Add xgboost to dependencies and reformat helper.py.

config/environment.yml

@@ -22,4 +22,5 @@ dependencies:
   - scikit-learn
   - sqlalchemy
   - statsmodels
-  - tabulate
+  - tabulate
+  - xgboost

machine_learning/helper.py

@@ -1,15 +1,18 @@
 from pathlib import Path
-from sklearn import linear_model, svm, kernel_ridge, gaussian_process, ensemble, naive_bayes, neighbors, tree
-from sklearn.model_selection import LeaveOneGroupOut, cross_validate, cross_validate
-from sklearn.metrics import mean_squared_error, r2_score
-from sklearn.impute import SimpleImputer
-from sklearn.dummy import DummyRegressor, DummyClassifier
 
-from xgboost import XGBRegressor, XGBClassifier
-import xgboost as xg
-
-import pandas as pd
 import numpy as np
+import pandas as pd
+from sklearn import (
+    ensemble,
+    gaussian_process,
+    kernel_ridge,
+    linear_model,
+    naive_bayes,
+    svm,
+)
+from sklearn.dummy import DummyClassifier, DummyRegressor
+from sklearn.model_selection import LeaveOneGroupOut, cross_validate
+from xgboost import XGBClassifier, XGBRegressor
 
 
 def safe_outer_merge_on_index(left: pd.DataFrame, right: pd.DataFrame) -> pd.DataFrame:
@@ -65,28 +68,48 @@ def construct_full_path(folder: Path, filename_prefix: str, data_type: str) -> P
     full_path = folder / export_filename
     return full_path
 
+
 def insert_row(df, row):
     return pd.concat([df, pd.DataFrame([row], columns=df.columns)], ignore_index=True)
 
-def prepare_regression_model_input(input_csv):
 
+def prepare_regression_model_input(input_csv):
     model_input = pd.read_csv(input_csv)
 
-    index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
+    index_columns = [
+        "local_segment",
+        "local_segment_label",
+        "local_segment_start_datetime",
+        "local_segment_end_datetime",
+    ]
     model_input.set_index(index_columns, inplace=True)
 
-    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+    data_x, data_y, data_groups = (
+        model_input.drop(["target", "pid"], axis=1),
+        model_input["target"],
+        model_input["pid"],
+    )
 
-    categorical_feature_colnames = ["gender", "startlanguage", "limesurvey_demand_control_ratio_quartile"]
+    categorical_feature_colnames = [
-    additional_categorical_features = [col for col in data_x.columns if "mostcommonactivity" in col or "homelabel" in col]
+        "gender",
+        "startlanguage",
+        "limesurvey_demand_control_ratio_quartile",
+    ]
+    additional_categorical_features = [
+        col
+        for col in data_x.columns
+        if "mostcommonactivity" in col or "homelabel" in col
+    ]
     categorical_feature_colnames += additional_categorical_features
-    #TODO: check whether limesurvey_demand_control_ratio_quartile NaNs could be replaced meaningfully
+    # TODO: check whether limesurvey_demand_control_ratio_quartile NaNs could be replaced meaningfully
     categorical_features = data_x[categorical_feature_colnames].copy()
     mode_categorical_features = categorical_features.mode().iloc[0]
     # fillna with mode
     categorical_features = categorical_features.fillna(mode_categorical_features)
     # one-hot encoding
-    categorical_features = categorical_features.apply(lambda col: col.astype("category"))
+    categorical_features = categorical_features.apply(
+        lambda col: col.astype("category")
+    )
     if not categorical_features.empty:
         categorical_features = pd.get_dummies(categorical_features)
 
@@ -108,7 +131,7 @@ def run_all_regression_models(input_csv):
         data_y,
         groups=data_groups,
     )
-    metrics = ['r2', 'neg_mean_absolute_error', 'neg_root_mean_squared_error']
+    metrics = ["r2", "neg_mean_absolute_error", "neg_root_mean_squared_error"]
     test_metrics = ["test_" + metric for metric in metrics]
     scores = pd.DataFrame(columns=["method", "max", "nanmedian"])
 
