pearson , Spearman, Kendall Correlation
5. Tree Model
6. Sequential Feature Selection
7. Variance Threshold
8. Recursive Feature Elimination

Ayushijain09

from sklearn.tree import DecisionTreeRegressor

model = DecisionTreeRegressor()
# fit the model
model.fit(X_train, y_train)
# get importance
importance = model.feature_importances_
# summarize feature importance
impList = zip(X_train.columns, importance)
for feature in sorted(impList, key = lambda t: t[1], reverse=True):

Ayushijain09

from sklearn.linear_model import Lasso
from sklearn.model_selection import GridSearchCV

lasso= Lasso()
parameters = {'alpha':[1e-15, 1e-10, 1e-8, 1e-4,1e-3,1e-2,1,3,5]}
lasso_model = GridSearchCV(lasso, parameters, scoring = 'r2',cv=5) 
lasso_model.fit(X_train,y_train)  
pred = lasso_model.predict(X_test)
print(lasso_model.best_params_)   #output {'alpha': 0.001}
print(lasso_model.best_score_)    #output 0.8630550401365724

Ayushijain09

from sklearn.feature_selection import RFE
lm = LinearRegression()
rfe1 = RFE(lm, 20)   # RFE with 20 features

# Fit on train and test data with 20 features
X_train_new = rfe1.fit_transform(X_train, y_train)
X_test_new = rfe1.transform(X_test)

# Print the boolean results
print(rfe1.support_)       # Output [False False False False  True False False False  True False False...]

Ayushijain09

from mlxtend.feature_selection import SequentialFeatureSelector
sfs = SequentialFeatureSelector(LinearRegression(),         # cv = k-fold cross validation, floating is another extension of SFS, not used here
           k_features=10, 
           forward=True, 
           floating=False,
           scoring='accuracy',
           cv=2)   
sfs = sfs.fit(X_train, y_train)

selected_features = x_train.columns[list(sfs.k_feature_idx_)]

Ayushijain09

from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression

fvalue_selector = SelectKBest(f_regression, k=20)  #select features with 20 best ANOVA F-Values
X_train_new = fvalue_selector.fit_transform(X_train, y_train)
print(X_train.shape, X_train_new.shape)     #output (143, 59) (143, 20)

Ayushijain09

from sklearn.feature_selection import mutual_info_regression  
from sklearn.feature_selection import SelectKBest
selector = SelectKBest(mutual_info_regression, k=10)
X_train_new = selector.fit_transform(X_train, y_train)  #Applying transformation to the training set
#to get names of the selected features
mask = selector.get_support()     # Output   array([False, False,  True,  True,  True, False ....])

print(selector.scores_)     #Output array([0.16978127, 0.01829886, 0.45461366, 0.55126343, 0.66081217, 0.27715287 ....])

new_features = X_train.columns[mask]

Ayushijain09

print(df_train.isnull().sum()/len(df_train)*100).nlargest())
#output => Returns the 5 largest values from the series. No missing values in automobile dataset, so all shows 0%.
"""symboling     0.0
   doornumber    0.0
   wheelbase     0.0
   carlength     0.0
   carwidth      0.0
   dtype: float64"""

Ayushijain09

from sklearn.feature_selection import SelectKBest 
from sklearn.feature_selection import chi2 
X_train = X_train.astype(int) 
chi2_features = SelectKBest(chi2 , k=12) 
X_kbest_features = chi2_features.fit_transform(X_train, y_train) 

Ayushijain09

from sklearn.feature_selection import VarianceThreshold
print(df_train.shape)     #output (143, 59)
var_filter = VarianceThreshold(threshold = 0.0)  
train = var_filter.fit_transform(df_train)
#to get the count of features that are not constant
print(train.shape())    # output (143, 56)       
#or
print(len(df_train.columns[var_filter.get_support()]))  #output 56