def feature_selection(x_train,y_train,k=50):
plot_corr(x_train)
reduced_features = percentile_k_features(x_train,y_train,k)
# print(reduced_features)
return reduced_features
def create_stats(X_train, X_test, y_train, y_test, enc="labelencoder"):
_, _, linear_model_scores = linear_model(X_train, X_test, y_train, y_test,
0.01)
_, _, lasso_scores = lasso(X_train, X_test, y_train, y_test)
_, _, ridge_scores = ridge(X_train, X_test, y_train, y_test)
selected_features = percentile_k_features(X_train, y_train, k=50)
X_train_features = X_train[selected_features]
X_test_features = X_test[selected_features]
_, _, linear_model_scores_features = linear_model(X_train_features,
X_test_features, y_train,
y_test, 0.01)
_, _, lasso_scores_features = lasso(X_train_features, X_test_features,
y_train, y_test)
_, _, ridge_scores_features = ridge(X_train_features, X_test_features,
y_train, y_test)
complete_stats = pd.concat([
linear_model_scores,
linear_model_scores_features,
#chain_stats_with_features_selection ,stats_chain,
lasso_scores,
lasso_scores_features,
ridge_scores,
ridge_scores_features
])
complete_stats.index = [
'linear_model_scores',
'linear_model_scores_features',
#chain_stats_with_features_selection ,stats_chain,
'lasso_scores',
'lasso_scores_features',
'ridge_scores',
'ridge_scores_features'
]
#complete_stats.columns=['Name', 'cross_validation','rmse','mae','r2']
complete_stats.mse = complete_stats.mse.fillna(0)
complete_stats.rmse = complete_stats.rmse.fillna(0)
complete_stats.rmse = complete_stats.mse + complete_stats.rmse
complete_stats = complete_stats.drop(['mse'], axis=1)
return complete_stats
def feature_selection(X,y,k=50):
feat = percentile_k_features(X, y, k)
return feat
def feature_selection(x_train,y_train,k=50):
plot_corr(pd.concat([x_train,y_train],axis=1))
ans = percentile_k_features(x_train,y_train,k)
return ans
def pick_features(X, y, k=50):
k_best_features = percentile_k_features(X, y, k)
return k_best_features
def feature_selection(X, y, k=50):
plot_corr(pd.concat([X, y], axis=1))
lst = percentile_k_features(X, y, k=50)
return lst
def feature_selection(x_train, y_train, k=50):
plot_corr(x_train, 11)
features= percentile_k_features(x_train, y_train, k=50)
return features
def feature_selection(X, y, k=50):
return percentile_k_features(X, y, k)
def feature_selection(x_train, y_train, k=50):
plot_corr(df, 11)
top_fea = percentile_k_features(x_train, y_train, 50)
return top_fea
def feature_selection(X, y, k=50):
plot_corr(X)
return percentile_k_features(X, y, k)
