Save results.

.gitignore

@@ -9,3 +9,5 @@ __pycache__/
 /data/features/
 /data/baseline/
 /data/*input*.csv
+/data/daily*
+/data/intradaily*

machine_learning/final_results/results_presentation.ipynb

@@ -16,7 +16,6 @@ from sklearn.metrics import mean_squared_error, r2_score
 from sklearn.impute import SimpleImputer
 from sklearn.dummy import DummyRegressor
 from sklearn.decomposition import PCA
-import xgboost as xg
 from IPython.core.interactiveshell import InteractiveShell
 InteractiveShell.ast_node_interactivity = "all"
 
@@ -27,7 +26,10 @@ if nb_dir not in sys.path:
 import machine_learning.helper
 
 # %%
-csv_name = "./data/daily_18_hours_all_targets/input_JCQ_job_demand_mean.csv"
+segment = "intradaily_30_min"
+target = "JCQ_job_demand"
+csv_name = "./data/" + segment + "_all_targets/input_" + target + "_mean.csv"
+#csv_name = "./data/daily_18_hours_all_targets/input_JCQ_job_demand_mean.csv"
 
 # %%
 data_x, data_y, data_groups = machine_learning.helper.prepare_model_input(csv_name)
@@ -66,7 +68,9 @@ print("Negative Mean Absolute Error", np.median(lin_reg_scores['test_neg_mean_ab
 print("Negative Root Mean Squared Error", np.median(lin_reg_scores['test_neg_root_mean_squared_error']))
 print("R2", np.median(lin_reg_scores['test_r2']))
 
+##################
 # %%
+chosen_model = "Random Forest"
 rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
 rfr_score = cross_validate(
     rfr,
@@ -84,13 +88,25 @@ print("R2", np.median(rfr_score['test_r2']))
 
 # %%
 y_predicted = cross_val_predict(rfr, data_x, data_y, groups=data_groups, cv=logo)
+#########################
+# %%
+chosen_model = "Bayesian Ridge"
+bayesian_ridge_reg = linear_model.BayesianRidge()
+bayesian_ridge_reg_score = cross_validate(
+    bayesian_ridge_reg,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=logo,
+    n_jobs=-1,
+    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
+)
+print("Negative Mean Absolute Error", np.median(bayesian_ridge_reg_score['test_neg_mean_absolute_error']))
+print("Negative Root Mean Squared Error", np.median(bayesian_ridge_reg_score['test_neg_root_mean_squared_error']))
+print("R2", np.median(bayesian_ridge_reg_score['test_r2']))
 
 # %%
-g1 = sns.relplot(data=data_y, x="y_true", y="y_predicted")
+y_predicted = cross_val_predict(bayesian_ridge_reg, data_x, data_y, groups=data_groups, cv=logo)
-#g1.set_axis_labels("true", "predicted")
-g1.set(title="Negative affect, Random Forest")
-display(g1)
-g1.savefig("d18NArfr_relplot.pdf")
 
 # %%
 data_y = pd.DataFrame(pd.concat([data_y, data_groups], axis=1))
@@ -100,6 +116,14 @@ data_y["y_predicted"] = y_predicted
 # %%
 data_y.head()
 
+# %%
+g1 = sns.relplot(data=data_y, x="y_true", y="y_predicted")
+#g1.set_axis_labels("true", "predicted")
+#g1.map(plt.axhline, y=0, color=".7", dashes=(2, 1), zorder=0)
+#g1.map(plt.axline, xy1=(0,0), slope=1)
+g1.set(title=",".join([segment, target, chosen_model]))
+display(g1)
+g1.savefig("_".join([segment, target, chosen_model, "_relplot.pdf"]))
 
 # %%
 data_y_long = pd.wide_to_long(
@@ -116,8 +140,8 @@ data_y_long.head()
 # %%
 g2 = sns.displot(data_y_long, x="y", hue="value", binwidth=0.1, height=5, aspect=1.5)
 sns.move_legend(g2, "upper left", bbox_to_anchor=(.55, .45))
-g2.set(title="Negative affect, Random Forest")
+g2.set(title=",".join([segment, target, chosen_model]))
-g2.savefig("d18NArfr_hist.pdf")
+g2.savefig("_".join([segment, target, chosen_model, "hist.pdf"]))
 
 # %%
 pca = PCA(n_components=2)
@@ -133,6 +157,7 @@ data_pca
 # %%
 
 g3 = sns.relplot(data = data_pca, x = "pca_0", y = "pca_1", hue = "y_true", palette = sns.color_palette("Spectral", as_cmap=True))
-g3.savefig("d18NArfr_PCA.pdf")
+g3.set(title=",".join([segment, target, chosen_model]) + "\n variance explained = " + str(round(sum(pca.explained_variance_ratio_), 2)))
+g3.savefig("_".join([segment, target, chosen_model, "_PCA.pdf"]))
 
 # %%