def create_stats(x_train, x_test, y_train, y_test):
l1, y_pred_l1, lasso_stats = lasso(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
l2, y_pred_l2, ridge_stats = ridge(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
features = feature_selection(x_train, y_train, k=50)
x_trainft = x_train[features].copy()
x_testft = x_test[features].copy()
l1ft, y_pred_l1ft, lasso_statsft = lasso(x_trainft,
x_testft,
y_train,
y_test,
alpha=0.1)
l2ft, y_pred_l2ft, ridge_statsft = ridge(x_trainft,
x_testft,
y_train,
y_test,
alpha=0.1)
complete_stats = pd.concat(
[lasso_stats, lasso_statsft, ridge_stats, ridge_statsft])
return complete_stats
def create_stats(x_train, x_test, y_train, y_test):
features = feature_selection(x_train, y_train, 50)
x_train_ft = x_train[features]
x_test_ft = x_test[features]
_, _, stats_lasso = lasso(x_train, x_test, y_train, y_test)
_, _, stats_lasso_ft = lasso(x_train_ft, x_test_ft, y_train, y_test)
_, _, stats_ridge = ridge(x_train, x_test, y_train, y_test)
_, _, stats_ridge_ft = ridge(x_train_ft, x_test_ft, y_train, y_test)
complete_stats = pd.concat([stats_lasso,stats_lasso_ft,stats_ridge,stats_ridge_ft])
return complete_stats
def create_stats(x_train, x_test, y_train, y_test):
ft = feature_selection(x_train,y_train,50)
model_Lasso,preds_lasso,stats_lasso = lasso(x_train, x_test, y_train, y_test)
model_Lasso_ft,pred_lasso_ft,stats_lasso_ft = lasso(x_train.loc[:,ft],x_test.loc[:,ft],y_train,y_test)
model_Ridge,preds_ridge,stats_ridge = ridge(x_train, x_test, y_train, y_test)
model_Ridge_ft,preds_ridge_ft,stats_ridge_ft = ridge(x_train.loc[:,ft],x_test.loc[:,ft],y_train,y_test)
complete_stats = pd.concat([stats_lasso,stats_lasso_ft,stats_ridge,stats_ridge_ft])
return complete_stats
def create_stats(x_train, x_test, y_train, y_test, enc="labelencoder"):
#Call basic model (Linear, Lasso and Ridge)
lm_model, lm_y_pred, lm_stats = linear_model(x_train, x_test, y_train,
y_test, 0.01)
la_model, la_y_pred, la_stats = lasso(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
ri_model, ri_y_pred, ri_stats = ridge(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
#Filter Best feature using K percentile
feat_sel = feature_selection(x_train, y_train, k=50)
x_train = x_train[feat_sel]
x_test = x_test[feat_sel]
#Call basic model with selected features only (Linear, Lasso and Ridge)
lm_model_fs, lm_y_pred_fs, lm_stats_fs = linear_model(
x_train, x_test, y_train, y_test, 0.01)
la_model_fs, la_y_pred_fs, la_stats_fs = lasso(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
ri_model_fs, ri_y_pred_fs, ri_stats_fs = ridge(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
#Concate the returned response.
complete_stats = pd.concat(
[lm_stats, lm_stats_fs, la_stats, la_stats_fs, ri_stats, ri_stats_fs])
complete_stats.index = [
'lm_score', 'lm_features_score', 'la_score', 'la_features_score',
'ri_score', 'ri_features_score'
]
#Rmse and mse for certain models are NaN. need to fill with zeros.