@@ -121,13 +144,13 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Dummy model:")
-    print("R^2: ", np.nanmedian(dummy_regr_scores['test_r2']))
+    print("R^2: ", np.nanmedian(dummy_regr_scores["test_r2"]))
-    
+
     scores_df = pd.DataFrame(dummy_regr_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "dummy"
     scores = pd.concat([scores, scores_df])
 
@@ -139,17 +162,17 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Linear regression:")
-    print("R^2: ", np.nanmedian(lin_reg_scores['test_r2']))
+    print("R^2: ", np.nanmedian(lin_reg_scores["test_r2"]))
 
     scores_df = pd.DataFrame(lin_reg_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "linear_reg"
     scores = pd.concat([scores, scores_df])
 
-    ridge_reg = linear_model.Ridge(alpha=.5)
+    ridge_reg = linear_model.Ridge(alpha=0.5)
     ridge_reg_scores = cross_validate(
         ridge_reg,
         X=data_x,
@@ -157,16 +180,15 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Ridge regression")
 
     scores_df = pd.DataFrame(ridge_reg_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "ridge_reg"
     scores = pd.concat([scores, scores_df])
 
-
     lasso_reg = linear_model.Lasso(alpha=0.1)
     lasso_reg_score = cross_validate(
         lasso_reg,
@@ -175,12 +197,12 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Lasso regression")
 
     scores_df = pd.DataFrame(lasso_reg_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "lasso_reg"
     scores = pd.concat([scores, scores_df])
 
@@ -192,12 +214,12 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Bayesian Ridge")
 
     scores_df = pd.DataFrame(bayesian_ridge_reg_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "bayesian_ridge"
     scores = pd.concat([scores, scores_df])
 
@@ -209,29 +231,23 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("RANSAC (outlier robust regression)")
 
     scores_df = pd.DataFrame(ransac_reg_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "RANSAC"
     scores = pd.concat([scores, scores_df])
 
     svr = svm.SVR()
     svr_score = cross_validate(
-        svr,
+        svr, X=data_x, y=data_y, groups=data_groups, cv=logo, n_jobs=-1, scoring=metrics
-        X=data_x,
-        y=data_y,
-        groups=data_groups,
-        cv=logo,
-        n_jobs=-1,
-        scoring=metrics
     )
     print("Support vector regression")
-    
+
     scores_df = pd.DataFrame(svr_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "SVR"
     scores = pd.concat([scores, scores_df])
 
@@ -243,80 +259,56 @@ def run_all_regression_models(input_csv):
         groups=data_groups,
         cv=logo,
         n_jobs=-1,
-        scoring=metrics
+        scoring=metrics,
     )
     print("Kernel Ridge regression")
-    
+
     scores_df = pd.DataFrame(kridge_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "kernel_ridge"
     scores = pd.concat([scores, scores_df])
 
     gpr = gaussian_process.GaussianProcessRegressor()
     gpr_score = cross_validate(
-        gpr,
+        gpr, X=data_x, y=data_y, groups=data_groups, cv=logo, n_jobs=-1, scoring=metrics
-        X=data_x,
-        y=data_y,
-        groups=data_groups,
-        cv=logo,
-        n_jobs=-1,
-        scoring=metrics
     )
     print("Gaussian Process Regression")
 
     scores_df = pd.DataFrame(gpr_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "gaussian_proc"
     scores = pd.concat([scores, scores_df])
 
     rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
     rfr_score = cross_validate(
-        rfr,
+        rfr, X=data_x, y=data_y, groups=data_groups, cv=logo, n_jobs=-1, scoring=metrics
-        X=data_x,
-        y=data_y,
-        groups=data_groups,
-        cv=logo,
-        n_jobs=-1,
-        scoring=metrics
     )
     print("Random Forest Regression")
 
     scores_df = pd.DataFrame(rfr_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "random_forest"
     scores = pd.concat([scores, scores_df])
 
     xgb = XGBRegressor()
     xgb_score = cross_validate(
-        xgb,
+        xgb, X=data_x, y=data_y, groups=data_groups, cv=logo, n_jobs=-1, scoring=metrics
-        X=data_x,
-        y=data_y,
-        groups=data_groups,
-        cv=logo,
-        n_jobs=-1,
-        scoring=metrics
     )
     print("XGBoost Regressor")
 
