Free up memory during model building.

machine_learning/helper.py

@@ -191,10 +191,12 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "dummy"
     scores = pd.concat([scores, scores_df])
+    del dummy_regr
+    del dummy_regr_scores
 
-    lin_reg_rapids = linear_model.LinearRegression()
+    lin_reg = linear_model.LinearRegression()
     lin_reg_scores = cross_validate(
-        lin_reg_rapids,
+        lin_reg,
         X=data_x,
         y=data_y,
         groups=data_groups,
@@ -209,6 +211,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "linear_reg"
     scores = pd.concat([scores, scores_df])
+    del lin_reg
+    del lin_reg_scores
 
     ridge_reg = linear_model.Ridge(alpha=0.5)
     ridge_reg_scores = cross_validate(
@@ -226,6 +230,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "ridge_reg"
     scores = pd.concat([scores, scores_df])
+    del ridge_reg
+    del ridge_reg_scores
 
     lasso_reg = linear_model.Lasso(alpha=0.1)
     lasso_reg_score = cross_validate(
@@ -243,6 +249,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "lasso_reg"
     scores = pd.concat([scores, scores_df])
+    del lasso_reg
+    del lasso_reg_score
 
     bayesian_ridge_reg = linear_model.BayesianRidge()
     bayesian_ridge_reg_score = cross_validate(
@@ -260,6 +268,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "bayesian_ridge"
     scores = pd.concat([scores, scores_df])
+    del bayesian_ridge_reg
+    del bayesian_ridge_reg_score
 
     ransac_reg = linear_model.RANSACRegressor()
     ransac_reg_score = cross_validate(
@@ -277,6 +287,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "RANSAC"
     scores = pd.concat([scores, scores_df])
+    del ransac_reg
+    del ransac_reg_score
 
     svr = svm.SVR()
     svr_score = cross_validate(
@@ -294,6 +306,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "SVR"
     scores = pd.concat([scores, scores_df])
+    del svr
+    del svr_score
 
     kridge = kernel_ridge.KernelRidge()
     kridge_score = cross_validate(
@@ -311,6 +325,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "kernel_ridge"
     scores = pd.concat([scores, scores_df])
+    del kridge
+    del kridge_score
 
     gpr = gaussian_process.GaussianProcessRegressor()
     gpr_score = cross_validate(
@@ -328,6 +344,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "gaussian_proc"
     scores = pd.concat([scores, scores_df])
+    del gpr
+    del gpr_score
 
     rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
     rfr_score = cross_validate(
@@ -345,6 +363,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "random_forest"
     scores = pd.concat([scores, scores_df])
+    del rfr
+    del rfr_score
 
     xgb = XGBRegressor()
     xgb_score = cross_validate(
@@ -362,6 +382,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "XGBoost"
     scores = pd.concat([scores, scores_df])
+    del xgb
+    del xgb_score
 
     ada = ensemble.AdaBoostRegressor()
     ada_score = cross_validate(
@@ -379,6 +401,8 @@ def run_all_regression_models(
     scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "ADA_boost"
     scores = pd.concat([scores, scores_df])
+    del ada
+    del ada_score
 
     return scores