complete_stats[['rmse', 'mse']] = complete_stats[['rmse', 'mse']].fillna(0)
complete_stats.mse += complete_stats.rmse
complete_stats = complete_stats.drop(['rmse'], axis=1)
return complete_stats
def create_stats(x_train, x_test, y_train, y_test):
lasso_stats = lasso(x_train, x_test, y_train, y_test, alpha=0.1)[2]
lasso_f_ft = feature_selection(x_train, y_train, k=50)
lasso_stats_ft = lasso(x_train[lasso_f_ft],
x_test[lasso_f_ft],
y_train,
y_test,
alpha=0.1)[2]
ridge_stats = ridge(x_train, x_test, y_train, y_test, alpha=0.1)[2]
ridge_f_ft = feature_selection(x_train, y_train, k=50)
ridge_stats_ft = ridge(x_train[ridge_f_ft],
x_test[ridge_f_ft],
y_train,
y_test,
alpha=0.1)[2]
complete_stats = pd.concat(
[lasso_stats, lasso_stats_ft, ridge_stats, ridge_stats_ft], axis=1)
return complete_stats
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 create_stats(x_train, x_test, y_train, y_test):
# lin_model, y_pred_lin, stats_lin = linear_model(x_train, x_test, y_train, y_test)
# plot_residuals(y_test,y_pred,"images/linear baseline "+enc)
lasso_model, y_pred_lasso, stats_lasso = lasso(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
# plot_residuals(y_test,y_pred,"images/lasso baseline "+enc)
ridge_model, y_pred_ridge, stats_ridge = ridge(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
# plot_residuals(y_test,y_pred,"images/ridge baseline "+enc)
feature_list = feature_selection(x_train, y_train, 50)
x_train = x_train[feature_list]
x_test = x_test[feature_list]
# lin_model_new, y_pred_lin_new, stats_lin_ft_new = linear_model(x_train, x_test, y_train, y_test)
# plot_residuals(y_test,y_pred,"images/linear ft "+enc)
lasso_model_new, y_pred_lasso_new, stats_lasso_ft_new = lasso(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
# plot_residuals(y_test,y_pred,"images/lasso ft "+enc)
ridge_model_new, y_pred_ridge_new, stats_ridge_ft_new = ridge(x_train,
x_test,
y_train,
y_test,
alpha=0.1)
# plot_residuals(y_test,y_pred,"images/ridge ft "+enc)
complete_stats = pd.concat(
[stats_lasso, stats_lasso_ft_new, stats_ridge, stats_ridge_ft_new])
return complete_stats
def create_stats(x_train, x_test, y_train, y_test):
lasso_modl, lasso_y_pred, lasso_stat = lasso(x_train, x_test, y_train,
y_test, 0.1)
ridge_modl, ridge_y_pred, ridge_stat = ridge(x_train, x_test, y_train,
y_test, 0.1)
features = feature_selection(x_train, y_train, k=50)
x_train_ft = x_train[features].copy()
x_test_ft = x_test[features].copy()
lasso_modl_ft, lasso_y_pred_ft, lasso_stat_ft = lasso(
x_train_ft, x_test_ft, y_train, y_test, 0.1)
ridge_modl_ft, ridge_y_pred_ft, ridge_stat_ft = ridge(
x_train_ft, x_test_ft, y_train, y_test, 0.1)
features = feature_selection(x_train_ft, y_train, k=50)
complete_stats = pd.concat(
[lasso_stat, lasso_stat_ft, ridge_stat, ridge_stat_ft])
return complete_stats
def create_stats(X_train, X_test, y_train, y_test, enc="labelencoder"):
a, b, lm_score = linear_model(X_train, X_test, y_train, y_test, '')
c, d, lasso_score = lasso(X_train, X_test, y_train, y_test)
e, f, ridge_score = ridge(X_train, X_test, y_train, y_test)
best_features = feature_selection(X_train, y_train, k=50)
a, b, lm_score_bf = linear_model(X_train[best_features],
X_test[best_features], y_train, y_test,
'')
c, d, lasso_score_bf = lasso(X_train[best_features], X_test[best_features],
y_train, y_test)
e, f, ridge_score_bf = ridge(X_train[best_features], X_test[best_features],
y_train, y_test)
complete_stats = pd.concat([
lm_score, lasso_score, ridge_score, lm_score_bf, lasso_score_bf,
ridge_score_bf
],
ignore_index=True)
del complete_stats['rmse']
return complete_stats #lm_score,lasso_score,ridge_score,lm_score_bf,lasso_score_bf,ridge_score_bf