y_train = house_train['SalePrice']
sns.distplot(y_train, hist=True)
y_trans = np.log1p(y_train)
sns.distplot(y_trans, hist=True)
scoring = metrics.make_scorer(log_rmse, greater_is_better=False)
#union of 3 feature selectors
lasso_estimator = linear_model.Lasso()
lasso_grid = {'alpha': [0.001, 0.005, 0.01, 0.05, 0.1, 0.2, 0.5]}
lasso_selector = get_best_model(lasso_estimator,
lasso_grid,
X_train,
y_trans,
scoring=scoring)
plot_feature_importances(lasso_selector, X_train, 50)
important_features_lasso = get_important_features(lasso_selector, X_train)
rf_estimator = ensemble.RandomForestRegressor(random_state=100)
rf_grid = {
'n_estimators': list(range(100, 501, 200)),
'max_features': [14, 16, 18, 20],
'max_depth': [3, 5, 7]
}
rf_selector = get_best_model(rf_estimator,
rf_grid,
X_train,
y_trans,
scoring=scoring)
plot_feature_importances(rf_selector, X_train, 50)
important_features_rf = get_important_features(rf_selector, X_train)
X_train = utils.ohe(titanic_train1, cat_features)
y_train = titanic_train['Survived']
#embedded feature selectors
rf_estimator = ensemble.RandomForestClassifier()
rf_grid = {
'max_depth': list(range(1, 9)),
'n_estimators': list(range(1, 300, 100))
}
rf_final_estimator = cutils.grid_search_best_model(rf_estimator, rf_grid,
X_train, y_train)
embedded_selector = feature_selection.SelectFromModel(rf_final_estimator,
prefit=True,
threshold='mean')
X_train1 = embedded_selector.transform(X_train)
utils.plot_feature_importances(rf_final_estimator, X_train)
gb_estimator = ensemble.GradientBoostingClassifier()
gb_grid = {
'max_depth': [1, 2, 3],
'n_estimators': list(range(50, 300, 100)),
'learning_rate': [0.001, 0.1, 1.0]
}
gb_final_estimator = cutils.grid_search_best_model(gb_estimator, gb_grid,
X_train, y_train)
embedded_selector = feature_selection.SelectFromModel(gb_final_estimator,
prefit=True,
threshold='mean')
X_train1 = embedded_selector.transform(X_train)
utils.plot_feature_importances(gb_final_estimator, X_train)
house1[imputable_cont_features]) house1.info() house2 = utils.ohe(house1, imputable_cat_features) scaler = utils.get_scaler(house2) house3 = scaler.transform(house2) house3 = pd.DataFrame(house3, columns=house2.columns) X_train = house3[:house_train.shape[0]] y_train = house_train['SalePrice'] lasso_selector = linear_model.Lasso() lasso_selector.fit(X_train, y_train) print(lasso_selector.coef_) utils.plot_feature_importances(lasso_selector, X_train, 40) X_train1 = utils.select_features(lasso_selector, X_train) utils.corr_heatmap(X_train1) lpca = decomposition.PCA(0.95) lpca.fit(X_train1) print(np.cumsum(lpca.explained_variance_ratio_)) pca_data = lpca.transform(X_train1) print(pca_data.shape) tsne = manifold.TSNE(n_components=2) tsne_data = tsne.fit_transform(pca_data) rutils.plot_data_3d_regression(tsne_data, y_train) scoring = metrics.make_scorer(log_rmse, greater_is_better=False)
#filter zero-variance features
variance = feature_selection.VarianceThreshold()
train2 = variance.fit_transform(train1)
#embedded feature selection
rf_estimator = ensemble.RandomForestClassifier()
rf_grid = {
'max_depth': list(range(1, 9)),
'n_estimators': list(range(1, 300, 100))
}
rf_final_estimator = cutils.grid_search_best_model(rf_estimator, rf_grid,
train1, y)
embedded_selector = feature_selection.SelectFromModel(rf_final_estimator,
prefit=True,
threshold='mean')
utils.plot_feature_importances(rf_final_estimator, train1, cutoff=50)
train2 = embedded_selector.transform(train1)
#statistical feature selection
statistical_selector = feature_selection.SelectKBest(
feature_selection.f_classif, k=20)
train2 = statistical_selector.fit_transform(train1, y)
print(statistical_selector.scores_)
#recursive feature elimination(rfe)
rf_estimator = ensemble.RandomForestClassifier()
rfe_selector = feature_selection.RFE(rf_estimator,
n_features_to_select=10,
step=5)
train2 = rfe_selector.fit_transform(train1, y)
print(rfe_selector.ranking_)