     scores_df = pd.DataFrame(xgb_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "XGBoost"
     scores = pd.concat([scores, scores_df])
 
     ada = ensemble.AdaBoostRegressor()
     ada_score = cross_validate(
-        ada,
+        ada, X=data_x, y=data_y, groups=data_groups, cv=logo, n_jobs=-1, scoring=metrics
-        X=data_x,
-        y=data_y,
-        groups=data_groups,
-        cv=logo,
-        n_jobs=-1,
-        scoring=metrics
     )
     print("ADA Boost Regressor")
 
     scores_df = pd.DataFrame(ada_score)[test_metrics]
-    scores_df = scores_df.agg(['max', np.nanmedian]).transpose()
+    scores_df = scores_df.agg(["max", np.nanmedian]).transpose()
     scores_df["method"] = "ADA_boost"
     scores = pd.concat([scores, scores_df])
 
@@ -324,7 +316,7 @@ def run_all_regression_models(input_csv):
 
 
 def run_all_classification_models(data_x, data_y, data_groups, cv_method):
-    metrics = ['accuracy', 'average_precision', 'recall', 'f1']
+    metrics = ["accuracy", "average_precision", "recall", "f1"]
     test_metrics = ["test_" + metric for metric in metrics]
 
     scores = pd.DataFrame(columns=["method", "max", "mean"])
@@ -332,127 +324,127 @@ def run_all_classification_models(data_x, data_y, data_groups, cv_method):
     dummy_class = DummyClassifier(strategy="most_frequent")
 
     dummy_score = cross_validate(
-    dummy_class,
+        dummy_class,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    error_score='raise',
+        error_score="raise",
-    scoring=metrics
+        scoring=metrics,
     )
     print("Dummy")
 
     scores_df = pd.DataFrame(dummy_score)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "Dummy"
     scores = pd.concat([scores, scores_df])
 
     logistic_regression = linear_model.LogisticRegression()
 
     log_reg_scores = cross_validate(
-    logistic_regression,
+        logistic_regression,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("Logistic regression")
 
     scores_df = pd.DataFrame(log_reg_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "logistic_reg"
     scores = pd.concat([scores, scores_df])
 
     svc = svm.SVC()
 
     svc_scores = cross_validate(
-    svc,
+        svc,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("Support Vector Machine")
 
     scores_df = pd.DataFrame(svc_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "svc"
     scores = pd.concat([scores, scores_df])
 
     gaussian_nb = naive_bayes.GaussianNB()
-    
+
     gaussian_nb_scores = cross_validate(
-    gaussian_nb,
+        gaussian_nb,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("Gaussian Naive Bayes")
 
     scores_df = pd.DataFrame(gaussian_nb_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "gaussian_naive_bayes"
     scores = pd.concat([scores, scores_df])
 
     sgdc = linear_model.SGDClassifier()
 
     sgdc_scores = cross_validate(
-    sgdc,
+        sgdc,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("Stochastic Gradient Descent")
 
     scores_df = pd.DataFrame(sgdc_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "stochastic_gradient_descent"
     scores = pd.concat([scores, scores_df])
 
     rfc = ensemble.RandomForestClassifier()
 
     rfc_scores = cross_validate(
-    rfc,
+        rfc,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("Random Forest")
 
     scores_df = pd.DataFrame(rfc_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "random_forest"
     scores = pd.concat([scores, scores_df])
 
     xgb_classifier = XGBClassifier()
 
     xgb_scores = cross_validate(
-    xgb_classifier,
+        xgb_classifier,
-    X=data_x,
+        X=data_x,
-    y=data_y,
+        y=data_y,
-    groups=data_groups,
+        groups=data_groups,
-    cv=cv_method,
+        cv=cv_method,
-    n_jobs=-1,
+        n_jobs=-1,
-    scoring=metrics
+        scoring=metrics,
     )
     print("XGBoost")
 
     scores_df = pd.DataFrame(xgb_scores)[test_metrics]
-    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df = scores_df.agg(["max", "mean"]).transpose()
     scores_df["method"] = "xgboost"
     scores = pd.concat([scores, scores_df])